drive by typo fix

this seems to have been fixed long enough ago.

.dockerignore

@@ -14,7 +14,6 @@
 !pgxn/
 !proxy/
 !safekeeper/
-!storage_broker/
 !vendor/postgres-v14/
 !vendor/postgres-v15/
 !workspace_hack/

.github/actions/allure-report/action.yml

@@ -32,8 +32,8 @@ runs:
           exit 2
         fi
 
-    - name: Calculate variables
-      id: calculate-vars
+    - name: Calculate key
+      id: calculate-key
       shell: bash -euxo pipefail {0}
       run: |
         # TODO: for manually triggered workflows (via workflow_dispatch) we need to have a separate key
@@ -41,22 +41,14 @@ runs:
         pr_number=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
         if [ "${pr_number}" != "null" ]; then
           key=pr-${pr_number}
-        elif [ "${GITHUB_REF_NAME}" = "main" ]; then
+        elif [ "${GITHUB_REF}" = "refs/heads/main" ]; then
           # Shortcut for a special branch
           key=main
-        elif [ "${GITHUB_REF_NAME}" = "release" ]; then
-          # Shortcut for a special branch
-          key=release
         else
-          key=branch-$(printf "${GITHUB_REF_NAME}" | tr -c "[:alnum:]._-" "-")
+          key=branch-$(echo ${GITHUB_REF#refs/heads/} | tr -c "[:alnum:]._-" "-")
         fi
         echo "KEY=${key}" >> $GITHUB_OUTPUT
 
-        # Sanitize test selection to remove `/` and any other special characters
-        # Use printf instead of echo to avoid having `\n` at the end of the string
-        test_selection=$(printf "${{ inputs.test_selection }}" | tr -c "[:alnum:]._-" "-" )
-        echo "TEST_SELECTION=${test_selection}" >> $GITHUB_OUTPUT
-
     - uses: actions/setup-java@v3
       if: ${{ inputs.action == 'generate' }}
       with:
@@ -82,11 +74,10 @@ runs:
     - name: Upload Allure results
       if: ${{ inputs.action == 'store' }}
       env:
-        REPORT_PREFIX: reports/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
-        RAW_PREFIX: reports-raw/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
+        REPORT_PREFIX: reports/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
+        RAW_PREFIX: reports-raw/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
         TEST_OUTPUT: /tmp/test_output
         BUCKET: neon-github-public-dev
-        TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
       shell: bash -euxo pipefail {0}
       run: |
         # Add metadata
@@ -107,7 +98,7 @@ runs:
           BUILD_TYPE=${{ inputs.build_type }}
         EOF
 
-        ARCHIVE="${GITHUB_RUN_ID}-${TEST_SELECTION}-${GITHUB_RUN_ATTEMPT}-$(date +%s).tar.zst"
+        ARCHIVE="${GITHUB_RUN_ID}-${{ inputs.test_selection }}-${GITHUB_RUN_ATTEMPT}-$(date +%s).tar.zst"
         ZSTD_NBTHREADS=0
 
         tar -C ${TEST_OUTPUT}/allure/results -cf ${ARCHIVE} --zstd .
@@ -118,9 +109,8 @@ runs:
       if: ${{ inputs.action == 'generate' }}
       shell: bash -euxo pipefail {0}
       env:
-        LOCK_FILE: reports/${{ steps.calculate-vars.outputs.KEY }}/lock.txt
+        LOCK_FILE: reports/${{ steps.calculate-key.outputs.KEY }}/lock.txt
         BUCKET: neon-github-public-dev
-        TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
       run: |
         LOCK_TIMEOUT=300 # seconds
 
@@ -133,12 +123,12 @@ runs:
             fi
             sleep 1
           done
-          echo "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" > lock.txt
+          echo "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" > lock.txt
           aws s3 mv --only-show-errors lock.txt "s3://${BUCKET}/${LOCK_FILE}"
 
           # A double-check that exactly WE have acquired the lock
           aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt
-          if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" ]; then
+          if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" ]; then
             break
           fi
         done
@@ -147,8 +137,8 @@ runs:
       if: ${{ inputs.action == 'generate' }}
       id: generate-report
       env:
-        REPORT_PREFIX: reports/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
-        RAW_PREFIX: reports-raw/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
+        REPORT_PREFIX: reports/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
+        RAW_PREFIX: reports-raw/${{ steps.calculate-key.outputs.KEY }}/${{ inputs.build_type }}
         TEST_OUTPUT: /tmp/test_output
         BUCKET: neon-github-public-dev
       shell: bash -euxo pipefail {0}
@@ -202,13 +192,12 @@ runs:
       if: ${{ inputs.action == 'generate' && always() }}
       shell: bash -euxo pipefail {0}
       env:
-        LOCK_FILE: reports/${{ steps.calculate-vars.outputs.KEY }}/lock.txt
+        LOCK_FILE: reports/${{ steps.calculate-key.outputs.KEY }}/lock.txt
         BUCKET: neon-github-public-dev
-        TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
       run: |
         aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt || exit 0
 
-        if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" ]; then
+        if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${{ inputs.test_selection }}" ]; then
           aws s3 rm "s3://${BUCKET}/${LOCK_FILE}"
         fi
 

.github/actions/neon-branch-create/action.yml

@@ -1,138 +0,0 @@
-name: 'Create Branch'
-description: 'Create Branch using API'
-
-inputs:
-  api_key:
-    desctiption: 'Neon API key'
-    required: true
-  project_id:
-    desctiption: 'ID of the Project to create Branch in'
-    required: true
-  api_host:
-    desctiption: 'Neon API host'
-    default: console.stage.neon.tech
-outputs:
-  dsn:
-    description: 'Created Branch DSN (for main database)'
-    value: ${{ steps.change-password.outputs.dsn }}
-  branch_id:
-    description: 'Created Branch ID'
-    value: ${{ steps.create-branch.outputs.branch_id }}
-
-runs:
-  using: "composite"
-  steps:
-    - name: Create New Branch
-      id: create-branch
-      shell: bash -euxo pipefail {0}
-      run: |
-        for i in $(seq 1 10); do
-         branch=$(curl \
-            "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches" \
-            --header "Accept: application/json" \
-            --header "Content-Type: application/json" \
-            --header "Authorization: Bearer ${API_KEY}" \
-            --data "{
-              \"branch\": {
-                \"name\": \"Created by actions/neon-branch-create; GITHUB_RUN_ID=${GITHUB_RUN_ID} at $(date +%s)\"
-              },
-              \"endpoints\": [
-                {
-                  \"type\": \"read_write\"
-                }
-              ]
-            }")
-
-          if [ -z "${branch}" ]; then
-            sleep 1
-            continue
-          fi
-
-          branch_id=$(echo $branch | jq --raw-output '.branch.id')
-          if [ "${branch_id}" == "null" ]; then
-            sleep 1
-            continue
-          fi
-
-          break
-        done
-
-        if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
-          echo 2>&1 "Failed to create branch after 10 attempts, the latest response was: ${branch}"
-          exit 1
-        fi
-
-        branch_id=$(echo $branch | jq --raw-output '.branch.id')
-        echo "branch_id=${branch_id}" >> $GITHUB_OUTPUT
-
-        host=$(echo $branch | jq --raw-output '.endpoints[0].host')
-        echo "host=${host}" >> $GITHUB_OUTPUT
-      env:
-        API_HOST: ${{ inputs.api_host }}
-        API_KEY: ${{ inputs.api_key }}
-        PROJECT_ID: ${{ inputs.project_id }}
-
-    - name: Get Role name
-      id: role-name
-      shell: bash -euxo pipefail {0}
-      run: |
-        roles=$(curl \
-          "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}/roles" \
-          --fail \
-          --header "Accept: application/json" \
-          --header "Content-Type: application/json" \
-          --header "Authorization: Bearer ${API_KEY}"
-          )
-
-        role_name=$(echo $roles | jq --raw-output '.roles[] | select(.protected == false) | .name')
-        echo "role_name=${role_name}" >> $GITHUB_OUTPUT
-      env:
-        API_HOST: ${{ inputs.api_host }}
-        API_KEY: ${{ inputs.api_key }}
-        PROJECT_ID: ${{ inputs.project_id }}
-        BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
-
-    - name: Change Password
-      id: change-password
-      # A shell without `set -x` to not to expose password/dsn in logs
-      shell: bash -euo pipefail {0}
-      run: |
-        for i in $(seq 1 10); do
-          reset_password=$(curl \
-            "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}/roles/${ROLE_NAME}/reset_password" \
-            --request POST \
-            --header "Accept: application/json" \
-            --header "Content-Type: application/json" \
-            --header "Authorization: Bearer ${API_KEY}"
-            )
-
-          if [ -z "${reset_password}" ]; then
-            sleep 1
-            continue
-          fi
-
-          password=$(echo $reset_password | jq --raw-output '.role.password')
-          if [ "${password}" == "null" ]; then
-            sleep 1
-            continue
-          fi
-
-          echo "::add-mask::${password}"
-          break
-        done
-
-        if [ -z "${password}" ] || [ "${password}" == "null" ]; then
-          echo 2>&1 "Failed to reset password after 10 attempts, the latest response was: ${reset_password}"
-          exit 1
-        fi
-
-        dsn="postgres://${ROLE_NAME}:${password}@${HOST}/neondb"
-        echo "::add-mask::${dsn}"
-        echo "dsn=${dsn}" >> $GITHUB_OUTPUT
-      env:
-        API_HOST: ${{ inputs.api_host }}
-        API_KEY: ${{ inputs.api_key }}
-        PROJECT_ID: ${{ inputs.project_id }}
-        BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
-        ROLE_NAME: ${{ steps.role-name.outputs.role_name }}
-        HOST: ${{ steps.create-branch.outputs.host }}

.github/actions/neon-branch-delete/action.yml

@@ -1,58 +0,0 @@
-name: 'Delete Branch'
-description: 'Delete Branch using API'
-
-inputs:
-  api_key:
-    desctiption: 'Neon API key'
-    required: true
-  project_id:
-    desctiption: 'ID of the Project which should be deleted'
-    required: true
-  branch_id:
-    desctiption: 'ID of the branch to delete'
-    required: true
-  api_host:
-    desctiption: 'Neon API host'
-    default: console.stage.neon.tech
-
-runs:
-  using: "composite"
-  steps:
-    - name: Delete Branch
-      # Do not try to delete a branch if .github/actions/neon-project-create
-      # or .github/actions/neon-branch-create failed before
-      if: ${{ inputs.project_id != '' && inputs.branch_id != '' }}
-      shell: bash -euxo pipefail {0}
-      run: |
-        for i in $(seq 1 10); do
-          deleted_branch=$(curl \
-            "https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}" \
-            --request DELETE \
-            --header "Accept: application/json" \
-            --header "Content-Type: application/json" \
-            --header "Authorization: Bearer ${API_KEY}"
-            )
-
-          if [ -z "${deleted_branch}" ]; then
-            sleep 1
-            continue
-          fi
-
-          branch_id=$(echo $deleted_branch | jq --raw-output '.branch.id')
-          if [ "${branch_id}" == "null" ]; then
-            sleep 1
-            continue
-          fi
-
-          break
-        done
-
-        if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
-          echo 2>&1 "Failed to delete branch after 10 attempts, the latest response was: ${deleted_branch}"
-          exit 1
-        fi
-      env:
-        API_HOST: ${{ inputs.api_host }}
-        API_KEY: ${{ inputs.api_key }}
-        PROJECT_ID: ${{ inputs.project_id }}
-        BRANCH_ID: ${{ inputs.branch_id }}

.github/actions/neon-project-create/action.yml

@@ -5,16 +5,12 @@ inputs:
   api_key:
     desctiption: 'Neon API key'
     required: true
+  environment:
+    desctiption: 'dev (aka captest) or stage'
+    required: true
   region_id:
     desctiption: 'Region ID, if not set the project will be created in the default region'
-    default: aws-us-east-2
-  postgres_version:
-    desctiption: 'Postgres version; default is 15'
-    default: 15
-  api_host:
-    desctiption: 'Neon API host'
-    default: console.stage.neon.tech
-
+    required: false
 outputs:
   dsn:
     description: 'Created Project DSN (for main database)'
@@ -26,13 +22,38 @@ outputs:
 runs:
   using: "composite"
   steps:
+    - name: Parse Input
+      id: parse-input
+      shell: bash -euxo pipefail {0}
+      run: |
+        case "${ENVIRONMENT}" in
+          dev)
+            API_HOST=console.dev.neon.tech
+            REGION_ID=${REGION_ID:-eu-west-1}
+            ;;
+          staging)
+            API_HOST=console.stage.neon.tech
+            REGION_ID=${REGION_ID:-us-east-1}
+            ;;
+          *)
+            echo 2>&1 "Unknown environment=${ENVIRONMENT}. Allowed 'dev' or 'staging' only"
+            exit 1
+            ;;
+        esac
+
+        echo "api_host=${API_HOST}" >> $GITHUB_OUTPUT
+        echo "region_id=${REGION_ID}" >> $GITHUB_OUTPUT
+      env:
+        ENVIRONMENT: ${{ inputs.environment }}
+        REGION_ID: ${{ inputs.region_id }}
+
     - name: Create Neon Project
       id: create-neon-project
       # A shell without `set -x` to not to expose password/dsn in logs
       shell: bash -euo pipefail {0}
       run: |
         project=$(curl \
-          "https://${API_HOST}/api/v2/projects" \
+          "https://${API_HOST}/api/v1/projects" \
           --fail \
           --header "Accept: application/json" \
           --header "Content-Type: application/json" \
@@ -40,7 +61,7 @@ runs:
           --data "{
             \"project\": {
               \"name\": \"Created by actions/neon-project-create; GITHUB_RUN_ID=${GITHUB_RUN_ID}\",
-              \"pg_version\": ${POSTGRES_VERSION},
+              \"platform_id\": \"aws\",
               \"region_id\": \"${REGION_ID}\",
               \"settings\": { }
             }
@@ -49,14 +70,13 @@ runs:
         # Mask password
         echo "::add-mask::$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .password')"
 
-        dsn=$(echo $project | jq --raw-output '.connection_uris[0].connection_uri')
+        dsn=$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .dsn')/main
         echo "::add-mask::${dsn}"
         echo "dsn=${dsn}" >> $GITHUB_OUTPUT
 
-        project_id=$(echo $project | jq --raw-output '.project.id')
+        project_id=$(echo $project | jq --raw-output '.id')
         echo "project_id=${project_id}" >> $GITHUB_OUTPUT
       env:
-        API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
-        REGION_ID: ${{ inputs.region_id }}
-        POSTGRES_VERSION: ${{ inputs.postgres_version }}
+        API_HOST: ${{ steps.parse-input.outputs.api_host }}
+        REGION_ID: ${{ steps.parse-input.outputs.region_id }}

.github/actions/neon-project-delete/action.yml

@@ -5,29 +5,50 @@ inputs:
   api_key:
     desctiption: 'Neon API key'
     required: true
+  environment:
+    desctiption: 'dev (aka captest) or stage'
+    required: true
   project_id:
     desctiption: 'ID of the Project to delete'
     required: true
-  api_host:
-    desctiption: 'Neon API host'
-    default: console.stage.neon.tech
 
 runs:
   using: "composite"
   steps:
-    - name: Delete Neon Project
-      # Do not try to delete a project if .github/actions/neon-project-create failed before
-      if: ${{ inputs.project_id != '' }}
+    - name: Parse Input
+      id: parse-input
       shell: bash -euxo pipefail {0}
       run: |
-        curl \
-          "https://${API_HOST}/api/v2/projects/${PROJECT_ID}" \
-          --fail \
-          --request DELETE \
-          --header "Accept: application/json" \
-          --header "Content-Type: application/json" \
-          --header "Authorization: Bearer ${API_KEY}"
+        case "${ENVIRONMENT}" in
+          dev)
+            API_HOST=console.dev.neon.tech
+            ;;
+          staging)
+            API_HOST=console.stage.neon.tech
+            ;;
+          *)
+            echo 2>&1 "Unknown environment=${ENVIRONMENT}. Allowed 'dev' or 'staging' only"
+            exit 1
+            ;;
+        esac
+
+        echo "api_host=${API_HOST}" >> $GITHUB_OUTPUT
+      env:
+        ENVIRONMENT: ${{ inputs.environment }}
+
+    - name: Delete Neon Project
+      shell: bash -euxo pipefail {0}
+      run: |
+        # Allow PROJECT_ID to be empty/null for cases when .github/actions/neon-project-create failed
+        if [ -n "${PROJECT_ID}" ]; then
+          curl -X "POST" \
+            "https://${API_HOST}/api/v1/projects/${PROJECT_ID}/delete" \
+            --fail \
+            --header "Accept: application/json" \
+            --header "Content-Type: application/json" \
+            --header "Authorization: Bearer ${API_KEY}"
+        fi
       env:
-        API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
         PROJECT_ID: ${{ inputs.project_id }}
+        API_HOST: ${{ steps.parse-input.outputs.api_host }}

.github/actions/run-python-test-set/action.yml

@@ -55,22 +55,6 @@ runs:
         name: neon-${{ runner.os }}-${{ inputs.build_type }}-artifact
         path: /tmp/neon
 
-    - name: Download Neon binaries for the previous release
-      if: inputs.build_type != 'remote'
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-${{ inputs.build_type }}-artifact
-        path: /tmp/neon-previous
-        prefix: latest
-
-    - name: Download compatibility snapshot for Postgres 14
-      if: inputs.build_type != 'remote'
-      uses: ./.github/actions/download
-      with:
-        name: compatibility-snapshot-${{ inputs.build_type }}-pg14
-        path: /tmp/compatibility_snapshot_pg14
-        prefix: latest
-
     - name: Checkout
       if: inputs.needs_postgres_source == 'true'
       uses: actions/checkout@v3
@@ -89,18 +73,23 @@ runs:
       shell: bash -euxo pipefail {0}
       run: ./scripts/pysync
 
+    - name: Download compatibility snapshot for Postgres 14
+      if: inputs.build_type != 'remote'
+      uses: ./.github/actions/download
+      with:
+        name: compatibility-snapshot-${{ inputs.build_type }}-pg14
+        path: /tmp/compatibility_snapshot_pg14
+        prefix: latest
+
     - name: Run pytest
       env:
         NEON_BIN: /tmp/neon/bin
-        COMPATIBILITY_NEON_BIN: /tmp/neon-previous/bin
-        COMPATIBILITY_POSTGRES_DISTRIB_DIR: /tmp/neon-previous/pg_install
         TEST_OUTPUT: /tmp/test_output
         BUILD_TYPE: ${{ inputs.build_type }}
         AWS_ACCESS_KEY_ID: ${{ inputs.real_s3_access_key_id }}
         AWS_SECRET_ACCESS_KEY: ${{ inputs.real_s3_secret_access_key }}
         COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg14
-        ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
-        ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
+        ALLOW_BREAKING_CHANGES: contains(github.event.pull_request.labels.*.name, 'breaking changes')
       shell: bash -euxo pipefail {0}
       run: |
         # PLATFORM will be embedded in the perf test report
@@ -123,12 +112,7 @@ runs:
           exit 1
         fi
         if [[ "${{ inputs.run_in_parallel }}" == "true" ]]; then
-          # -n4 uses four processes to run tests via pytest-xdist
           EXTRA_PARAMS="-n4 $EXTRA_PARAMS"
-
-          # --dist=loadgroup points tests marked with @pytest.mark.xdist_group
-          # to the same worker to make @pytest.mark.order work with xdist
-          EXTRA_PARAMS="--dist=loadgroup $EXTRA_PARAMS"
         fi
 
         if [[ "${{ inputs.run_with_real_s3 }}" == "true" ]]; then
@@ -163,9 +147,9 @@ runs:
         # --verbose prints name of each test (helpful when there are
         # multiple tests in one file)
         # -rA prints summary in the end
+        # -n4 uses four processes to run tests via pytest-xdist
         # -s is not used to prevent pytest from capturing output, because tests are running
         # in parallel and logs are mixed between different tests
-        #
         mkdir -p $TEST_OUTPUT/allure/results
         "${cov_prefix[@]}" ./scripts/pytest \
           --junitxml=$TEST_OUTPUT/junit.xml \
@@ -185,12 +169,12 @@ runs:
       uses: ./.github/actions/upload
       with:
         name: compatibility-snapshot-${{ inputs.build_type }}-pg14-${{ github.run_id }}
-        # The path includes a test name (test_create_snapshot) and directory that the test creates (compatibility_snapshot_pg14), keep the path in sync with the test
-        path: /tmp/test_output/test_create_snapshot/compatibility_snapshot_pg14/
+        # The path includes a test name (test_prepare_snapshot) and directory that the test creates (compatibility_snapshot_pg14), keep the path in sync with the test
+        path: /tmp/test_output/test_prepare_snapshot/compatibility_snapshot_pg14/
         prefix: latest
 
     - name: Create Allure report
-      if: success() || failure()
+      if: always()
       uses: ./.github/actions/allure-report
       with:
         action: store

.github/ansible/.gitignore

@@ -1,3 +1,5 @@
+zenith_install.tar.gz
+.zenith_current_version
 neon_install.tar.gz
 .neon_current_version
 

.github/ansible/get_binaries.sh

@@ -25,7 +25,6 @@ mkdir neon_install/bin/
 docker cp ${ID}:/usr/local/bin/pageserver neon_install/bin/
 docker cp ${ID}:/usr/local/bin/pageserver_binutils neon_install/bin/
 docker cp ${ID}:/usr/local/bin/safekeeper neon_install/bin/
-docker cp ${ID}:/usr/local/bin/storage_broker neon_install/bin/
 docker cp ${ID}:/usr/local/bin/proxy neon_install/bin/
 docker cp ${ID}:/usr/local/v14/bin/ neon_install/v14/bin/
 docker cp ${ID}:/usr/local/v15/bin/ neon_install/v15/bin/

.github/ansible/neon-stress.hosts.yaml

@@ -3,7 +3,7 @@ storage:
     bucket_name: neon-storage-ireland
     bucket_region: eu-west-1
     console_mgmt_base_url: http://neon-stress-console.local
-    broker_endpoint: http://storage-broker.neon-stress.local:50051
+    etcd_endpoints: neon-stress-etcd.local:2379
     safekeeper_enable_s3_offload: 'false'
     pageserver_config_stub:
       pg_distrib_dir: /usr/local

.github/ansible/prod.ap-southeast-1.hosts.yaml

@@ -3,7 +3,7 @@ storage:
     bucket_name: neon-prod-storage-ap-southeast-1
     bucket_region: ap-southeast-1
     console_mgmt_base_url: http://console-release.local
-    broker_endpoint: https://storage-broker.epsilon.ap-southeast-1.internal.aws.neon.tech:443
+    etcd_endpoints: etcd-0.ap-southeast-1.aws.neon.tech:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
       remote_storage:

.github/ansible/prod.eu-central-1.hosts.yaml

@@ -3,7 +3,7 @@ storage:
     bucket_name: neon-prod-storage-eu-central-1
     bucket_region: eu-central-1
     console_mgmt_base_url: http://console-release.local
-    broker_endpoint: https://storage-broker.gamma.eu-central-1.internal.aws.neon.tech:443
+    etcd_endpoints: etcd-0.eu-central-1.aws.neon.tech:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
       remote_storage:

.github/ansible/prod.us-east-2.hosts.yaml

@@ -3,7 +3,7 @@ storage:
     bucket_name: neon-prod-storage-us-east-2
     bucket_region: us-east-2
     console_mgmt_base_url: http://console-release.local
-    broker_endpoint: https://storage-broker.delta.us-east-2.internal.aws.neon.tech:443
+    etcd_endpoints: etcd-0.us-east-2.aws.neon.tech:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
       remote_storage:

.github/ansible/production.hosts.yaml

@@ -4,7 +4,7 @@ storage:
     console_mgmt_base_url: http://console-release.local
     bucket_name: zenith-storage-oregon
     bucket_region: us-west-2
-    broker_endpoint: http://storage-broker.prod.local:50051
+    etcd_endpoints: zenith-1-etcd.local:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
       remote_storage:
@@ -22,10 +22,6 @@ storage:
           console_region_id: aws-us-west-2
         zenith-1-ps-3:
           console_region_id: aws-us-west-2
-        zenith-1-ps-4:
-          console_region_id: aws-us-west-2
-        zenith-1-ps-5:
-          console_region_id: aws-us-west-2
 
     safekeepers:
       hosts:

.github/ansible/scripts/init_pageserver.sh

@@ -1,8 +1,7 @@
 #!/bin/sh
 
-# fetch params from meta-data service
+# get instance id from meta-data service
 INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-AZ_ID=$(curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone)
 
 # store fqdn hostname in var
 HOST=$(hostname -f)
@@ -17,8 +16,7 @@ cat <<EOF | tee /tmp/payload
   "instance_id": "${INSTANCE_ID}",
   "http_host": "${HOST}",
   "http_port": 9898,
-  "active": false,
-  "availability_zone_id": "${AZ_ID}"
+  "active": false
 }
 EOF
 

.github/ansible/staging.eu-west-1.hosts.yaml

@@ -1,33 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-dev-storage-eu-west-1
-    bucket_region: eu-west-1
-    console_mgmt_base_url: http://console-staging.local
-    broker_endpoint: https://storage-broker.zeta.eu-west-1.internal.aws.neon.build:443
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "pageserver/v1"
-    safekeeper_s3_prefix: safekeeper/v1/wal
-    hostname_suffix: ""
-    remote_user: ssm-user
-    ansible_aws_ssm_region: eu-west-1
-    ansible_aws_ssm_bucket_name: neon-dev-storage-eu-west-1
-    console_region_id: aws-eu-west-1
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.eu-west-1.aws.neon.build:
-          ansible_host: i-01d496c5041c7f34c
-
-    safekeepers:
-      hosts:
-        safekeeper-0.eu-west-1.aws.neon.build:
-          ansible_host: i-05226ef85722831bf
-        safekeeper-1.eu-west-1.aws.neon.build:
-          ansible_host: i-06969ee1bf2958bfc
-        safekeeper-2.eu-west-1.aws.neon.build:
-          ansible_host: i-087892e9625984a0b

.github/ansible/staging.hosts.yaml

@@ -3,7 +3,7 @@ storage:
     bucket_name: zenith-staging-storage-us-east-1
     bucket_region: us-east-1
     console_mgmt_base_url: http://console-staging.local
-    broker_endpoint: http://storage-broker.staging.local:50051
+    etcd_endpoints: zenith-us-stage-etcd.local:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
       remote_storage:

.github/ansible/staging.us-east-2.hosts.yaml

@@ -3,7 +3,7 @@ storage:
     bucket_name: neon-staging-storage-us-east-2
     bucket_region: us-east-2
     console_mgmt_base_url: http://console-staging.local
-    broker_endpoint: https://storage-broker.beta.us-east-2.internal.aws.neon.build:443
+    etcd_endpoints: etcd-0.us-east-2.aws.neon.build:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
       remote_storage:
@@ -22,8 +22,6 @@ storage:
       hosts:
         pageserver-0.us-east-2.aws.neon.build:
           ansible_host: i-0c3e70929edb5d691
-        pageserver-1.us-east-2.aws.neon.build:
-          ansible_host: i-0565a8b4008aa3f40
 
     safekeepers:
       hosts:

.github/ansible/systemd/pageserver.service

@@ -5,8 +5,8 @@ After=network.target auditd.service
 [Service]
 Type=simple
 User=pageserver
-Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/v14/lib SENTRY_DSN={{ SENTRY_URL_PAGESERVER }}
-ExecStart=/usr/local/bin/pageserver -c "pg_distrib_dir='/usr/local'" -c "listen_pg_addr='0.0.0.0:6400'" -c "listen_http_addr='0.0.0.0:9898'" -c "broker_endpoint='{{ broker_endpoint }}'" -D /storage/pageserver/data
+Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/v14/lib
+ExecStart=/usr/local/bin/pageserver -c "pg_distrib_dir='/usr/local'" -c "listen_pg_addr='0.0.0.0:6400'" -c "listen_http_addr='0.0.0.0:9898'" -c "broker_endpoints=['{{ etcd_endpoints }}']" -D /storage/pageserver/data
 ExecReload=/bin/kill -HUP $MAINPID
 KillMode=mixed
 KillSignal=SIGINT

.github/ansible/systemd/safekeeper.service

@@ -5,8 +5,8 @@ After=network.target auditd.service
 [Service]
 Type=simple
 User=safekeeper
-Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/safekeeper/data LD_LIBRARY_PATH=/usr/local/v14/lib SENTRY_DSN={{ SENTRY_URL_SAFEKEEPER }}
-ExecStart=/usr/local/bin/safekeeper -l {{ inventory_hostname }}{{ hostname_suffix }}:6500 --listen-http {{ inventory_hostname }}{{ hostname_suffix }}:7676 -D /storage/safekeeper/data --broker-endpoint={{ broker_endpoint }} --remote-storage='{bucket_name="{{bucket_name}}", bucket_region="{{bucket_region}}", prefix_in_bucket="{{ safekeeper_s3_prefix }}"}'
+Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/safekeeper/data LD_LIBRARY_PATH=/usr/local/v14/lib
+ExecStart=/usr/local/bin/safekeeper -l {{ inventory_hostname }}{{ hostname_suffix }}:6500 --listen-http {{ inventory_hostname }}{{ hostname_suffix }}:7676 -D /storage/safekeeper/data --broker-endpoints={{ etcd_endpoints }} --remote-storage='{bucket_name="{{bucket_name}}", bucket_region="{{bucket_region}}", prefix_in_bucket="{{ safekeeper_s3_prefix }}"}'
 ExecReload=/bin/kill -HUP $MAINPID
 KillMode=mixed
 KillSignal=SIGINT

.github/helm-values/dev-eu-west-1-zeta.neon-proxy-scram.yaml

@@ -1,31 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-staging.local/management/api/v2"
-  domain: "*.eu-west-1.aws.neon.build"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: dev
-  zenith_region: eu-west-1
-  zenith_region_slug: eu-west-1
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: eu-west-1.aws.neon.build
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/dev-eu-west-1-zeta.neon-storage-broker.yaml

@@ -1,53 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: staging
-  neon_service: storage-broker
-
-ingress:
-  enabled: true
-  annotations:
-    kubernetes.io/ingress.class: nginx-internal
-    nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
-    nginx.ingress.kubernetes.io/ssl-redirect: "true"
-    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
-    cert-manager.io/cluster-issuer: "cert-manager-clusterissuer"
-
-  hosts:
-    - host: storage-broker.zeta.eu-west-1.internal.aws.neon.build
-      paths:
-        - path: /
-          pathType: Prefix
-  tls:
-    - hosts:
-        - storage-broker.zeta.eu-west-1.internal.aws.neon.build
-      secretName: storage-broker-tls
-
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/dev-us-east-2-beta.neon-proxy-link.yaml

@@ -1,39 +0,0 @@
-# Helm chart values for neon-proxy-link.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "link"
-  authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
-  uri: "https://console.stage.neon.tech/psql_session/"
-
-# -- Additional labels for neon-proxy-link pods
-podLabels:
-  zenith_service: proxy
-  zenith_env: dev
-  zenith_region: us-east-2
-  zenith_region_slug: us-east-2
-
-service:
-  type: LoadBalancer
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internal
-    external-dns.alpha.kubernetes.io/hostname: neon-proxy-link-mgmt.beta.us-east-2.aws.neon.build
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: neon-proxy-link.beta.us-east-2.aws.neon.build
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/dev-us-east-2-beta.neon-proxy-scram-legacy.yaml

@@ -1,31 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-staging.local/management/api/v2"
-  domain: "*.cloud.stage.neon.tech"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  zenith_service: proxy-scram-legacy
-  zenith_env: dev
-  zenith_region: us-east-2
-  zenith_region_slug: us-east-2
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: neon-proxy-scram-legacy.beta.us-east-2.aws.neon.build
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/dev-us-east-2-beta.neon-storage-broker.yaml

@@ -1,53 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: staging
-  neon_service: storage-broker
-
-ingress:
-  enabled: true
-  annotations:
-    kubernetes.io/ingress.class: nginx-internal
-    nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
-    nginx.ingress.kubernetes.io/ssl-redirect: "true"
-    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
-    cert-manager.io/cluster-issuer: "cert-manager-clusterissuer"
-
-  hosts:
-    - host: storage-broker.beta.us-east-2.internal.aws.neon.build
-      paths:
-        - path: /
-          pathType: Prefix
-  tls:
-    - hosts:
-        - storage-broker.beta.us-east-2.internal.aws.neon.build
-      secretName: storage-broker-tls
-
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/neon-stress.neon-storage-broker.yaml

@@ -1,54 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: neon-stress
-  neon_service: storage-broker
-
-# Use L4 LB
-service:
-  # service.annotations -- Annotations to add to the service
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
-    # assign service to this name at external-dns
-    external-dns.alpha.kubernetes.io/hostname: storage-broker.neon-stress.local
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/prod-ap-southeast-1-epsilon.neon-storage-broker.yaml

@@ -1,53 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: production
-  neon_service: storage-broker
-
-ingress:
-  enabled: true
-  annotations:
-    kubernetes.io/ingress.class: nginx-internal
-    nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
-    nginx.ingress.kubernetes.io/ssl-redirect: "true"
-    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
-    cert-manager.io/cluster-issuer: "cert-manager-clusterissuer"
-
-  hosts:
-    - host: storage-broker.epsilon.ap-southeast-1.internal.aws.neon.tech
-      paths:
-        - path: /
-          pathType: Prefix
-  tls:
-    - hosts:
-        - storage-broker.epsilon.ap-southeast-1.internal.aws.neon.tech
-      secretName: storage-broker-tls
-
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/prod-eu-central-1-gamma.neon-storage-broker.yaml

@@ -1,53 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: production
-  neon_service: storage-broker
-
-ingress:
-  enabled: true
-  annotations:
-    kubernetes.io/ingress.class: nginx-internal
-    nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
-    nginx.ingress.kubernetes.io/ssl-redirect: "true"
-    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
-    cert-manager.io/cluster-issuer: "cert-manager-clusterissuer"
-
-  hosts:
-    - host: storage-broker.gamma.eu-central-1.internal.aws.neon.tech
-      paths:
-        - path: /
-          pathType: Prefix
-  tls:
-    - hosts:
-        - storage-broker.gamma.eu-central-1.internal.aws.neon.tech
-      secretName: storage-broker-tls
-
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/prod-us-east-2-delta.neon-storage-broker.yaml

@@ -1,53 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: production
-  neon_service: storage-broker
-
-ingress:
-  enabled: true
-  annotations:
-    kubernetes.io/ingress.class: nginx-internal
-    nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
-    nginx.ingress.kubernetes.io/ssl-redirect: "true"
-    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
-    cert-manager.io/cluster-issuer: "cert-manager-clusterissuer"
-
-  hosts:
-    - host: storage-broker.delta.us-east-2.internal.aws.neon.tech
-      paths:
-        - path: /
-          pathType: Prefix
-  tls:
-    - hosts:
-        - storage-broker.delta.us-east-2.internal.aws.neon.tech
-      secretName: storage-broker-tls
-
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/prod-us-west-2-eta.neon-proxy-scram.yaml

@@ -1,31 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://console-release.local/management/api/v2"
-  domain: "*.us-west-2.aws.neon.tech"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  zenith_service: proxy-scram
-  zenith_env: prod
-  zenith_region: us-west-2
-  zenith_region_slug: us-west-2
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: us-west-2.aws.neon.tech
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack

.github/helm-values/prod-us-west-2-eta.neon-storage-broker.yaml

@@ -1,53 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: production
-  neon_service: storage-broker
-
-ingress:
-  enabled: true
-  annotations:
-    kubernetes.io/ingress.class: nginx-internal
-    nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
-    nginx.ingress.kubernetes.io/ssl-redirect: "true"
-    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
-    cert-manager.io/cluster-issuer: "cert-manager-clusterissuer"
-
-  hosts:
-    - host: storage-broker.eta.us-west-2.internal.aws.neon.tech
-      paths:
-        - path: /
-          pathType: Prefix
-  tls:
-    - hosts:
-        - storage-broker.eta.us-west-2.internal.aws.neon.tech
-      secretName: storage-broker-tls
-
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/production.neon-storage-broker.yaml

@@ -1,54 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: production
-  neon_service: storage-broker
-
-# Use L4 LB
-service:
-  # service.annotations -- Annotations to add to the service
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
-    # assign service to this name at external-dns
-    external-dns.alpha.kubernetes.io/hostname: storage-broker.prod.local
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/helm-values/staging.neon-storage-broker.yaml

@@ -1,54 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: staging
-  neon_service: storage-broker
-
-# Use L4 LB
-service:
-  # service.annotations -- Annotations to add to the service
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
-    # assign service to this name at external-dns
-    external-dns.alpha.kubernetes.io/hostname: storage-broker.staging.local
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-metrics:
-  enabled: true
-  serviceMonitor:
-    enabled: true
-    selector:
-      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-

.github/workflows/benchmarking.yml

@@ -15,6 +15,9 @@ on:
 
   workflow_dispatch: # adds ability to run this manually
     inputs:
+      environment:
+        description: 'Environment to run remote tests on (dev or staging)'
+        required: false
       region_id:
         description: 'Use a particular region. If not set the default region will be used'
         required: false
@@ -34,69 +37,97 @@ concurrency:
 
 jobs:
   bench:
-    env:
-      TEST_PG_BENCH_DURATIONS_MATRIX: "300"
-      TEST_PG_BENCH_SCALES_MATRIX: "10,100"
-      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      DEFAULT_PG_VERSION: 14
-      TEST_OUTPUT: /tmp/test_output
-      BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
-      PLATFORM: "neon-staging"
+    # this workflow runs on self hosteed runner
+    # it's environment is quite different from usual guthub runner
+    # probably the most important difference is that it doesn't start from clean workspace each time
+    # e g if you install system packages they are not cleaned up since you install them directly in host machine
+    # not a container or something
+    # See documentation for more info: https://docs.github.com/en/actions/hosting-your-own-runners/about-self-hosted-runners
+    runs-on: [self-hosted, zenith-benchmarker]
 
-    runs-on: [ self-hosted, us-east-2, x64 ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    env:
+      POSTGRES_DISTRIB_DIR: /usr/pgsql
+      DEFAULT_PG_VERSION: 14
 
     steps:
-    - uses: actions/checkout@v3
+    - name: Checkout zenith repo
+      uses: actions/checkout@v3
 
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-release-artifact
-        path: /tmp/neon/
-        prefix: latest
+    # actions/setup-python@v2 is not working correctly on self-hosted runners
+    # see https://github.com/actions/setup-python/issues/162
+    # and probably https://github.com/actions/setup-python/issues/162#issuecomment-865387976 in particular
+    # so the simplest solution to me is to use already installed system python and spin virtualenvs for job runs.
+    # there is Python 3.7.10 already installed on the machine so use it to install poetry and then use poetry's virtuealenvs
+    - name: Install poetry & deps
+      run: |
+        python3 -m pip install --upgrade poetry wheel
+        # since pip/poetry caches are reused there shouldn't be any troubles with install every time
+        ./scripts/pysync
+
+    - name: Show versions
+      run: |
+        echo Python
+        python3 --version
+        poetry run python3 --version
+        echo Poetry
+        poetry --version
+        echo Pgbench
+        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
 
     - name: Create Neon Project
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
-        region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
-        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
-        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
+        environment: ${{ github.event.inputs.environment || 'staging' }}
+        api_key: ${{ ( github.event.inputs.environment || 'staging' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}
 
     - name: Run benchmark
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        # Set --sparse-ordering option of pytest-order plugin
-        # to ensure tests are running in order of appears in the file.
-        # It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
-        extra_params: -m remote_cluster --sparse-ordering --timeout 5400 --ignore test_runner/performance/test_perf_olap.py
+      # pgbench is installed system wide from official repo
+      # https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
+      # via
+      # sudo tee /etc/yum.repos.d/pgdg.repo<<EOF
+      # [pgdg13]
+      # name=PostgreSQL 13 for RHEL/CentOS 7 - x86_64
+      # baseurl=https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
+      # enabled=1
+      # gpgcheck=0
+      # EOF
+      # sudo yum makecache
+      # sudo yum install postgresql13-contrib
+      # actual binaries are located in /usr/pgsql-13/bin/
       env:
+        # The pgbench test runs two tests of given duration against each scale.
+        # So the total runtime with these parameters is 2 * 2 * 300 = 1200, or 20 minutes.
+        # Plus time needed to initialize the test databases.
+        TEST_PG_BENCH_DURATIONS_MATRIX: "300"
+        TEST_PG_BENCH_SCALES_MATRIX: "10,100"
+        PLATFORM: "neon-staging"
         BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
+        REMOTE_ENV: "1" # indicate to test harness that we do not have zenith binaries locally
+      run: |
+        # just to be sure that no data was cached on self hosted runner
+        # since it might generate duplicates when calling ingest_perf_test_result.py
+        rm -rf perf-report-staging
+        mkdir -p perf-report-staging
+        # Set --sparse-ordering option of pytest-order plugin to ensure tests are running in order of appears in the file,
+        # it's important for test_perf_pgbench.py::test_pgbench_remote_* tests
+        ./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --sparse-ordering --out-dir perf-report-staging --timeout 5400
+
+    - name: Submit result
+      env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
+      run: |
+        REPORT_FROM=$(realpath perf-report-staging) REPORT_TO=staging scripts/generate_and_push_perf_report.sh
 
     - name: Delete Neon Project
       if: ${{ always() }}
       uses: ./.github/actions/neon-project-delete
       with:
+        environment: staging
         project_id: ${{ steps.create-neon-project.outputs.project_id }}
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
-    - name: Create Allure report
-      if: success() || failure()
-      uses: ./.github/actions/allure-report
-      with:
-        action: generate
-        build_type: ${{ env.BUILD_TYPE }}
-
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
       uses: slackapi/slack-github-action@v1
@@ -113,24 +144,15 @@ jobs:
         # neon-captest-new: Run pgbench in a freshly created project
         # neon-captest-reuse: Same, but reusing existing project
         # neon-captest-prefetch: Same, with prefetching enabled (new project)
-        # rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
-        # rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
-        platform: [ neon-captest-new, neon-captest-prefetch, rds-postgres ]
+        platform: [ neon-captest-new, neon-captest-reuse, neon-captest-prefetch ]
         db_size: [ 10gb ]
-        runner: [ us-east-2 ]
         include:
-          - platform: neon-captest-reuse
-            db_size: 10gb
-            runner: dev  # TODO: Switch to us-east-2 after dry-bonus-223539 migration to staging
           - platform: neon-captest-new
             db_size: 50gb
-            runner: us-east-2
           - platform: neon-captest-prefetch
             db_size: 50gb
-            runner: us-east-2
           - platform: rds-aurora
             db_size: 50gb
-            runner: us-east-2
 
     env:
       TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
@@ -142,9 +164,9 @@ jobs:
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
       PLATFORM: ${{ matrix.platform }}
 
-    runs-on: [ self-hosted, "${{ matrix.runner }}", x64 ]
+    runs-on: dev
     container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:pinned
       options: --init
 
     timeout-minutes: 360 # 6h
@@ -169,9 +191,8 @@ jobs:
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
-        region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
-        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
-        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
+        environment: ${{ github.event.inputs.environment || 'dev' }}
+        api_key: ${{ ( github.event.inputs.environment || 'dev' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}
 
     - name: Set up Connection String
       id: set-up-connstr
@@ -184,13 +205,10 @@ jobs:
             CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
             ;;
           rds-aurora)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
-            ;;
-          rds-postgres)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
+            CONNSTR=${{ secrets.BENCHMARK_RDS_CONNSTR }}
             ;;
           *)
-            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch' or 'rds-aurora'"
             exit 1
             ;;
         esac
@@ -202,11 +220,8 @@ jobs:
     - name: Set database options
       if: matrix.platform == 'neon-captest-prefetch'
       run: |
-        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
-
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET enable_seqscan_prefetch=on"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET seqscan_prefetch_buffers=10"
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
 
@@ -249,20 +264,21 @@ jobs:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
 
-    - name: Delete Neon Project
-      if: ${{ steps.create-neon-project.outputs.project_id && always() }}
-      uses: ./.github/actions/neon-project-delete
-      with:
-        project_id: ${{ steps.create-neon-project.outputs.project_id }}
-        api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-
     - name: Create Allure report
-      if: success() || failure()
+      if: always()
       uses: ./.github/actions/allure-report
       with:
         action: generate
         build_type: ${{ env.BUILD_TYPE }}
 
+    - name: Delete Neon Project
+      if: ${{ steps.create-neon-project.outputs.project_id && always() }}
+      uses: ./.github/actions/neon-project-delete
+      with:
+        environment: dev
+        project_id: ${{ steps.create-neon-project.outputs.project_id }}
+        api_key: ${{ secrets.NEON_CAPTEST_API_KEY }}
+
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
       uses: slackapi/slack-github-action@v1
@@ -271,226 +287,3 @@ jobs:
         slack-message: "Periodic perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
       env:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-
-  clickbench-compare:
-    # ClichBench DB for rds-aurora and rds-Postgres deployed to the same clusters
-    # we use for performance testing in pgbench-compare.
-    # Run this job only when pgbench-compare is finished to avoid the intersection.
-    # We might change it after https://github.com/neondatabase/neon/issues/2900.
-    #
-    # *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
-    # *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
-    if: success() || failure()
-    needs: [ pgbench-compare ]
-
-    strategy:
-      fail-fast: false
-      matrix:
-        # neon-captest-prefetch: We have pre-created projects with prefetch enabled
-        # rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
-        # rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
-        platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
-
-    env:
-      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      DEFAULT_PG_VERSION: 14
-      TEST_OUTPUT: /tmp/test_output
-      BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
-      PLATFORM: ${{ matrix.platform }}
-
-    runs-on: [ self-hosted, us-east-2, x64 ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
-
-    timeout-minutes: 360 # 6h
-
-    steps:
-    - uses: actions/checkout@v3
-
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-release-artifact
-        path: /tmp/neon/
-        prefix: latest
-
-    - name: Add Postgres binaries to PATH
-      run: |
-        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
-        echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
-
-    - name: Set up Connection String
-      id: set-up-connstr
-      run: |
-        case "${PLATFORM}" in
-          neon-captest-prefetch)
-            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
-            ;;
-          rds-aurora)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
-            ;;
-          rds-postgres)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
-            ;;
-          *)
-            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
-            exit 1
-            ;;
-        esac
-
-        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
-
-        psql ${CONNSTR} -c "SELECT version();"
-
-    - name: Set database options
-      if: matrix.platform == 'neon-captest-prefetch'
-      run: |
-        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
-
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-
-    - name: ClickBench benchmark
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance/test_perf_olap.py
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_clickbench
-      env:
-        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
-        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-
-    - name: Create Allure report
-      if: success() || failure()
-      uses: ./.github/actions/allure-report
-      with:
-        action: generate
-        build_type: ${{ env.BUILD_TYPE }}
-
-    - name: Post to a Slack channel
-      if: ${{ github.event.schedule && failure() }}
-      uses: slackapi/slack-github-action@v1
-      with:
-        channel-id: "C033QLM5P7D" # dev-staging-stream
-        slack-message: "Periodic OLAP perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
-      env:
-        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-
-  tpch-compare:
-    # TCP-H DB for rds-aurora and rds-Postgres deployed to the same clusters
-    # we use for performance testing in pgbench-compare & clickbench-compare.
-    # Run this job only when clickbench-compare is finished to avoid the intersection.
-    # We might change it after https://github.com/neondatabase/neon/issues/2900.
-    #
-    # *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
-    if: success() || failure()
-    needs: [ clickbench-compare ]
-
-    strategy:
-      fail-fast: false
-      matrix:
-        # neon-captest-prefetch: We have pre-created projects with prefetch enabled
-        # rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
-        # rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
-        platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
-
-    env:
-      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      DEFAULT_PG_VERSION: 14
-      TEST_OUTPUT: /tmp/test_output
-      BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
-      PLATFORM: ${{ matrix.platform }}
-
-    runs-on: [ self-hosted, us-east-2, x64 ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:pinned
-      options: --init
-
-    timeout-minutes: 360 # 6h
-
-    steps:
-    - uses: actions/checkout@v3
-
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-release-artifact
-        path: /tmp/neon/
-        prefix: latest
-
-    - name: Add Postgres binaries to PATH
-      run: |
-        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
-        echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
-
-    - name: Set up Connection String
-      id: set-up-connstr
-      run: |
-        case "${PLATFORM}" in
-          neon-captest-prefetch)
-            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_TPCH_S10_CONNSTR }}
-            ;;
-          rds-aurora)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_TPCH_S10_CONNSTR }}
-            ;;
-          rds-postgres)
-            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR }}
-            ;;
-          *)
-            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
-            exit 1
-            ;;
-        esac
-
-        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
-
-        psql ${CONNSTR} -c "SELECT version();"
-
-    - name: Set database options
-      if: matrix.platform == 'neon-captest-prefetch'
-      run: |
-        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
-
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-
-    - name: Run TPC-H benchmark
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance/test_perf_olap.py
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_tpch
-      env:
-        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
-        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-
-    - name: Create Allure report
-      if: success() || failure()
-      uses: ./.github/actions/allure-report
-      with:
-        action: generate
-        build_type: ${{ env.BUILD_TYPE }}
-
-    - name: Post to a Slack channel
-      if: ${{ github.event.schedule && failure() }}
-      uses: slackapi/slack-github-action@v1
-      with:
-        channel-id: "C033QLM5P7D" # dev-staging-stream
-        slack-message: "Periodic TPC-H perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
-      env:
-        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

.github/workflows/build_and_test.yml

@@ -7,10 +7,6 @@ on:
       - release
   pull_request:
 
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
 concurrency:
   # Allow only one workflow per any non-`main` branch.
   group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
@@ -22,8 +18,8 @@ env:
 
 jobs:
   tag:
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
+    runs-on: dev
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
     outputs:
       build-tag: ${{steps.build-tag.outputs.tag}}
 
@@ -49,85 +45,8 @@ jobs:
         shell: bash
         id: build-tag
 
-  check-codestyle-python:
-    runs-on: [ self-hosted, dev, x64 ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cloud:pinned
-      options: --init
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: false
-          fetch-depth: 1
-
-      - name: Cache poetry deps
-        id: cache_poetry
-        uses: actions/cache@v3
-        with:
-          path: ~/.cache/pypoetry/virtualenvs
-          key: v1-codestyle-python-deps-${{ hashFiles('poetry.lock') }}
-
-      - name: Install Python deps
-        run: ./scripts/pysync
-
-      - name: Run isort to ensure code format
-        run: poetry run isort --diff --check .
-
-      - name: Run black to ensure code format
-        run: poetry run black --diff --check .
-
-      - name: Run flake8 to ensure code format
-        run: poetry run flake8 .
-
-      - name: Run mypy to check types
-        run: poetry run mypy .
-
-  check-codestyle-rust:
-    runs-on: [ self-hosted, dev, x64 ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 1
-
-      - name: Restore cargo deps cache
-        id: cache_cargo
-        uses: actions/cache@v3
-        with:
-          path: |
-            ~/.cargo/registry/
-            !~/.cargo/registry/src
-            ~/.cargo/git/
-            target/
-          key: v1-${{ runner.os }}-cargo-clippy-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
-
-      # Some of our rust modules use FFI and need those to be checked
-      - name: Get postgres headers
-        run: make postgres-headers -j$(nproc)
-      - name: Run cargo clippy
-        run: ./run_clippy.sh
-
-      # Use `${{ !cancelled() }}` to run quck tests after the longer clippy run
-      - name: Check formatting
-        if: ${{ !cancelled() }}
-        run: cargo fmt --all -- --check
-
-      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
-      - name: Check rust dependencies
-        if: ${{ !cancelled() }}
-        run: |
-          cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
-          cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack
-
   build-neon:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -160,10 +79,12 @@ jobs:
       - name: Set pg 14 revision for caching
         id: pg_v14_rev
         run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
+        shell: bash -euxo pipefail {0}
 
       - name: Set pg 15 revision for caching
         id: pg_v15_rev
         run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
+        shell: bash -euxo pipefail {0}
 
       # Set some environment variables used by all the steps.
       #
@@ -180,15 +101,16 @@ jobs:
           if [[ $BUILD_TYPE == "debug" ]]; then
             cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
             CARGO_FEATURES="--features testing"
-            CARGO_FLAGS="--locked $CARGO_FEATURES"
+            CARGO_FLAGS="--locked --timings $CARGO_FEATURES"
           elif [[ $BUILD_TYPE == "release" ]]; then
             cov_prefix=""
             CARGO_FEATURES="--features testing,profiling"
-            CARGO_FLAGS="--locked --release $CARGO_FEATURES"
+            CARGO_FLAGS="--locked --timings --release $CARGO_FEATURES"
           fi
           echo "cov_prefix=${cov_prefix}" >> $GITHUB_ENV
           echo "CARGO_FEATURES=${CARGO_FEATURES}" >> $GITHUB_ENV
           echo "CARGO_FLAGS=${CARGO_FLAGS}" >> $GITHUB_ENV
+        shell: bash -euxo pipefail {0}
 
       # Don't include the ~/.cargo/registry/src directory. It contains just
       # uncompressed versions of the crates in ~/.cargo/registry/cache
@@ -205,8 +127,8 @@ jobs:
             target/
           # Fall back to older versions of the key, if no cache for current Cargo.lock was found
           key: |
-            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
-            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-
+            v10-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('Cargo.lock') }}
+            v10-${{ runner.os }}-${{ matrix.build_type }}-cargo-
 
       - name: Cache postgres v14 build
         id: cache_pg_14
@@ -225,21 +147,26 @@ jobs:
       - name: Build postgres v14
         if: steps.cache_pg_14.outputs.cache-hit != 'true'
         run: mold -run make postgres-v14 -j$(nproc)
+        shell: bash -euxo pipefail {0}
 
       - name: Build postgres v15
         if: steps.cache_pg_15.outputs.cache-hit != 'true'
         run: mold -run make postgres-v15 -j$(nproc)
+        shell: bash -euxo pipefail {0}
 
       - name: Build neon extensions
         run: mold -run make neon-pg-ext -j$(nproc)
+        shell: bash -euxo pipefail {0}
 
       - name: Run cargo build
         run: |
           ${cov_prefix} mold -run cargo build $CARGO_FLAGS --bins --tests
+        shell: bash -euxo pipefail {0}
 
       - name: Run cargo test
         run: |
           ${cov_prefix} cargo test $CARGO_FLAGS
+        shell: bash -euxo pipefail {0}
 
       - name: Install rust binaries
         run: |
@@ -280,9 +207,11 @@ jobs:
               echo "/tmp/neon/bin/$bin" >> /tmp/coverage/binaries.list
             done
           fi
+        shell: bash -euxo pipefail {0}
 
       - name: Install postgres binaries
         run: cp -a pg_install /tmp/neon/pg_install
+        shell: bash -euxo pipefail {0}
 
       - name: Upload Neon artifact
         uses: ./.github/actions/upload
@@ -290,13 +219,24 @@ jobs:
           name: neon-${{ runner.os }}-${{ matrix.build_type }}-artifact
           path: /tmp/neon
 
+      - name: Prepare cargo build timing stats for storing
+        run: |
+          mkdir -p "/tmp/neon/cargo-timings/$BUILD_TYPE/"
+          cp -r ./target/cargo-timings/* "/tmp/neon/cargo-timings/$BUILD_TYPE/"
+        shell: bash -euxo pipefail {0}
+      - name: Upload cargo build stats
+        uses: ./.github/actions/upload
+        with:
+          name: neon-${{ runner.os }}-${{ matrix.build_type }}-build-stats
+          path: /tmp/neon/cargo-timings/
+
       # XXX: keep this after the binaries.list is formed, so the coverage can properly work later
       - name: Merge and upload coverage data
         if: matrix.build_type == 'debug'
         uses: ./.github/actions/save-coverage-data
 
   regress-tests:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -310,7 +250,7 @@ jobs:
         uses: actions/checkout@v3
         with:
           submodules: true
-          fetch-depth: 1
+          fetch-depth: 2
 
       - name: Pytest regression tests
         uses: ./.github/actions/run-python-test-set
@@ -328,8 +268,34 @@ jobs:
         if: matrix.build_type == 'debug'
         uses: ./.github/actions/save-coverage-data
 
+  upload-latest-artifacts:
+    runs-on: dev
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+    needs: [ regress-tests ]
+    if: github.ref_name == 'main'
+    steps:
+      - name: Copy Neon artifact to the latest directory
+        shell: bash -euxo pipefail {0}
+        env:
+          BUCKET: neon-github-public-dev
+          PREFIX: artifacts/${{ github.run_id }}
+        run: |
+          for build_type in debug release; do
+            FILENAME=neon-${{ runner.os }}-${build_type}-artifact.tar.zst
+
+            S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${PREFIX} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
+            if [ -z "${S3_KEY}" ]; then
+              echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
+              exit 1
+            fi
+
+            time aws s3 cp --only-show-errors s3://${BUCKET}/${S3_KEY} s3://${BUCKET}/artifacts/latest/${FILENAME}
+          done
+
   benchmarks:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -344,7 +310,7 @@ jobs:
         uses: actions/checkout@v3
         with:
           submodules: true
-          fetch-depth: 1
+          fetch-depth: 2
 
       - name: Pytest benchmarks
         uses: ./.github/actions/run-python-test-set
@@ -360,12 +326,12 @@ jobs:
       # while coverage is currently collected for the debug ones
 
   merge-allure-report:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
     needs: [ regress-tests, benchmarks ]
-    if: ${{ !cancelled() }}
+    if: always()
     strategy:
       fail-fast: false
       matrix:
@@ -390,6 +356,7 @@ jobs:
           SHA: ${{ github.event.pull_request.head.sha || github.sha }}
           REPORT_URL: ${{ steps.create-allure-report.outputs.report-url }}
           TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR }}
+        shell: bash -euxo pipefail {0}
         run: |
           curl --fail --output suites.json ${REPORT_URL%/index.html}/data/suites.json
           ./scripts/pysync
@@ -397,7 +364,7 @@ jobs:
           DATABASE_URL="$TEST_RESULT_CONNSTR" poetry run python3 scripts/ingest_regress_test_result.py --revision ${SHA} --reference ${GITHUB_REF} --build-type ${BUILD_TYPE} --ingest suites.json
 
   coverage-report:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -422,7 +389,7 @@ jobs:
             !~/.cargo/registry/src
             ~/.cargo/git/
             target/
-          key: v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
+          key: v10-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('Cargo.lock') }}
 
       - name: Get Neon artifact
         uses: ./.github/actions/download
@@ -438,6 +405,7 @@ jobs:
 
       - name: Merge coverage data
         run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
+        shell: bash -euxo pipefail {0}
 
       - name: Build and upload coverage report
         run: |
@@ -470,21 +438,18 @@ jobs:
               \"description\": \"Coverage report is ready\",
               \"target_url\": \"$REPORT_URL\"
             }"
+        shell: bash -euxo pipefail {0}
 
   trigger-e2e-tests:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
       options: --init
-    needs: [ push-docker-hub, tag ]
+    needs: [ build-neon ]
     steps:
       - name: Set PR's status to pending and request a remote CI test
         run: |
-          # For pull requests, GH Actions set "github.sha" variable to point at a fake merge commit
-          # but we need to use a real sha of a latest commit in the PR's branch for the e2e job,
-          # to place a job run status update later.
           COMMIT_SHA=${{ github.event.pull_request.head.sha }}
-          # For non-PR kinds of runs, the above will produce an empty variable, pick the original sha value for those
           COMMIT_SHA=${COMMIT_SHA:-${{ github.sha }}}
 
           REMOTE_REPO="${{ github.repository_owner }}/cloud"
@@ -510,19 +475,14 @@ jobs:
               \"inputs\": {
                 \"ci_job_name\": \"neon-cloud-e2e\",
                 \"commit_hash\": \"$COMMIT_SHA\",
-                \"remote_repo\": \"${{ github.repository }}\",
-                \"storage_image_tag\": \"${{ needs.tag.outputs.build-tag }}\",
-                \"compute_image_tag\": \"${{ needs.tag.outputs.build-tag }}\"
+                \"remote_repo\": \"${{ github.repository }}\"
               }
             }"
 
   neon-image:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     needs: [ tag ]
     container: gcr.io/kaniko-project/executor:v1.9.0-debug
-    defaults:
-      run:
-        shell: sh -eu {0}
 
     steps:
       - name: Checkout
@@ -538,12 +498,9 @@ jobs:
         run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --build-arg GIT_VERSION=${{ github.sha }} --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}}
 
   compute-tools-image:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     needs: [ tag ]
     container: gcr.io/kaniko-project/executor:v1.9.0-debug
-    defaults:
-      run:
-        shell: sh -eu {0}
 
     steps:
       - name: Checkout
@@ -555,14 +512,30 @@ jobs:
       - name: Kaniko build compute tools
         run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-tools --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}}
 
-  compute-node-image-v14:
-    runs-on: [ self-hosted, dev, x64 ]
+  compute-node-image:
+    runs-on: dev
     container: gcr.io/kaniko-project/executor:v1.9.0-debug
     needs: [ tag ]
-    defaults:
-      run:
-        shell: sh -eu {0}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v1 # v3 won't work with kaniko
+        with:
+          submodules: true
+          fetch-depth: 0
 
+      - name: Configure ECR login
+        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
+
+        # compute-node uses postgres 14, which is default now
+        # cloud repo depends on this image name, thus duplicating it
+        # remove compute-node when cloud repo is updated
+      - name: Kaniko build compute node with extensions v14 (compatibility)
+        run: /kaniko/executor --skip-unused-stages --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-node-v14 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:${{needs.tag.outputs.build-tag}}
+
+  compute-node-image-v14:
+    runs-on: dev
+    container: gcr.io/kaniko-project/executor:v1.9.0-debug
+    needs: [ tag ]
     steps:
       - name: Checkout
         uses: actions/checkout@v1 # v3 won't work with kaniko
@@ -576,14 +549,11 @@ jobs:
       - name: Kaniko build compute node with extensions v14
         run: /kaniko/executor --skip-unused-stages  --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache  --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-node-v14 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}}
 
+
   compute-node-image-v15:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container: gcr.io/kaniko-project/executor:v1.9.0-debug
     needs: [ tag ]
-    defaults:
-      run:
-        shell: sh -eu {0}
-
     steps:
       - name: Checkout
         uses: actions/checkout@v1 # v3 won't work with kaniko
@@ -597,58 +567,18 @@ jobs:
       - name: Kaniko build compute node with extensions v15
         run: /kaniko/executor --skip-unused-stages --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-node-v15 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}}
 
-  test-images:
-    needs: [ tag, neon-image, compute-node-image-v14, compute-node-image-v15, compute-tools-image ]
-    runs-on: [ self-hosted, dev, x64 ]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      # `neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
-      # Pick pageserver as currently the only binary with extra "version" features printed in the string to verify.
-      # Regular pageserver version string looks like
-      #   Neon page server git-env:32d14403bd6ab4f4520a94cbfd81a6acef7a526c failpoints: true, features: []
-      # Bad versions might loop like:
-      #   Neon page server git-env:local failpoints: true, features: ["testing"]
-      # Ensure that we don't have bad versions.
-      - name: Verify image versions
-        shell: bash # ensure no set -e for better error messages
-        run: |
-          pageserver_version=$(docker run --rm 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} "/bin/sh" "-c" "/usr/local/bin/pageserver --version")
-
-          echo "Pageserver version string: $pageserver_version"
-
-          if ! echo "$pageserver_version" | grep -qv 'git-env:local' ; then
-            echo "Pageserver version should not be the default Dockerfile one"
-            exit 1
-          fi
-
-          if ! echo "$pageserver_version" | grep -qv '"testing"' ; then
-            echo "Pageserver version should have no testing feature enabled"
-            exit 1
-          fi
-
-      - name: Verify docker-compose example
-        run: env REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com TAG=${{needs.tag.outputs.build-tag}} ./docker-compose/docker_compose_test.sh
-
-      - name: Print logs and clean up
-        if: always()
-        run: |
-          docker compose -f ./docker-compose/docker-compose.yml logs || 0
-          docker compose -f ./docker-compose/docker-compose.yml down
-
   promote-images:
-    runs-on: [ self-hosted, dev, x64 ]
-    needs: [ tag, test-images ]
+    runs-on: dev
+    needs: [ tag, neon-image, compute-node-image, compute-node-image-v14, compute-node-image-v15, compute-tools-image ]
     if: github.event_name != 'workflow_dispatch'
     container: amazon/aws-cli
     strategy:
       fail-fast: false
       matrix:
-        name: [ neon, compute-node-v14, compute-node-v15, compute-tools ]
+        # compute-node uses postgres 14, which is default now
+        # cloud repo depends on this image name, thus duplicating it
+        # remove compute-node when cloud repo is updated
+        name: [ neon, compute-node, compute-node-v14, compute-node-v15, compute-tools ]
 
     steps:
       - name: Promote image to latest
@@ -657,7 +587,7 @@ jobs:
           aws ecr put-image --repository-name ${{ matrix.name }} --image-tag latest --image-manifest "$MANIFEST"
 
   push-docker-hub:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     needs: [ promote-images, tag ]
     container: golang:1.19-bullseye
 
@@ -678,6 +608,9 @@ jobs:
       - name: Pull compute tools image from ECR
         run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} compute-tools
 
+      - name: Pull compute node image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:${{needs.tag.outputs.build-tag}} compute-node
+
       - name: Pull compute node v14 image from ECR
         run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} compute-node-v14
 
@@ -694,6 +627,7 @@ jobs:
         run: |
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/neon:latest
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:latest
+          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node:latest
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:latest
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:latest
 
@@ -709,6 +643,9 @@ jobs:
       - name: Push compute tools image to Docker Hub
         run: crane push compute-tools neondatabase/compute-tools:${{needs.tag.outputs.build-tag}}
 
+      - name: Push compute node image to Docker Hub
+        run: crane push compute-node neondatabase/compute-node:${{needs.tag.outputs.build-tag}}
+
       - name: Push compute node v14 image to Docker Hub
         run: crane push compute-node-v14 neondatabase/compute-node-v14:${{needs.tag.outputs.build-tag}}
 
@@ -725,11 +662,12 @@ jobs:
         run: |
           crane tag neondatabase/neon:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-tools:${{needs.tag.outputs.build-tag}} latest
+          crane tag neondatabase/compute-node:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-node-v14:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-node-v15:${{needs.tag.outputs.build-tag}} latest
 
   calculate-deploy-targets:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: [ self-hosted, Linux, k8s-runner ]
     if: |
       (github.ref_name == 'main' || github.ref_name == 'release') &&
       github.event_name != 'workflow_dispatch'
@@ -739,11 +677,11 @@ jobs:
       - id: set-matrix
         run: |
           if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-            STAGING='{"env_name": "staging", "proxy_job": "neon-proxy", "proxy_config": "staging.proxy", "storage_broker_ns": "neon-storage-broker", "storage_broker_config": "staging.neon-storage-broker", "kubeconfig_secret": "STAGING_KUBECONFIG_DATA", "console_api_key_secret": "NEON_STAGING_API_KEY"}'
-            NEON_STRESS='{"env_name": "neon-stress", "proxy_job": "neon-stress-proxy", "proxy_config": "neon-stress.proxy", "storage_broker_ns": "neon-stress-storage-broker", "storage_broker_config": "neon-stress.neon-storage-broker", "kubeconfig_secret": "NEON_STRESS_KUBECONFIG_DATA", "console_api_key_secret": "NEON_CAPTEST_API_KEY"}'
+            STAGING='{"env_name": "staging", "proxy_job": "neon-proxy", "proxy_config": "staging.proxy", "kubeconfig_secret": "STAGING_KUBECONFIG_DATA", "console_api_key_secret": "NEON_STAGING_API_KEY"}'
+            NEON_STRESS='{"env_name": "neon-stress", "proxy_job": "neon-stress-proxy", "proxy_config": "neon-stress.proxy", "kubeconfig_secret": "NEON_STRESS_KUBECONFIG_DATA", "console_api_key_secret": "NEON_CAPTEST_API_KEY"}'
             echo "include=[$STAGING, $NEON_STRESS]" >> $GITHUB_OUTPUT
           elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-            PRODUCTION='{"env_name": "production", "proxy_job": "neon-proxy", "proxy_config": "production.proxy", "storage_broker_ns": "neon-storage-broker", "storage_broker_config": "production.neon-storage-broker", "kubeconfig_secret": "PRODUCTION_KUBECONFIG_DATA", "console_api_key_secret": "NEON_PRODUCTION_API_KEY"}'
+            PRODUCTION='{"env_name": "production", "proxy_job": "neon-proxy", "proxy_config": "production.proxy", "kubeconfig_secret": "PRODUCTION_KUBECONFIG_DATA", "console_api_key_secret": "NEON_PRODUCTION_API_KEY"}'
             echo "include=[$PRODUCTION]" >> $GITHUB_OUTPUT
           else
             echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
@@ -751,8 +689,8 @@ jobs:
           fi
 
   deploy:
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
+    runs-on: [ self-hosted, Linux, k8s-runner ]
+    #container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
     # We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
     # If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
     needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
@@ -803,11 +741,11 @@ jobs:
           ssh-add ssh-key
           rm -f ssh-key ssh-key-cert.pub
           ansible-galaxy collection install sivel.toiletwater
-          ansible-playbook deploy.yaml -i ${{ matrix.env_name }}.hosts.yaml -e CONSOLE_API_TOKEN=${{ secrets[matrix.console_api_key_secret] }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          ansible-playbook deploy.yaml -i ${{ matrix.env_name }}.hosts.yaml -e CONSOLE_API_TOKEN=${{ secrets[matrix.console_api_key_secret] }}
           rm -f neon_install.tar.gz .neon_current_version
 
   deploy-new:
-    runs-on: [ self-hosted, dev, x64 ]
+    runs-on: dev
     container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
     # We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
     # If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
@@ -832,6 +770,7 @@ jobs:
         run: |
           export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
           cd "$(pwd)/.github/ansible"
+
           if [[ "$GITHUB_REF_NAME" == "main" ]]; then
             ./get_binaries.sh
           elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
@@ -840,41 +779,9 @@ jobs:
             echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
             exit 1
           fi
-          ansible-galaxy collection install sivel.toiletwater
-          ansible-playbook deploy.yaml -i staging.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_STAGING_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
-          rm -f neon_install.tar.gz .neon_current_version
-
-  deploy-pr-test-new:
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-    # We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
-    # If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
-    needs: [ push-docker-hub, tag, regress-tests ]
-    if: |
-      contains(github.event.pull_request.labels.*.name, 'deploy-test-storage') &&
-      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        target_region: [ eu-west-1 ]
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Redeploy
-        run: |
-          export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          cd "$(pwd)/.github/ansible"
-
-          ./get_binaries.sh
 
           ansible-galaxy collection install sivel.toiletwater
-          ansible-playbook deploy.yaml -i staging.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_STAGING_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          ansible-playbook deploy.yaml -i staging.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{secrets.NEON_STAGING_API_KEY}}
           rm -f neon_install.tar.gz .neon_current_version
 
   deploy-prod-new:
@@ -882,7 +789,7 @@ jobs:
     container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
     # We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
     # If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
-    needs: [ push-docker-hub, tag, regress-tests ]
+    needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
     if: |
       (github.ref_name == 'release') &&
       github.event_name != 'workflow_dispatch'
@@ -914,12 +821,12 @@ jobs:
           fi
 
           ansible-galaxy collection install sivel.toiletwater
-          ansible-playbook deploy.yaml -i prod.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_PRODUCTION_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          ansible-playbook deploy.yaml -i prod.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{secrets.NEON_PRODUCTION_API_KEY}}
           rm -f neon_install.tar.gz .neon_current_version
 
   deploy-proxy:
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
+    runs-on: dev
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
     # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
     needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
     if: |
@@ -956,55 +863,14 @@ jobs:
       - name: Re-deploy proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade ${{ matrix.proxy_job }}       neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}.yaml       --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-          helm upgrade ${{ matrix.proxy_job }}-scram neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+          helm upgrade ${{ matrix.proxy_job }}       neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
+          helm upgrade ${{ matrix.proxy_job }}-scram neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}-scram.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
 
-  deploy-storage-broker:
-    name: deploy storage broker on old staging and old prod
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
+  deploy-proxy-new:
+    runs-on: dev
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
     # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
     needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
-    if: |
-      (github.ref_name == 'main' || github.ref_name == 'release') &&
-      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
-    env:
-      KUBECONFIG: .kubeconfig
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Add curl
-        run: apt update && apt install curl -y
-
-      - name: Store kubeconfig file
-        run: |
-          echo "${{ secrets[matrix.kubeconfig_secret] }}" | base64 --decode > ${KUBECONFIG}
-          chmod 0600 ${KUBECONFIG}
-
-      - name: Setup helm v3
-        run: |
-          curl -s https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-          helm repo add neondatabase https://neondatabase.github.io/helm-charts
-
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker neondatabase/neon-storage-broker --namespace ${{ matrix.storage_broker_ns }} --create-namespace --install --atomic -f .github/helm-values/${{ matrix.storage_broker_config }}.yaml --set image.tag=${{ needs.tag.outputs.build-tag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
-
-  deploy-proxy-new:
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
-    needs: [ push-docker-hub, tag, regress-tests ]
     if: |
       (github.ref_name == 'main') &&
       github.event_name != 'workflow_dispatch'
@@ -1016,12 +882,6 @@ jobs:
         include:
           - target_region:  us-east-2
             target_cluster: dev-us-east-2-beta
-            deploy_link_proxy: true
-            deploy_legacy_scram_proxy: true
-          - target_region:  eu-west-1
-            target_cluster: dev-eu-west-1-zeta
-            deploy_link_proxy: false
-            deploy_legacy_scram_proxy: false
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -1034,62 +894,16 @@ jobs:
           helm repo add neondatabase https://neondatabase.github.io/helm-charts
           aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
 
-      - name: Re-deploy scram proxy
+      - name: Re-deploy proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-
-      - name: Re-deploy link proxy
-        if: matrix.deploy_link_proxy
-        run: |
-          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-
-      - name: Re-deploy legacy scram proxy
-        if: matrix.deploy_legacy_scram_proxy
-        run: |
-          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram-legacy.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-
-  deploy-storage-broker-dev-new:
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
-    needs: [ push-docker-hub, tag, regress-tests ]
-    if: |
-      (github.ref_name == 'main') &&
-      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  us-east-2
-            target_cluster: dev-us-east-2-beta
-          - target_region:  eu-west-1
-            target_cluster: dev-eu-west-1-zeta
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Configure environment
-        run: |
-          helm repo add neondatabase https://neondatabase.github.io/helm-charts
-          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
-
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker neondatabase/neon-storage-broker --namespace neon-storage-broker --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ needs.tag.outputs.build-tag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
+          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
 
   deploy-proxy-prod-new:
     runs-on: prod
     container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
     # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
-    needs: [ push-docker-hub, tag, regress-tests ]
+    needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
     if: |
       (github.ref_name == 'release') &&
       github.event_name != 'workflow_dispatch'
@@ -1101,8 +915,6 @@ jobs:
         include:
           - target_region:  us-east-2
             target_cluster: prod-us-east-2-delta
-          - target_region:  us-west-2
-            target_cluster: prod-us-west-2-eta
           - target_region: eu-central-1
             target_cluster: prod-eu-central-1-gamma
           - target_region: ap-southeast-1
@@ -1122,48 +934,10 @@ jobs:
       - name: Re-deploy proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
 
-  deploy-storage-broker-prod-new:
-    runs-on: prod
-    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
-    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
-    needs: [ push-docker-hub, tag, regress-tests ]
-    if: |
-      (github.ref_name == 'release') &&
-      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  us-east-2
-            target_cluster: prod-us-east-2-delta
-          - target_region:  us-west-2
-            target_cluster: prod-us-west-2-eta
-          - target_region: eu-central-1
-            target_cluster: prod-eu-central-1-gamma
-          - target_region: ap-southeast-1
-            target_cluster: prod-ap-southeast-1-epsilon
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Configure environment
-        run: |
-          helm repo add neondatabase https://neondatabase.github.io/helm-charts
-          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
-
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker neondatabase/neon-storage-broker --namespace neon-storage-broker --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ needs.tag.outputs.build-tag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
-
-  promote-compatibility-data:
-    runs-on: [ self-hosted, dev, x64 ]
+  promote-compatibility-test-snapshot:
+    runs-on: dev
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -1171,28 +945,14 @@ jobs:
     if: github.ref_name == 'release' && github.event_name != 'workflow_dispatch'
     steps:
       - name: Promote compatibility snapshot for the release
+        shell: bash -euxo pipefail {0}
         env:
           BUCKET: neon-github-public-dev
           PREFIX: artifacts/latest
         run: |
-          # Update compatibility snapshot for the release
           for build_type in debug release; do
             OLD_FILENAME=compatibility-snapshot-${build_type}-pg14-${GITHUB_RUN_ID}.tar.zst
             NEW_FILENAME=compatibility-snapshot-${build_type}-pg14.tar.zst
 
             time aws s3 mv --only-show-errors s3://${BUCKET}/${PREFIX}/${OLD_FILENAME} s3://${BUCKET}/${PREFIX}/${NEW_FILENAME}
           done
-
-          # Update Neon artifact for the release (reuse already uploaded artifact)
-          for build_type in debug release; do
-            OLD_PREFIX=artifacts/${GITHUB_RUN_ID}
-            FILENAME=neon-${{ runner.os }}-${build_type}-artifact.tar.zst
-
-            S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${OLD_PREFIX} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
-            if [ -z "${S3_KEY}" ]; then
-              echo 2>&1 "Neither s3://${BUCKET}/${OLD_PREFIX}/${FILENAME} nor its version from previous attempts exist"
-              exit 1
-            fi
-
-            time aws s3 cp --only-show-errors s3://${BUCKET}/${S3_KEY} s3://${BUCKET}/${PREFIX}/${FILENAME}
-          done

.github/workflows/codestyle.yml

@@ -0,0 +1,166 @@
+name: Check code style and build
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+defaults:
+  run:
+    shell: bash -euxo pipefail {0}
+
+concurrency:
+  # Allow only one workflow per any non-`main` branch.
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
+  cancel-in-progress: true
+
+env:
+  RUST_BACKTRACE: 1
+  COPT: '-Werror'
+
+jobs:
+  check-codestyle-rust:
+    strategy:
+      fail-fast: false
+      matrix:
+        # XXX: both OSes have rustup
+        #   * https://github.com/actions/runner-images/blob/main/images/macos/macos-12-Readme.md#rust-tools
+        #   * https://github.com/actions/runner-images/blob/main/images/linux/Ubuntu2204-Readme.md#rust-tools
+        # this is all we need to install our toolchain later via rust-toolchain.toml
+        # so don't install any toolchain explicitly.
+        os: [ubuntu-latest, macos-latest]
+    timeout-minutes: 90
+    name: check codestyle rust and postgres
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 2
+
+      - name: Check formatting
+        run: cargo fmt --all -- --check
+
+      - name: Install Ubuntu postgres dependencies
+        if: matrix.os == 'ubuntu-latest'
+        run: |
+          sudo apt update
+          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev
+
+      - name: Install macOS postgres dependencies
+        if: matrix.os == 'macos-latest'
+        run: brew install flex bison openssl
+
+      - name: Set pg 14 revision for caching
+        id: pg_v14_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
+        shell: bash -euxo pipefail {0}
+
+      - name: Set pg 15 revision for caching
+        id: pg_v15_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
+        shell: bash -euxo pipefail {0}
+
+      - name: Cache postgres v14 build
+        id: cache_pg_14
+        uses: actions/cache@v3
+        with:
+          path: pg_install/v14
+          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+
+      - name: Cache postgres v15 build
+        id: cache_pg_15
+        uses: actions/cache@v3
+        with:
+          path: pg_install/v15
+          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
+
+      - name: Set extra env for macOS
+        if: matrix.os == 'macos-latest'
+        run: |
+          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
+          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
+
+      - name: Build postgres v14
+        if: steps.cache_pg_14.outputs.cache-hit != 'true'
+        run: make postgres-v14
+        shell: bash -euxo pipefail {0}
+
+      - name: Build postgres v15
+        if: steps.cache_pg_15.outputs.cache-hit != 'true'
+        run: make postgres-v15
+        shell: bash -euxo pipefail {0}
+
+      - name: Build neon extensions
+        run: make neon-pg-ext
+
+      - name: Cache cargo deps
+        id: cache_cargo
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cargo/registry
+            !~/.cargo/registry/src
+            ~/.cargo/git
+            target
+          key: v6-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust
+
+      - name: Run cargo clippy
+        run: ./run_clippy.sh
+
+      - name: Ensure all project builds
+        run: cargo build --locked --all --all-targets
+
+  check-rust-dependencies:
+    runs-on: dev
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: false
+          fetch-depth: 1
+
+      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
+      - name: Check every project module is covered by Hakari
+        run: |
+          cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
+          cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack
+        shell: bash -euxo pipefail {0}
+
+  check-codestyle-python:
+    runs-on: [ self-hosted, Linux, k8s-runner ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: false
+          fetch-depth: 1
+
+      - name: Cache poetry deps
+        id: cache_poetry
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pypoetry/virtualenvs
+          key: v1-codestyle-python-deps-${{ hashFiles('poetry.lock') }}
+
+      - name: Install Python deps
+        run: ./scripts/pysync
+
+      - name: Run isort to ensure code format
+        run: poetry run isort --diff --check .
+
+      - name: Run black to ensure code format
+        run: poetry run black --diff --check .
+
+      - name: Run flake8 to ensure code format
+        run: poetry run flake8 .
+
+      - name: Run mypy to check types
+        run: poetry run mypy .

.github/workflows/neon_extra_builds.yml

@@ -1,128 +0,0 @@
-name: Check neon with extra platform builds
-
-on:
-  push:
-    branches:
-    - main
-
-defaults:
-  run:
-    shell: bash -euxo pipefail {0}
-
-concurrency:
-  # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
-  cancel-in-progress: true
-
-env:
-  RUST_BACKTRACE: 1
-  COPT: '-Werror'
-
-jobs:
-  check-macos-build:
-    timeout-minutes: 90
-    runs-on: macos-latest
-
-    env:
-      # Use release build only, to have less debug info around
-      # Hence keeping target/ (and general cache size) smaller
-      BUILD_TYPE: release
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 1
-
-      - name: Install macOS postgres dependencies
-        run: brew install flex bison openssl protobuf
-
-      - name: Set pg 14 revision for caching
-        id: pg_v14_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
-
-      - name: Set pg 15 revision for caching
-        id: pg_v15_rev
-        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
-
-      - name: Cache postgres v14 build
-        id: cache_pg_14
-        uses: actions/cache@v3
-        with:
-          path: pg_install/v14
-          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-
-      - name: Cache postgres v15 build
-        id: cache_pg_15
-        uses: actions/cache@v3
-        with:
-          path: pg_install/v15
-          key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
-
-      - name: Set extra env for macOS
-        run: |
-          echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
-          echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
-
-      - name: Cache cargo deps
-        uses: actions/cache@v3
-        with:
-          path: |
-            ~/.cargo/registry
-            !~/.cargo/registry/src
-            ~/.cargo/git
-            target
-          key: v1-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
-
-      - name: Build postgres v14
-        if: steps.cache_pg_14.outputs.cache-hit != 'true'
-        run: make postgres-v14 -j$(nproc)
-
-      - name: Build postgres v15
-        if: steps.cache_pg_15.outputs.cache-hit != 'true'
-        run: make postgres-v15 -j$(nproc)
-
-      - name: Build neon extensions
-        run: make neon-pg-ext -j$(nproc)
-
-      - name: Run cargo build
-        run: cargo build --all --release
-
-      - name: Check that no warnings are produced
-        run: ./run_clippy.sh
-
-  gather-rust-build-stats:
-    timeout-minutes: 90
-    runs-on: ubuntu-latest
-
-    env:
-      BUILD_TYPE: release
-      # build with incremental compilation produce partial results
-      # so do not attempt to cache this build, also disable the incremental compilation
-      CARGO_INCREMENTAL: 0
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 1
-
-      - name: Install Ubuntu postgres dependencies
-        run: |
-          sudo apt update
-          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev protobuf-compiler
-
-      # Some of our rust modules use FFI and need those to be checked
-      - name: Get postgres headers
-        run: make postgres-headers -j$(nproc)
-
-      - name: Produce the build stats
-        run: cargo build --all --release --timings
-
-      - name: Upload the build stats
-        uses: actions/upload-artifact@v3
-        with:
-          name: neon-${{ runner.os }}-release-build-stats
-          path: ./target/cargo-timings/

.github/workflows/pg_clients.yml

@@ -23,7 +23,6 @@ jobs:
     runs-on: [ ubuntu-latest ]
 
     env:
-      DEFAULT_PG_VERSION: 14
       TEST_OUTPUT: /tmp/test_output
 
     steps:
@@ -52,8 +51,8 @@ jobs:
       id: create-neon-project
       uses: ./.github/actions/neon-project-create
       with:
+        environment: staging
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
-        postgres_version: ${{ env.DEFAULT_PG_VERSION }}
 
     - name: Run pytest
       env:
@@ -64,7 +63,7 @@ jobs:
       run: |
         # Test framework expects we have psql binary;
         # but since we don't really need it in this test, let's mock it
-        mkdir -p "$POSTGRES_DISTRIB_DIR/v${DEFAULT_PG_VERSION}/bin" && touch "$POSTGRES_DISTRIB_DIR/v${DEFAULT_PG_VERSION}/bin/psql";
+        mkdir -p "$POSTGRES_DISTRIB_DIR/v14/bin" && touch "$POSTGRES_DISTRIB_DIR/v14/bin/psql";
         ./scripts/pytest \
           --junitxml=$TEST_OUTPUT/junit.xml \
           --tb=short \
@@ -76,6 +75,7 @@ jobs:
       if: ${{ always() }}
       uses: ./.github/actions/neon-project-delete
       with:
+        environment: staging
         project_id: ${{ steps.create-neon-project.outputs.project_id }}
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 

.gitmodules

@@ -1,7 +1,7 @@
 [submodule "vendor/postgres-v14"]
 	path = vendor/postgres-v14
 	url = https://github.com/neondatabase/postgres.git
-	branch = REL_14_STABLE_neon
+	branch = main
 [submodule "vendor/postgres-v15"]
 	path = vendor/postgres-v15
 	url = https://github.com/neondatabase/postgres.git

CODEOWNERS

@@ -1,11 +0,0 @@
-/compute_tools/ @neondatabase/control-plane
-/control_plane/ @neondatabase/compute @neondatabase/storage
-/libs/pageserver_api/ @neondatabase/compute @neondatabase/storage
-/libs/postgres_ffi/ @neondatabase/compute 
-/libs/remote_storage/ @neondatabase/storage 
-/libs/safekeeper_api/ @neondatabase/safekeepers  
-/pageserver/ @neondatabase/compute @neondatabase/storage 
-/pgxn/ @neondatabase/compute
-/proxy/ @neondatabase/control-plane 
-/safekeeper/ @neondatabase/safekeepers
-/vendor/ @neondatabase/compute

Cargo.toml

@@ -16,7 +16,6 @@ members = [
     "pageserver",
     "proxy",
     "safekeeper",
-    "storage_broker",
     "workspace_hack",
     "libs/*",
 ]
@@ -26,10 +25,6 @@ members = [
 # Besides, debug info should not affect the performance.
 debug = true
 
-# disable debug symbols for all packages except this one to decrease binaries size
-[profile.release.package."*"]
-debug = false
-
 [profile.release-line-debug]
 inherits = "release"
 debug = 1 # true = 2 = all symbols, 1 = line only

Dockerfile

@@ -44,7 +44,7 @@ COPY . .
 # Show build caching stats to check if it was used in the end.
 # Has to be the part of the same RUN since cachepot daemon is killed in the end of this RUN, losing the compilation stats.
 RUN set -e \
-&& mold -run cargo build --bin pageserver --bin pageserver_binutils --bin draw_timeline_dir --bin safekeeper --bin storage_broker --bin proxy --locked --release \
+&& mold -run cargo build --bin pageserver --bin pageserver_binutils --bin draw_timeline_dir --bin safekeeper --bin proxy --locked --release \
     && cachepot -s
 
 # Build final image
@@ -67,7 +67,6 @@ COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver_binutils /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/draw_timeline_dir   /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/safekeeper          /usr/local/bin
-COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_broker         /usr/local/bin
 COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy               /usr/local/bin
 
 COPY --from=pg-build /home/nonroot/pg_install/v14 /usr/local/v14/
@@ -79,7 +78,7 @@ COPY --from=pg-build /home/nonroot/postgres_install.tar.gz /data/
 RUN mkdir -p /data/.neon/ && chown -R neon:neon /data/.neon/ \
     && /usr/local/bin/pageserver -D /data/.neon/ --init \
        -c "id=1234" \
-       -c "broker_endpoint='http://storage_broker:50051'" \
+       -c "broker_endpoints=['http://etcd:2379']" \
        -c "pg_distrib_dir='/usr/local/'" \
        -c "listen_pg_addr='0.0.0.0:6400'" \
        -c "listen_http_addr='0.0.0.0:9898'"

Dockerfile.compute-node-v14

@@ -200,6 +200,9 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
 # libreadline8 for psql
 # libossp-uuid16 for extension ossp-uuid
 # libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
+#
+# Lastly, link compute_ctl into zenith_ctl while we're at it,
+# so that we don't need to put this in another layer.
 RUN apt update &&  \
     apt install --no-install-recommends -y \
         libreadline8 \
@@ -208,7 +211,8 @@ RUN apt update &&  \
         libgdal28 \
         libproj19 \
         libprotobuf-c1 && \
-    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
+    ln /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
 
 USER postgres
 ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Dockerfile.compute-node-v15

@@ -200,6 +200,9 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
 # libreadline8 for psql
 # libossp-uuid16 for extension ossp-uuid
 # libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
+#
+# Lastly, link compute_ctl into zenith_ctl while we're at it,
+# so that we don't need to put this in another layer.
 RUN apt update &&  \
     apt install --no-install-recommends -y \
         libreadline8 \
@@ -208,7 +211,8 @@ RUN apt update &&  \
         libgdal28 \
         libproj19 \
         libprotobuf-c1 && \
-    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
+    ln /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
 
 USER postgres
 ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Dockerfile.compute-node.legacy

@@ -0,0 +1,88 @@
+#
+# Legacy version of the Dockerfile for the compute node.
+# Used by e2e CI. Building Dockerfile.compute-node will take
+# unreasonable ammount of time without v2 runners.
+#
+# TODO: remove once cloud repo CI is moved to v2 runners.
+#
+
+
+# Allow specifiyng different compute-tools tag and image repo, so we are
+# able to use different images
+ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
+ARG IMAGE=compute-tools
+ARG TAG=latest
+
+#
+# Image with pre-built tools
+#
+FROM $REPOSITORY/$IMAGE:$TAG AS compute-deps
+# Only to get ready compute_ctl binary as deppendency
+
+#
+# Image with Postgres build deps
+#
+FROM debian:bullseye-slim AS build-deps
+
+RUN apt-get update && apt-get -yq install automake libtool build-essential bison flex libreadline-dev zlib1g-dev libxml2-dev \
+                                          libcurl4-openssl-dev libossp-uuid-dev
+
+#
+# Image with built Postgres
+#
+FROM build-deps AS pg-build
+
+# Add user postgres
+RUN adduser postgres
+RUN mkdir /pg && chown postgres:postgres /pg
+
+# Copy source files
+# version 14 is default for now
+COPY ./vendor/postgres-v14 /pg/
+COPY ./pgxn /pg/
+
+# Build and install Postgres locally
+RUN mkdir /pg/compute_build && cd /pg/compute_build && \
+    ../configure CFLAGS='-O2 -g3' --prefix=$(pwd)/postgres_bin --enable-debug --with-uuid=ossp && \
+    # Install main binaries and contribs
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
+    # Install headers
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/include install
+
+# Install neon contrib
+RUN make MAKELEVEL=0 PG_CONFIG=/pg/compute_build/postgres_bin/bin/pg_config -j $(getconf _NPROCESSORS_ONLN) -C /pg/neon install
+
+USER postgres
+WORKDIR /pg
+
+#
+# Final compute node image to be exported
+#
+FROM debian:bullseye-slim
+
+# libreadline-dev is required to run psql
+RUN apt-get update && apt-get -yq install libreadline-dev libossp-uuid-dev
+
+# Add user postgres
+RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
+    echo "postgres:test_console_pass" | chpasswd && \
+    mkdir /var/db/postgres/compute && mkdir /var/db/postgres/specs && \
+    chown -R postgres:postgres /var/db/postgres && \
+    chmod 0750 /var/db/postgres/compute
+
+# Copy ready Postgres binaries
+COPY --from=pg-build /pg/compute_build/postgres_bin /usr/local
+
+# Copy binaries from compute-tools
+COPY --from=compute-deps /usr/local/bin/compute_ctl /usr/local/bin/compute_ctl
+
+# XXX: temporary symlink for compatibility with old control-plane
+RUN ln -s /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
+
+# Add postgres shared objects to the search path
+RUN echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
+
+USER postgres
+
+ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Makefile

@@ -20,18 +20,18 @@ else
 	$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
 endif
 
+# Seccomp BPF is only available for Linux
 UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
-	# Seccomp BPF is only available for Linux
 	PG_CONFIGURE_OPTS += --with-libseccomp
-else ifeq ($(UNAME_S),Darwin)
-	# macOS with brew-installed openssl requires explicit paths
-	# It can be configured with OPENSSL_PREFIX variable
-	OPENSSL_PREFIX ?= $(shell brew --prefix openssl@3)
-	PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
-	# macOS already has bison and flex in the system, but they are old and result in postgres-v14 target failure
-	# brew formulae are keg-only and not symlinked into HOMEBREW_PREFIX, force their usage
-	EXTRA_PATH_OVERRIDES += $(shell brew --prefix bison)/bin/:$(shell brew --prefix flex)/bin/:
+endif
+
+# macOS with brew-installed openssl requires explicit paths
+# It can be configured with OPENSSL_PREFIX variable
+UNAME_S := $(shell uname -s)
+ifeq ($(UNAME_S),Darwin)
+    OPENSSL_PREFIX ?= $(shell brew --prefix openssl@3)
+    PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
 endif
 
 # Use -C option so that when PostgreSQL "make install" installs the
@@ -73,8 +73,7 @@ $(POSTGRES_INSTALL_DIR)/build/v14/config.status:
 	+@echo "Configuring Postgres v14 build"
 	mkdir -p $(POSTGRES_INSTALL_DIR)/build/v14
 	(cd $(POSTGRES_INSTALL_DIR)/build/v14 && \
-	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-v14/configure \
-		CFLAGS='$(PG_CFLAGS)' \
+	$(ROOT_PROJECT_DIR)/vendor/postgres-v14/configure CFLAGS='$(PG_CFLAGS)' \
 		$(PG_CONFIGURE_OPTS) \
 		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/v14 > configure.log)
 
@@ -82,8 +81,7 @@ $(POSTGRES_INSTALL_DIR)/build/v15/config.status:
 	+@echo "Configuring Postgres v15 build"
 	mkdir -p $(POSTGRES_INSTALL_DIR)/build/v15
 	(cd $(POSTGRES_INSTALL_DIR)/build/v15 && \
-	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-v15/configure \
-		CFLAGS='$(PG_CFLAGS)' \
+	$(ROOT_PROJECT_DIR)/vendor/postgres-v15/configure CFLAGS='$(PG_CFLAGS)' \
 		$(PG_CONFIGURE_OPTS) \
 		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/v15 > configure.log)
 
@@ -113,8 +111,6 @@ postgres-v14: postgres-v14-configure \
 	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14 MAKELEVEL=0 install
 	+@echo "Compiling libpq v14"
 	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/interfaces/libpq install
-	+@echo "Compiling pg_prewarm v14"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_prewarm install
 	+@echo "Compiling pg_buffercache v14"
 	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_buffercache install
 	+@echo "Compiling pageinspect v14"
@@ -127,8 +123,6 @@ postgres-v15: postgres-v15-configure \
 	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15 MAKELEVEL=0 install
 	+@echo "Compiling libpq v15"
 	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/src/interfaces/libpq install
-	+@echo "Compiling pg_prewarm v15"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pg_prewarm install
 	+@echo "Compiling pg_buffercache v15"
 	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pg_buffercache install
 	+@echo "Compiling pageinspect v15"

README.md

@@ -2,20 +2,29 @@
 
 Neon is a serverless open-source alternative to AWS Aurora Postgres. It separates storage and compute and substitutes the PostgreSQL storage layer by redistributing data across a cluster of nodes.
 
+The project used to be called "Zenith". Many of the commands and code comments
+still refer to "zenith", but we are in the process of renaming things.
+
 ## Quick start
-Try the [Neon Free Tier](https://neon.tech/docs/introduction/technical-preview-free-tier/) to create a serverless Postgres instance. Then connect to it with your preferred Postgres client (psql, dbeaver, etc) or use the online [SQL Editor](https://neon.tech/docs/get-started-with-neon/query-with-neon-sql-editor/). See [Connect from any application](https://neon.tech/docs/connect/connect-from-any-app/) for connection instructions.
+[Join the waitlist](https://neon.tech/) for our free tier to receive your serverless postgres instance. Then connect to it with your preferred postgres client (psql, dbeaver, etc) or use the online SQL editor.
 
 Alternatively, compile and run the project [locally](#running-local-installation).
 
 ## Architecture overview
 
-A Neon installation consists of compute nodes and the Neon storage engine. Compute nodes are stateless PostgreSQL nodes backed by the Neon storage engine.
+A Neon installation consists of compute nodes and a Neon storage engine.
+
+Compute nodes are stateless PostgreSQL nodes backed by the Neon storage engine.
 
 The Neon storage engine consists of two major components:
 - Pageserver. Scalable storage backend for the compute nodes.
-- Safekeepers. The safekeepers form a redundant WAL service that received WAL from the compute node, and stores it durably until it has been processed by the pageserver and uploaded to cloud storage.
+- WAL service. The service receives WAL from the compute node and ensures that it is stored durably.
 
-See developer documentation in [/docs/SUMMARY.md](/docs/SUMMARY.md) for more information.
+Pageserver consists of:
+- Repository - Neon storage implementation.
+- WAL receiver - service that receives WAL from WAL service and stores it in the repository.
+- Page service - service that communicates with compute nodes and responds with pages from the repository.
+- WAL redo - service that builds pages from base images and WAL records on Page service request
 
 ## Running local installation
 
@@ -26,12 +35,12 @@ See developer documentation in [/docs/SUMMARY.md](/docs/SUMMARY.md) for more inf
 * On Ubuntu or Debian, this set of packages should be sufficient to build the code:
 ```bash
 apt install build-essential libtool libreadline-dev zlib1g-dev flex bison libseccomp-dev \
-libssl-dev clang pkg-config libpq-dev cmake postgresql-client protobuf-compiler
+libssl-dev clang pkg-config libpq-dev etcd cmake postgresql-client
 ```
 * On Fedora, these packages are needed:
 ```bash
 dnf install flex bison readline-devel zlib-devel openssl-devel \
-  libseccomp-devel perl clang cmake postgresql postgresql-contrib protobuf-compiler
+  libseccomp-devel perl clang cmake etcd postgresql postgresql-contrib
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -44,7 +53,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
 1. Install XCode and dependencies
 ```
 xcode-select --install
-brew install protobuf openssl flex bison
+brew install protobuf etcd openssl
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -116,23 +125,24 @@ Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (r
 # Create repository in .neon with proper paths to binaries and data
 # Later that would be responsibility of a package install script
 > ./target/debug/neon_local init
-Starting pageserver at '127.0.0.1:64000' in '.neon'.
-pageserver started, pid: 2545906
-Successfully initialized timeline de200bd42b49cc1814412c7e592dd6e9
-Stopped pageserver 1 process with pid 2545906
+Starting pageserver at '127.0.0.1:64000' in '.neon'
+
+Pageserver started
+Successfully initialized timeline 7dd0907914ac399ff3be45fb252bfdb7
+Stopping pageserver gracefully...done!
 
 # start pageserver and safekeeper
 > ./target/debug/neon_local start
-Starting neon broker at 127.0.0.1:50051
-storage_broker started, pid: 2918372
-Starting pageserver at '127.0.0.1:64000' in '.neon'.
-pageserver started, pid: 2918386
-Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'.
-safekeeper 1 started, pid: 2918437
+Starting etcd broker using /usr/bin/etcd
+Starting pageserver at '127.0.0.1:64000' in '.neon'
+
+Pageserver started
+Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'
+Safekeeper started
 
 # start postgres compute node
 > ./target/debug/neon_local pg start main
-Starting new postgres (v14) main on timeline de200bd42b49cc1814412c7e592dd6e9 ...
+Starting new postgres main on timeline de200bd42b49cc1814412c7e592dd6e9 ...
 Extracting base backup to create postgres instance: path=.neon/pgdatadirs/tenants/9ef87a5bf0d92544f6fafeeb3239695c/main port=55432
 Starting postgres node at 'host=127.0.0.1 port=55432 user=cloud_admin dbname=postgres'
 
@@ -220,20 +230,12 @@ CARGO_BUILD_FLAGS="--features=testing" make
 
 ## Documentation
 
-[/docs/](/docs/) Contains a top-level overview of all available markdown documentation.
+Now we use README files to cover design ideas and overall architecture for each module and `rustdoc` style documentation comments. See also [/docs/](/docs/) a top-level overview of all available markdown documentation.
 
 - [/docs/sourcetree.md](/docs/sourcetree.md) contains overview of source tree layout.
 
 To view your `rustdoc` documentation in a browser, try running `cargo doc --no-deps --open`
 
-See also README files in some source directories, and `rustdoc` style documentation comments.
-
-Other resources:
-
-- [SELECT 'Hello, World'](https://neon.tech/blog/hello-world/): Blog post by Nikita Shamgunov on the high level architecture
-- [Architecture decisions in Neon](https://neon.tech/blog/architecture-decisions-in-neon/): Blog post by Heikki Linnakangas
-- [Neon: Serverless PostgreSQL!](https://www.youtube.com/watch?v=rES0yzeERns): Presentation on storage system by Heikki Linnakangas in the CMU Database Group seminar series
-
 ### Postgres-specific terms
 
 Due to Neon's very close relation with PostgreSQL internals, numerous specific terms are used.

cli-v2-story.md

@@ -0,0 +1,188 @@
+Create a new Zenith repository in the current directory:
+
+    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli init
+    The files belonging to this database system will be owned by user "heikki".
+    This user must also own the server process.
+    
+    The database cluster will be initialized with locale "en_GB.UTF-8".
+    The default database encoding has accordingly been set to "UTF8".
+    The default text search configuration will be set to "english".
+    
+    Data page checksums are disabled.
+    
+    creating directory tmp ... ok
+    creating subdirectories ... ok
+    selecting dynamic shared memory implementation ... posix
+    selecting default max_connections ... 100
+    selecting default shared_buffers ... 128MB
+    selecting default time zone ... Europe/Helsinki
+    creating configuration files ... ok
+    running bootstrap script ... ok
+    performing post-bootstrap initialization ... ok
+    syncing data to disk ... ok
+    
+    initdb: warning: enabling "trust" authentication for local connections
+    You can change this by editing pg_hba.conf or using the option -A, or
+    --auth-local and --auth-host, the next time you run initdb.
+    new zenith repository was created in .zenith
+
+Initially, there is only one branch:
+
+    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch
+      main
+
+Start a local Postgres instance on the branch:
+
+    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start main
+    Creating data directory from snapshot at 0/15FFB08...
+    waiting for server to start....2021-04-13 09:27:43.919 EEST [984664] LOG:  starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
+    2021-04-13 09:27:43.920 EEST [984664] LOG:  listening on IPv6 address "::1", port 5432
+    2021-04-13 09:27:43.920 EEST [984664] LOG:  listening on IPv4 address "127.0.0.1", port 5432
+    2021-04-13 09:27:43.927 EEST [984664] LOG:  listening on Unix socket "/tmp/.s.PGSQL.5432"
+    2021-04-13 09:27:43.939 EEST [984665] LOG:  database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
+    2021-04-13 09:27:43.939 EEST [984665] LOG:  creating missing WAL directory "pg_wal/archive_status"
+    2021-04-13 09:27:44.189 EEST [984665] LOG:  database system was not properly shut down; automatic recovery in progress
+    2021-04-13 09:27:44.195 EEST [984665] LOG:  invalid record length at 0/15FFB80: wanted 24, got 0
+    2021-04-13 09:27:44.195 EEST [984665] LOG:  redo is not required
+    2021-04-13 09:27:44.225 EEST [984664] LOG:  database system is ready to accept connections
+     done
+    server started
+
+Run some commands against it:
+
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -c "create table foo (t text);" 
+    CREATE TABLE
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -c "insert into foo values ('inserted on the main branch');" 
+    INSERT 0 1
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -c "select * from foo" 
+                  t              
+    -----------------------------
+     inserted on the main branch
+    (1 row)
+
+Create a new branch called 'experimental'. We create it from the
+current end of the 'main' branch, but you could specify a different
+LSN as the start point instead.
+
+    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch experimental main
+    branching at end of WAL: 0/161F478
+    
+    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch 
+      experimental
+      main
+
+Start another Postgres instance off the 'experimental' branch:
+
+    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start experimental -- -o -p5433
+    Creating data directory from snapshot at 0/15FFB08...
+    waiting for server to start....2021-04-13 09:28:41.874 EEST [984766] LOG:  starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
+    2021-04-13 09:28:41.875 EEST [984766] LOG:  listening on IPv6 address "::1", port 5433
+    2021-04-13 09:28:41.875 EEST [984766] LOG:  listening on IPv4 address "127.0.0.1", port 5433
+    2021-04-13 09:28:41.883 EEST [984766] LOG:  listening on Unix socket "/tmp/.s.PGSQL.5433"
+    2021-04-13 09:28:41.896 EEST [984767] LOG:  database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
+    2021-04-13 09:28:42.265 EEST [984767] LOG:  database system was not properly shut down; automatic recovery in progress
+    2021-04-13 09:28:42.269 EEST [984767] LOG:  redo starts at 0/15FFB80
+    2021-04-13 09:28:42.272 EEST [984767] LOG:  invalid record length at 0/161F4B0: wanted 24, got 0
+    2021-04-13 09:28:42.272 EEST [984767] LOG:  redo done at 0/161F478 system usage: CPU: user: 0.00 s, system: 0.00 s, elapsed: 0.00 s
+    2021-04-13 09:28:42.321 EEST [984766] LOG:  database system is ready to accept connections
+     done
+    server started
+
+Insert some a row on the 'experimental' branch:
+
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo" 
+                  t              
+    -----------------------------
+     inserted on the main branch
+    (1 row)
+    
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "insert into foo values ('inserted on experimental')" 
+    INSERT 0 1
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo" 
+                  t              
+    -----------------------------
+     inserted on the main branch
+     inserted on experimental
+    (2 rows)
+    
+See that the other Postgres instance is still running on 'main' branch on port 5432:
+
+
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5432 -c "select * from foo" 
+                  t              
+    -----------------------------
+     inserted on the main branch
+    (1 row)
+
+
+
+
+Everything is stored in the .zenith directory:
+
+    ~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/
+    total 12
+    drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:28 datadirs
+    drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:27 refs
+    drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:28 timelines
+
+The 'datadirs' directory contains the datadirs of the running instances:
+
+    ~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/datadirs/
+    total 8
+    drwx------ 18 heikki heikki 4096 Apr 13 09:27 3c0c634c1674079b2c6d4edf7c91523e
+    drwx------ 18 heikki heikki 4096 Apr 13 09:28 697e3c103d4b1763cd6e82e4ff361d76
+    ~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/datadirs/3c0c634c1674079b2c6d4edf7c91523e/
+    total 124
+    drwxr-xr-x 5 heikki heikki  4096 Apr 13 09:27 base
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 global
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_commit_ts
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_dynshmem
+    -rw------- 1 heikki heikki  4760 Apr 13 09:27 pg_hba.conf
+    -rw------- 1 heikki heikki  1636 Apr 13 09:27 pg_ident.conf
+    drwxr-xr-x 4 heikki heikki  4096 Apr 13 09:32 pg_logical
+    drwxr-xr-x 4 heikki heikki  4096 Apr 13 09:27 pg_multixact
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_notify
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_replslot
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_serial
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_snapshots
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_stat
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:34 pg_stat_tmp
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_subtrans
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_tblspc
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_twophase
+    -rw------- 1 heikki heikki     3 Apr 13 09:27 PG_VERSION
+    lrwxrwxrwx 1 heikki heikki    52 Apr 13 09:27 pg_wal -> ../../timelines/3c0c634c1674079b2c6d4edf7c91523e/wal
+    drwxr-xr-x 2 heikki heikki  4096 Apr 13 09:27 pg_xact
+    -rw------- 1 heikki heikki    88 Apr 13 09:27 postgresql.auto.conf
+    -rw------- 1 heikki heikki 28688 Apr 13 09:27 postgresql.conf
+    -rw------- 1 heikki heikki    96 Apr 13 09:27 postmaster.opts
+    -rw------- 1 heikki heikki   149 Apr 13 09:27 postmaster.pid
+
+Note how 'pg_wal' is just a symlink to the 'timelines' directory. The
+datadir is ephemeral, you can delete it at any time, and it can be reconstructed
+from the snapshots and WAL stored in the 'timelines' directory. So if you push/pull
+the repository, the 'datadirs' are not included. (They are like git working trees)
+
+    ~/git-sandbox/zenith (cli-v2)$ killall -9 postgres
+    ~/git-sandbox/zenith (cli-v2)$ rm -rf .zenith/datadirs/*
+    ~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start experimental -- -o -p5433
+    Creating data directory from snapshot at 0/15FFB08...
+    waiting for server to start....2021-04-13 09:37:05.476 EEST [985340] LOG:  starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
+    2021-04-13 09:37:05.477 EEST [985340] LOG:  listening on IPv6 address "::1", port 5433
+    2021-04-13 09:37:05.477 EEST [985340] LOG:  listening on IPv4 address "127.0.0.1", port 5433
+    2021-04-13 09:37:05.487 EEST [985340] LOG:  listening on Unix socket "/tmp/.s.PGSQL.5433"
+    2021-04-13 09:37:05.498 EEST [985341] LOG:  database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
+    2021-04-13 09:37:05.808 EEST [985341] LOG:  database system was not properly shut down; automatic recovery in progress
+    2021-04-13 09:37:05.813 EEST [985341] LOG:  redo starts at 0/15FFB80
+    2021-04-13 09:37:05.815 EEST [985341] LOG:  invalid record length at 0/161F770: wanted 24, got 0
+    2021-04-13 09:37:05.815 EEST [985341] LOG:  redo done at 0/161F738 system usage: CPU: user: 0.00 s, system: 0.00 s, elapsed: 0.00 s
+    2021-04-13 09:37:05.866 EEST [985340] LOG:  database system is ready to accept connections
+     done
+    server started
+    ~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo" 
+                  t              
+    -----------------------------
+     inserted on the main branch
+     inserted on experimental
+    (2 rows)
+

compute_tools/Cargo.toml

@@ -5,7 +5,7 @@ edition = "2021"
 
 [dependencies]
 anyhow = "1.0"
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
+chrono = "0.4"
 clap = "4.0"
 env_logger = "0.9"
 futures = "0.3.13"

compute_tools/src/pg_helpers.rs

@@ -65,7 +65,7 @@ impl GenericOption {
             let name = match self.name.as_str() {
                 "safekeepers" => "neon.safekeepers",
                 "wal_acceptor_reconnect" => "neon.safekeeper_reconnect_timeout",
-                "wal_acceptor_connection_timeout" => "neon.safekeeper_connection_timeout",
+                "wal_acceptor_connect_timeout" => "neon.safekeeper_connect_timeout",
                 it => it,
             };
 

control_plane/Cargo.toml

@@ -23,9 +23,6 @@ url = "2.2.2"
 # Note: Do not directly depend on pageserver or safekeeper; use pageserver_api or safekeeper_api
 # instead, so that recompile times are better.
 pageserver_api = { path = "../libs/pageserver_api" }
-postgres_connection = { path = "../libs/postgres_connection" }
 safekeeper_api = { path = "../libs/safekeeper_api" }
-# Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
-storage_broker = { version = "0.1", path = "../storage_broker" }
 utils = { path = "../libs/utils" }
 workspace_hack = { version = "0.1", path = "../workspace_hack" }

control_plane/simple.conf

@@ -10,5 +10,5 @@ id = 1
 pg_port = 5454
 http_port = 7676
 
-[broker]
-listen_addr = '127.0.0.1:50051'
+[etcd_broker]
+broker_endpoints = ['http://127.0.0.1:2379']

control_plane/src/background_process.rs

@@ -14,32 +14,20 @@
 
 use std::ffi::OsStr;
 use std::io::Write;
-use std::os::unix::prelude::AsRawFd;
-use std::os::unix::process::CommandExt;
-use std::path::{Path, PathBuf};
+use std::path::Path;
 use std::process::{Child, Command};
 use std::time::Duration;
 use std::{fs, io, thread};
 
-use anyhow::Context;
+use anyhow::{anyhow, bail, Context, Result};
 use nix::errno::Errno;
-use nix::fcntl::{FcntlArg, FdFlag};
 use nix::sys::signal::{kill, Signal};
 use nix::unistd::Pid;
-use utils::pid_file::{self, PidFileRead};
 
-// These constants control the loop used to poll for process start / stop.
-//
-// The loop waits for at most 10 seconds, polling every 100 ms.
-// Once a second, it prints a dot ("."), to give the user an indication that
-// it's waiting. If the process hasn't started/stopped after 5 seconds,
-// it prints a notice that it's taking long, but keeps waiting.
-//
-const RETRY_UNTIL_SECS: u64 = 10;
-const RETRIES: u64 = (RETRY_UNTIL_SECS * 1000) / RETRY_INTERVAL_MILLIS;
-const RETRY_INTERVAL_MILLIS: u64 = 100;
-const DOT_EVERY_RETRIES: u64 = 10;
-const NOTICE_AFTER_RETRIES: u64 = 50;
+use utils::lock_file;
+
+const RETRIES: u32 = 15;
+const RETRY_TIMEOUT_MILLIS: u64 = 500;
 
 /// Argument to `start_process`, to indicate whether it should create pidfile or if the process creates
 /// it itself.
@@ -51,16 +39,11 @@ pub enum InitialPidFile<'t> {
 }
 
 /// Start a background child process using the parameters given.
-pub fn start_process<
-    F,
-    S: AsRef<OsStr>,
-    EI: IntoIterator<Item = (String, String)>, // Not generic AsRef<OsStr>, otherwise empty `envs` prevents type inference
->(
+pub fn start_process<F, S: AsRef<OsStr>>(
     process_name: &str,
     datadir: &Path,
     command: &Path,
     args: &[S],
-    envs: EI,
     initial_pid_file: InitialPidFile,
     process_status_check: F,
 ) -> anyhow::Result<Child>
@@ -86,15 +69,6 @@ where
         .stderr(same_file_for_stderr)
         .args(args);
     let filled_cmd = fill_aws_secrets_vars(fill_rust_env_vars(background_command));
-    filled_cmd.envs(envs);
-
-    let pid_file_to_check = match initial_pid_file {
-        InitialPidFile::Create(path) => {
-            pre_exec_create_pidfile(filled_cmd, path);
-            path
-        }
-        InitialPidFile::Expect(path) => path,
-    };
 
     let mut spawned_process = filled_cmd.spawn().with_context(|| {
         format!("Could not spawn {process_name}, see console output and log files for details.")
@@ -105,23 +79,44 @@ where
             .with_context(|| format!("Subprocess {process_name} has invalid pid {pid}"))?,
     );
 
+    let pid_file_to_check = match initial_pid_file {
+        InitialPidFile::Create(target_pid_file_path) => {
+            match lock_file::create_lock_file(target_pid_file_path, pid.to_string()) {
+                lock_file::LockCreationResult::Created { .. } => {
+                    // We use "lock" file here only to create the pid file. The lock on the pidfile will be dropped as soon
+                    // as this CLI invocation exits, so it's a bit useless, but doesn't any harm either.
+                }
+                lock_file::LockCreationResult::AlreadyLocked { .. } => {
+                    anyhow::bail!("Cannot write pid file for {process_name} at path {target_pid_file_path:?}: file is already locked by another process")
+                }
+                lock_file::LockCreationResult::CreationFailed(e) => {
+                    return Err(e.context(format!(
+                    "Failed to create pid file for {process_name} at path {target_pid_file_path:?}"
+                )))
+                }
+            }
+            None
+        }
+        InitialPidFile::Expect(pid_file_path) => Some(pid_file_path),
+    };
+
     for retries in 0..RETRIES {
-        match process_started(pid, Some(pid_file_to_check), &process_status_check) {
+        match process_started(pid, pid_file_to_check, &process_status_check) {
             Ok(true) => {
                 println!("\n{process_name} started, pid: {pid}");
                 return Ok(spawned_process);
             }
             Ok(false) => {
-                if retries == NOTICE_AFTER_RETRIES {
-                    // The process is taking a long time to start up. Keep waiting, but
-                    // print a message
-                    print!("\n{process_name} has not started yet, continuing to wait");
-                }
-                if retries % DOT_EVERY_RETRIES == 0 {
+                if retries < 5 {
                     print!(".");
                     io::stdout().flush().unwrap();
+                } else {
+                    if retries == 5 {
+                        println!() // put a line break after dots for second message
+                    }
+                    println!("{process_name} has not started yet, retrying ({retries})...");
                 }
-                thread::sleep(Duration::from_millis(RETRY_INTERVAL_MILLIS));
+                thread::sleep(Duration::from_millis(RETRY_TIMEOUT_MILLIS));
             }
             Err(e) => {
                 println!("{process_name} failed to start: {e:#}");
@@ -132,49 +127,17 @@ where
             }
         }
     }
-    println!();
-    anyhow::bail!("{process_name} did not start in {RETRY_UNTIL_SECS} seconds");
-}
-
-/// Send SIGTERM to child process
-pub fn send_stop_child_process(child: &std::process::Child) -> anyhow::Result<()> {
-    let pid = child.id();
-    match kill(
-        nix::unistd::Pid::from_raw(pid.try_into().unwrap()),
-        Signal::SIGTERM,
-    ) {
-        Ok(()) => Ok(()),
-        Err(Errno::ESRCH) => {
-            println!("child process with pid {pid} does not exist");
-            Ok(())
-        }
-        Err(e) => anyhow::bail!("Failed to send signal to child process with pid {pid}: {e}"),
-    }
+    anyhow::bail!("{process_name} could not start in {RETRIES} attempts");
 }
 
 /// Stops the process, using the pid file given. Returns Ok also if the process is already not running.
 pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> anyhow::Result<()> {
-    let pid = match pid_file::read(pid_file)
-        .with_context(|| format!("read pid_file {pid_file:?}"))?
-    {
-        PidFileRead::NotExist => {
-            println!("{process_name} is already stopped: no pid file present at {pid_file:?}");
-            return Ok(());
-        }
-        PidFileRead::NotHeldByAnyProcess(_) => {
-            // Don't try to kill according to file contents beacuse the pid might have been re-used by another process.
-            // Don't delete the file either, it can race with new pid file creation.
-            // Read `pid_file` module comment for details.
-            println!(
-                "No process is holding the pidfile. The process must have already exited. Leave in place to avoid race conditions: {pid_file:?}"
-            );
-            return Ok(());
-        }
-        PidFileRead::LockedByOtherProcess(pid) => pid,
-    };
-    // XXX the pid could become invalid (and recycled) at any time before the kill() below.
+    if !pid_file.exists() {
+        println!("{process_name} is already stopped: no pid file {pid_file:?} is present");
+        return Ok(());
+    }
+    let pid = read_pidfile(pid_file)?;
 
-    // send signal
     let sig = if immediate {
         print!("Stopping {process_name} with pid {pid} immediately..");
         Signal::SIGQUIT
@@ -186,9 +149,8 @@ pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> any
     match kill(pid, sig) {
         Ok(()) => (),
         Err(Errno::ESRCH) => {
-            // Again, don't delete the pid file. The unlink can race with a new pid file being created.
             println!(
-                "{process_name} with pid {pid} does not exist, but a pid file {pid_file:?} was found. Likely the pid got recycled. Lucky we didn't harm anyone."
+                "{process_name} with pid {pid} does not exist, but a pid file {pid_file:?} was found"
             );
             return Ok(());
         }
@@ -196,23 +158,21 @@ pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> any
     }
 
     // Wait until process is gone
-    for retries in 0..RETRIES {
+    for _ in 0..RETRIES {
         match process_has_stopped(pid) {
             Ok(true) => {
                 println!("\n{process_name} stopped");
+                if let Err(e) = fs::remove_file(pid_file) {
+                    if e.kind() != io::ErrorKind::NotFound {
+                        eprintln!("Failed to remove pid file {pid_file:?} after stopping the process: {e:#}");
+                    }
+                }
                 return Ok(());
             }
             Ok(false) => {
-                if retries == NOTICE_AFTER_RETRIES {
-                    // The process is taking a long time to start up. Keep waiting, but
-                    // print a message
-                    print!("\n{process_name} has not stopped yet, continuing to wait");
-                }
-                if retries % DOT_EVERY_RETRIES == 0 {
-                    print!(".");
-                    io::stdout().flush().unwrap();
-                }
-                thread::sleep(Duration::from_millis(RETRY_INTERVAL_MILLIS));
+                print!(".");
+                io::stdout().flush().unwrap();
+                thread::sleep(Duration::from_secs(1))
             }
             Err(e) => {
                 println!("{process_name} with pid {pid} failed to stop: {e:#}");
@@ -220,28 +180,24 @@ pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> any
             }
         }
     }
-    println!();
-    anyhow::bail!("{process_name} with pid {pid} did not stop in {RETRY_UNTIL_SECS} seconds");
+
+    anyhow::bail!("{process_name} with pid {pid} failed to stop in {RETRIES} attempts");
 }
 
 fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
-    // If RUST_BACKTRACE is set, pass it through. But if it's not set, default
-    // to RUST_BACKTRACE=1.
-    let backtrace_setting = std::env::var_os("RUST_BACKTRACE");
-    let backtrace_setting = backtrace_setting
-        .as_deref()
-        .unwrap_or_else(|| OsStr::new("1"));
+    let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", "1");
 
-    let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", backtrace_setting);
-
-    // Pass through these environment variables to the command
-    for var in ["LLVM_PROFILE_FILE", "FAILPOINTS", "RUST_LOG"] {
-        if let Some(val) = std::env::var_os(var) {
-            filled_cmd = filled_cmd.env(var, val);
-        }
+    let var = "LLVM_PROFILE_FILE";
+    if let Some(val) = std::env::var_os(var) {
+        filled_cmd = filled_cmd.env(var, val);
     }
 
-    filled_cmd
+    const RUST_LOG_KEY: &str = "RUST_LOG";
+    if let Ok(rust_log_value) = std::env::var(RUST_LOG_KEY) {
+        filled_cmd.env(RUST_LOG_KEY, rust_log_value)
+    } else {
+        filled_cmd
+    }
 }
 
 fn fill_aws_secrets_vars(mut cmd: &mut Command) -> &mut Command {
@@ -257,69 +213,6 @@ fn fill_aws_secrets_vars(mut cmd: &mut Command) -> &mut Command {
     cmd
 }
 
-/// Add a `pre_exec` to the cmd that, inbetween fork() and exec(),
-/// 1. Claims a pidfile with a fcntl lock on it and
-/// 2. Sets up the pidfile's file descriptor so that it (and the lock)
-///    will remain held until the cmd exits.
-fn pre_exec_create_pidfile<P>(cmd: &mut Command, path: P) -> &mut Command
-where
-    P: Into<PathBuf>,
-{
-    let path: PathBuf = path.into();
-    // SAFETY
-    // pre_exec is marked unsafe because it runs between fork and exec.
-    // Why is that dangerous in various ways?
-    // Long answer:  https://github.com/rust-lang/rust/issues/39575
-    // Short answer: in a multi-threaded program, other threads may have
-    // been inside of critical sections at the time of fork. In the
-    // original process, that was allright, assuming they protected
-    // the critical sections appropriately, e.g., through locks.
-    // Fork adds another process to the mix that
-    //   1. Has a single thread T
-    //   2. In an exact copy of the address space at the time of fork.
-    // A variety of problems scan occur now:
-    //   1. T tries to grab a lock that was locked at the time of fork.
-    //      It will wait forever since in its address space, the lock
-    //      is in state 'taken' but the thread that would unlock it is
-    //      not there.
-    //   2. A rust object that represented some external resource in the
-    //      parent now got implicitly copied by the the fork, even though
-    //      the object's type is not `Copy`. The parent program may use
-    //      non-copyability as way to enforce unique ownership of an
-    //      external resource in the typesystem. The fork breaks that
-    //      assumption, as now both parent and child process have an
-    //      owned instance of the object that represents the same
-    //      underlying resource.
-    // While these seem like niche problems, (1) in particular is
-    // highly relevant. For example, `malloc()` may grab a mutex internally,
-    // and so, if we forked while another thread was mallocing' and our
-    // pre_exec closure allocates as well, it will block on the malloc
-    // mutex forever
-    //
-    // The proper solution is to only use C library functions that are marked
-    // "async-signal-safe": https://man7.org/linux/man-pages/man7/signal-safety.7.html
-    //
-    // With this specific pre_exec() closure, the non-error path doesn't allocate.
-    // The error path uses `anyhow`, and hence does allocate.
-    // We take our chances there, hoping that any potential disaster is constrained
-    // to the child process (e.g., malloc has no state ourside of the child process).
-    // Last, `expect` prints to stderr, and stdio is not async-signal-safe.
-    // Again, we take our chances, making the same assumptions as for malloc.
-    unsafe {
-        cmd.pre_exec(move || {
-            let file = pid_file::claim_for_current_process(&path).expect("claim pid file");
-            // Remove the FD_CLOEXEC flag on the pidfile descriptor so that the pidfile
-            // remains locked after exec.
-            nix::fcntl::fcntl(file.as_raw_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
-                .expect("remove FD_CLOEXEC");
-            // Don't run drop(file), it would close the file before we actually exec.
-            std::mem::forget(file);
-            Ok(())
-        });
-    }
-    cmd
-}
-
 fn process_started<F>(
     pid: Pid,
     pid_file_to_check: Option<&Path>,
@@ -330,11 +223,14 @@ where
 {
     match status_check() {
         Ok(true) => match pid_file_to_check {
-            Some(pid_file_path) => match pid_file::read(pid_file_path)? {
-                PidFileRead::NotExist => Ok(false),
-                PidFileRead::LockedByOtherProcess(pid_in_file) => Ok(pid_in_file == pid),
-                PidFileRead::NotHeldByAnyProcess(_) => Ok(false),
-            },
+            Some(pid_file_path) => {
+                if pid_file_path.exists() {
+                    let pid_in_file = read_pidfile(pid_file_path)?;
+                    Ok(pid_in_file == pid)
+                } else {
+                    Ok(false)
+                }
+            }
             None => Ok(true),
         },
         Ok(false) => Ok(false),
@@ -342,6 +238,21 @@ where
     }
 }
 
+/// Read a PID file
+///
+/// We expect a file that contains a single integer.
+fn read_pidfile(pidfile: &Path) -> Result<Pid> {
+    let pid_str = fs::read_to_string(pidfile)
+        .with_context(|| format!("failed to read pidfile {pidfile:?}"))?;
+    let pid: i32 = pid_str
+        .parse()
+        .map_err(|_| anyhow!("failed to parse pidfile {pidfile:?}"))?;
+    if pid < 1 {
+        bail!("pidfile {pidfile:?} contained bad value '{pid}'");
+    }
+    Ok(Pid::from_raw(pid))
+}
+
 fn process_has_stopped(pid: Pid) -> anyhow::Result<bool> {
     match kill(pid, None) {
         // Process exists, keep waiting

control_plane/src/bin/neon_local.rs

@@ -8,10 +8,10 @@
 use anyhow::{anyhow, bail, Context, Result};
 use clap::{value_parser, Arg, ArgAction, ArgMatches, Command};
 use control_plane::compute::ComputeControlPlane;
-use control_plane::local_env::LocalEnv;
+use control_plane::local_env::{EtcdBroker, LocalEnv};
 use control_plane::pageserver::PageServerNode;
 use control_plane::safekeeper::SafekeeperNode;
-use control_plane::{broker, local_env};
+use control_plane::{etcd, local_env};
 use pageserver_api::models::TimelineInfo;
 use pageserver_api::{
     DEFAULT_HTTP_LISTEN_ADDR as DEFAULT_PAGESERVER_HTTP_ADDR,
@@ -22,10 +22,9 @@ use safekeeper_api::{
     DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT,
 };
 use std::collections::{BTreeSet, HashMap};
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 use std::process::exit;
 use std::str::FromStr;
-use storage_broker::DEFAULT_LISTEN_ADDR as DEFAULT_BROKER_ADDR;
 use utils::{
     auth::{Claims, Scope},
     id::{NodeId, TenantId, TenantTimelineId, TimelineId},
@@ -42,12 +41,13 @@ project_git_version!(GIT_VERSION);
 
 const DEFAULT_PG_VERSION: &str = "14";
 
-fn default_conf() -> String {
+fn default_conf(etcd_binary_path: &Path) -> String {
     format!(
         r#"
 # Default built-in configuration, defined in main.rs
-[broker]
-listen_addr = '{DEFAULT_BROKER_ADDR}'
+[etcd_broker]
+broker_endpoints = ['http://localhost:2379']
+etcd_binary_path = '{etcd_binary_path}'
 
 [pageserver]
 id = {DEFAULT_PAGESERVER_ID}
@@ -60,6 +60,7 @@ id = {DEFAULT_SAFEKEEPER_ID}
 pg_port = {DEFAULT_SAFEKEEPER_PG_PORT}
 http_port = {DEFAULT_SAFEKEEPER_HTTP_PORT}
 "#,
+        etcd_binary_path = etcd_binary_path.display(),
         pageserver_auth_type = AuthType::Trust,
     )
 }
@@ -297,7 +298,7 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
         })?
     } else {
         // Built-in default config
-        default_conf()
+        default_conf(&EtcdBroker::locate_etcd()?)
     };
 
     let pg_version = init_match
@@ -323,7 +324,7 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
             pg_version,
         )
         .unwrap_or_else(|e| {
-            eprintln!("pageserver init failed: {e:?}");
+            eprintln!("pageserver init failed: {e}");
             exit(1);
         });
 
@@ -806,14 +807,14 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
 }
 
 fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    broker::start_broker_process(env)?;
+    etcd::start_etcd_process(env)?;
     let pageserver = PageServerNode::from_env(env);
 
     // Postgres nodes are not started automatically
 
     if let Err(e) = pageserver.start(&pageserver_config_overrides(sub_match)) {
         eprintln!("pageserver start failed: {e}");
-        try_stop_storage_broker_process(env);
+        try_stop_etcd_process(env);
         exit(1);
     }
 
@@ -821,7 +822,7 @@ fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.start() {
             eprintln!("safekeeper '{}' start failed: {e}", safekeeper.id);
-            try_stop_storage_broker_process(env);
+            try_stop_etcd_process(env);
             exit(1);
         }
     }
@@ -853,14 +854,14 @@ fn handle_stop_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<
         }
     }
 
-    try_stop_storage_broker_process(env);
+    try_stop_etcd_process(env);
 
     Ok(())
 }
 
-fn try_stop_storage_broker_process(env: &local_env::LocalEnv) {
-    if let Err(e) = broker::stop_broker_process(env) {
-        eprintln!("neon broker stop failed: {e}");
+fn try_stop_etcd_process(env: &local_env::LocalEnv) {
+    if let Err(e) = etcd::stop_etcd_process(env) {
+        eprintln!("etcd stop failed: {e}");
     }
 }
 

control_plane/src/broker.rs

@@ -1,48 +0,0 @@
-use anyhow::Context;
-
-use std::path::PathBuf;
-
-use crate::{background_process, local_env};
-
-pub fn start_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    let broker = &env.broker;
-    let listen_addr = &broker.listen_addr;
-
-    print!("Starting neon broker at {}", listen_addr);
-
-    let args = [format!("--listen-addr={listen_addr}")];
-
-    let client = reqwest::blocking::Client::new();
-    background_process::start_process(
-        "storage_broker",
-        &env.base_data_dir,
-        &env.storage_broker_bin(),
-        &args,
-        [],
-        background_process::InitialPidFile::Create(&storage_broker_pid_file_path(env)),
-        || {
-            let url = broker.client_url();
-            let status_url = url.join("status").with_context(|| {
-                format!("Failed to append /status path to broker endpoint {url}",)
-            })?;
-            let request = client
-                .get(status_url)
-                .build()
-                .with_context(|| format!("Failed to construct request to broker endpoint {url}"))?;
-            match client.execute(request) {
-                Ok(resp) => Ok(resp.status().is_success()),
-                Err(_) => Ok(false),
-            }
-        },
-    )
-    .context("Failed to spawn storage_broker subprocess")?;
-    Ok(())
-}
-
-pub fn stop_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    background_process::stop_process(true, "storage_broker", &storage_broker_pid_file_path(env))
-}
-
-fn storage_broker_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {
-    env.base_data_dir.join("storage_broker.pid")
-}

control_plane/src/compute.rs

@@ -322,9 +322,6 @@ impl PostgresNode {
         conf.append("shared_preload_libraries", "neon");
         conf.append_line("");
         conf.append("neon.pageserver_connstring", &pageserver_connstr);
-        if let AuthType::NeonJWT = auth_type {
-            conf.append("neon.safekeeper_token_env", "$ZENITH_AUTH_TOKEN");
-        }
         conf.append("neon.tenant_id", &self.tenant_id.to_string());
         conf.append("neon.timeline_id", &self.timeline_id.to_string());
         if let Some(lsn) = self.lsn {
@@ -346,7 +343,7 @@ impl PostgresNode {
         //   To be able to restore database in case of pageserver node crash, safekeeper should not
         //   remove WAL beyond this point. Too large lag can cause space exhaustion in safekeepers
         //   (if they are not able to upload WAL to S3).
-        conf.append("max_replication_write_lag", "15MB");
+        conf.append("max_replication_write_lag", "500MB");
         conf.append("max_replication_flush_lag", "10GB");
 
         if !self.env.safekeepers.is_empty() {

control_plane/src/connection.rs

@@ -0,0 +1,57 @@
+use url::Url;
+
+#[derive(Debug)]
+pub struct PgConnectionConfig {
+    url: Url,
+}
+
+impl PgConnectionConfig {
+    pub fn host(&self) -> &str {
+        self.url.host_str().expect("BUG: no host")
+    }
+
+    pub fn port(&self) -> u16 {
+        self.url.port().expect("BUG: no port")
+    }
+
+    /// Return a `<host>:<port>` string.
+    pub fn raw_address(&self) -> String {
+        format!("{}:{}", self.host(), self.port())
+    }
+
+    /// Connect using postgres protocol with TLS disabled.
+    pub fn connect_no_tls(&self) -> Result<postgres::Client, postgres::Error> {
+        postgres::Client::connect(self.url.as_str(), postgres::NoTls)
+    }
+}
+
+impl std::str::FromStr for PgConnectionConfig {
+    type Err = anyhow::Error;
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        let mut url: Url = s.parse()?;
+
+        match url.scheme() {
+            "postgres" | "postgresql" => {}
+            other => anyhow::bail!("invalid scheme: {other}"),
+        }
+
+        // It's not a valid connection url if host is unavailable.
+        if url.host().is_none() {
+            anyhow::bail!(url::ParseError::EmptyHost);
+        }
+
+        // E.g. `postgres:bar`.
+        if url.cannot_be_a_base() {
+            anyhow::bail!("URL cannot be a base");
+        }
+
+        // Set the default PG port if it's missing.
+        if url.port().is_none() {
+            url.set_port(Some(5432))
+                .expect("BUG: couldn't set the default port");
+        }
+
+        Ok(Self { url })
+    }
+}

control_plane/src/etcd.rs

@@ -0,0 +1,77 @@
+use std::{fs, path::PathBuf};
+
+use anyhow::Context;
+
+use crate::{background_process, local_env};
+
+pub fn start_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    let etcd_broker = &env.etcd_broker;
+    println!(
+        "Starting etcd broker using {:?}",
+        etcd_broker.etcd_binary_path
+    );
+
+    let etcd_data_dir = env.base_data_dir.join("etcd");
+    fs::create_dir_all(&etcd_data_dir)
+        .with_context(|| format!("Failed to create etcd data dir {etcd_data_dir:?}"))?;
+
+    let client_urls = etcd_broker.comma_separated_endpoints();
+    let args = [
+        format!("--data-dir={}", etcd_data_dir.display()),
+        format!("--listen-client-urls={client_urls}"),
+        format!("--advertise-client-urls={client_urls}"),
+        // Set --quota-backend-bytes to keep the etcd virtual memory
+        // size smaller. Our test etcd clusters are very small.
+        // See https://github.com/etcd-io/etcd/issues/7910
+        "--quota-backend-bytes=100000000".to_string(),
+        // etcd doesn't compact (vacuum) with default settings,
+        // enable it to prevent space exhaustion.
+        "--auto-compaction-mode=revision".to_string(),
+        "--auto-compaction-retention=1".to_string(),
+    ];
+
+    let pid_file_path = etcd_pid_file_path(env);
+
+    let client = reqwest::blocking::Client::new();
+
+    background_process::start_process(
+        "etcd",
+        &etcd_data_dir,
+        &etcd_broker.etcd_binary_path,
+        &args,
+        background_process::InitialPidFile::Create(&pid_file_path),
+        || {
+            for broker_endpoint in &etcd_broker.broker_endpoints {
+                let request = broker_endpoint
+                    .join("health")
+                    .with_context(|| {
+                        format!(
+                            "Failed to append /health path to broker endopint {}",
+                            broker_endpoint
+                        )
+                    })
+                    .and_then(|url| {
+                        client.get(&url.to_string()).build().with_context(|| {
+                            format!("Failed to construct request to etcd endpoint {url}")
+                        })
+                    })?;
+                if client.execute(request).is_ok() {
+                    return Ok(true);
+                }
+            }
+
+            Ok(false)
+        },
+    )
+    .context("Failed to spawn etcd subprocess")?;
+
+    Ok(())
+}
+
+pub fn stop_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    background_process::stop_process(true, "etcd", &etcd_pid_file_path(env))
+}
+
+fn etcd_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {
+    env.base_data_dir.join("etcd.pid")
+}

control_plane/src/lib.rs

@@ -8,8 +8,9 @@
 //
 
 mod background_process;
-pub mod broker;
 pub mod compute;
+pub mod connection;
+pub mod etcd;
 pub mod local_env;
 pub mod pageserver;
 pub mod postgresql_conf;

control_plane/src/local_env.rs

@@ -4,16 +4,12 @@
 //! script which will use local paths.
 
 use anyhow::{bail, ensure, Context};
-
 use reqwest::Url;
 use serde::{Deserialize, Serialize};
 use serde_with::{serde_as, DisplayFromStr};
 use std::collections::HashMap;
 use std::env;
 use std::fs;
-use std::net::IpAddr;
-use std::net::Ipv4Addr;
-use std::net::SocketAddr;
 use std::path::{Path, PathBuf};
 use std::process::{Command, Stdio};
 use utils::{
@@ -66,7 +62,7 @@ pub struct LocalEnv {
     #[serde(default)]
     pub private_key_path: PathBuf,
 
-    pub broker: NeonBroker,
+    pub etcd_broker: EtcdBroker,
 
     pub pageserver: PageServerConf,
 
@@ -82,26 +78,67 @@ pub struct LocalEnv {
     branch_name_mappings: HashMap<String, Vec<(TenantId, TimelineId)>>,
 }
 
-/// Broker config for cluster internal communication.
+/// Etcd broker config for cluster internal communication.
+#[serde_as]
 #[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
-#[serde(default)]
-pub struct NeonBroker {
-    /// Broker listen address for storage nodes coordination, e.g. '127.0.0.1:50051'.
-    pub listen_addr: SocketAddr,
+pub struct EtcdBroker {
+    /// A prefix to all to any key when pushing/polling etcd from a node.
+    #[serde(default)]
+    pub broker_etcd_prefix: Option<String>,
+
+    /// Broker (etcd) endpoints for storage nodes coordination, e.g. 'http://127.0.0.1:2379'.
+    #[serde(default)]
+    #[serde_as(as = "Vec<DisplayFromStr>")]
+    pub broker_endpoints: Vec<Url>,
+
+    /// Etcd binary path to use.
+    #[serde(default)]
+    pub etcd_binary_path: PathBuf,
 }
 
-// Dummy Default impl to satisfy Deserialize derive.
-impl Default for NeonBroker {
-    fn default() -> Self {
-        NeonBroker {
-            listen_addr: SocketAddr::new(IpAddr::V4(Ipv4Addr::new(0, 0, 0, 0)), 0),
-        }
+impl EtcdBroker {
+    pub fn locate_etcd() -> anyhow::Result<PathBuf> {
+        let which_output = Command::new("which")
+            .arg("etcd")
+            .output()
+            .context("Failed to run 'which etcd' command")?;
+        let stdout = String::from_utf8_lossy(&which_output.stdout);
+        ensure!(
+            which_output.status.success(),
+            "'which etcd' invocation failed. Status: {}, stdout: {stdout}, stderr: {}",
+            which_output.status,
+            String::from_utf8_lossy(&which_output.stderr)
+        );
+
+        let etcd_path = PathBuf::from(stdout.trim());
+        ensure!(
+            etcd_path.is_file(),
+            "'which etcd' invocation was successful, but the path it returned is not a file or does not exist: {}",
+            etcd_path.display()
+        );
+
+        Ok(etcd_path)
     }
-}
 
-impl NeonBroker {
-    pub fn client_url(&self) -> Url {
-        Url::parse(&format!("http://{}", self.listen_addr)).expect("failed to construct url")
+    pub fn comma_separated_endpoints(&self) -> String {
+        self.broker_endpoints
+            .iter()
+            .map(|url| {
+                // URL by default adds a '/' path at the end, which is not what etcd CLI wants.
+                let url_string = url.as_str();
+                if url_string.ends_with('/') {
+                    &url_string[0..url_string.len() - 1]
+                } else {
+                    url_string
+                }
+            })
+            .fold(String::new(), |mut comma_separated_urls, url| {
+                if !comma_separated_urls.is_empty() {
+                    comma_separated_urls.push(',');
+                }
+                comma_separated_urls.push_str(url);
+                comma_separated_urls
+            })
     }
 }
 
@@ -197,10 +234,6 @@ impl LocalEnv {
         self.neon_distrib_dir.join("safekeeper")
     }
 
-    pub fn storage_broker_bin(&self) -> PathBuf {
-        self.neon_distrib_dir.join("storage_broker")
-    }
-
     pub fn pg_data_dirs_path(&self) -> PathBuf {
         self.base_data_dir.join("pgdatadirs").join("tenants")
     }
@@ -478,8 +511,8 @@ mod tests {
             "failed to parse simple config {simple_conf_toml}, reason: {simple_conf_parse_result:?}"
         );
 
-        let string_to_replace = "listen_addr = '127.0.0.1:50051'";
-        let spoiled_url_str = "listen_addr = '!@$XOXO%^&'";
+        let string_to_replace = "broker_endpoints = ['http://127.0.0.1:2379']";
+        let spoiled_url_str = "broker_endpoints = ['!@$XOXO%^&']";
         let spoiled_url_toml = simple_conf_toml.replace(string_to_replace, spoiled_url_str);
         assert!(
             spoiled_url_toml.contains(spoiled_url_str),

control_plane/src/pageserver.rs

@@ -1,20 +1,19 @@
 use std::collections::HashMap;
-use std::fs::File;
+use std::fs::{self, File};
 use std::io::{BufReader, Write};
 use std::num::NonZeroU64;
 use std::path::{Path, PathBuf};
 use std::process::Child;
 use std::{io, result};
 
-use anyhow::{bail, ensure, Context};
+use crate::connection::PgConnectionConfig;
+use anyhow::{bail, Context};
 use pageserver_api::models::{
     TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
 };
-use postgres_connection::{parse_host_port, PgConnectionConfig};
 use reqwest::blocking::{Client, RequestBuilder, Response};
 use reqwest::{IntoUrl, Method};
 use thiserror::Error;
-use utils::auth::{Claims, Scope};
 use utils::{
     http::error::HttpErrorBody,
     id::{TenantId, TimelineId},
@@ -78,26 +77,37 @@ pub struct PageServerNode {
 
 impl PageServerNode {
     pub fn from_env(env: &LocalEnv) -> PageServerNode {
-        let (host, port) = parse_host_port(&env.pageserver.listen_pg_addr)
-            .expect("Unable to parse listen_pg_addr");
-        let port = port.unwrap_or(5432);
         let password = if env.pageserver.auth_type == AuthType::NeonJWT {
-            Some(env.pageserver.auth_token.clone())
+            &env.pageserver.auth_token
         } else {
-            None
+            ""
         };
 
         Self {
-            pg_connection_config: PgConnectionConfig::new_host_port(host, port)
-                .set_password(password),
+            pg_connection_config: Self::pageserver_connection_config(
+                password,
+                &env.pageserver.listen_pg_addr,
+            ),
             env: env.clone(),
             http_client: Client::new(),
             http_base_url: format!("http://{}/v1", env.pageserver.listen_http_addr),
         }
     }
 
-    // pageserver conf overrides defined by neon_local configuration.
-    fn neon_local_overrides(&self) -> Vec<String> {
+    /// Construct libpq connection string for connecting to the pageserver.
+    fn pageserver_connection_config(password: &str, listen_addr: &str) -> PgConnectionConfig {
+        format!("postgresql://no_user:{password}@{listen_addr}/no_db")
+            .parse()
+            .unwrap()
+    }
+
+    pub fn initialize(
+        &self,
+        create_tenant: Option<TenantId>,
+        initial_timeline_id: Option<TimelineId>,
+        config_overrides: &[&str],
+        pg_version: u32,
+    ) -> anyhow::Result<TimelineId> {
         let id = format!("id={}", self.env.pageserver.id);
         // FIXME: the paths should be shell-escaped to handle paths with spaces, quotas etc.
         let pg_distrib_dir_param = format!(
@@ -112,32 +122,41 @@ impl PageServerNode {
         );
         let listen_pg_addr_param =
             format!("listen_pg_addr='{}'", self.env.pageserver.listen_pg_addr);
-        let broker_endpoint_param = format!("broker_endpoint='{}'", self.env.broker.client_url());
+        let broker_endpoints_param = format!(
+            "broker_endpoints=[{}]",
+            self.env
+                .etcd_broker
+                .broker_endpoints
+                .iter()
+                .map(|url| format!("'{url}'"))
+                .collect::<Vec<_>>()
+                .join(",")
+        );
+        let broker_etcd_prefix_param = self
+            .env
+            .etcd_broker
+            .broker_etcd_prefix
+            .as_ref()
+            .map(|prefix| format!("broker_etcd_prefix='{prefix}'"));
 
-        let mut overrides = vec![
-            id,
-            pg_distrib_dir_param,
-            authg_type_param,
-            listen_http_addr_param,
-            listen_pg_addr_param,
-            broker_endpoint_param,
-        ];
+        let mut init_config_overrides = config_overrides.to_vec();
+        init_config_overrides.push(&id);
+        init_config_overrides.push(&pg_distrib_dir_param);
+        init_config_overrides.push(&authg_type_param);
+        init_config_overrides.push(&listen_http_addr_param);
+        init_config_overrides.push(&listen_pg_addr_param);
+        init_config_overrides.push(&broker_endpoints_param);
+
+        if let Some(broker_etcd_prefix_param) = broker_etcd_prefix_param.as_deref() {
+            init_config_overrides.push(broker_etcd_prefix_param);
+        }
 
         if self.env.pageserver.auth_type != AuthType::Trust {
-            overrides.push("auth_validation_public_key_path='auth_public_key.pem'".to_owned());
+            init_config_overrides.push("auth_validation_public_key_path='auth_public_key.pem'");
         }
-        overrides
-    }
 
-    pub fn initialize(
-        &self,
-        create_tenant: Option<TenantId>,
-        initial_timeline_id: Option<TimelineId>,
-        config_overrides: &[&str],
-        pg_version: u32,
-    ) -> anyhow::Result<TimelineId> {
         let mut pageserver_process = self
-            .start_node(config_overrides, &self.env.base_data_dir, true)
+            .start_node(&init_config_overrides, &self.env.base_data_dir, true)
             .with_context(|| {
                 format!(
                     "Failed to start a process for pageserver {}",
@@ -154,21 +173,29 @@ impl PageServerNode {
             }
             Err(e) => eprintln!("{e:#}"),
         }
-        background_process::send_stop_child_process(&pageserver_process)?;
-
-        let exit_code = pageserver_process.wait()?;
-        ensure!(
-            exit_code.success(),
-            format!(
-                "pageserver init failed with exit code {:?}",
-                exit_code.code()
-            )
-        );
-        println!(
-            "Stopped pageserver {} process with pid {}",
-            self.env.pageserver.id,
-            pageserver_process.id(),
-        );
+        match pageserver_process.kill() {
+            Err(e) => {
+                eprintln!(
+                    "Failed to stop pageserver {} process with pid {}: {e:#}",
+                    self.env.pageserver.id,
+                    pageserver_process.id(),
+                )
+            }
+            Ok(()) => {
+                println!(
+                    "Stopped pageserver {} process with pid {}",
+                    self.env.pageserver.id,
+                    pageserver_process.id(),
+                );
+                // cleanup after pageserver startup, since we do not call regular `stop_process` during init
+                let pid_file = self.pid_file();
+                if let Err(e) = fs::remove_file(&pid_file) {
+                    if e.kind() != io::ErrorKind::NotFound {
+                        eprintln!("Failed to remove pid file {pid_file:?} after stopping the process: {e:#}");
+                    }
+                }
+            }
+        }
         init_result
     }
 
@@ -210,10 +237,7 @@ impl PageServerNode {
         datadir: &Path,
         update_config: bool,
     ) -> anyhow::Result<Child> {
-        let mut overrides = self.neon_local_overrides();
-        overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
-
-        print!(
+        println!(
             "Starting pageserver at '{}' in '{}'",
             self.pg_connection_config.raw_address(),
             datadir.display()
@@ -231,25 +255,15 @@ impl PageServerNode {
             args.push("--update-config");
         }
 
-        for config_override in &overrides {
+        for config_override in config_overrides {
             args.extend(["-c", config_override]);
         }
 
-        let envs = if self.env.pageserver.auth_type != AuthType::Trust {
-            // Generate a token to connect from the pageserver to a safekeeper
-            let token = self
-                .env
-                .generate_auth_token(&Claims::new(None, Scope::SafekeeperData))?;
-            vec![("ZENITH_AUTH_TOKEN".to_owned(), token)]
-        } else {
-            vec![]
-        };
         background_process::start_process(
             "pageserver",
             datadir,
             &self.env.pageserver_bin(),
             &args,
-            envs,
             background_process::InitialPidFile::Expect(&self.pid_file()),
             || match self.check_status() {
                 Ok(()) => Ok(true),
@@ -348,11 +362,6 @@ impl PageServerNode {
                 .map(|x| x.parse::<NonZeroU64>())
                 .transpose()
                 .context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
-            trace_read_requests: settings
-                .remove("trace_read_requests")
-                .map(|x| x.parse::<bool>())
-                .transpose()
-                .context("Failed to parse 'trace_read_requests' as bool")?,
         };
         if !settings.is_empty() {
             bail!("Unrecognized tenant settings: {settings:?}")
@@ -415,11 +424,6 @@ impl PageServerNode {
                     .map(|x| x.parse::<NonZeroU64>())
                     .transpose()
                     .context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
-                trace_read_requests: settings
-                    .get("trace_read_requests")
-                    .map(|x| x.parse::<bool>())
-                    .transpose()
-                    .context("Failed to parse 'trace_read_requests' as bool")?,
             })
             .send()?
             .error_from_body()?;

control_plane/src/safekeeper.rs

@@ -5,12 +5,12 @@ use std::sync::Arc;
 use std::{io, result};
 
 use anyhow::Context;
-use postgres_connection::PgConnectionConfig;
 use reqwest::blocking::{Client, RequestBuilder, Response};
 use reqwest::{IntoUrl, Method};
 use thiserror::Error;
 use utils::{http::error::HttpErrorBody, id::NodeId};
 
+use crate::connection::PgConnectionConfig;
 use crate::pageserver::PageServerNode;
 use crate::{
     background_process,
@@ -86,7 +86,10 @@ impl SafekeeperNode {
 
     /// Construct libpq connection string for connecting to this safekeeper.
     fn safekeeper_connection_config(port: u16) -> PgConnectionConfig {
-        PgConnectionConfig::new_host_port(url::Host::parse("127.0.0.1").unwrap(), port)
+        // TODO safekeeper authentication not implemented yet
+        format!("postgresql://no_user@127.0.0.1:{port}/no_db")
+            .parse()
+            .unwrap()
     }
 
     pub fn datadir_path_by_id(env: &LocalEnv, sk_id: NodeId) -> PathBuf {
@@ -131,8 +134,13 @@ impl SafekeeperNode {
             args.push("--no-sync");
         }
 
-        let broker_endpoint = format!("{}", self.env.broker.client_url());
-        args.extend(["--broker-endpoint", &broker_endpoint]);
+        let comma_separated_endpoints = self.env.etcd_broker.comma_separated_endpoints();
+        if !comma_separated_endpoints.is_empty() {
+            args.extend(["--broker-endpoints", &comma_separated_endpoints]);
+        }
+        if let Some(prefix) = self.env.etcd_broker.broker_etcd_prefix.as_deref() {
+            args.extend(["--broker-etcd-prefix", prefix]);
+        }
 
         let mut backup_threads = String::new();
         if let Some(threads) = self.conf.backup_threads {
@@ -161,7 +169,6 @@ impl SafekeeperNode {
             &datadir,
             &self.env.safekeeper_bin(),
             &args,
-            [],
             background_process::InitialPidFile::Expect(&self.pid_file()),
             || match self.check_status() {
                 Ok(()) => Ok(true),

docker-compose/compute_wrapper/Dockerfile

@@ -1,13 +0,0 @@
-ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
-ARG COMPUTE_IMAGE=compute-node-v14
-ARG TAG=latest
-
-FROM $REPOSITORY/${COMPUTE_IMAGE}:$TAG
-
-USER root
-RUN apt-get update &&       \
-    apt-get install -y curl \
-                       jq   \
-                       netcat
-
-USER postgres

docker-compose/docker-compose.yml

@@ -1,8 +1,29 @@
 version: '3'
 
 services:
+  etcd:
+    image: quay.io/coreos/etcd:v3.5.4
+    ports:
+      - 2379:2379
+      - 2380:2380
+    environment:
+      # This signifficantly speeds up etcd and we anyway don't data persistency there.
+      ETCD_UNSAFE_NO_FSYNC: "1"
+    command: 
+      - "etcd"
+      - "--auto-compaction-mode=revision"
+      - "--auto-compaction-retention=1"
+      - "--name=etcd-cluster"
+      - "--initial-cluster-state=new"
+      - "--initial-cluster-token=etcd-cluster-1"
+      - "--initial-cluster=etcd-cluster=http://etcd:2380"
+      - "--initial-advertise-peer-urls=http://etcd:2380"
+      - "--advertise-client-urls=http://etcd:2379"
+      - "--listen-client-urls=http://0.0.0.0:2379"
+      - "--listen-peer-urls=http://0.0.0.0:2380"
+      - "--quota-backend-bytes=134217728" # 128 MB
+
   minio:
-    restart: always
     image: quay.io/minio/minio:RELEASE.2022-10-20T00-55-09Z
     ports:
       - 9000:9000
@@ -20,7 +41,7 @@ services:
     entrypoint:
       - "/bin/sh"
       - "-c"
-    command:
+    command: 
       - "until (/usr/bin/mc alias set minio http://minio:9000 $$MINIO_ROOT_USER $$MINIO_ROOT_PASSWORD) do
              echo 'Waiting to start minio...' && sleep 1;
          done;
@@ -30,10 +51,9 @@ services:
       - minio
 
   pageserver:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
+    image: neondatabase/neon:${TAG:-latest}
     environment:
-      - BROKER_ENDPOINT='http://storage_broker:50051'
+      - BROKER_ENDPOINT='http://etcd:2379'
       - AWS_ACCESS_KEY_ID=minio
       - AWS_SECRET_ACCESS_KEY=password
       #- RUST_BACKTRACE=1
@@ -45,7 +65,7 @@ services:
       - "-c"
     command:
       - "/usr/local/bin/pageserver -D /data/.neon/
-                                   -c \"broker_endpoint=$$BROKER_ENDPOINT\"
+                                   -c \"broker_endpoints=[$$BROKER_ENDPOINT]\"
                                    -c \"listen_pg_addr='0.0.0.0:6400'\"
                                    -c \"listen_http_addr='0.0.0.0:9898'\"
                                    -c \"remote_storage={endpoint='http://minio:9000',
@@ -53,16 +73,15 @@ services:
                                                         bucket_region='eu-north-1',
                                                         prefix_in_bucket='/pageserver/'}\""
     depends_on:
-      - storage_broker
+      - etcd
       - minio_create_buckets
 
   safekeeper1:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
+    image: neondatabase/neon:${TAG:-latest}
     environment:
       - SAFEKEEPER_ADVERTISE_URL=safekeeper1:5454
       - SAFEKEEPER_ID=1
-      - BROKER_ENDPOINT=http://storage_broker:50051
+      - BROKER_ENDPOINT=http://etcd:2379
       - AWS_ACCESS_KEY_ID=minio
       - AWS_SECRET_ACCESS_KEY=password
       #- RUST_BACKTRACE=1
@@ -76,23 +95,22 @@ services:
       - "safekeeper --listen-pg=$$SAFEKEEPER_ADVERTISE_URL
                     --listen-http='0.0.0.0:7676'
                     --id=$$SAFEKEEPER_ID
-                    --broker-endpoint=$$BROKER_ENDPOINT
+                    --broker-endpoints=$$BROKER_ENDPOINT
                     -D /data
                     --remote-storage=\"{endpoint='http://minio:9000',
                                         bucket_name='neon',
                                         bucket_region='eu-north-1',
                                         prefix_in_bucket='/safekeeper/'}\""
     depends_on:
-      - storage_broker
+      - etcd
       - minio_create_buckets
 
   safekeeper2:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
+    image: neondatabase/neon:${TAG:-latest}
     environment:
       - SAFEKEEPER_ADVERTISE_URL=safekeeper2:5454
       - SAFEKEEPER_ID=2
-      - BROKER_ENDPOINT=http://storage_broker:50051
+      - BROKER_ENDPOINT=http://etcd:2379
       - AWS_ACCESS_KEY_ID=minio
       - AWS_SECRET_ACCESS_KEY=password
       #- RUST_BACKTRACE=1
@@ -106,23 +124,22 @@ services:
       - "safekeeper --listen-pg=$$SAFEKEEPER_ADVERTISE_URL
                     --listen-http='0.0.0.0:7676'
                     --id=$$SAFEKEEPER_ID
-                    --broker-endpoint=$$BROKER_ENDPOINT
+                    --broker-endpoints=$$BROKER_ENDPOINT
                     -D /data
                     --remote-storage=\"{endpoint='http://minio:9000',
                                         bucket_name='neon',
                                         bucket_region='eu-north-1',
                                         prefix_in_bucket='/safekeeper/'}\""
     depends_on:
-      - storage_broker
+      - etcd
       - minio_create_buckets
 
   safekeeper3:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
+    image: neondatabase/neon:${TAG:-latest}
     environment:
       - SAFEKEEPER_ADVERTISE_URL=safekeeper3:5454
       - SAFEKEEPER_ID=3
-      - BROKER_ENDPOINT=http://storage_broker:50051
+      - BROKER_ENDPOINT=http://etcd:2379
       - AWS_ACCESS_KEY_ID=minio
       - AWS_SECRET_ACCESS_KEY=password
       #- RUST_BACKTRACE=1
@@ -136,41 +153,29 @@ services:
       - "safekeeper --listen-pg=$$SAFEKEEPER_ADVERTISE_URL
                     --listen-http='0.0.0.0:7676'
                     --id=$$SAFEKEEPER_ID
-                    --broker-endpoint=$$BROKER_ENDPOINT
+                    --broker-endpoints=$$BROKER_ENDPOINT
                     -D /data
                     --remote-storage=\"{endpoint='http://minio:9000',
                                         bucket_name='neon',
                                         bucket_region='eu-north-1',
                                         prefix_in_bucket='/safekeeper/'}\""
     depends_on:
-      - storage_broker
+      - etcd
       - minio_create_buckets
 
-  storage_broker:
-    restart: always
-    image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
-    ports:
-      - 50051:50051
-    command:
-      - "storage_broker"
-      - "--listen-addr=0.0.0.0:50051"
-
   compute:
-    restart: always
     build:
-      context: ./compute_wrapper/
+      context: ./image/compute
       args:
-        - COMPUTE_IMAGE=compute-node-v${PG_VERSION:-14}
-        - TAG=${TAG:-latest}
+        - COMPUTE_IMAGE=compute-node-v${PG_VERSION:-14}:${TAG:-latest}
         - http_proxy=$http_proxy
         - https_proxy=$https_proxy
     environment:
       - PG_VERSION=${PG_VERSION:-14}
       #- RUST_BACKTRACE=1
-    # Mount the test files directly, for faster editing cycle.
     volumes:
-      - ./compute_wrapper/var/db/postgres/specs/:/var/db/postgres/specs/
-      - ./compute_wrapper/shell/:/shell/
+      - ./compute/var/db/postgres/specs/:/var/db/postgres/specs/
+      - ./compute/shell/:/shell/
     ports:
       - 55433:55433 # pg protocol handler
       - 3080:3080 # http endpoints

docker-compose/docker_compose_test.sh

@@ -1,60 +0,0 @@
-#!/bin/bash
-
-# A basic test to ensure Docker images are built correctly.
-# Build a wrapper around the compute, start all services and runs a simple SQL query.
-# Repeats the process for all currenly supported Postgres versions.
-
-# Implicitly accepts `REPOSITORY` and `TAG` env vars that are passed into the compose file
-# Their defaults point at DockerHub `neondatabase/neon:latest` image.`,
-# to verify custom image builds (e.g pre-published ones).
-
-# XXX: Current does not work on M1 macs due to x86_64 Docker images compiled only, and no seccomp support in M1 Docker emulation layer.
-
-set -eux -o pipefail
-
-SCRIPT_DIR="$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )"
-COMPOSE_FILE=$SCRIPT_DIR/docker-compose.yml
-
-COMPUTE_CONTAINER_NAME=docker-compose-compute-1
-SQL="CREATE TABLE t(key int primary key, value text); insert into t values(1,1); select * from t;"
-PSQL_OPTION="-h localhost -U cloud_admin -p 55433 -c '$SQL' postgres"
-
-cleanup() {
-    echo "show container information"
-    docker ps
-    docker compose -f $COMPOSE_FILE logs
-    echo "stop containers..."
-    docker compose -f $COMPOSE_FILE down
-}
-
-echo "clean up containers if exists"
-cleanup
-
-for pg_version in 14 15; do
-    echo "start containers (pg_version=$pg_version)."
-    PG_VERSION=$pg_version docker compose -f $COMPOSE_FILE up --build -d
-
-    echo "wait until the compute is ready. timeout after 60s. "
-    cnt=0
-    while sleep 1; do
-        # check timeout
-        cnt=`expr $cnt + 1`
-        if [ $cnt -gt 60 ]; then
-            echo "timeout before the compute is ready."
-            cleanup
-            exit 1
-        fi
-
-        # check if the compute is ready
-        set +o pipefail
-        result=`docker compose -f $COMPOSE_FILE logs "compute_is_ready" | grep "accepting connections" | wc -l`
-        set -o pipefail
-        if [ $result -eq 1 ]; then
-            echo "OK. The compute is ready to connect."
-            echo "execute simple queries."
-            docker exec $COMPUTE_CONTAINER_NAME /bin/bash -c "psql $PSQL_OPTION"
-            cleanup
-            break
-        fi
-    done
-done

docker-compose/image/compute/Dockerfile

@@ -0,0 +1,10 @@
+ARG COMPUTE_IMAGE=compute-node-v14:latest
+FROM neondatabase/${COMPUTE_IMAGE}
+
+USER root
+RUN apt-get update &&       \
+    apt-get install -y curl \
+                       jq   \
+                       netcat
+
+USER postgres

docs/SUMMARY.md

@@ -37,7 +37,7 @@
 
 - [Source view](./sourcetree.md)
   - [docker.md](./docker.md) — Docker images and building pipeline.
-  - [Error handling and logging](./error-handling.md)
+  - [Error handling and logging]()
   - [Testing]()
     - [Unit testing]()
     - [Integration testing]()

docs/authentication.md

@@ -1,154 +1,30 @@
 ## Authentication
 
 ### Overview
-We use JWT tokens in communication between almost all components (compute, pageserver, safekeeper, CLI) regardless of the protocol used (HTTP/PostgreSQL).
-storage_broker currently has no authentication.
-Authentication is optional and is disabled by default for easier debugging.
-It is used in some tests, though.
-Note that we do not cover authentication with `pg.neon.tech` here.
 
-For HTTP connections we use the Bearer authentication scheme.
-For PostgreSQL connections we expect the token to be passed as a password.
-There is a caveat for `psql`: it silently truncates passwords to 100 symbols, so to correctly pass JWT via `psql` you have to either use `PGPASSWORD` environment variable, or store password in `psql`'s config file.
-
-Current token scopes are described in `utils::auth::Scope`.
-There are no expiration or rotation schemes.
-
-_TODO_: some scopes allow both access to server management API and to the data.
-These probably should be split into multiple scopes.
-
-Tokens should not occur in logs.
-They may sometimes occur in configuration files, although this is discouraged
-because configs may be parsed and dumped into logs.
-
-#### Tokens generation and validation
-JWT tokens are signed using a private key.
-Compute/pageserver/safekeeper use the private key's public counterpart to validate JWT tokens.
-These components should not have access to the private key and may only get tokens from their configuration or external clients. 
-
-The key pair is generated once for an installation of compute/pageserver/safekeeper, e.g. by `neon_local init`.
-There is currently no way to rotate the key without bringing down all components.
-
-### CLI
-CLI generates a key pair during call to `neon_local init` with the following commands:
+Current state of authentication includes usage of JWT tokens in communication between compute and pageserver and between CLI and pageserver. JWT token is signed using RSA keys. CLI generates a key pair during call to `neon_local init`. Using following openssl commands:
 
 ```bash
-openssl genrsa -out auth_private_key.pem 2048
-openssl rsa -in auth_private_key.pem -pubout -outform PEM -out auth_public_key.pem
+openssl genrsa -out private_key.pem 2048
+openssl rsa -in private_key.pem -pubout -outform PEM -out public_key.pem
 ```
 
-Configuration files for all components point to `public_key.pem` for JWT validation.
-However, authentication is disabled by default.
-There is no way to automatically enable it everywhere, you have to configure each component individually.
+CLI also generates signed token and saves it in the config for later access to pageserver. Now authentication is optional. Pageserver has two variables in config: `auth_validation_public_key_path` and `auth_type`, so when auth type present and set to `NeonJWT` pageserver will require authentication for connections. Actual JWT is passed in password field of connection string. There is a caveat for psql, it silently truncates passwords to 100 symbols, so to correctly pass JWT via psql you have to either use PGPASSWORD environment variable, or store password in psql config file.
 
-CLI also generates signed token (full access to Pageserver) and saves it in
-the CLI's `config` file under `pageserver.auth_token`.
-Note that pageserver's config does not have any similar parameter.
-CLI is the only component which accesses that token.
-Technically it could generate it from the private key on each run,
-but it does not do that for some reason (_TODO_).
+Currently there is no authentication between compute and safekeepers, because this communication layer is under heavy refactoring. After this refactoring support for authentication will be added there too. Now safekeeper supports "hardcoded" token passed via environment variable to be able to use callmemaybe command in pageserver.
 
-### Compute
-#### Overview
-Compute is a per-timeline PostgreSQL instance, so it should not have
-any access to data of other tenants.
-All tokens used by a compute are restricted to a specific tenant.
-There is no auth isolation from other timelines of the same tenant,
-but a non-rogue client never accesses another timeline even by an accident:
-timeline IDs are random and hard to guess.
+Compute uses token passed via environment variable to communicate to pageserver and in the future to the safekeeper too.
 
-#### Incoming connections
-All incoming connections are from PostgreSQL clients.
-Their authentication is just plain PostgreSQL authentication and out of scope for this document.
+JWT authentication now supports two scopes: tenant and pageserverapi. Tenant scope is intended for use in tenant related api calls, e.g. create_branch. Compute launched for particular tenant also uses this scope. Scope pageserver api is intended to be used by console to manage pageserver. For now we have only one management operation - create tenant.
 
-There is no administrative API except those provided by PostgreSQL.
-
-#### Outgoing connections
-Compute connects to Pageserver for getting pages.
-The connection string is configured by the `neon.pageserver_connstring` PostgreSQL GUC, e.g. `postgresql://no_user:$ZENITH_AUTH_TOKEN@localhost:15028`.
-The environment variable inside the connection string is substituted with
-the JWT token.
-
-Compute connects to Safekeepers to write and commit data.
-The token is the same for all safekeepers.
-It's stored in an environment variable, whose name is configured
-by the `neon.safekeeper_token_env` PostgreSQL GUC.
-If the GUC is unset, no token is passed.
-
-Note that both tokens can be (and typically are) the same;
-the scope is the tenant and the token is usually passed through the
-`$ZENITH_AUTH_TOKEN` environment variable.
-
-### Pageserver
-#### Overview
-Pageserver keeps track of multiple tenants, each having multiple timelines.
-For each timeline, it connects to the corresponding Safekeeper.
-Information about "corresponding Safekeeper" is published by Safekeepers
-in the storage_broker, but they do not publish access tokens, otherwise what is
-the point of authentication.
-
-Pageserver keeps a connection to some set of Safekeepers, which
-may or may not correspond to active Computes.
-Hence, we cannot obtain a per-timeline access token from a Compute.
-E.g. if the timeline's Compute terminates before all WAL is
-consumed by the Pageserver, the Pageserver continues consuming WAL.
-
-Pageserver replicas' authentication is the same as the main's.
-
-#### Incoming connections
-Pageserver listens for connections from computes.
-Each compute should present a token valid for the timeline's tenant.
-
-Pageserver also has HTTP API: some parts are per-tenant,
-some parts are server-wide, these are different scopes.
-
-The `auth_type` configuration variable in Pageserver's config may have
-either of three values:
-
-* `Trust` removes all authentication. The outdated `MD5` value does likewise
-* `NeonJWT` enables JWT validation.
-   Tokens are validated using the public key which lies in a PEM file
-   specified in the `auth_validation_public_key_path` config.
-
-#### Outgoing connections
-Pageserver makes a connection to a Safekeeper for each active timeline.
-As Pageserver may want to access any timeline it has on the disk,
-it is given a blanket JWT token to access any data on any Safekeeper.
-This token is passed through an environment variable called `ZENITH_AUTH_TOKEN`
-(non-configurable as of writing this text).
-
-A better way _may be_ to store JWT token for each timeline next to it,
-but may be not.
-
-### Safekeeper
-#### Overview
-Safekeeper keeps track of multiple tenants, each having multiple timelines.
-
-#### Incoming connections
-Safekeeper accepts connections from Compute/Pageserver, each
-connection corresponds to a specific timeline and requires
-a corresponding JWT token.
-
-Safekeeper also has HTTP API: some parts are per-tenant,
-some parts are server-wide, these are different scopes.
-
-The `auth-validation-public-key-path` command line options controls
-the authentication mode:
-
-* If the option is missing, there is no authentication or JWT token validation.
-* If the option is present, it should be a path to the public key PEM file used for JWT token validation.
-
-#### Outgoing connections
-No connections are initiated by a Safekeeper.
-
-### In the source code
-Tests do not use authentication by default.
-If you need it, you can enable it by configuring the test's environment:
+Examples for token generation in python:
 
 ```python
-neon_env_builder.auth_enabled = True
+# generate pageserverapi token
+management_token = jwt.encode({"scope": "pageserverapi"}, auth_keys.priv, algorithm="RS256")
+
+# generate tenant token
+tenant_token = jwt.encode({"scope": "tenant", "tenant_id": ps.initial_tenant}, auth_keys.priv, algorithm="RS256")
 ```
 
-You will have to generate tokens if you want to access components inside the test directly,
-use `AuthKeys.generate_*_token` methods for that.
-If you create a new scope, please create a new method to prevent mistypes in scope's name.
+Utility functions to work with jwts in rust are located in libs/utils/src/auth.rs

docs/docker.md

@@ -23,9 +23,9 @@ We build all images after a successful `release` tests run and push automaticall
 
 You can see a [docker compose](https://docs.docker.com/compose/) example to create a neon cluster in [/docker-compose/docker-compose.yml](/docker-compose/docker-compose.yml). It creates the following conatainers.
 
+- etcd x 1
 - pageserver x 1
 - safekeeper x 3
-- storage_broker x 1
 - compute x 1
 - MinIO x 1        # This is Amazon S3 compatible object storage
 
@@ -41,7 +41,7 @@ $ cd docker-compose/docker-compose.yml
 $ docker-compose down   # remove the conainers if exists
 $ PG_VERSION=15 TAG=2221 docker-compose up --build -d  # You can specify the postgres and image version
 Creating network "dockercompose_default" with the default driver
-Creating docker-compose_storage_broker_1       ... done
+Creating dockercompose_etcd3_1 ...
 (...omit...)
 ```
 

docs/error-handling.md

@@ -1,198 +0,0 @@
-# Error handling and logging
-
-## Logging errors
-
-The principle is that errors are logged when they are handled. If you
-just propagate an error to the caller in a function, you don't need to
-log it; the caller will. But if you consume an error in a function,
-you *must* log it (if it needs to be logged at all).
-
-For example:
-
-```rust
-fn read_motd_file() -> std::io::Result<String> {
-    let mut f = File::open("/etc/motd")?;
-    let mut result = String::new();
-    f.read_to_string(&mut result)?;
-    result
-}
-```
-
-Opening or reading the file could fail, but there is no need to log
-the error here. The function merely propagates the error to the
-caller, and it is up to the caller to log the error or propagate it
-further, if the failure is not expected. But if, for example, it is
-normal that the "/etc/motd" file doesn't exist, the caller can choose
-to silently ignore the error, or log it as an INFO or DEBUG level
-message:
-
-```rust
-fn get_message_of_the_day() -> String {
-    // Get the motd from /etc/motd, or return the default proverb
-    match read_motd_file() {
-        Ok(motd) => motd,
-        Err(err)  => {
-            // It's normal that /etc/motd doesn't exist, but if we fail to
-            // read it for some other reason, that's unexpected. The message
-            // of the day isn't very important though, so we just WARN and
-            // continue with the default in any case.
-            if err.kind() != std::io::ErrorKind::NotFound {
-                 tracing::warn!("could not read \"/etc/motd\": {err:?}");
-            }
-            "An old error is always more popular than a new truth. - German proverb"
-        }
-    }
-}
-```
-
-## Error types
-
-We use the `anyhow` crate widely. It contains many convenient macros
-like `bail!` and `ensure!` to construct and return errors, and to
-propagate many kinds of low-level errors, wrapped in `anyhow::Error`.
-
-A downside of `anyhow::Error` is that the caller cannot distinguish
-between different error cases. Most errors are propagated all the way
-to the mgmt API handler function, or the main loop that handles a
-connection with the compute node, and they are all handled the same
-way: the error is logged and returned to the client as an HTTP or
-libpq error.
-
-But in some cases, we need to distinguish between errors and handle
-them differently. For example, attaching a tenant to the pageserver
-could fail either because the tenant has already been attached, or
-because we could not load its metadata from cloud storage. The first
-case is more or less expected. The console sends the Attach request to
-the pageserver, and the pageserver completes the operation, but the
-network connection might be lost before the console receives the
-response. The console will retry the operation in that case, but the
-tenant has already been attached. It is important that the pagserver
-responds with the HTTP 403 Already Exists error in that case, rather
-than a generic HTTP 500 Internal Server Error.
-
-If you need to distinguish between different kinds of errors, create a
-new `Error` type. The `thiserror` crate is useful for that. But in
-most cases `anyhow::Error` is good enough.
-
-## Panics
-
-Depending on where a panic happens, it can cause the whole pageserver
-or safekeeper to restart, or just a single tenant. In either case,
-that is pretty bad and causes an outage. Avoid panics. Never use
-`unwrap()` or other calls that might panic, to verify inputs from the
-network or from disk.
-
-It is acceptable to use functions that might panic, like `unwrap()`, if
-it is obvious that it cannot panic. For example, if you have just
-checked that a variable is not None, it is OK to call `unwrap()` on it,
-but it is still preferable to use `expect("reason")` instead to explain
-why the function cannot fail.
-
-`assert!` and `panic!` are reserved for checking clear invariants and
-very obvious "can't happen" cases. When in doubt, use anyhow `ensure!`
-or `bail!` instead.
-
-## Error levels
-
-`tracing::Level` doesn't provide very clear guidelines on what the
-different levels mean, or when to use which level. Here is how we use
-them:
-
-### Error
-
-Examples:
-- could not open file "foobar"
-- invalid tenant id
-
-Errors are not expected to happen during normal operation. Incorrect
-inputs from client can cause ERRORs. For example, if a client tries to
-call a mgmt API that doesn't exist, or if a compute node sends passes
-an LSN that has already been garbage collected away.
-
-These should *not* happen during normal operations. "Normal
-operations" is not a very precise concept. But for example, disk
-errors are not expected to happen when the system is working, so those
-count as Errors. However, if a TCP connection to a compute node is
-lost, that is not considered an Error, because it doesn't affect the
-pageserver's or safekeeper's operation in any way, and happens fairly
-frequently when compute nodes are shut down, or are killed abruptly
-because of errors in the compute.
-
-**Errors are monitored, and always need human investigation to determine
-the cause.**
-
-Whether something should be logged at ERROR, WARNING or INFO level can
-depend on the callers and clients. For example, it might be unexpected
-and a sign of a serious issue if the console calls the
-"timeline_detail" mgmt API for a timeline that doesn't exist. ERROR
-would be appropriate in that case. But if the console routinely calls
-the API after deleting a timeline, to check if the deletion has
-completed, then it would be totally normal and an INFO or DEBUG level
-message would be more appropriate. If a message is logged as an ERROR,
-but it in fact happens frequently in production and never requires any
-action, it should probably be demoted to an INFO level message.
-
-### Warn
-
-Examples:
-- could not remove temporary file "foobar.temp"
-- unrecognized file "foobar" in timeline directory
-
-Warnings are similar to Errors, in that they should not happen
-when the system is operating normally. The difference between Error and
-Warning is that an Error means that the operation failed, whereas Warning
-means that something unexpected happened, but the operation continued anyway.
-For example, if deleting a file fails because the file already didn't exist,
-it should be logged as Warning.
-
-> **Note:** The python regression tests, under `test_regress`, check the
-> pageserver log after each test for any ERROR and WARN lines. If there are
-> any ERRORs or WARNs that have not been explicitly listed in the test as
-> allowed, the test is marked a failed. This is to catch unexpected errors
-> e.g. in background operations, that don't cause immediate misbehaviour in
-> the tested functionality.
-
-### Info
-
-Info level is used to log useful information when the system is
-operating normally. Info level is appropriate e.g. for logging state
-changes, background operations, and network connections.
-
-Examples:
-- "system is shutting down"
-- "tenant was created"
-- "retrying S3 upload"
-
-### Debug & Trace
-
-Debug and Trace level messages are not printed to the log in our normal
-production configuration, but could be enabled for a specific server or
-tenant, to aid debugging. (Although we don't actually have that
-capability as of this writing).
-
-## Context
-
-We use logging "spans" to hold context information about the current
-operation. Almost every operation happens on a particular tenant and
-timeline, so we enter a span with the "tenant_id" and "timeline_id"
-very early when processing an incoming API request, for example. All
-background operations should also run in a span containing at least
-those two fields, and any other parameters or information that might
-be useful when debugging an error that might happen when performing
-the operation.
-
-TODO: Spans are not captured in the Error when it is created, but when
-the error is logged. It would be more useful to capture them at Error
-creation. We should consider using `tracing_error::SpanTrace` to do
-that.
-
-## Error message style
-
-PostgreSQL has a style guide for writing error messages:
-
-https://www.postgresql.org/docs/current/error-style-guide.html
-
-Follow that guide when writing error messages in the PostgreSQL
-extension. We don't follow it strictly in the pageserver and
-safekeeper, but the advice in the PostgreSQL style guide is generally
-good, and you can't go wrong by following it.

docs/rfcs/021-autoscaling-compute-cache.md

@@ -1,201 +0,0 @@
-# Context
-
-In Neon, one host runs a lot of compute nodes. Most of the compute
-nodes are fairly small, 1-2 vCPUs and 1-2 GB of memory. But some
-compute nodes can be larger, and we also want to autoscale from small
-to large, and back again, without shutting down the compute.
-
-    +----------------------------+
-    |      Host                  |
-    | +------------------------+ |
-    | |    Container VM        | |               +------------+
-    | | +--------------------+ | |               |            |
-    | | |  Postgres          | | |               | Pageserver |
-    | | |                    | | |               |            |
-    | | |  ################  | | |               |            |
-    | | |  # shared_      #  | | |               +------------+
-    | | |  # buffers      #  | | |
-    | | |  ################  | | |
-    | | |                    | | |
-    | | +--------------------+ | |
-    | +------------------------+ |
-    +----------------------------+
-
-Each Postgres runs in a qemu VM, which in turn runs in a kubernetes
-pod. Kubernetes manages the placement of these Postgres compute nodes
-to hosts.
-
-# Problem
-
-PostgreSQL normally relies heavily on the kernel page cache for
-performance. PostgreSQL has its own buffer cache, configured by the
-shared_buffers setting, but the usual advice is to set shared_buffers
-to around 10-20% of the overall system RAM available, leaving the rest
-for the kernel page cache. However with Neon, the I/O operations don't
-go through the kernel filesystem layer, so we bypass the kernel page
-cache and rely solely on the Postgres shared buffer cache for caching
-in the compute node.
-
-Because we don't make use of the kernel page cache, we have to either
-set shared_buffers larger than you would with normal PostgreSQL, or
-you send a lot more I/O requests to the pageserver than you otherwise
-would. However in PostgreSQL, shared_buffers setting cannot be changed
-while the server is running.
-
-Furthermore, we have fast local SSDs available in the compute hosts
-that we could also utilize for caching.
-
-
-
-# Solution 1: Scale shared buffers
-
-This solution consists of:
-
-- Core PostgreSQL changes to allow changing shared_buffers on the fly
-
-- New code to orchestrate changing the memory size of the VM, and tell
-  PostgreSQL to change the shared_buffers setting accordingly.
-
-- New code to Postgres that measures current shared buffer cache usage
-  to determine what the "cache pressure" is, i.e. how useful it would
-  be to have a larger shared buffer cache. This could be in an
-  extension.
-  
-- A new governor in the host that chooses which VM to allocate
-  how much memory.
-
-Picture:
-
-    +----------------------------+
-    |      Host                  |
-    | +------------------------+ |
-    | |    Container VM        | |               +------------+
-    | | +--------------------+ | |               |            |
-    | | |  Postgres          | | |               | Pageserver |
-    | | |                    | | |               |            |
-    | | |  ################  | | |               |            |
-    | | |  # shared_      #  | | |               +------------+
-    | | |  # buffers      #  | | |
-    | | |  #              #  | | |
-    | | |  .    |         .  | | |
-    | | |  .    |         .  | | |
-    | | |  .    V         .  | | |
-    | | |  ################  | | |
-    | | |                    | | |
-    | | +--------------------+ | |
-    | +------------------------+ |
-    +----------------------------+
-
-Pros:
-
-- best possible performance for the cached data
-
-Cons:
-
-- Scales only memory, cannot take advantage of local SSDs in host machine
-- Needs explicit operations to scale. Won't dynamicaly share resources
-  between tenants, we'll need to start a resizing process to change
-  the allocations.
-- Needs patches to core PostgreSQL
-
-
-# Alternative 2: Local filesystem cache
-
-Add code to Postgres Neon extension to use a local file on disk for
-caching.  When a page is evicted from Postgres buffer cache, write it
-to the local file, and read it back if it's requested again. Rely on
-kernel page cache to keep the most hot part of that file in memory.
-
-Like in solution 1, need a governor in the host to allocate the local
-disk for each VM, and orchestration to scale it up and down.
-
-
-    +----------------------------+
-    |      Host                  |
-    | +------------------------+ |
-    | |    Container VM        | |               +------------+
-    | | +--------------------+ | |               |            |
-    | | |  Postgres          | | |               | Pageserver |
-    | | |                    | | |               |            |
-    | | |  ################  | | |               |            |
-    | | |  # shared_      #  | | |               +------------+
-    | | |  # buffers      #  | | |
-    | | |  ################  | | |
-    | | |                    | | |
-    | | |  ################  | | |
-    | | |  # Local FS     #  | | |
-    | | |  # cache        #  | | |
-    | | |  #              #  | | |
-    | | |  ################  | | |
-    | | |                    | | |
-    | | +--------------------+ | |
-    | +------------------------+ |
-    +----------------------------+
-
-Pros:
-
-- No PostgreSQL core changes required
-- Automatically takes advantage of local SSDs, not just memory
-
-Cons:
-
-- Needs explicit operations to change the size of the cache file
-- Need support for live migration of the filesystem
-
-
-Question:
-How is the page cache shared between the host kernel and the VMs? Does
-each VM maintain their own page cache? I think that depends on the
-filesystem and qemu driver we choose. If we use a raw block device and
-let the VM manage it, I believe the VM will maintain the page
-cache. But if we use a driver to access the host filesystem directly,
-or use something like NFS, I'm not sure.
-
-
-# Alternative 3: Host cache
-
-Implement a new host cache process that intercepts all the I/O
-requests from all VMs running on the host, and manages a local cache.
-Postgres can communicate with the host cache using TCP, or via custom
-virtio driver.
-
-    +----------------------------+
-    |      Host                  |
-    |                            |
-    |   ######################   |
-    |   #                    #   |
-    |   # shared host cache  #   |
-    |   #                    #   |
-    |   #                    #   |
-    |   #                    #   |
-    |   #                    #   |
-    |   ######################   |
-    |                            |
-    | +------------------------+ |
-    | |    Container VM        | |               +------------+
-    | | +--------------------+ | |               |            |
-    | | |  Postgres          | | |               | Pageserver |
-    | | |                    | | |               |            |
-    | | |  ################  | | |               |            |
-    | | |  # shared_      #  | | |               +------------+
-    | | |  # buffers      #  | | |
-    | | |  ################  | | |
-    | | |                    | | |
-    | | +--------------------+ | |
-    | +------------------------+ |
-    +----------------------------+
-
-Pros:
-- dynamic sharing between all tenants (one cache and eviction policy for all)
-- No PostgreSQL core changes required
-- Takes advantage of local SSDs, not just memory
-
-Cons:
-
-- Whole new component to write
-
-
-One way to achieve this would be to collocate the pageserver on the
-host itself. That would eliminate the network roundtrip between
-Postgres and the pageserver, effectively making the pageserver itself
-be the host shared cache.

docs/settings.md

@@ -10,6 +10,7 @@ the values in the config file, if any are specified for the same key and get int
 
 ```toml
 # Initial configuration file created by 'pageserver --init'
+
 listen_pg_addr = '127.0.0.1:64000'
 listen_http_addr = '127.0.0.1:9898'
 
@@ -24,12 +25,13 @@ max_file_descriptors = '100'
 # initial superuser role name to use when creating a new tenant
 initial_superuser_name = 'cloud_admin'
 
-broker_endpoint = 'http://127.0.0.1:50051'
+broker_etcd_prefix = 'neon'
+broker_endpoints = ['some://etcd']
 
 # [remote_storage]
 ```
 
-The config above shows default values for all basic pageserver settings, besides `broker_endpoint`: that one has to be set by the user,
+The config above shows default values for all basic pageserver settings, besides `broker_endpoints`: that one has to be set by the user,
 see the corresponding section below.
 Pageserver uses default values for all files that are missing in the config, so it's not a hard error to leave the config blank.
 Yet, it validates the config values it can (e.g. postgres install dir) and errors if the validation fails, refusing to start.
@@ -48,10 +50,16 @@ Example: `${PAGESERVER_BIN} -c "checkpoint_timeout = '10 m'" -c "remote_storage=
 
 Note that TOML distinguishes between strings and integers, the former require single or double quotes around them.
 
-#### broker_endpoint
+#### broker_endpoints
 
-A storage broker endpoint to connect and pull the information from. Default is
-`'http://127.0.0.1:50051'`. 
+A list of endpoints (etcd currently) to connect and pull the information from.
+Mandatory, does not have a default, since requires etcd to be started as a separate process,
+and its connection url should be specified separately.
+
+#### broker_etcd_prefix
+
+A prefix to add for every etcd key used, to separate one group of related instances from another, in the same cluster.
+Default is `neon`.
 
 #### checkpoint_distance
 

docs/sourcetree.md

@@ -2,11 +2,6 @@
 
 Below you will find a brief overview of each subdir in the source tree in alphabetical order.
 
-`storage_broker`:
-
-Neon storage broker, providing messaging between safekeepers and pageservers.
-[storage_broker.md](./storage_broker.md)
-
 `/control_plane`:
 
 Local control plane.
@@ -45,9 +40,9 @@ and create new databases and accounts (control plane API in our case).
 
 Integration tests, written in Python using the `pytest` framework.
 
-`/vendor/postgres-v14` and `/vendor/postgres-v15`:
+`/vendor/postgres-v14`:
 
-PostgreSQL source tree per version, with the modifications needed for Neon.
+PostgreSQL source tree, with the modifications needed for Neon.
 
 `/pgxn/neon`:
 
@@ -88,16 +83,6 @@ A subject for future modularization.
 `/libs/metrics`:
 Helpers for exposing Prometheus metrics from the server.
 
-### Adding dependencies
-When you add a Cargo dependency, you should update hakari manifest by running commands below and committing the updated `Cargo.lock` and `workspace_hack/`. There may be no changes, that's fine.
-
-```bash
-cargo hakari generate
-cargo hakari manage-deps
-```
-
-If you don't have hakari installed (`error: no such subcommand: hakari`), install it by running `cargo install cargo-hakari`.
-
 ## Using Python
 Note that Debian/Ubuntu Python packages are stale, as it commonly happens,
 so manual installation of dependencies is not recommended.

docs/storage_broker.md

@@ -1,27 +0,0 @@
-# Storage broker
-
-Storage broker targets two issues:
-- Allowing safekeepers and pageservers learn which nodes also hold their
-  timelines, and timeline statuses there.
-- Avoiding O(n^2) connections between storage nodes while doing so.
-
-This is used
-- By pageservers to determine the most advanced and alive safekeeper to pull WAL from.
-- By safekeepers to synchronize on the timeline: advance
-  `remote_consistent_lsn`, `backup_lsn`, choose who offloads WAL to s3.
-
-Technically, it is a simple stateless pub-sub message broker based on tonic
-(grpc) making multiplexing easy. Since it is stateless, fault tolerance can be
-provided by k8s; there is no built in replication support, though it is not hard
-to add.
-
-Currently, the only message is `SafekeeperTimelineInfo`. Each safekeeper, for
-each active timeline, once in a while pushes timeline status to the broker.
-Other nodes subscribe and receive this info, using it per above.
-
-Broker serves /metrics on the same port as grpc service. 
-
-grpcurl can be used to check which values are currently being pushed:
-```
-grpcurl -proto broker/proto/broker.proto -d '{"all":{}}' -plaintext localhost:50051 storage_broker.BrokerService/SubscribeSafekeeperInfo
-```

libs/etcd_broker/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+ name = "etcd_broker"
+ version = "0.1.0"
+ edition = "2021"
+
+ [dependencies]
+ etcd-client = "0.9.0"
+ regex = "1.4.5"
+ serde = { version = "1.0", features = ["derive"] }
+ serde_json = "1"
+ serde_with = "2.0"
+ once_cell = "1.13.0"
+
+ utils = { path = "../utils" }
+ workspace_hack = { version = "0.1", path = "../../workspace_hack" }
+ tokio = "1"
+ tracing = "0.1"
+ thiserror = "1"

libs/etcd_broker/src/lib.rs

@@ -0,0 +1,209 @@
+//! A set of primitives to access a shared data/updates, propagated via etcd broker (not persistent).
+//! Intended to connect services to each other, not to store their data.
+
+/// All broker keys, that are used when dealing with etcd.
+pub mod subscription_key;
+/// All broker values, possible to use when dealing with etcd.
+pub mod subscription_value;
+
+use std::str::FromStr;
+
+use serde::de::DeserializeOwned;
+
+use subscription_key::SubscriptionKey;
+use tokio::{sync::mpsc, task::JoinHandle};
+use tracing::*;
+
+use crate::subscription_key::SubscriptionFullKey;
+
+pub use etcd_client::*;
+
+/// Default value to use for prefixing to all etcd keys with.
+/// This way allows isolating safekeeper/pageserver groups in the same etcd cluster.
+pub const DEFAULT_NEON_BROKER_ETCD_PREFIX: &str = "neon";
+
+/// A way to control the data retrieval from a certain subscription.
+pub struct BrokerSubscription<V> {
+    /// An unbounded channel to fetch the relevant etcd updates from.
+    pub value_updates: mpsc::UnboundedReceiver<BrokerUpdate<V>>,
+    key: SubscriptionKey,
+    /// A subscription task handle, to allow waiting on it for the task to complete.
+    /// Both the updates channel and the handle require `&mut`, so it's better to keep
+    /// both `pub` to allow using both in the same structures without borrow checker complaining.
+    pub watcher_handle: JoinHandle<Result<(), BrokerError>>,
+    watcher: Watcher,
+}
+
+impl<V> BrokerSubscription<V> {
+    /// Cancels the subscription, stopping the data poller and waiting for it to shut down.
+    pub async fn cancel(mut self) -> Result<(), BrokerError> {
+        self.watcher.cancel().await.map_err(|e| {
+            BrokerError::EtcdClient(
+                e,
+                format!("Failed to cancel broker subscription, kind: {:?}", self.key),
+            )
+        })?;
+        match (&mut self.watcher_handle).await {
+            Ok(res) => res,
+            Err(e) => {
+                if e.is_cancelled() {
+                    // don't error on the tasks that are cancelled already
+                    Ok(())
+                } else {
+                    Err(BrokerError::InternalError(format!(
+                        "Panicked during broker subscription task, kind: {:?}, error: {e}",
+                        self.key
+                    )))
+                }
+            }
+        }
+    }
+}
+
+impl<V> Drop for BrokerSubscription<V> {
+    fn drop(&mut self) {
+        // we poll data from etcd into the channel in the same struct, so if the whole struct gets dropped,
+        // no more data is used by the receiver and it's safe to cancel and drop the whole etcd subscription task.
+        self.watcher_handle.abort();
+    }
+}
+
+/// An update from the etcd broker.
+pub struct BrokerUpdate<V> {
+    /// Etcd generation version, the bigger the more actual the data is.
+    pub etcd_version: i64,
+    /// Etcd key for the corresponding value, parsed from the broker KV.
+    pub key: SubscriptionFullKey,
+    /// Current etcd value, parsed from the broker KV.
+    pub value: V,
+}
+
+#[derive(Debug, thiserror::Error)]
+pub enum BrokerError {
+    #[error("Etcd client error: {0}. Context: {1}")]
+    EtcdClient(etcd_client::Error, String),
+    #[error("Error during parsing etcd key: {0}")]
+    KeyNotParsed(String),
+    #[error("Internal error: {0}")]
+    InternalError(String),
+}
+
+/// Creates a background task to poll etcd for timeline updates from safekeepers.
+/// Stops and returns `Err` on any error during etcd communication.
+/// Watches the key changes until either the watcher is cancelled via etcd or the subscription cancellation handle,
+/// exiting normally in such cases.
+/// Etcd values are parsed as json fukes into a type, specified in the generic patameter.
+pub async fn subscribe_for_json_values<V>(
+    client: &mut Client,
+    key: SubscriptionKey,
+) -> Result<BrokerSubscription<V>, BrokerError>
+where
+    V: DeserializeOwned + Send + 'static,
+{
+    subscribe_for_values(client, key, |_, value_str| {
+        match serde_json::from_str::<V>(value_str) {
+            Ok(value) => Some(value),
+            Err(e) => {
+                error!("Failed to parse value str '{value_str}': {e}");
+                None
+            }
+        }
+    })
+    .await
+}
+
+/// Same as [`subscribe_for_json_values`], but allows to specify a custom parser of a etcd value string.
+pub async fn subscribe_for_values<P, V>(
+    client: &mut Client,
+    key: SubscriptionKey,
+    value_parser: P,
+) -> Result<BrokerSubscription<V>, BrokerError>
+where
+    V: Send + 'static,
+    P: Fn(SubscriptionFullKey, &str) -> Option<V> + Send + 'static,
+{
+    info!("Subscribing to broker value updates, key: {key:?}");
+    let subscription_key = key.clone();
+
+    let (watcher, mut stream) = client
+        .watch(key.watch_key(), Some(WatchOptions::new().with_prefix()))
+        .await
+        .map_err(|e| {
+            BrokerError::EtcdClient(
+                e,
+                format!("Failed to init the watch for subscription {key:?}"),
+            )
+        })?;
+
+    let (value_updates_sender, value_updates_receiver) = mpsc::unbounded_channel();
+    let watcher_handle = tokio::spawn(async move {
+        while let Some(resp) = stream.message().await.map_err(|e| BrokerError::InternalError(format!(
+            "Failed to get messages from the subscription stream, kind: {:?}, error: {e}", key.kind
+        )))? {
+            if resp.canceled() {
+                info!("Watch for timeline updates subscription was canceled, exiting");
+                break;
+            }
+
+            let events = resp.events();
+            debug!("Processing {} events", events.len());
+
+            for event in events {
+                if EventType::Put == event.event_type() {
+                    if let Some(new_etcd_kv) = event.kv() {
+                        match parse_etcd_kv(new_etcd_kv, &value_parser, &key.cluster_prefix) {
+                            Ok(Some((key, value))) => if let Err(e) = value_updates_sender.send(BrokerUpdate {
+                                etcd_version: new_etcd_kv.version(),
+                                key,
+                                value,
+                            }) {
+                                info!("Broker value updates for key {key:?} sender got dropped, exiting: {e}");
+                                break;
+                            },
+                            Ok(None) => debug!("Ignoring key {key:?} : no value was returned by the parser"),
+                            Err(BrokerError::KeyNotParsed(e)) => debug!("Unexpected key {key:?} for timeline update: {e}"),
+                            Err(e) => error!("Failed to represent etcd KV {new_etcd_kv:?}: {e}"),
+                        };
+                    }
+                }
+            }
+        }
+
+        Ok(())
+    }.instrument(info_span!("etcd_broker")));
+
+    Ok(BrokerSubscription {
+        key: subscription_key,
+        value_updates: value_updates_receiver,
+        watcher_handle,
+        watcher,
+    })
+}
+
+fn parse_etcd_kv<P, V>(
+    kv: &KeyValue,
+    value_parser: &P,
+    cluster_prefix: &str,
+) -> Result<Option<(SubscriptionFullKey, V)>, BrokerError>
+where
+    P: Fn(SubscriptionFullKey, &str) -> Option<V>,
+{
+    let key_str = kv.key_str().map_err(|e| {
+        BrokerError::EtcdClient(e, "Failed to extract key str out of etcd KV".to_string())
+    })?;
+    let value_str = kv.value_str().map_err(|e| {
+        BrokerError::EtcdClient(e, "Failed to extract value str out of etcd KV".to_string())
+    })?;
+
+    if !key_str.starts_with(cluster_prefix) {
+        return Err(BrokerError::KeyNotParsed(format!(
+            "KV has unexpected key '{key_str}' that does not start with cluster prefix {cluster_prefix}"
+        )));
+    }
+
+    let key = SubscriptionFullKey::from_str(&key_str[cluster_prefix.len()..]).map_err(|e| {
+        BrokerError::KeyNotParsed(format!("Failed to parse KV key '{key_str}': {e}"))
+    })?;
+
+    Ok(value_parser(key, value_str).map(|value| (key, value)))
+}

libs/etcd_broker/src/subscription_key.rs

@@ -0,0 +1,310 @@
+//! Etcd broker keys, used in the project and shared between instances.
+//! The keys are split into two categories:
+//!
+//! * [`SubscriptionFullKey`] full key format: `<cluster_prefix>/<tenant>/<timeline>/<node_kind>/<operation>/<node_id>`
+//! Always returned from etcd in this form, always start with the user key provided.
+//!
+//! * [`SubscriptionKey`] user input key format: always partial, since it's unknown which `node_id`'s are available.
+//! Full key always starts with the user input one, due to etcd subscription properties.
+
+use std::{fmt::Display, str::FromStr};
+
+use once_cell::sync::Lazy;
+use regex::{Captures, Regex};
+use utils::id::{NodeId, TenantId, TenantTimelineId};
+
+/// The subscription kind to the timeline updates from safekeeper.
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
+pub struct SubscriptionKey {
+    /// Generic cluster prefix, allowing to use the same etcd instance by multiple logic groups.
+    pub cluster_prefix: String,
+    /// The subscription kind.
+    pub kind: SubscriptionKind,
+}
+
+/// All currently possible key kinds of a etcd broker subscription.
+/// Etcd works so, that every key that starts with the subbscription key given is considered matching and
+/// returned as part of the subscrption.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
+pub enum SubscriptionKind {
+    /// Get every update in etcd.
+    All,
+    /// Get etcd updates for any timeiline of a certain tenant, affected by any operation from any node kind.
+    TenantTimelines(TenantId),
+    /// Get etcd updates for a certain timeline of a tenant, affected by any operation from any node kind.
+    Timeline(TenantTimelineId),
+    /// Get etcd timeline updates, specific to a certain node kind.
+    Node(TenantTimelineId, NodeKind),
+    /// Get etcd timeline updates for a certain operation on specific nodes.
+    Operation(TenantTimelineId, NodeKind, OperationKind),
+}
+
+/// All kinds of nodes, able to write into etcd.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
+pub enum NodeKind {
+    Safekeeper,
+    Pageserver,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
+pub enum OperationKind {
+    Safekeeper(SkOperationKind),
+}
+
+/// Current operations, running inside the safekeeper node.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
+pub enum SkOperationKind {
+    TimelineInfo,
+    WalBackup,
+}
+
+static SUBSCRIPTION_FULL_KEY_REGEX: Lazy<Regex> = Lazy::new(|| {
+    Regex::new("/([[:xdigit:]]+)/([[:xdigit:]]+)/([^/]+)/([^/]+)/([[:digit:]]+)$")
+        .expect("wrong subscription full etcd key regex")
+});
+
+/// Full key, received from etcd during any of the component's work.
+/// No other etcd keys are considered during system's work.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
+pub struct SubscriptionFullKey {
+    pub id: TenantTimelineId,
+    pub node_kind: NodeKind,
+    pub operation: OperationKind,
+    pub node_id: NodeId,
+}
+
+impl SubscriptionKey {
+    /// Subscribes for all etcd updates.
+    pub fn all(cluster_prefix: String) -> Self {
+        SubscriptionKey {
+            cluster_prefix,
+            kind: SubscriptionKind::All,
+        }
+    }
+
+    /// Subscribes to a given timeline info updates from safekeepers.
+    pub fn sk_timeline_info(cluster_prefix: String, timeline: TenantTimelineId) -> Self {
+        Self {
+            cluster_prefix,
+            kind: SubscriptionKind::Operation(
+                timeline,
+                NodeKind::Safekeeper,
+                OperationKind::Safekeeper(SkOperationKind::TimelineInfo),
+            ),
+        }
+    }
+
+    /// Subscribes to all timeine updates during specific operations, running on the corresponding nodes.
+    pub fn operation(
+        cluster_prefix: String,
+        timeline: TenantTimelineId,
+        node_kind: NodeKind,
+        operation: OperationKind,
+    ) -> Self {
+        Self {
+            cluster_prefix,
+            kind: SubscriptionKind::Operation(timeline, node_kind, operation),
+        }
+    }
+
+    /// Etcd key to use for watching a certain timeline updates from safekeepers.
+    pub fn watch_key(&self) -> String {
+        let cluster_prefix = &self.cluster_prefix;
+        match self.kind {
+            SubscriptionKind::All => cluster_prefix.to_string(),
+            SubscriptionKind::TenantTimelines(tenant_id) => {
+                format!("{cluster_prefix}/{tenant_id}")
+            }
+            SubscriptionKind::Timeline(id) => {
+                format!("{cluster_prefix}/{id}")
+            }
+            SubscriptionKind::Node(id, node_kind) => {
+                format!("{cluster_prefix}/{id}/{node_kind}")
+            }
+            SubscriptionKind::Operation(id, node_kind, operation_kind) => {
+                format!("{cluster_prefix}/{id}/{node_kind}/{operation_kind}")
+            }
+        }
+    }
+}
+
+impl Display for OperationKind {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            OperationKind::Safekeeper(o) => o.fmt(f),
+        }
+    }
+}
+
+impl FromStr for OperationKind {
+    type Err = String;
+
+    fn from_str(operation_kind_str: &str) -> Result<Self, Self::Err> {
+        match operation_kind_str {
+            "timeline_info" => Ok(OperationKind::Safekeeper(SkOperationKind::TimelineInfo)),
+            "wal_backup" => Ok(OperationKind::Safekeeper(SkOperationKind::WalBackup)),
+            _ => Err(format!("Unknown operation kind: {operation_kind_str}")),
+        }
+    }
+}
+
+impl Display for SubscriptionFullKey {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        let Self {
+            id,
+            node_kind,
+            operation,
+            node_id,
+        } = self;
+        write!(f, "{id}/{node_kind}/{operation}/{node_id}")
+    }
+}
+
+impl FromStr for SubscriptionFullKey {
+    type Err = String;
+
+    fn from_str(subscription_kind_str: &str) -> Result<Self, Self::Err> {
+        let key_captures = match SUBSCRIPTION_FULL_KEY_REGEX.captures(subscription_kind_str) {
+            Some(captures) => captures,
+            None => {
+                return Err(format!(
+                    "Subscription kind str does not match a subscription full key regex {}",
+                    SUBSCRIPTION_FULL_KEY_REGEX.as_str()
+                ));
+            }
+        };
+
+        Ok(Self {
+            id: TenantTimelineId::new(
+                parse_capture(&key_captures, 1)?,
+                parse_capture(&key_captures, 2)?,
+            ),
+            node_kind: parse_capture(&key_captures, 3)?,
+            operation: parse_capture(&key_captures, 4)?,
+            node_id: NodeId(parse_capture(&key_captures, 5)?),
+        })
+    }
+}
+
+fn parse_capture<T>(caps: &Captures, index: usize) -> Result<T, String>
+where
+    T: FromStr,
+    <T as FromStr>::Err: Display,
+{
+    let capture_match = caps
+        .get(index)
+        .ok_or_else(|| format!("Failed to get capture match at index {index}"))?
+        .as_str();
+    capture_match.parse().map_err(|e| {
+        format!(
+            "Failed to parse {} from {capture_match}: {e}",
+            std::any::type_name::<T>()
+        )
+    })
+}
+
+impl Display for NodeKind {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::Safekeeper => write!(f, "safekeeper"),
+            Self::Pageserver => write!(f, "pageserver"),
+        }
+    }
+}
+
+impl FromStr for NodeKind {
+    type Err = String;
+
+    fn from_str(node_kind_str: &str) -> Result<Self, Self::Err> {
+        match node_kind_str {
+            "safekeeper" => Ok(Self::Safekeeper),
+            "pageserver" => Ok(Self::Pageserver),
+            _ => Err(format!("Invalid node kind: {node_kind_str}")),
+        }
+    }
+}
+
+impl Display for SkOperationKind {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::TimelineInfo => write!(f, "timeline_info"),
+            Self::WalBackup => write!(f, "wal_backup"),
+        }
+    }
+}
+
+impl FromStr for SkOperationKind {
+    type Err = String;
+
+    fn from_str(operation_str: &str) -> Result<Self, Self::Err> {
+        match operation_str {
+            "timeline_info" => Ok(Self::TimelineInfo),
+            "wal_backup" => Ok(Self::WalBackup),
+            _ => Err(format!("Invalid operation: {operation_str}")),
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use utils::id::TimelineId;
+
+    use super::*;
+
+    #[test]
+    fn full_cluster_key_parsing() {
+        let prefix = "neon";
+        let node_kind = NodeKind::Safekeeper;
+        let operation_kind = OperationKind::Safekeeper(SkOperationKind::WalBackup);
+        let tenant_id = TenantId::generate();
+        let timeline_id = TimelineId::generate();
+        let id = TenantTimelineId::new(tenant_id, timeline_id);
+        let node_id = NodeId(1);
+
+        let timeline_subscription_keys = [
+            SubscriptionKey {
+                cluster_prefix: prefix.to_string(),
+                kind: SubscriptionKind::All,
+            },
+            SubscriptionKey {
+                cluster_prefix: prefix.to_string(),
+                kind: SubscriptionKind::TenantTimelines(tenant_id),
+            },
+            SubscriptionKey {
+                cluster_prefix: prefix.to_string(),
+                kind: SubscriptionKind::Timeline(id),
+            },
+            SubscriptionKey {
+                cluster_prefix: prefix.to_string(),
+                kind: SubscriptionKind::Node(id, node_kind),
+            },
+            SubscriptionKey {
+                cluster_prefix: prefix.to_string(),
+                kind: SubscriptionKind::Operation(id, node_kind, operation_kind),
+            },
+        ];
+
+        let full_key_string = format!(
+            "{}/{node_id}",
+            timeline_subscription_keys.last().unwrap().watch_key()
+        );
+
+        for key in timeline_subscription_keys {
+            assert!(full_key_string.starts_with(&key.watch_key()), "Full key '{full_key_string}' should start with any of the keys, keys, but {key:?} did not match");
+        }
+
+        let full_key = SubscriptionFullKey::from_str(&full_key_string).unwrap_or_else(|e| {
+            panic!("Failed to parse {full_key_string} as a subscription full key: {e}")
+        });
+
+        assert_eq!(
+            full_key,
+            SubscriptionFullKey {
+                id,
+                node_kind,
+                operation: operation_kind,
+                node_id
+            }
+        )
+    }
+}

libs/etcd_broker/src/subscription_value.rs

@@ -0,0 +1,38 @@
+//! Module for the values to put into etcd.
+
+use serde::{Deserialize, Serialize};
+use serde_with::{serde_as, DisplayFromStr};
+use utils::lsn::Lsn;
+
+/// Data about safekeeper's timeline. Fields made optional for easy migrations.
+#[serde_as]
+#[derive(Debug, Clone, Deserialize, Serialize)]
+pub struct SkTimelineInfo {
+    /// Term of the last entry.
+    pub last_log_term: Option<u64>,
+    /// LSN of the last record.
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    #[serde(default)]
+    pub flush_lsn: Option<Lsn>,
+    /// Up to which LSN safekeeper regards its WAL as committed.
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    #[serde(default)]
+    pub commit_lsn: Option<Lsn>,
+    /// LSN up to which safekeeper has backed WAL.
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    #[serde(default)]
+    pub backup_lsn: Option<Lsn>,
+    /// LSN of last checkpoint uploaded by pageserver.
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    #[serde(default)]
+    pub remote_consistent_lsn: Option<Lsn>,
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    #[serde(default)]
+    pub peer_horizon_lsn: Option<Lsn>,
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    #[serde(default)]
+    pub local_start_lsn: Option<Lsn>,
+    /// A connection string to use for WAL receiving.
+    #[serde(default)]
+    pub safekeeper_connstr: Option<String>,
+}

libs/pageserver_api/Cargo.toml

@@ -9,7 +9,6 @@ serde_with = "2.0"
 const_format = "0.2.21"
 anyhow = { version = "1.0", features = ["backtrace"] }
 bytes = "1.0.1"
-byteorder = "1.4.3"
 
 utils = { path = "../utils" }
 postgres_ffi = { path = "../postgres_ffi" }

libs/pageserver_api/src/models.rs

@@ -1,6 +1,5 @@
 use std::num::NonZeroU64;
 
-use byteorder::{BigEndian, ReadBytesExt};
 use serde::{Deserialize, Serialize};
 use serde_with::{serde_as, DisplayFromStr};
 use utils::{
@@ -10,42 +9,24 @@ use utils::{
 
 use crate::reltag::RelTag;
 use anyhow::bail;
-use bytes::{BufMut, Bytes, BytesMut};
+use bytes::{Buf, BufMut, Bytes, BytesMut};
 
 /// A state of a tenant in pageserver's memory.
 #[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 pub enum TenantState {
-    // This tenant is being loaded from local disk
-    Loading,
-    // This tenant is being downloaded from cloud storage.
-    Attaching,
-    /// Tenant is fully operational
-    Active,
-    /// A tenant is recognized by pageserver, but it is being detached or the
-    /// system is being shut down.
-    Stopping,
-    /// A tenant is recognized by the pageserver, but can no longer be used for
-    /// any operations, because it failed to be activated.
+    /// Tenant is fully operational, its background jobs might be running or not.
+    Active { background_jobs_running: bool },
+    /// A tenant is recognized by pageserver, but not yet ready to operate:
+    /// e.g. not present locally and being downloaded or being read into memory from the file system.
+    Paused,
+    /// A tenant is recognized by the pageserver, but no longer used for any operations, as failed to get activated.
     Broken,
 }
 
-impl TenantState {
-    pub fn has_in_progress_downloads(&self) -> bool {
-        match self {
-            Self::Loading => true,
-            Self::Attaching => true,
-            Self::Active => false,
-            Self::Stopping => false,
-            Self::Broken => false,
-        }
-    }
-}
-
 /// A state of a timeline in pageserver's memory.
 #[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 pub enum TimelineState {
-    /// Timeline is fully operational. If the containing Tenant is Active, the timeline's
-    /// background jobs are running otherwise they will be launched when the tenant is activated.
+    /// Timeline is fully operational, its background jobs are running.
     Active,
     /// A timeline is recognized by pageserver, but not yet ready to operate.
     /// The status indicates, that the timeline could eventually go back to Active automatically:
@@ -53,9 +34,8 @@ pub enum TimelineState {
     Suspended,
     /// A timeline is recognized by pageserver, but not yet ready to operate and not allowed to
     /// automatically become Active after certain events: only a management call can change this status.
-    Stopping,
-    /// A timeline is recognized by the pageserver, but can no longer be used for
-    /// any operations, because it failed to be activated.
+    Paused,
+    /// A timeline is recognized by the pageserver, but no longer used for any operations, as failed to get activated.
     Broken,
 }
 
@@ -92,7 +72,6 @@ pub struct TenantCreateRequest {
     pub walreceiver_connect_timeout: Option<String>,
     pub lagging_wal_timeout: Option<String>,
     pub max_lsn_wal_lag: Option<NonZeroU64>,
-    pub trace_read_requests: Option<bool>,
 }
 
 #[serde_as]
@@ -132,7 +111,6 @@ pub struct TenantConfigRequest {
     pub walreceiver_connect_timeout: Option<String>,
     pub lagging_wal_timeout: Option<String>,
     pub max_lsn_wal_lag: Option<NonZeroU64>,
-    pub trace_read_requests: Option<bool>,
 }
 
 impl TenantConfigRequest {
@@ -151,7 +129,6 @@ impl TenantConfigRequest {
             walreceiver_connect_timeout: None,
             lagging_wal_timeout: None,
             max_lsn_wal_lag: None,
-            trace_read_requests: None,
         }
     }
 }
@@ -187,8 +164,6 @@ pub struct TimelineInfo {
     pub latest_gc_cutoff_lsn: Lsn,
     #[serde_as(as = "DisplayFromStr")]
     pub disk_consistent_lsn: Lsn,
-    #[serde_as(as = "DisplayFromStr")]
-    pub remote_consistent_lsn: Lsn,
     pub current_logical_size: Option<u64>, // is None when timeline is Unloaded
     pub current_physical_size: Option<u64>, // is None when timeline is Unloaded
     pub current_logical_size_non_incremental: Option<u64>,
@@ -201,6 +176,10 @@ pub struct TimelineInfo {
     pub last_received_msg_ts: Option<u128>,
     pub pg_version: u32,
 
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    pub remote_consistent_lsn: Option<Lsn>,
+    pub awaits_download: bool,
+
     pub state: TimelineState,
 
     // Some of the above fields are duplicated in 'local' and 'remote', for backwards-
@@ -246,7 +225,6 @@ pub struct TimelineGcRequest {
 }
 
 // Wrapped in libpq CopyData
-#[derive(PartialEq, Eq)]
 pub enum PagestreamFeMessage {
     Exists(PagestreamExistsRequest),
     Nblocks(PagestreamNblocksRequest),
@@ -263,21 +241,21 @@ pub enum PagestreamBeMessage {
     DbSize(PagestreamDbSizeResponse),
 }
 
-#[derive(Debug, PartialEq, Eq)]
+#[derive(Debug)]
 pub struct PagestreamExistsRequest {
     pub latest: bool,
     pub lsn: Lsn,
     pub rel: RelTag,
 }
 
-#[derive(Debug, PartialEq, Eq)]
+#[derive(Debug)]
 pub struct PagestreamNblocksRequest {
     pub latest: bool,
     pub lsn: Lsn,
     pub rel: RelTag,
 }
 
-#[derive(Debug, PartialEq, Eq)]
+#[derive(Debug)]
 pub struct PagestreamGetPageRequest {
     pub latest: bool,
     pub lsn: Lsn,
@@ -285,7 +263,7 @@ pub struct PagestreamGetPageRequest {
     pub blkno: u32,
 }
 
-#[derive(Debug, PartialEq, Eq)]
+#[derive(Debug)]
 pub struct PagestreamDbSizeRequest {
     pub latest: bool,
     pub lsn: Lsn,
@@ -318,98 +296,52 @@ pub struct PagestreamDbSizeResponse {
 }
 
 impl PagestreamFeMessage {
-    pub fn serialize(&self) -> Bytes {
-        let mut bytes = BytesMut::new();
-
-        match self {
-            Self::Exists(req) => {
-                bytes.put_u8(0);
-                bytes.put_u8(if req.latest { 1 } else { 0 });
-                bytes.put_u64(req.lsn.0);
-                bytes.put_u32(req.rel.spcnode);
-                bytes.put_u32(req.rel.dbnode);
-                bytes.put_u32(req.rel.relnode);
-                bytes.put_u8(req.rel.forknum);
-            }
-
-            Self::Nblocks(req) => {
-                bytes.put_u8(1);
-                bytes.put_u8(if req.latest { 1 } else { 0 });
-                bytes.put_u64(req.lsn.0);
-                bytes.put_u32(req.rel.spcnode);
-                bytes.put_u32(req.rel.dbnode);
-                bytes.put_u32(req.rel.relnode);
-                bytes.put_u8(req.rel.forknum);
-            }
-
-            Self::GetPage(req) => {
-                bytes.put_u8(2);
-                bytes.put_u8(if req.latest { 1 } else { 0 });
-                bytes.put_u64(req.lsn.0);
-                bytes.put_u32(req.rel.spcnode);
-                bytes.put_u32(req.rel.dbnode);
-                bytes.put_u32(req.rel.relnode);
-                bytes.put_u8(req.rel.forknum);
-                bytes.put_u32(req.blkno);
-            }
-
-            Self::DbSize(req) => {
-                bytes.put_u8(3);
-                bytes.put_u8(if req.latest { 1 } else { 0 });
-                bytes.put_u64(req.lsn.0);
-                bytes.put_u32(req.dbnode);
-            }
-        }
-
-        bytes.into()
-    }
-
-    pub fn parse<R: std::io::Read>(body: &mut R) -> anyhow::Result<PagestreamFeMessage> {
+    pub fn parse(mut body: Bytes) -> anyhow::Result<PagestreamFeMessage> {
         // TODO these gets can fail
 
         // these correspond to the NeonMessageTag enum in pagestore_client.h
         //
         // TODO: consider using protobuf or serde bincode for less error prone
         // serialization.
-        let msg_tag = body.read_u8()?;
+        let msg_tag = body.get_u8();
         match msg_tag {
             0 => Ok(PagestreamFeMessage::Exists(PagestreamExistsRequest {
-                latest: body.read_u8()? != 0,
-                lsn: Lsn::from(body.read_u64::<BigEndian>()?),
+                latest: body.get_u8() != 0,
+                lsn: Lsn::from(body.get_u64()),
                 rel: RelTag {
-                    spcnode: body.read_u32::<BigEndian>()?,
-                    dbnode: body.read_u32::<BigEndian>()?,
-                    relnode: body.read_u32::<BigEndian>()?,
-                    forknum: body.read_u8()?,
+                    spcnode: body.get_u32(),
+                    dbnode: body.get_u32(),
+                    relnode: body.get_u32(),
+                    forknum: body.get_u8(),
                 },
             })),
             1 => Ok(PagestreamFeMessage::Nblocks(PagestreamNblocksRequest {
-                latest: body.read_u8()? != 0,
-                lsn: Lsn::from(body.read_u64::<BigEndian>()?),
+                latest: body.get_u8() != 0,
+                lsn: Lsn::from(body.get_u64()),
                 rel: RelTag {
-                    spcnode: body.read_u32::<BigEndian>()?,
-                    dbnode: body.read_u32::<BigEndian>()?,
-                    relnode: body.read_u32::<BigEndian>()?,
-                    forknum: body.read_u8()?,
+                    spcnode: body.get_u32(),
+                    dbnode: body.get_u32(),
+                    relnode: body.get_u32(),
+                    forknum: body.get_u8(),
                 },
             })),
             2 => Ok(PagestreamFeMessage::GetPage(PagestreamGetPageRequest {
-                latest: body.read_u8()? != 0,
-                lsn: Lsn::from(body.read_u64::<BigEndian>()?),
+                latest: body.get_u8() != 0,
+                lsn: Lsn::from(body.get_u64()),
                 rel: RelTag {
-                    spcnode: body.read_u32::<BigEndian>()?,
-                    dbnode: body.read_u32::<BigEndian>()?,
-                    relnode: body.read_u32::<BigEndian>()?,
-                    forknum: body.read_u8()?,
+                    spcnode: body.get_u32(),
+                    dbnode: body.get_u32(),
+                    relnode: body.get_u32(),
+                    forknum: body.get_u8(),
                 },
-                blkno: body.read_u32::<BigEndian>()?,
+                blkno: body.get_u32(),
             })),
             3 => Ok(PagestreamFeMessage::DbSize(PagestreamDbSizeRequest {
-                latest: body.read_u8()? != 0,
-                lsn: Lsn::from(body.read_u64::<BigEndian>()?),
-                dbnode: body.read_u32::<BigEndian>()?,
+                latest: body.get_u8() != 0,
+                lsn: Lsn::from(body.get_u64()),
+                dbnode: body.get_u32(),
             })),
-            _ => bail!("unknown smgr message tag: {:?}", msg_tag),
+            _ => bail!("unknown smgr message tag: {},'{:?}'", msg_tag, body),
         }
     }
 }
@@ -448,58 +380,3 @@ impl PagestreamBeMessage {
         bytes.into()
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use bytes::Buf;
-
-    use super::*;
-
-    #[test]
-    fn test_pagestream() {
-        // Test serialization/deserialization of PagestreamFeMessage
-        let messages = vec![
-            PagestreamFeMessage::Exists(PagestreamExistsRequest {
-                latest: true,
-                lsn: Lsn(4),
-                rel: RelTag {
-                    forknum: 1,
-                    spcnode: 2,
-                    dbnode: 3,
-                    relnode: 4,
-                },
-            }),
-            PagestreamFeMessage::Nblocks(PagestreamNblocksRequest {
-                latest: false,
-                lsn: Lsn(4),
-                rel: RelTag {
-                    forknum: 1,
-                    spcnode: 2,
-                    dbnode: 3,
-                    relnode: 4,
-                },
-            }),
-            PagestreamFeMessage::GetPage(PagestreamGetPageRequest {
-                latest: true,
-                lsn: Lsn(4),
-                rel: RelTag {
-                    forknum: 1,
-                    spcnode: 2,
-                    dbnode: 3,
-                    relnode: 4,
-                },
-                blkno: 7,
-            }),
-            PagestreamFeMessage::DbSize(PagestreamDbSizeRequest {
-                latest: true,
-                lsn: Lsn(4),
-                dbnode: 7,
-            }),
-        ];
-        for msg in messages {
-            let bytes = msg.serialize();
-            let reconstructed = PagestreamFeMessage::parse(&mut bytes.reader()).unwrap();
-            assert!(msg == reconstructed);
-        }
-    }
-}

libs/postgres_connection/Cargo.toml

@@ -1,17 +0,0 @@
-[package]
-name = "postgres_connection"
-version = "0.1.0"
-edition = "2021"
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-anyhow = "1.0"
-itertools = "0.10.3"
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
-url = "2.2.2"
-workspace_hack = { version = "0.1", path = "../../workspace_hack" }
-
-[dev-dependencies]
-once_cell = "1.13.0"

libs/postgres_connection/src/lib.rs

@@ -1,253 +0,0 @@
-use anyhow::{bail, Context};
-use itertools::Itertools;
-use std::borrow::Cow;
-use std::fmt;
-use url::Host;
-
-/// Parses a string of format either `host:port` or `host` into a corresponding pair.
-/// The `host` part should be a correct `url::Host`, while `port` (if present) should be
-/// a valid decimal u16 of digits only.
-pub fn parse_host_port<S: AsRef<str>>(host_port: S) -> Result<(Host, Option<u16>), anyhow::Error> {
-    let (host, port) = match host_port.as_ref().rsplit_once(':') {
-        Some((host, port)) => (
-            host,
-            // +80 is a valid u16, but not a valid port
-            if port.chars().all(|c| c.is_ascii_digit()) {
-                Some(port.parse::<u16>().context("Unable to parse port")?)
-            } else {
-                bail!("Port contains a non-ascii-digit")
-            },
-        ),
-        None => (host_port.as_ref(), None), // No colons, no port specified
-    };
-    let host = Host::parse(host).context("Unable to parse host")?;
-    Ok((host, port))
-}
-
-#[cfg(test)]
-mod tests_parse_host_port {
-    use crate::parse_host_port;
-    use url::Host;
-
-    #[test]
-    fn test_normal() {
-        let (host, port) = parse_host_port("hello:123").unwrap();
-        assert_eq!(host, Host::Domain("hello".to_owned()));
-        assert_eq!(port, Some(123));
-    }
-
-    #[test]
-    fn test_no_port() {
-        let (host, port) = parse_host_port("hello").unwrap();
-        assert_eq!(host, Host::Domain("hello".to_owned()));
-        assert_eq!(port, None);
-    }
-
-    #[test]
-    fn test_ipv6() {
-        let (host, port) = parse_host_port("[::1]:123").unwrap();
-        assert_eq!(host, Host::<String>::Ipv6(std::net::Ipv6Addr::LOCALHOST));
-        assert_eq!(port, Some(123));
-    }
-
-    #[test]
-    fn test_invalid_host() {
-        assert!(parse_host_port("hello world").is_err());
-    }
-
-    #[test]
-    fn test_invalid_port() {
-        assert!(parse_host_port("hello:+80").is_err());
-    }
-}
-
-#[derive(Clone)]
-pub struct PgConnectionConfig {
-    host: Host,
-    port: u16,
-    password: Option<String>,
-    options: Vec<String>,
-}
-
-/// A simplified PostgreSQL connection configuration. Supports only a subset of possible
-/// settings for simplicity. A password getter or `to_connection_string` methods are not
-/// added by design to avoid accidentally leaking password through logging, command line
-/// arguments to a child process, or likewise.
-impl PgConnectionConfig {
-    pub fn new_host_port(host: Host, port: u16) -> Self {
-        PgConnectionConfig {
-            host,
-            port,
-            password: None,
-            options: vec![],
-        }
-    }
-
-    pub fn host(&self) -> &Host {
-        &self.host
-    }
-
-    pub fn port(&self) -> u16 {
-        self.port
-    }
-
-    pub fn set_host(mut self, h: Host) -> Self {
-        self.host = h;
-        self
-    }
-
-    pub fn set_port(mut self, p: u16) -> Self {
-        self.port = p;
-        self
-    }
-
-    pub fn set_password(mut self, s: Option<String>) -> Self {
-        self.password = s;
-        self
-    }
-
-    pub fn extend_options<I: IntoIterator<Item = S>, S: Into<String>>(mut self, i: I) -> Self {
-        self.options.extend(i.into_iter().map(|s| s.into()));
-        self
-    }
-
-    /// Return a `<host>:<port>` string.
-    pub fn raw_address(&self) -> String {
-        format!("{}:{}", self.host(), self.port())
-    }
-
-    /// Build a client library-specific connection configuration.
-    /// Used for testing and when we need to add some obscure configuration
-    /// elements at the last moment.
-    pub fn to_tokio_postgres_config(&self) -> tokio_postgres::Config {
-        // Use `tokio_postgres::Config` instead of `postgres::Config` because
-        // the former supports more options to fiddle with later.
-        let mut config = tokio_postgres::Config::new();
-        config.host(&self.host().to_string()).port(self.port);
-        if let Some(password) = &self.password {
-            config.password(password);
-        }
-        if !self.options.is_empty() {
-            // These options are command-line options and should be escaped before being passed
-            // as an 'options' connection string parameter, see
-            // https://www.postgresql.org/docs/15/libpq-connect.html#LIBPQ-CONNECT-OPTIONS
-            //
-            // They will be space-separated, so each space inside an option should be escaped,
-            // and all backslashes should be escaped before that. Although we don't expect options
-            // with spaces at the moment, they're supported by PostgreSQL. Hence we support them
-            // in this typesafe interface.
-            //
-            // We use `Cow` to avoid allocations in the best case (no escaping). A fully imperative
-            // solution would require 1-2 allocations in the worst case as well, but it's harder to
-            // implement and this function is hardly a bottleneck. The function is only called around
-            // establishing a new connection.
-            #[allow(unstable_name_collisions)]
-            config.options(
-                &self
-                    .options
-                    .iter()
-                    .map(|s| {
-                        if s.contains(['\\', ' ']) {
-                            Cow::Owned(s.replace('\\', "\\\\").replace(' ', "\\ "))
-                        } else {
-                            Cow::Borrowed(s.as_str())
-                        }
-                    })
-                    .intersperse(Cow::Borrowed(" ")) // TODO: use impl from std once it's stabilized
-                    .collect::<String>(),
-            );
-        }
-        config
-    }
-
-    /// Connect using postgres protocol with TLS disabled.
-    pub fn connect_no_tls(&self) -> Result<postgres::Client, postgres::Error> {
-        postgres::Config::from(self.to_tokio_postgres_config()).connect(postgres::NoTls)
-    }
-}
-
-impl fmt::Debug for PgConnectionConfig {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        // We want `password: Some(REDACTED-STRING)`, not `password: Some("REDACTED-STRING")`
-        // so even if the password is `REDACTED-STRING` (quite unlikely) there is no confusion.
-        // Hence `format_args!()`, it returns a "safe" string which is not escaped by `Debug`.
-        f.debug_struct("PgConnectionConfig")
-            .field("host", &self.host)
-            .field("port", &self.port)
-            .field(
-                "password",
-                &self
-                    .password
-                    .as_ref()
-                    .map(|_| format_args!("REDACTED-STRING")),
-            )
-            .finish()
-    }
-}
-
-#[cfg(test)]
-mod tests_pg_connection_config {
-    use crate::PgConnectionConfig;
-    use once_cell::sync::Lazy;
-    use url::Host;
-
-    static STUB_HOST: Lazy<Host> = Lazy::new(|| Host::Domain("stub.host.example".to_owned()));
-
-    #[test]
-    fn test_no_password() {
-        let cfg = PgConnectionConfig::new_host_port(STUB_HOST.clone(), 123);
-        assert_eq!(cfg.host(), &*STUB_HOST);
-        assert_eq!(cfg.port(), 123);
-        assert_eq!(cfg.raw_address(), "stub.host.example:123");
-        assert_eq!(
-            format!("{:?}", cfg),
-            "PgConnectionConfig { host: Domain(\"stub.host.example\"), port: 123, password: None }"
-        );
-    }
-
-    #[test]
-    fn test_ipv6() {
-        // May be a special case because hostname contains a colon.
-        let cfg = PgConnectionConfig::new_host_port(Host::parse("[::1]").unwrap(), 123);
-        assert_eq!(
-            cfg.host(),
-            &Host::<String>::Ipv6(std::net::Ipv6Addr::LOCALHOST)
-        );
-        assert_eq!(cfg.port(), 123);
-        assert_eq!(cfg.raw_address(), "[::1]:123");
-        assert_eq!(
-            format!("{:?}", cfg),
-            "PgConnectionConfig { host: Ipv6(::1), port: 123, password: None }"
-        );
-    }
-
-    #[test]
-    fn test_with_password() {
-        let cfg = PgConnectionConfig::new_host_port(STUB_HOST.clone(), 123)
-            .set_password(Some("password".to_owned()));
-        assert_eq!(cfg.host(), &*STUB_HOST);
-        assert_eq!(cfg.port(), 123);
-        assert_eq!(cfg.raw_address(), "stub.host.example:123");
-        assert_eq!(
-            format!("{:?}", cfg),
-            "PgConnectionConfig { host: Domain(\"stub.host.example\"), port: 123, password: Some(REDACTED-STRING) }"
-        );
-    }
-
-    #[test]
-    fn test_with_options() {
-        let cfg = PgConnectionConfig::new_host_port(STUB_HOST.clone(), 123).extend_options([
-            "hello",
-            "world",
-            "with space",
-            "and \\ backslashes",
-        ]);
-        assert_eq!(cfg.host(), &*STUB_HOST);
-        assert_eq!(cfg.port(), 123);
-        assert_eq!(cfg.raw_address(), "stub.host.example:123");
-        assert_eq!(
-            cfg.to_tokio_postgres_config().get_options(),
-            Some("hello world with\\ space and\\ \\\\\\ backslashes")
-        );
-    }
-}

libs/postgres_ffi/src/lib.rs

@@ -163,27 +163,6 @@ pub fn page_set_lsn(pg: &mut [u8], lsn: Lsn) {
     pg[4..8].copy_from_slice(&(lsn.0 as u32).to_le_bytes());
 }
 
-// This is port of function with the same name from freespace.c.
-// The only difference is that it does not have "level" parameter because XLogRecordPageWithFreeSpace
-// always call it with level=FSM_BOTTOM_LEVEL
-pub fn fsm_logical_to_physical(addr: BlockNumber) -> BlockNumber {
-    let mut leafno = addr;
-    const FSM_TREE_DEPTH: u32 = if pg_constants::SLOTS_PER_FSM_PAGE >= 1626 {
-        3
-    } else {
-        4
-    };
-
-    /* Count upper level nodes required to address the leaf page */
-    let mut pages: BlockNumber = 0;
-    for _l in 0..FSM_TREE_DEPTH {
-        pages += leafno + 1;
-        leafno /= pg_constants::SLOTS_PER_FSM_PAGE;
-    }
-    /* Turn the page count into 0-based block number */
-    pages - 1
-}
-
 pub mod waldecoder {
 
     use crate::{v14, v15};

libs/postgres_ffi/src/pg_constants.rs

@@ -197,16 +197,6 @@ pub const XLOG_CHECKPOINT_SHUTDOWN: u8 = 0x00;
 pub const XLOG_CHECKPOINT_ONLINE: u8 = 0x10;
 pub const XLP_LONG_HEADER: u16 = 0x0002;
 
-/* From fsm_internals.h */
-const FSM_NODES_PER_PAGE: usize = BLCKSZ as usize - SIZEOF_PAGE_HEADER_DATA - 4;
-const FSM_NON_LEAF_NODES_PER_PAGE: usize = BLCKSZ as usize / 2 - 1;
-const FSM_LEAF_NODES_PER_PAGE: usize = FSM_NODES_PER_PAGE - FSM_NON_LEAF_NODES_PER_PAGE;
-pub const SLOTS_PER_FSM_PAGE: u32 = FSM_LEAF_NODES_PER_PAGE as u32;
-
-/* From visibilitymap.c */
-pub const VM_HEAPBLOCKS_PER_PAGE: u32 =
-    (BLCKSZ as usize - SIZEOF_PAGE_HEADER_DATA) as u32 * (8 / 2); // MAPSIZE * (BITS_PER_BYTE / BITS_PER_HEAPBLOCK)
-
 // List of subdirectories inside pgdata.
 // Copied from src/bin/initdb/initdb.c
 pub const PGDATA_SUBDIRS: [&str; 22] = [

libs/postgres_ffi/wal_craft/src/lib.rs

@@ -1,6 +1,7 @@
 use anyhow::*;
 use core::time::Duration;
 use log::*;
+use once_cell::sync::Lazy;
 use postgres::types::PgLsn;
 use postgres::Client;
 use postgres_ffi::{WAL_SEGMENT_SIZE, XLOG_BLCKSZ};
@@ -25,13 +26,15 @@ pub struct PostgresServer {
     client_config: postgres::Config,
 }
 
-pub static REQUIRED_POSTGRES_CONFIG: [&str; 4] = [
-    "wal_keep_size=50MB",            // Ensure old WAL is not removed
-    "shared_preload_libraries=neon", // can only be loaded at startup
-    // Disable background processes as much as possible
-    "wal_writer_delay=10s",
-    "autovacuum=off",
-];
+pub static REQUIRED_POSTGRES_CONFIG: Lazy<Vec<&'static str>> = Lazy::new(|| {
+    vec![
+        "wal_keep_size=50MB",            // Ensure old WAL is not removed
+        "shared_preload_libraries=neon", // can only be loaded at startup
+        // Disable background processes as much as possible
+        "wal_writer_delay=10s",
+        "autovacuum=off",
+    ]
+});
 
 impl Conf {
     pub fn pg_distrib_dir(&self) -> anyhow::Result<PathBuf> {

libs/pq_proto/Cargo.toml

@@ -1,16 +0,0 @@
-[package]
-name = "pq_proto"
-version = "0.1.0"
-edition = "2021"
-
-[dependencies]
-anyhow = "1.0"
-bytes = "1.0.1"
-pin-project-lite = "0.2.7"
-postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
-rand = "0.8.3"
-serde = { version = "1.0", features = ["derive"] }
-tokio = { version = "1.17", features = ["macros"] }
-tracing = "0.1"
-
-workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/remote_storage/Cargo.toml

@@ -9,11 +9,8 @@ async-trait = "0.1"
 metrics = { version = "0.1", path = "../metrics" }
 utils = { version = "0.1", path = "../utils" }
 once_cell = "1.13.0"
-aws-smithy-http = "0.51.0"
-aws-types = "0.51.0"
-aws-config = { version = "0.51.0", default-features = false, features=["rustls"] }
-aws-sdk-s3 = "0.21.0"
-hyper = { version = "0.14", features = ["stream"] }
+rusoto_core = "0.48"
+rusoto_s3 = "0.48"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1"
 tokio = { version = "1.17", features = ["sync", "macros", "fs", "io-util"] }

libs/remote_storage/src/lib.rs

@@ -10,7 +10,7 @@ mod s3_bucket;
 
 use std::{
     collections::HashMap,
-    fmt::Debug,
+    fmt::{Debug, Display},
     num::{NonZeroU32, NonZeroUsize},
     ops::Deref,
     path::{Path, PathBuf},
@@ -41,27 +41,44 @@ pub const DEFAULT_REMOTE_STORAGE_S3_CONCURRENCY_LIMIT: usize = 100;
 
 const REMOTE_STORAGE_PREFIX_SEPARATOR: char = '/';
 
-/// Path on the remote storage, relative to some inner prefix.
-/// The prefix is an implementation detail, that allows representing local paths
-/// as the remote ones, stripping the local storage prefix away.
-#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash)]
-pub struct RemotePath(PathBuf);
-
-impl RemotePath {
-    pub fn new(relative_path: &Path) -> anyhow::Result<Self> {
-        anyhow::ensure!(
-            relative_path.is_relative(),
-            "Path {relative_path:?} is not relative"
-        );
-        Ok(Self(relative_path.to_path_buf()))
-    }
-
-    pub fn with_base(&self, base_path: &Path) -> PathBuf {
-        base_path.join(&self.0)
-    }
+#[derive(Clone, PartialEq, Eq)]
+pub struct RemoteObjectId(String);
 
+///
+/// A key that refers to an object in remote storage. It works much like a Path,
+/// but it's a separate datatype so that you don't accidentally mix local paths
+/// and remote keys.
+///
+impl RemoteObjectId {
+    // Needed to retrieve last component for RemoteObjectId.
+    // In other words a file name
+    /// Turn a/b/c or a/b/c/ into c
     pub fn object_name(&self) -> Option<&str> {
-        self.0.file_name().and_then(|os_str| os_str.to_str())
+        // corner case, char::to_string is not const, thats why this is more verbose than it needs to be
+        // see https://github.com/rust-lang/rust/issues/88674
+        if self.0.len() == 1 && self.0.chars().next().unwrap() == REMOTE_STORAGE_PREFIX_SEPARATOR {
+            return None;
+        }
+
+        if self.0.ends_with(REMOTE_STORAGE_PREFIX_SEPARATOR) {
+            self.0.rsplit(REMOTE_STORAGE_PREFIX_SEPARATOR).nth(1)
+        } else {
+            self.0
+                .rsplit_once(REMOTE_STORAGE_PREFIX_SEPARATOR)
+                .map(|(_, last)| last)
+        }
+    }
+}
+
+impl Debug for RemoteObjectId {
+    fn fmt(&self, fmt: &mut std::fmt::Formatter<'_>) -> Result<(), std::fmt::Error> {
+        Debug::fmt(&self.0, fmt)
+    }
+}
+
+impl Display for RemoteObjectId {
+    fn fmt(&self, fmt: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        Display::fmt(&self.0, fmt)
     }
 }
 
@@ -70,40 +87,49 @@ impl RemotePath {
 /// providing basic CRUD operations for storage files.
 #[async_trait::async_trait]
 pub trait RemoteStorage: Send + Sync + 'static {
+    /// Attempts to derive the storage path out of the local path, if the latter is correct.
+    fn remote_object_id(&self, local_path: &Path) -> anyhow::Result<RemoteObjectId>;
+
+    /// Gets the download path of the given storage file.
+    fn local_path(&self, remote_object_id: &RemoteObjectId) -> anyhow::Result<PathBuf>;
+
     /// Lists all items the storage has right now.
-    async fn list(&self) -> anyhow::Result<Vec<RemotePath>>;
+    async fn list(&self) -> anyhow::Result<Vec<RemoteObjectId>>;
 
     /// Lists all top level subdirectories for a given prefix
     /// Note: here we assume that if the prefix is passed it was obtained via remote_object_id
     /// which already takes into account any kind of global prefix (prefix_in_bucket for S3 or storage_root for LocalFS)
     /// so this method doesnt need to.
-    async fn list_prefixes(&self, prefix: Option<&RemotePath>) -> anyhow::Result<Vec<RemotePath>>;
+    async fn list_prefixes(
+        &self,
+        prefix: Option<&RemoteObjectId>,
+    ) -> anyhow::Result<Vec<RemoteObjectId>>;
 
     /// Streams the local file contents into remote into the remote storage entry.
     async fn upload(
         &self,
-        data: Box<(dyn io::AsyncRead + Unpin + Send + Sync + 'static)>,
+        from: Box<(dyn io::AsyncRead + Unpin + Send + Sync + 'static)>,
         // S3 PUT request requires the content length to be specified,
         // otherwise it starts to fail with the concurrent connection count increasing.
-        data_size_bytes: usize,
-        to: &RemotePath,
+        from_size_bytes: usize,
+        to: &RemoteObjectId,
         metadata: Option<StorageMetadata>,
     ) -> anyhow::Result<()>;
 
     /// Streams the remote storage entry contents into the buffered writer given, returns the filled writer.
     /// Returns the metadata, if any was stored with the file previously.
-    async fn download(&self, from: &RemotePath) -> Result<Download, DownloadError>;
+    async fn download(&self, from: &RemoteObjectId) -> Result<Download, DownloadError>;
 
     /// Streams a given byte range of the remote storage entry contents into the buffered writer given, returns the filled writer.
     /// Returns the metadata, if any was stored with the file previously.
     async fn download_byte_range(
         &self,
-        from: &RemotePath,
+        from: &RemoteObjectId,
         start_inclusive: u64,
         end_exclusive: Option<u64>,
     ) -> Result<Download, DownloadError>;
 
-    async fn delete(&self, path: &RemotePath) -> anyhow::Result<()>;
+    async fn delete(&self, path: &RemoteObjectId) -> anyhow::Result<()>;
 
     /// Downcast to LocalFs implementation. For tests.
     fn as_local(&self) -> Option<&LocalFs> {
@@ -142,7 +168,7 @@ impl std::fmt::Display for DownloadError {
                 write!(f, "Failed to download a remote file due to user input: {e}")
             }
             DownloadError::NotFound => write!(f, "No file found for the remote object id given"),
-            DownloadError::Other(e) => write!(f, "Failed to download a remote file: {e:?}"),
+            DownloadError::Other(e) => write!(f, "Failed to download a remote file: {e}"),
         }
     }
 }
@@ -152,35 +178,34 @@ impl std::error::Error for DownloadError {}
 /// Every storage, currently supported.
 /// Serves as a simple way to pass around the [`RemoteStorage`] without dealing with generics.
 #[derive(Clone)]
-pub enum GenericRemoteStorage {
-    LocalFs(LocalFs),
-    AwsS3(Arc<S3Bucket>),
-}
+pub struct GenericRemoteStorage(Arc<dyn RemoteStorage>);
 
 impl Deref for GenericRemoteStorage {
     type Target = dyn RemoteStorage;
 
     fn deref(&self) -> &Self::Target {
-        match self {
-            GenericRemoteStorage::LocalFs(local_fs) => local_fs,
-            GenericRemoteStorage::AwsS3(s3_bucket) => s3_bucket.as_ref(),
-        }
+        self.0.as_ref()
     }
 }
 
 impl GenericRemoteStorage {
+    pub fn new(storage: impl RemoteStorage) -> Self {
+        Self(Arc::new(storage))
+    }
+
     pub fn from_config(
+        working_directory: PathBuf,
         storage_config: &RemoteStorageConfig,
     ) -> anyhow::Result<GenericRemoteStorage> {
         Ok(match &storage_config.storage {
             RemoteStorageKind::LocalFs(root) => {
                 info!("Using fs root '{}' as a remote storage", root.display());
-                GenericRemoteStorage::LocalFs(LocalFs::new(root.clone())?)
+                GenericRemoteStorage::new(LocalFs::new(root.clone(), working_directory)?)
             }
             RemoteStorageKind::AwsS3(s3_config) => {
                 info!("Using s3 bucket '{}' in region '{}' as a remote storage, prefix in bucket: '{:?}', bucket endpoint: '{:?}'",
                       s3_config.bucket_name, s3_config.bucket_region, s3_config.prefix_in_bucket, s3_config.endpoint);
-                GenericRemoteStorage::AwsS3(Arc::new(S3Bucket::new(s3_config)?))
+                GenericRemoteStorage::new(S3Bucket::new(s3_config, working_directory)?)
             }
         })
     }
@@ -194,12 +219,23 @@ impl GenericRemoteStorage {
         &self,
         from: Box<dyn tokio::io::AsyncRead + Unpin + Send + Sync + 'static>,
         from_size_bytes: usize,
-        to: &RemotePath,
+        from_path: &Path,
     ) -> anyhow::Result<()> {
-        self.upload(from, from_size_bytes, to, None)
+        let target_storage_path = self.remote_object_id(from_path).with_context(|| {
+            format!(
+                "Failed to get the storage path for source local path '{}'",
+                from_path.display()
+            )
+        })?;
+
+        self.upload(from, from_size_bytes, &target_storage_path, None)
             .await
             .with_context(|| {
-                format!("Failed to upload data of length {from_size_bytes} to storage path {to:?}")
+                format!(
+                    "Failed to upload from '{}' to storage path '{:?}'",
+                    from_path.display(),
+                    target_storage_path
+                )
             })
     }
 
@@ -208,11 +244,24 @@ impl GenericRemoteStorage {
     pub async fn download_storage_object(
         &self,
         byte_range: Option<(u64, Option<u64>)>,
-        from: &RemotePath,
+        to_path: &Path,
     ) -> Result<Download, DownloadError> {
+        let remote_object_path = self
+            .remote_object_id(to_path)
+            .with_context(|| {
+                format!(
+                    "Failed to get the storage path for target local path '{}'",
+                    to_path.display()
+                )
+            })
+            .map_err(DownloadError::BadInput)?;
+
         match byte_range {
-            Some((start, end)) => self.download_byte_range(from, start, end).await,
-            None => self.download(from).await,
+            Some((start, end)) => {
+                self.download_byte_range(&remote_object_path, start, end)
+                    .await
+            }
+            None => self.download(&remote_object_path).await,
         }
     }
 }
@@ -222,6 +271,23 @@ impl GenericRemoteStorage {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct StorageMetadata(HashMap<String, String>);
 
+fn strip_path_prefix<'a>(prefix: &'a Path, path: &'a Path) -> anyhow::Result<&'a Path> {
+    if prefix == path {
+        anyhow::bail!(
+            "Prefix and the path are equal, cannot strip: '{}'",
+            prefix.display()
+        )
+    } else {
+        path.strip_prefix(prefix).with_context(|| {
+            format!(
+                "Path '{}' is not prefixed with '{}'",
+                path.display(),
+                prefix.display(),
+            )
+        })
+    }
+}
+
 /// External backup storage configuration, enough for creating a client for that storage.
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct RemoteStorageConfig {
@@ -365,24 +431,21 @@ mod tests {
     use super::*;
 
     #[test]
-    fn test_object_name() {
-        let k = RemotePath::new(Path::new("a/b/c")).unwrap();
+    fn object_name() {
+        let k = RemoteObjectId("a/b/c".to_owned());
         assert_eq!(k.object_name(), Some("c"));
 
-        let k = RemotePath::new(Path::new("a/b/c/")).unwrap();
+        let k = RemoteObjectId("a/b/c/".to_owned());
         assert_eq!(k.object_name(), Some("c"));
 
-        let k = RemotePath::new(Path::new("a/")).unwrap();
+        let k = RemoteObjectId("a/".to_owned());
         assert_eq!(k.object_name(), Some("a"));
 
         // XXX is it impossible to have an empty key?
-        let k = RemotePath::new(Path::new("")).unwrap();
+        let k = RemoteObjectId("".to_owned());
+        assert_eq!(k.object_name(), None);
+
+        let k = RemoteObjectId("/".to_owned());
         assert_eq!(k.object_name(), None);
     }
-
-    #[test]
-    fn rempte_path_cannot_be_created_from_absolute_ones() {
-        let err = RemotePath::new(Path::new("/")).expect_err("Should fail on absolute paths");
-        assert_eq!(err.to_string(), "Path \"/\" is not relative");
-    }
 }

libs/remote_storage/src/local_fs.rs

@@ -5,7 +5,6 @@
 //! volume is mounted to the local FS.
 
 use std::{
-    borrow::Cow,
     future::Future,
     path::{Path, PathBuf},
     pin::Pin,
@@ -19,33 +18,60 @@ use tokio::{
 use tracing::*;
 use utils::crashsafe::path_with_suffix_extension;
 
-use crate::{Download, DownloadError, RemotePath};
+use crate::{Download, DownloadError, RemoteObjectId};
 
-use super::{RemoteStorage, StorageMetadata};
+use super::{strip_path_prefix, RemoteStorage, StorageMetadata};
 
 const LOCAL_FS_TEMP_FILE_SUFFIX: &str = "___temp";
 
-#[derive(Debug, Clone)]
+/// Convert a Path in the remote storage into a RemoteObjectId
+fn remote_object_id_from_path(path: &Path) -> anyhow::Result<RemoteObjectId> {
+    Ok(RemoteObjectId(
+        path.to_str()
+            .ok_or_else(|| anyhow::anyhow!("unexpected characters found in path"))?
+            .to_string(),
+    ))
+}
+
 pub struct LocalFs {
+    working_directory: PathBuf,
     storage_root: PathBuf,
 }
 
 impl LocalFs {
     /// Attempts to create local FS storage, along with its root directory.
-    /// Storage root will be created (if does not exist) and transformed into an absolute path (if passed as relative).
-    pub fn new(mut storage_root: PathBuf) -> anyhow::Result<Self> {
-        if !storage_root.exists() {
-            std::fs::create_dir_all(&storage_root).with_context(|| {
-                format!("Failed to create all directories in the given root path {storage_root:?}")
-            })?;
-        }
-        if !storage_root.is_absolute() {
-            storage_root = storage_root.canonicalize().with_context(|| {
-                format!("Failed to represent path {storage_root:?} as an absolute path")
+    pub fn new(root: PathBuf, working_directory: PathBuf) -> anyhow::Result<Self> {
+        if !root.exists() {
+            std::fs::create_dir_all(&root).with_context(|| {
+                format!(
+                    "Failed to create all directories in the given root path '{}'",
+                    root.display(),
+                )
             })?;
         }
+        Ok(Self {
+            working_directory,
+            storage_root: root,
+        })
+    }
 
-        Ok(Self { storage_root })
+    ///
+    /// Get the absolute path in the local filesystem to given remote object.
+    ///
+    /// This is public so that it can be used in tests. Should not be used elsewhere.
+    ///
+    pub fn resolve_in_storage(&self, remote_object_id: &RemoteObjectId) -> anyhow::Result<PathBuf> {
+        let path = PathBuf::from(&remote_object_id.0);
+        if path.is_relative() {
+            Ok(self.storage_root.join(path))
+        } else if path.starts_with(&self.storage_root) {
+            Ok(path)
+        } else {
+            bail!(
+                "Path '{}' does not belong to the current storage",
+                path.display()
+            )
+        }
     }
 
     async fn read_storage_metadata(
@@ -77,48 +103,45 @@ impl LocalFs {
 
 #[async_trait::async_trait]
 impl RemoteStorage for LocalFs {
-    async fn list(&self) -> anyhow::Result<Vec<RemotePath>> {
-        Ok(get_all_files(&self.storage_root, true)
-            .await?
-            .into_iter()
-            .map(|path| {
-                path.strip_prefix(&self.storage_root)
-                    .context("Failed to strip storage root prefix")
-                    .and_then(RemotePath::new)
-                    .expect(
-                        "We list files for storage root, hence should be able to remote the prefix",
-                    )
-            })
-            .collect())
+    /// Convert a "local" path into a "remote path"
+    fn remote_object_id(&self, local_path: &Path) -> anyhow::Result<RemoteObjectId> {
+        let path = self.storage_root.join(
+            strip_path_prefix(&self.working_directory, local_path)
+                .context("local path does not belong to this storage")?,
+        );
+        remote_object_id_from_path(&path)
     }
 
-    async fn list_prefixes(&self, prefix: Option<&RemotePath>) -> anyhow::Result<Vec<RemotePath>> {
+    fn local_path(&self, remote_object_id: &RemoteObjectId) -> anyhow::Result<PathBuf> {
+        let storage_path = PathBuf::from(&remote_object_id.0);
+        let relative_path = strip_path_prefix(&self.storage_root, &storage_path)
+            .context("local path does not belong to this storage")?;
+        Ok(self.working_directory.join(relative_path))
+    }
+
+    async fn list(&self) -> anyhow::Result<Vec<RemoteObjectId>> {
+        get_all_files(&self.storage_root, true).await
+    }
+
+    async fn list_prefixes(
+        &self,
+        prefix: Option<&RemoteObjectId>,
+    ) -> anyhow::Result<Vec<RemoteObjectId>> {
         let path = match prefix {
-            Some(prefix) => Cow::Owned(prefix.with_base(&self.storage_root)),
-            None => Cow::Borrowed(&self.storage_root),
+            Some(prefix) => Path::new(&prefix.0),
+            None => &self.storage_root,
         };
-        Ok(get_all_files(path.as_ref(), false)
-            .await?
-            .into_iter()
-            .map(|path| {
-                path.strip_prefix(&self.storage_root)
-                    .context("Failed to strip preifix")
-                    .and_then(RemotePath::new)
-                    .expect(
-                        "We list files for storage root, hence should be able to remote the prefix",
-                    )
-            })
-            .collect())
+        get_all_files(path, false).await
     }
 
     async fn upload(
         &self,
-        data: Box<(dyn io::AsyncRead + Unpin + Send + Sync + 'static)>,
-        data_size_bytes: usize,
-        to: &RemotePath,
+        from: Box<(dyn io::AsyncRead + Unpin + Send + Sync + 'static)>,
+        from_size_bytes: usize,
+        to: &RemoteObjectId,
         metadata: Option<StorageMetadata>,
     ) -> anyhow::Result<()> {
-        let target_file_path = to.with_base(&self.storage_root);
+        let target_file_path = self.resolve_in_storage(to)?;
         create_target_directory(&target_file_path).await?;
         // We need this dance with sort of durable rename (without fsyncs)
         // to prevent partial uploads. This was really hit when pageserver shutdown
@@ -139,8 +162,8 @@ impl RemoteStorage for LocalFs {
                 })?,
         );
 
-        let from_size_bytes = data_size_bytes as u64;
-        let mut buffer_to_read = data.take(from_size_bytes);
+        let from_size_bytes = from_size_bytes as u64;
+        let mut buffer_to_read = from.take(from_size_bytes);
 
         let bytes_read = io::copy(&mut buffer_to_read, &mut destination)
             .await
@@ -197,22 +220,27 @@ impl RemoteStorage for LocalFs {
         Ok(())
     }
 
-    async fn download(&self, from: &RemotePath) -> Result<Download, DownloadError> {
-        let target_path = from.with_base(&self.storage_root);
-        if file_exists(&target_path).map_err(DownloadError::BadInput)? {
+    async fn download(&self, from: &RemoteObjectId) -> Result<Download, DownloadError> {
+        let file_path = self
+            .resolve_in_storage(from)
+            .map_err(DownloadError::BadInput)?;
+        if file_exists(&file_path).map_err(DownloadError::BadInput)? {
             let source = io::BufReader::new(
                 fs::OpenOptions::new()
                     .read(true)
-                    .open(&target_path)
+                    .open(&file_path)
                     .await
                     .with_context(|| {
-                        format!("Failed to open source file {target_path:?} to use in the download")
+                        format!(
+                            "Failed to open source file '{}' to use in the download",
+                            file_path.display()
+                        )
                     })
                     .map_err(DownloadError::Other)?,
             );
 
             let metadata = self
-                .read_storage_metadata(&target_path)
+                .read_storage_metadata(&file_path)
                 .await
                 .map_err(DownloadError::Other)?;
             Ok(Download {
@@ -226,7 +254,7 @@ impl RemoteStorage for LocalFs {
 
     async fn download_byte_range(
         &self,
-        from: &RemotePath,
+        from: &RemoteObjectId,
         start_inclusive: u64,
         end_exclusive: Option<u64>,
     ) -> Result<Download, DownloadError> {
@@ -238,15 +266,20 @@ impl RemoteStorage for LocalFs {
                 return Err(DownloadError::Other(anyhow::anyhow!("Invalid range, start ({start_inclusive}) and end_exclusive ({end_exclusive:?}) difference is zero bytes")));
             }
         }
-        let target_path = from.with_base(&self.storage_root);
-        if file_exists(&target_path).map_err(DownloadError::BadInput)? {
+        let file_path = self
+            .resolve_in_storage(from)
+            .map_err(DownloadError::BadInput)?;
+        if file_exists(&file_path).map_err(DownloadError::BadInput)? {
             let mut source = io::BufReader::new(
                 fs::OpenOptions::new()
                     .read(true)
-                    .open(&target_path)
+                    .open(&file_path)
                     .await
                     .with_context(|| {
-                        format!("Failed to open source file {target_path:?} to use in the download")
+                        format!(
+                            "Failed to open source file '{}' to use in the download",
+                            file_path.display()
+                        )
                     })
                     .map_err(DownloadError::Other)?,
             );
@@ -256,7 +289,7 @@ impl RemoteStorage for LocalFs {
                 .context("Failed to seek to the range start in a local storage file")
                 .map_err(DownloadError::Other)?;
             let metadata = self
-                .read_storage_metadata(&target_path)
+                .read_storage_metadata(&file_path)
                 .await
                 .map_err(DownloadError::Other)?;
 
@@ -275,12 +308,15 @@ impl RemoteStorage for LocalFs {
         }
     }
 
-    async fn delete(&self, path: &RemotePath) -> anyhow::Result<()> {
-        let file_path = path.with_base(&self.storage_root);
+    async fn delete(&self, path: &RemoteObjectId) -> anyhow::Result<()> {
+        let file_path = self.resolve_in_storage(path)?;
         if file_path.exists() && file_path.is_file() {
             Ok(fs::remove_file(file_path).await?)
         } else {
-            bail!("File {file_path:?} either does not exist or is not a file")
+            bail!(
+                "File '{}' either does not exist or is not a file",
+                file_path.display()
+            )
         }
     }
 
@@ -296,7 +332,7 @@ fn storage_metadata_path(original_path: &Path) -> PathBuf {
 fn get_all_files<'a, P>(
     directory_path: P,
     recursive: bool,
-) -> Pin<Box<dyn Future<Output = anyhow::Result<Vec<PathBuf>>> + Send + Sync + 'a>>
+) -> Pin<Box<dyn Future<Output = anyhow::Result<Vec<RemoteObjectId>>> + Send + Sync + 'a>>
 where
     P: AsRef<Path> + Send + Sync + 'a,
 {
@@ -310,20 +346,20 @@ where
                     let file_type = dir_entry.file_type().await?;
                     let entry_path = dir_entry.path();
                     if file_type.is_symlink() {
-                        debug!("{entry_path:?} us a symlink, skipping")
+                        debug!("{:?} us a symlink, skipping", entry_path)
                     } else if file_type.is_dir() {
                         if recursive {
                             paths.extend(get_all_files(&entry_path, true).await?.into_iter())
                         } else {
-                            paths.push(entry_path)
+                            paths.push(remote_object_id_from_path(&dir_entry.path())?)
                         }
                     } else {
-                        paths.push(entry_path);
+                        paths.push(remote_object_id_from_path(&dir_entry.path())?);
                     }
                 }
                 Ok(paths)
             } else {
-                bail!("Path {directory_path:?} is not a directory")
+                bail!("Path '{}' is not a directory", directory_path.display())
             }
         } else {
             Ok(Vec::new())
@@ -358,6 +394,173 @@ fn file_exists(file_path: &Path) -> anyhow::Result<bool> {
     }
 }
 
+#[cfg(test)]
+mod pure_tests {
+    use tempfile::tempdir;
+
+    use super::*;
+
+    #[test]
+    fn storage_path_positive() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+
+        let storage_root = PathBuf::from("somewhere").join("else");
+        let storage = LocalFs {
+            working_directory: workdir.clone(),
+            storage_root: storage_root.clone(),
+        };
+
+        let local_path = workdir
+            .join("timelines")
+            .join("some_timeline")
+            .join("file_name");
+        let expected_path = storage_root.join(local_path.strip_prefix(&workdir)?);
+
+        let actual_path = PathBuf::from(
+            storage
+                .remote_object_id(&local_path)
+                .expect("Matching path should map to storage path normally")
+                .0,
+        );
+        assert_eq!(
+            expected_path,
+            actual_path,
+            "File paths from workdir should be stored in local fs storage with the same path they have relative to the workdir"
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn storage_path_negatives() -> anyhow::Result<()> {
+        #[track_caller]
+        fn storage_path_error(storage: &LocalFs, mismatching_path: &Path) -> String {
+            match storage.remote_object_id(mismatching_path) {
+                Ok(wrong_path) => panic!(
+                    "Expected path '{}' to error, but got storage path: {:?}",
+                    mismatching_path.display(),
+                    wrong_path,
+                ),
+                Err(e) => format!("{:?}", e),
+            }
+        }
+
+        let workdir = tempdir()?.path().to_owned();
+        let storage_root = PathBuf::from("somewhere").join("else");
+        let storage = LocalFs {
+            working_directory: workdir.clone(),
+            storage_root,
+        };
+
+        let error_string = storage_path_error(&storage, &workdir);
+        assert!(error_string.contains("does not belong to this storage"));
+        assert!(error_string.contains(workdir.to_str().unwrap()));
+
+        let mismatching_path_str = "/something/else";
+        let error_message = storage_path_error(&storage, Path::new(mismatching_path_str));
+        assert!(
+            error_message.contains(mismatching_path_str),
+            "Error should mention wrong path"
+        );
+        assert!(
+            error_message.contains(workdir.to_str().unwrap()),
+            "Error should mention server workdir"
+        );
+        assert!(error_message.contains("does not belong to this storage"));
+
+        Ok(())
+    }
+
+    #[test]
+    fn local_path_positive() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+        let storage_root = PathBuf::from("somewhere").join("else");
+        let storage = LocalFs {
+            working_directory: workdir.clone(),
+            storage_root: storage_root.clone(),
+        };
+
+        let name = "not a metadata";
+        let local_path = workdir.join("timelines").join("some_timeline").join(name);
+        assert_eq!(
+            local_path,
+            storage
+                .local_path(&remote_object_id_from_path(
+                    &storage_root.join(local_path.strip_prefix(&workdir)?)
+                )?)
+                .expect("For a valid input, valid local path should be parsed"),
+            "Should be able to parse metadata out of the correctly named remote delta file"
+        );
+
+        let local_metadata_path = workdir
+            .join("timelines")
+            .join("some_timeline")
+            .join("metadata");
+        let remote_metadata_path = storage.remote_object_id(&local_metadata_path)?;
+        assert_eq!(
+            local_metadata_path,
+            storage
+                .local_path(&remote_metadata_path)
+                .expect("For a valid input, valid local path should be parsed"),
+            "Should be able to parse metadata out of the correctly named remote metadata file"
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn local_path_negatives() -> anyhow::Result<()> {
+        #[track_caller]
+        fn local_path_error(storage: &LocalFs, storage_path: &RemoteObjectId) -> String {
+            match storage.local_path(storage_path) {
+                Ok(wrong_path) => panic!(
+                    "Expected local path input {:?} to cause an error, but got file path: {:?}",
+                    storage_path, wrong_path,
+                ),
+                Err(e) => format!("{:?}", e),
+            }
+        }
+
+        let storage_root = PathBuf::from("somewhere").join("else");
+        let storage = LocalFs {
+            working_directory: tempdir()?.path().to_owned(),
+            storage_root,
+        };
+
+        let totally_wrong_path = "wrong_wrong_wrong";
+        let error_message =
+            local_path_error(&storage, &RemoteObjectId(totally_wrong_path.to_string()));
+        assert!(error_message.contains(totally_wrong_path));
+
+        Ok(())
+    }
+
+    #[test]
+    fn download_destination_matches_original_path() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+        let original_path = workdir
+            .join("timelines")
+            .join("some_timeline")
+            .join("some name");
+
+        let storage_root = PathBuf::from("somewhere").join("else");
+        let dummy_storage = LocalFs {
+            working_directory: workdir,
+            storage_root,
+        };
+
+        let storage_path = dummy_storage.remote_object_id(&original_path)?;
+        let download_destination = dummy_storage.local_path(&storage_path)?;
+
+        assert_eq!(
+            original_path, download_destination,
+            "'original path -> storage path -> matching fs path' transformation should produce the same path as the input one for the correct path"
+        );
+
+        Ok(())
+    }
+}
+
 #[cfg(test)]
 mod fs_tests {
     use super::*;
@@ -369,7 +572,7 @@ mod fs_tests {
         storage: &LocalFs,
         #[allow(clippy::ptr_arg)]
         // have to use &PathBuf due to `storage.local_path` parameter requirements
-        remote_storage_path: &RemotePath,
+        remote_storage_path: &RemoteObjectId,
         expected_metadata: Option<&StorageMetadata>,
     ) -> anyhow::Result<String> {
         let mut download = storage
@@ -392,16 +595,41 @@ mod fs_tests {
 
     #[tokio::test]
     async fn upload_file() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
         let storage = create_storage()?;
 
-        let target_path_1 = upload_dummy_file(&storage, "upload_1", None).await?;
+        let (file, size) = create_file_for_upload(
+            &storage.working_directory.join("whatever"),
+            "whatever_contents",
+        )
+        .await?;
+        let target_path = "/somewhere/else";
+        match storage
+            .upload(
+                Box::new(file),
+                size,
+                &RemoteObjectId(target_path.to_string()),
+                None,
+            )
+            .await
+        {
+            Ok(()) => panic!("Should not allow storing files with wrong target path"),
+            Err(e) => {
+                let message = format!("{:?}", e);
+                assert!(message.contains(target_path));
+                assert!(message.contains("does not belong to the current storage"));
+            }
+        }
+        assert!(storage.list().await?.is_empty());
+
+        let target_path_1 = upload_dummy_file(&workdir, &storage, "upload_1", None).await?;
         assert_eq!(
             storage.list().await?,
             vec![target_path_1.clone()],
             "Should list a single file after first upload"
         );
 
-        let target_path_2 = upload_dummy_file(&storage, "upload_2", None).await?;
+        let target_path_2 = upload_dummy_file(&workdir, &storage, "upload_2", None).await?;
         assert_eq!(
             list_files_sorted(&storage).await?,
             vec![target_path_1.clone(), target_path_2.clone()],
@@ -415,7 +643,7 @@ mod fs_tests {
     async fn upload_file_negatives() -> anyhow::Result<()> {
         let storage = create_storage()?;
 
-        let id = RemotePath::new(Path::new("dummy"))?;
+        let id = storage.remote_object_id(&storage.working_directory.join("dummy"))?;
         let content = std::io::Cursor::new(b"12345");
 
         // Check that you get an error if the size parameter doesn't match the actual
@@ -440,14 +668,16 @@ mod fs_tests {
     }
 
     fn create_storage() -> anyhow::Result<LocalFs> {
-        LocalFs::new(tempdir()?.path().to_owned())
+        LocalFs::new(tempdir()?.path().to_owned(), tempdir()?.path().to_owned())
     }
 
     #[tokio::test]
     async fn download_file() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+
         let storage = create_storage()?;
         let upload_name = "upload_1";
-        let upload_target = upload_dummy_file(&storage, upload_name, None).await?;
+        let upload_target = upload_dummy_file(&workdir, &storage, upload_name, None).await?;
 
         let contents = read_and_assert_remote_file_contents(&storage, &upload_target, None).await?;
         assert_eq!(
@@ -457,7 +687,7 @@ mod fs_tests {
         );
 
         let non_existing_path = "somewhere/else";
-        match storage.download(&RemotePath::new(Path::new(non_existing_path))?).await {
+        match storage.download(&RemoteObjectId(non_existing_path.to_string())).await {
             Err(DownloadError::NotFound) => {} // Should get NotFound for non existing keys
             other => panic!("Should get a NotFound error when downloading non-existing storage files, but got: {other:?}"),
         }
@@ -466,9 +696,11 @@ mod fs_tests {
 
     #[tokio::test]
     async fn download_file_range_positive() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+
         let storage = create_storage()?;
         let upload_name = "upload_1";
-        let upload_target = upload_dummy_file(&storage, upload_name, None).await?;
+        let upload_target = upload_dummy_file(&workdir, &storage, upload_name, None).await?;
 
         let full_range_download_contents =
             read_and_assert_remote_file_contents(&storage, &upload_target, None).await?;
@@ -534,9 +766,11 @@ mod fs_tests {
 
     #[tokio::test]
     async fn download_file_range_negative() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+
         let storage = create_storage()?;
         let upload_name = "upload_1";
-        let upload_target = upload_dummy_file(&storage, upload_name, None).await?;
+        let upload_target = upload_dummy_file(&workdir, &storage, upload_name, None).await?;
 
         let start = 1_000_000_000;
         let end = start + 1;
@@ -578,9 +812,11 @@ mod fs_tests {
 
     #[tokio::test]
     async fn delete_file() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+
         let storage = create_storage()?;
         let upload_name = "upload_1";
-        let upload_target = upload_dummy_file(&storage, upload_name, None).await?;
+        let upload_target = upload_dummy_file(&workdir, &storage, upload_name, None).await?;
 
         storage.delete(&upload_target).await?;
         assert!(storage.list().await?.is_empty());
@@ -590,8 +826,7 @@ mod fs_tests {
             Err(e) => {
                 let error_string = e.to_string();
                 assert!(error_string.contains("does not exist"));
-                let expected_path = upload_target.with_base(&storage.storage_root);
-                assert!(error_string.contains(expected_path.to_str().unwrap()));
+                assert!(error_string.contains(&upload_target.0));
             }
         }
         Ok(())
@@ -599,6 +834,8 @@ mod fs_tests {
 
     #[tokio::test]
     async fn file_with_metadata() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+
         let storage = create_storage()?;
         let upload_name = "upload_1";
         let metadata = StorageMetadata(HashMap::from([
@@ -606,7 +843,7 @@ mod fs_tests {
             ("two".to_string(), "2".to_string()),
         ]));
         let upload_target =
-            upload_dummy_file(&storage, upload_name, Some(metadata.clone())).await?;
+            upload_dummy_file(&workdir, &storage, upload_name, Some(metadata.clone())).await?;
 
         let full_range_download_contents =
             read_and_assert_remote_file_contents(&storage, &upload_target, Some(&metadata)).await?;
@@ -646,32 +883,23 @@ mod fs_tests {
     }
 
     async fn upload_dummy_file(
+        workdir: &Path,
         storage: &LocalFs,
         name: &str,
         metadata: Option<StorageMetadata>,
-    ) -> anyhow::Result<RemotePath> {
-        let from_path = storage
-            .storage_root
-            .join("timelines")
-            .join("some_timeline")
-            .join(name);
+    ) -> anyhow::Result<RemoteObjectId> {
+        let timeline_path = workdir.join("timelines").join("some_timeline");
+        let relative_timeline_path = timeline_path.strip_prefix(&workdir)?;
+        let storage_path = storage.storage_root.join(relative_timeline_path).join(name);
+        let remote_object_id = RemoteObjectId(storage_path.to_str().unwrap().to_string());
+
+        let from_path = storage.working_directory.join(name);
         let (file, size) = create_file_for_upload(&from_path, &dummy_contents(name)).await?;
 
-        let relative_path = from_path
-            .strip_prefix(&storage.storage_root)
-            .context("Failed to strip storage root prefix")
-            .and_then(RemotePath::new)
-            .with_context(|| {
-                format!(
-                    "Failed to resolve remote part of path {:?} for base {:?}",
-                    from_path, storage.storage_root
-                )
-            })?;
-
         storage
-            .upload(Box::new(file), size, &relative_path, metadata)
+            .upload(Box::new(file), size, &remote_object_id, metadata)
             .await?;
-        Ok(relative_path)
+        remote_object_id_from_path(&storage_path)
     }
 
     async fn create_file_for_upload(
@@ -696,7 +924,7 @@ mod fs_tests {
         format!("contents for {name}")
     }
 
-    async fn list_files_sorted(storage: &LocalFs) -> anyhow::Result<Vec<RemotePath>> {
+    async fn list_files_sorted(storage: &LocalFs) -> anyhow::Result<Vec<RemoteObjectId>> {
         let mut files = storage.list().await?;
         files.sort_by(|a, b| a.0.cmp(&b.0));
         Ok(files)

libs/remote_storage/src/s3_bucket.rs

@@ -4,34 +4,27 @@
 //! allowing multiple api users to independently work with the same S3 bucket, if
 //! their bucket prefixes are both specified and different.
 
-use std::env::var;
-use std::sync::Arc;
-use std::time::Duration;
+use std::path::{Path, PathBuf};
 
 use anyhow::Context;
-use aws_config::{
-    environment::credentials::EnvironmentVariableCredentialsProvider, imds,
-    imds::credentials::ImdsCredentialsProvider, meta::credentials::provide_credentials_fn,
+use rusoto_core::{
+    credential::{InstanceMetadataProvider, StaticProvider},
+    HttpClient, Region, RusotoError,
 };
-use aws_sdk_s3::{
-    config::Config,
-    error::{GetObjectError, GetObjectErrorKind},
-    types::{ByteStream, SdkError},
-    Client, Endpoint, Region,
+use rusoto_s3::{
+    DeleteObjectRequest, GetObjectError, GetObjectRequest, ListObjectsV2Request, PutObjectRequest,
+    S3Client, StreamingBody, S3,
 };
-use aws_smithy_http::body::SdkBody;
-use aws_types::credentials::{CredentialsError, ProvideCredentials};
-use hyper::Body;
 use tokio::{io, sync::Semaphore};
 use tokio_util::io::ReaderStream;
 use tracing::debug;
 
-use super::StorageMetadata;
 use crate::{
-    Download, DownloadError, RemotePath, RemoteStorage, S3Config, REMOTE_STORAGE_PREFIX_SEPARATOR,
+    strip_path_prefix, Download, DownloadError, RemoteObjectId, RemoteStorage, S3Config,
+    REMOTE_STORAGE_PREFIX_SEPARATOR,
 };
 
-const DEFAULT_IMDS_TIMEOUT: Duration = Duration::from_secs(10);
+use super::StorageMetadata;
 
 pub(super) mod metrics {
     use metrics::{register_int_counter_vec, IntCounterVec};
@@ -98,9 +91,32 @@ pub(super) mod metrics {
     }
 }
 
+fn download_destination(
+    id: &RemoteObjectId,
+    workdir: &Path,
+    prefix_to_strip: Option<&str>,
+) -> PathBuf {
+    let path_without_prefix = match prefix_to_strip {
+        Some(prefix) => id.0.strip_prefix(prefix).unwrap_or_else(|| {
+            panic!(
+                "Could not strip prefix '{}' from S3 object key '{}'",
+                prefix, id.0
+            )
+        }),
+        None => &id.0,
+    };
+
+    workdir.join(
+        path_without_prefix
+            .split(REMOTE_STORAGE_PREFIX_SEPARATOR)
+            .collect::<PathBuf>(),
+    )
+}
+
 /// AWS S3 storage.
 pub struct S3Bucket {
-    client: Client,
+    workdir: PathBuf,
+    client: S3Client,
     bucket_name: String,
     prefix_in_bucket: Option<String>,
     // Every request to S3 can be throttled or cancelled, if a certain number of requests per second is exceeded.
@@ -109,53 +125,50 @@ pub struct S3Bucket {
     concurrency_limiter: Semaphore,
 }
 
-#[derive(Default)]
-struct GetObjectRequest {
-    bucket: String,
-    key: String,
-    range: Option<String>,
-}
 impl S3Bucket {
     /// Creates the S3 storage, errors if incorrect AWS S3 configuration provided.
-    pub fn new(aws_config: &S3Config) -> anyhow::Result<Self> {
+    pub fn new(aws_config: &S3Config, workdir: PathBuf) -> anyhow::Result<Self> {
         debug!(
             "Creating s3 remote storage for S3 bucket {}",
             aws_config.bucket_name
         );
-        let mut config_builder = Config::builder()
-            .region(Region::new(aws_config.bucket_region.clone()))
-            .credentials_provider(provide_credentials_fn(|| async {
-                match var("AWS_ACCESS_KEY_ID").is_ok() && var("AWS_SECRET_ACCESS_KEY").is_ok() {
-                    true => {
-                        EnvironmentVariableCredentialsProvider::new()
-                            .provide_credentials()
-                            .await
-                    }
-                    false => {
-                        let imds_client = imds::Client::builder()
-                            .connect_timeout(DEFAULT_IMDS_TIMEOUT)
-                            .read_timeout(DEFAULT_IMDS_TIMEOUT)
-                            .build()
-                            .await
-                            .map_err(CredentialsError::unhandled)?;
-                        ImdsCredentialsProvider::builder()
-                            .imds_client(imds_client)
-                            .build()
-                            .provide_credentials()
-                            .await
-                    }
-                }
-            }));
+        let region = match aws_config.endpoint.clone() {
+            Some(custom_endpoint) => Region::Custom {
+                name: aws_config.bucket_region.clone(),
+                endpoint: custom_endpoint,
+            },
+            None => aws_config
+                .bucket_region
+                .parse::<Region>()
+                .context("Failed to parse the s3 region from config")?,
+        };
+        let request_dispatcher = HttpClient::new().context("Failed to create S3 http client")?;
 
-        if let Some(custom_endpoint) = aws_config.endpoint.clone() {
-            let endpoint = Endpoint::immutable(
-                custom_endpoint
-                    .parse()
-                    .expect("Failed to parse S3 custom endpoint"),
+        let access_key_id = std::env::var("AWS_ACCESS_KEY_ID").ok();
+        let secret_access_key = std::env::var("AWS_SECRET_ACCESS_KEY").ok();
+        // session token is used when authorizing through sso
+        // which is typically the case when testing locally on developer machine
+        let session_token = std::env::var("AWS_SESSION_TOKEN").ok();
+
+        let client = if access_key_id.is_none() && secret_access_key.is_none() {
+            debug!("Using IAM-based AWS access");
+            S3Client::new_with(request_dispatcher, InstanceMetadataProvider::new(), region)
+        } else {
+            debug!(
+                "Using credentials-based AWS access. Session token is set: {}",
+                session_token.is_some()
             );
-            config_builder.set_endpoint_resolver(Some(Arc::new(endpoint)));
-        }
-        let client = Client::from_conf(config_builder.build());
+            S3Client::new_with(
+                request_dispatcher,
+                StaticProvider::new(
+                    access_key_id.unwrap_or_default(),
+                    secret_access_key.unwrap_or_default(),
+                    session_token,
+                    None,
+                ),
+                region,
+            )
+        };
 
         let prefix_in_bucket = aws_config.prefix_in_bucket.as_deref().map(|prefix| {
             let mut prefix = prefix;
@@ -169,41 +182,16 @@ impl S3Bucket {
             }
             prefix
         });
+
         Ok(Self {
             client,
+            workdir,
             bucket_name: aws_config.bucket_name.clone(),
             prefix_in_bucket,
             concurrency_limiter: Semaphore::new(aws_config.concurrency_limit.get()),
         })
     }
 
-    fn s3_object_to_relative_path(&self, key: &str) -> RemotePath {
-        let relative_path =
-            match key.strip_prefix(self.prefix_in_bucket.as_deref().unwrap_or_default()) {
-                Some(stripped) => stripped,
-                // we rely on AWS to return properly prefixed paths
-                // for requests with a certain prefix
-                None => panic!(
-                    "Key {} does not start with bucket prefix {:?}",
-                    key, self.prefix_in_bucket
-                ),
-            };
-        RemotePath(
-            relative_path
-                .split(REMOTE_STORAGE_PREFIX_SEPARATOR)
-                .collect(),
-        )
-    }
-
-    fn relative_path_to_s3_object(&self, path: &RemotePath) -> String {
-        let mut full_path = self.prefix_in_bucket.clone().unwrap_or_default();
-        for segment in path.0.iter() {
-            full_path.push(REMOTE_STORAGE_PREFIX_SEPARATOR);
-            full_path.push_str(segment.to_str().unwrap_or_default());
-        }
-        full_path
-    }
-
     async fn download_object(&self, request: GetObjectRequest) -> Result<Download, DownloadError> {
         let _guard = self
             .concurrency_limiter
@@ -214,33 +202,20 @@ impl S3Bucket {
 
         metrics::inc_get_object();
 
-        let get_object = self
-            .client
-            .get_object()
-            .bucket(request.bucket)
-            .key(request.key)
-            .set_range(request.range)
-            .send()
-            .await;
-
-        match get_object {
-            Ok(object_output) => {
-                let metadata = object_output.metadata().cloned().map(StorageMetadata);
-                Ok(Download {
-                    metadata,
-                    download_stream: Box::pin(io::BufReader::new(
-                        object_output.body.into_async_read(),
-                    )),
-                })
-            }
-            Err(SdkError::ServiceError {
-                err:
-                    GetObjectError {
-                        kind: GetObjectErrorKind::NoSuchKey(..),
-                        ..
-                    },
-                ..
-            }) => Err(DownloadError::NotFound),
+        match self.client.get_object(request).await {
+            Ok(object_output) => match object_output.body {
+                None => {
+                    metrics::inc_get_object_fail();
+                    Err(DownloadError::Other(anyhow::anyhow!(
+                        "Got no body for the S3 object given"
+                    )))
+                }
+                Some(body) => Ok(Download {
+                    metadata: object_output.metadata.map(StorageMetadata),
+                    download_stream: Box::pin(io::BufReader::new(body.into_async_read())),
+                }),
+            },
+            Err(RusotoError::Service(GetObjectError::NoSuchKey(_))) => Err(DownloadError::NotFound),
             Err(e) => {
                 metrics::inc_get_object_fail();
                 Err(DownloadError::Other(anyhow::anyhow!(
@@ -253,7 +228,25 @@ impl S3Bucket {
 
 #[async_trait::async_trait]
 impl RemoteStorage for S3Bucket {
-    async fn list(&self) -> anyhow::Result<Vec<RemotePath>> {
+    fn remote_object_id(&self, local_path: &Path) -> anyhow::Result<RemoteObjectId> {
+        let relative_path = strip_path_prefix(&self.workdir, local_path)?;
+        let mut key = self.prefix_in_bucket.clone().unwrap_or_default();
+        for segment in relative_path {
+            key.push(REMOTE_STORAGE_PREFIX_SEPARATOR);
+            key.push_str(&segment.to_string_lossy());
+        }
+        Ok(RemoteObjectId(key))
+    }
+
+    fn local_path(&self, storage_path: &RemoteObjectId) -> anyhow::Result<PathBuf> {
+        Ok(download_destination(
+            storage_path,
+            &self.workdir,
+            self.prefix_in_bucket.as_deref(),
+        ))
+    }
+
+    async fn list(&self) -> anyhow::Result<Vec<RemoteObjectId>> {
         let mut document_keys = Vec::new();
 
         let mut continuation_token = None;
@@ -268,11 +261,12 @@ impl RemoteStorage for S3Bucket {
 
             let fetch_response = self
                 .client
-                .list_objects_v2()
-                .bucket(self.bucket_name.clone())
-                .set_prefix(self.prefix_in_bucket.clone())
-                .set_continuation_token(continuation_token)
-                .send()
+                .list_objects_v2(ListObjectsV2Request {
+                    bucket: self.bucket_name.clone(),
+                    prefix: self.prefix_in_bucket.clone(),
+                    continuation_token,
+                    ..ListObjectsV2Request::default()
+                })
                 .await
                 .map_err(|e| {
                     metrics::inc_list_objects_fail();
@@ -283,7 +277,7 @@ impl RemoteStorage for S3Bucket {
                     .contents
                     .unwrap_or_default()
                     .into_iter()
-                    .filter_map(|o| Some(self.s3_object_to_relative_path(o.key()?))),
+                    .filter_map(|o| Some(RemoteObjectId(o.key?))),
             );
 
             match fetch_response.continuation_token {
@@ -297,10 +291,13 @@ impl RemoteStorage for S3Bucket {
 
     /// See the doc for `RemoteStorage::list_prefixes`
     /// Note: it wont include empty "directories"
-    async fn list_prefixes(&self, prefix: Option<&RemotePath>) -> anyhow::Result<Vec<RemotePath>> {
+    async fn list_prefixes(
+        &self,
+        prefix: Option<&RemoteObjectId>,
+    ) -> anyhow::Result<Vec<RemoteObjectId>> {
         // get the passed prefix or if it is not set use prefix_in_bucket value
         let list_prefix = prefix
-            .map(|p| self.relative_path_to_s3_object(p))
+            .map(|p| p.0.clone())
             .or_else(|| self.prefix_in_bucket.clone())
             .map(|mut p| {
                 // required to end with a separator
@@ -325,12 +322,13 @@ impl RemoteStorage for S3Bucket {
 
             let fetch_response = self
                 .client
-                .list_objects_v2()
-                .bucket(self.bucket_name.clone())
-                .set_prefix(list_prefix.clone())
-                .set_continuation_token(continuation_token)
-                .delimiter(REMOTE_STORAGE_PREFIX_SEPARATOR.to_string())
-                .send()
+                .list_objects_v2(ListObjectsV2Request {
+                    bucket: self.bucket_name.clone(),
+                    prefix: list_prefix.clone(),
+                    continuation_token,
+                    delimiter: Some(REMOTE_STORAGE_PREFIX_SEPARATOR.to_string()),
+                    ..ListObjectsV2Request::default()
+                })
                 .await
                 .map_err(|e| {
                     metrics::inc_list_objects_fail();
@@ -342,7 +340,7 @@ impl RemoteStorage for S3Bucket {
                     .common_prefixes
                     .unwrap_or_default()
                     .into_iter()
-                    .filter_map(|o| Some(self.s3_object_to_relative_path(o.prefix()?))),
+                    .filter_map(|o| Some(RemoteObjectId(o.prefix?))),
             );
 
             match fetch_response.continuation_token {
@@ -358,7 +356,7 @@ impl RemoteStorage for S3Bucket {
         &self,
         from: Box<(dyn io::AsyncRead + Unpin + Send + Sync + 'static)>,
         from_size_bytes: usize,
-        to: &RemotePath,
+        to: &RemoteObjectId,
         metadata: Option<StorageMetadata>,
     ) -> anyhow::Result<()> {
         let _guard = self
@@ -368,18 +366,17 @@ impl RemoteStorage for S3Bucket {
             .context("Concurrency limiter semaphore got closed during S3 upload")?;
 
         metrics::inc_put_object();
-
-        let body = Body::wrap_stream(ReaderStream::new(from));
-        let bytes_stream = ByteStream::new(SdkBody::from(body));
-
         self.client
-            .put_object()
-            .bucket(self.bucket_name.clone())
-            .key(self.relative_path_to_s3_object(to))
-            .set_metadata(metadata.map(|m| m.0))
-            .content_length(from_size_bytes.try_into()?)
-            .body(bytes_stream)
-            .send()
+            .put_object(PutObjectRequest {
+                body: Some(StreamingBody::new_with_size(
+                    ReaderStream::new(from),
+                    from_size_bytes,
+                )),
+                bucket: self.bucket_name.clone(),
+                key: to.0.to_owned(),
+                metadata: metadata.map(|m| m.0),
+                ..PutObjectRequest::default()
+            })
             .await
             .map_err(|e| {
                 metrics::inc_put_object_fail();
@@ -388,10 +385,10 @@ impl RemoteStorage for S3Bucket {
         Ok(())
     }
 
-    async fn download(&self, from: &RemotePath) -> Result<Download, DownloadError> {
+    async fn download(&self, from: &RemoteObjectId) -> Result<Download, DownloadError> {
         self.download_object(GetObjectRequest {
             bucket: self.bucket_name.clone(),
-            key: self.relative_path_to_s3_object(from),
+            key: from.0.to_owned(),
             ..GetObjectRequest::default()
         })
         .await
@@ -399,7 +396,7 @@ impl RemoteStorage for S3Bucket {
 
     async fn download_byte_range(
         &self,
-        from: &RemotePath,
+        from: &RemoteObjectId,
         start_inclusive: u64,
         end_exclusive: Option<u64>,
     ) -> Result<Download, DownloadError> {
@@ -407,19 +404,20 @@ impl RemoteStorage for S3Bucket {
         // and needs both ends to be exclusive
         let end_inclusive = end_exclusive.map(|end| end.saturating_sub(1));
         let range = Some(match end_inclusive {
-            Some(end_inclusive) => format!("bytes={start_inclusive}-{end_inclusive}"),
-            None => format!("bytes={start_inclusive}-"),
+            Some(end_inclusive) => format!("bytes={}-{}", start_inclusive, end_inclusive),
+            None => format!("bytes={}-", start_inclusive),
         });
 
         self.download_object(GetObjectRequest {
             bucket: self.bucket_name.clone(),
-            key: self.relative_path_to_s3_object(from),
+            key: from.0.to_owned(),
             range,
+            ..GetObjectRequest::default()
         })
         .await
     }
 
-    async fn delete(&self, path: &RemotePath) -> anyhow::Result<()> {
+    async fn delete(&self, remote_object_id: &RemoteObjectId) -> anyhow::Result<()> {
         let _guard = self
             .concurrency_limiter
             .acquire()
@@ -429,10 +427,11 @@ impl RemoteStorage for S3Bucket {
         metrics::inc_delete_object();
 
         self.client
-            .delete_object()
-            .bucket(self.bucket_name.clone())
-            .key(self.relative_path_to_s3_object(path))
-            .send()
+            .delete_object(DeleteObjectRequest {
+                bucket: self.bucket_name.clone(),
+                key: remote_object_id.0.to_owned(),
+                ..DeleteObjectRequest::default()
+            })
             .await
             .map_err(|e| {
                 metrics::inc_delete_object_fail();
@@ -441,3 +440,181 @@ impl RemoteStorage for S3Bucket {
         Ok(())
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use tempfile::tempdir;
+
+    use super::*;
+
+    #[test]
+    fn test_download_destination() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+        let local_path = workdir.join("one").join("two").join("test_name");
+        let relative_path = local_path.strip_prefix(&workdir)?;
+
+        let key = RemoteObjectId(format!(
+            "{}{}",
+            REMOTE_STORAGE_PREFIX_SEPARATOR,
+            relative_path
+                .iter()
+                .map(|segment| segment.to_str().unwrap())
+                .collect::<Vec<_>>()
+                .join(&REMOTE_STORAGE_PREFIX_SEPARATOR.to_string()),
+        ));
+
+        assert_eq!(
+            local_path,
+            download_destination(&key, &workdir, None),
+            "Download destination should consist of s3 path joined with the workdir prefix"
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn storage_path_positive() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+
+        let segment_1 = "matching";
+        let segment_2 = "file";
+        let local_path = &workdir.join(segment_1).join(segment_2);
+
+        let storage = dummy_storage(workdir);
+
+        let expected_key = RemoteObjectId(format!(
+            "{}{REMOTE_STORAGE_PREFIX_SEPARATOR}{segment_1}{REMOTE_STORAGE_PREFIX_SEPARATOR}{segment_2}",
+            storage.prefix_in_bucket.as_deref().unwrap_or_default(),
+        ));
+
+        let actual_key = storage
+            .remote_object_id(local_path)
+            .expect("Matching path should map to S3 path normally");
+        assert_eq!(
+            expected_key,
+            actual_key,
+            "S3 key from the matching path should contain all segments after the workspace prefix, separated with S3 separator"
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn storage_path_negatives() -> anyhow::Result<()> {
+        #[track_caller]
+        fn storage_path_error(storage: &S3Bucket, mismatching_path: &Path) -> String {
+            match storage.remote_object_id(mismatching_path) {
+                Ok(wrong_key) => panic!(
+                    "Expected path '{}' to error, but got S3 key: {:?}",
+                    mismatching_path.display(),
+                    wrong_key,
+                ),
+                Err(e) => e.to_string(),
+            }
+        }
+
+        let workdir = tempdir()?.path().to_owned();
+        let storage = dummy_storage(workdir.clone());
+
+        let error_message = storage_path_error(&storage, &workdir);
+        assert!(
+            error_message.contains("Prefix and the path are equal"),
+            "Message '{}' does not contain the required string",
+            error_message
+        );
+
+        let mismatching_path = PathBuf::from("somewhere").join("else");
+        let error_message = storage_path_error(&storage, &mismatching_path);
+        assert!(
+            error_message.contains(mismatching_path.to_str().unwrap()),
+            "Error should mention wrong path"
+        );
+        assert!(
+            error_message.contains(workdir.to_str().unwrap()),
+            "Error should mention server workdir"
+        );
+        assert!(
+            error_message.contains("is not prefixed with"),
+            "Message '{}' does not contain a required string",
+            error_message
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn local_path_positive() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+        let storage = dummy_storage(workdir.clone());
+        let timeline_dir = workdir.join("timelines").join("test_timeline");
+        let relative_timeline_path = timeline_dir.strip_prefix(&workdir)?;
+
+        let s3_key = create_s3_key(
+            &relative_timeline_path.join("not a metadata"),
+            storage.prefix_in_bucket.as_deref(),
+        );
+        assert_eq!(
+            download_destination(&s3_key, &workdir, storage.prefix_in_bucket.as_deref()),
+            storage
+                .local_path(&s3_key)
+                .expect("For a valid input, valid S3 info should be parsed"),
+            "Should be able to parse metadata out of the correctly named remote delta file"
+        );
+
+        let s3_key = create_s3_key(
+            &relative_timeline_path.join("metadata"),
+            storage.prefix_in_bucket.as_deref(),
+        );
+        assert_eq!(
+            download_destination(&s3_key, &workdir, storage.prefix_in_bucket.as_deref()),
+            storage
+                .local_path(&s3_key)
+                .expect("For a valid input, valid S3 info should be parsed"),
+            "Should be able to parse metadata out of the correctly named remote metadata file"
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn download_destination_matches_original_path() -> anyhow::Result<()> {
+        let workdir = tempdir()?.path().to_owned();
+        let original_path = workdir
+            .join("timelines")
+            .join("some_timeline")
+            .join("some name");
+
+        let dummy_storage = dummy_storage(workdir);
+
+        let key = dummy_storage.remote_object_id(&original_path)?;
+        let download_destination = dummy_storage.local_path(&key)?;
+
+        assert_eq!(
+            original_path, download_destination,
+            "'original path -> storage key -> matching fs path' transformation should produce the same path as the input one for the correct path"
+        );
+
+        Ok(())
+    }
+
+    fn dummy_storage(workdir: PathBuf) -> S3Bucket {
+        S3Bucket {
+            workdir,
+            client: S3Client::new("us-east-1".parse().unwrap()),
+            bucket_name: "dummy-bucket".to_string(),
+            prefix_in_bucket: Some("dummy_prefix/".to_string()),
+            concurrency_limiter: Semaphore::new(1),
+        }
+    }
+
+    fn create_s3_key(relative_file_path: &Path, prefix: Option<&str>) -> RemoteObjectId {
+        RemoteObjectId(relative_file_path.iter().fold(
+            prefix.unwrap_or_default().to_string(),
+            |mut path_string, segment| {
+                path_string.push(REMOTE_STORAGE_PREFIX_SEPARATOR);
+                path_string.push_str(segment.to_str().unwrap());
+                path_string
+            },
+        ))
+    }
+}

libs/safekeeper_api/src/models.rs

@@ -22,40 +22,3 @@ pub struct TimelineCreateRequest {
     // If not passed, it is assigned to the beginning of commit_lsn segment.
     pub local_start_lsn: Option<Lsn>,
 }
-
-fn lsn_invalid() -> Lsn {
-    Lsn::INVALID
-}
-
-/// Data about safekeeper's timeline, mirrors broker.proto.
-#[serde_as]
-#[derive(Debug, Clone, Deserialize, Serialize)]
-pub struct SkTimelineInfo {
-    /// Term of the last entry.
-    pub last_log_term: Option<u64>,
-    /// LSN of the last record.
-    #[serde_as(as = "DisplayFromStr")]
-    #[serde(default = "lsn_invalid")]
-    pub flush_lsn: Lsn,
-    /// Up to which LSN safekeeper regards its WAL as committed.
-    #[serde_as(as = "DisplayFromStr")]
-    #[serde(default = "lsn_invalid")]
-    pub commit_lsn: Lsn,
-    /// LSN up to which safekeeper has backed WAL.
-    #[serde_as(as = "DisplayFromStr")]
-    #[serde(default = "lsn_invalid")]
-    pub backup_lsn: Lsn,
-    /// LSN of last checkpoint uploaded by pageserver.
-    #[serde_as(as = "DisplayFromStr")]
-    #[serde(default = "lsn_invalid")]
-    pub remote_consistent_lsn: Lsn,
-    #[serde_as(as = "DisplayFromStr")]
-    #[serde(default = "lsn_invalid")]
-    pub peer_horizon_lsn: Lsn,
-    #[serde_as(as = "DisplayFromStr")]
-    #[serde(default = "lsn_invalid")]
-    pub local_start_lsn: Lsn,
-    /// A connection string to use for WAL receiving.
-    #[serde(default)]
-    pub safekeeper_connstr: Option<String>,
-}

libs/tenant_size_model/.gitignore

@@ -1,3 +0,0 @@
-*.dot
-*.png
-*.svg

libs/tenant_size_model/Cargo.toml

@@ -1,8 +0,0 @@
-[package]
-name = "tenant_size_model"
-version = "0.1.0"
-edition = "2021"
-publish = false
-
-[dependencies]
-workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/tenant_size_model/Makefile

@@ -1,13 +0,0 @@
-all: 1.svg 2.svg 3.svg 4.svg 1.png 2.png 3.png 4.png
-
-../../target/debug/tenant_size_model: Cargo.toml src/main.rs src/lib.rs
-	cargo build --bin tenant_size_model
-
-%.svg: %.dot
-	dot -Tsvg $< > $@
-
-%.png: %.dot
-	dot -Tpng $< > $@
-
-%.dot: ../../target/debug/tenant_size_model
-	../../target/debug/tenant_size_model $* > $@

libs/tenant_size_model/README.md

@@ -1,7 +0,0 @@
-# Logical size + WAL pricing
-
-This is a simulator to calculate the tenant size in different scenarios,
-using the "Logical size + WAL" method. Makefile produces diagrams used in a
-private presentation:
-
-https://docs.google.com/presentation/d/1OapE4k11xmcwMh7I7YvNWGC63yCRLh6udO9bXZ-fZmo/edit?usp=sharing

libs/tenant_size_model/src/lib.rs

@@ -1,382 +0,0 @@
-use std::borrow::Cow;
-use std::collections::HashMap;
-
-/// Pricing model or history size builder.
-///
-/// Maintains knowledge of the branches and their modifications. Generic over the branch name key
-/// type.
-pub struct Storage<K: 'static> {
-    segments: Vec<Segment>,
-
-    /// Mapping from the branch name to the index of a segment describing it's latest state.
-    branches: HashMap<K, usize>,
-}
-
-/// Snapshot of a branch.
-#[derive(Clone, Debug, Eq, PartialEq)]
-pub struct Segment {
-    /// Previous segment index into ['Storage::segments`], if any.
-    parent: Option<usize>,
-
-    /// Description of how did we get to this state.
-    ///
-    /// Mainly used in the original scenarios 1..=4 with insert, delete and update. Not used when
-    /// modifying a branch directly.
-    pub op: Cow<'static, str>,
-
-    /// LSN before this state
-    start_lsn: u64,
-
-    /// LSN at this state
-    pub end_lsn: u64,
-
-    /// Logical size before this state
-    start_size: u64,
-
-    /// Logical size at this state. Can be None in the last Segment of a branch.
-    pub end_size: Option<u64>,
-
-    /// Indices to [`Storage::segments`]
-    ///
-    /// FIXME: this could be an Option<usize>
-    children_after: Vec<usize>,
-
-    /// Determined by `retention_period` given to [`Storage::calculate`]
-    pub needed: bool,
-}
-
-//
-//
-//
-//
-//                 *-g--*---D--->
-//                /
-//               /
-//              /                 *---b----*-B--->
-//             /                 /
-//            /                 /
-//      -----*--e---*-----f----* C
-//           E                  \
-//                               \
-//                                *--a---*---A-->
-//
-// If A and B need to be retained, is it cheaper to store
-// snapshot at C+a+b, or snapshots at A and B ?
-//
-// If D also needs to be retained, which is cheaper:
-//
-// 1. E+g+e+f+a+b
-// 2. D+C+a+b
-// 3. D+A+B
-
-/// [`Segment`] which has had it's size calculated.
-pub struct SegmentSize {
-    pub seg_id: usize,
-
-    pub method: SegmentMethod,
-
-    this_size: u64,
-
-    pub children: Vec<SegmentSize>,
-}
-
-impl SegmentSize {
-    fn total(&self) -> u64 {
-        self.this_size + self.children.iter().fold(0, |acc, x| acc + x.total())
-    }
-
-    pub fn total_children(&self) -> u64 {
-        if self.method == SnapshotAfter {
-            self.this_size + self.children.iter().fold(0, |acc, x| acc + x.total())
-        } else {
-            self.children.iter().fold(0, |acc, x| acc + x.total())
-        }
-    }
-}
-
-/// Different methods to retain history from a particular state
-#[derive(Clone, Copy, Debug, Eq, PartialEq)]
-pub enum SegmentMethod {
-    SnapshotAfter,
-    Wal,
-    WalNeeded,
-    Skipped,
-}
-
-use SegmentMethod::*;
-
-impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
-    /// Creates a new storage with the given default branch name.
-    pub fn new(initial_branch: K) -> Storage<K> {
-        let init_segment = Segment {
-            op: "".into(),
-            needed: false,
-            parent: None,
-            start_lsn: 0,
-            end_lsn: 0,
-            start_size: 0,
-            end_size: Some(0),
-            children_after: Vec::new(),
-        };
-
-        Storage {
-            segments: vec![init_segment],
-            branches: HashMap::from([(initial_branch, 0)]),
-        }
-    }
-
-    /// Advances the branch with a new point, at given LSN.
-    pub fn insert_point<Q: ?Sized>(
-        &mut self,
-        branch: &Q,
-        op: Cow<'static, str>,
-        lsn: u64,
-        size: Option<u64>,
-    ) where
-        K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq,
-    {
-        let lastseg_id = *self.branches.get(branch).unwrap();
-        let newseg_id = self.segments.len();
-        let lastseg = &mut self.segments[lastseg_id];
-
-        assert!(lsn > lastseg.end_lsn);
-
-        let newseg = Segment {
-            op,
-            parent: Some(lastseg_id),
-            start_lsn: lastseg.end_lsn,
-            end_lsn: lsn,
-            start_size: lastseg.end_size.unwrap(),
-            end_size: size,
-            children_after: Vec::new(),
-            needed: false,
-        };
-        lastseg.children_after.push(newseg_id);
-
-        self.segments.push(newseg);
-        *self.branches.get_mut(branch).expect("read already") = newseg_id;
-    }
-
-    /// Advances the branch with the named operation, by the relative LSN and logical size bytes.
-    pub fn modify_branch<Q: ?Sized>(
-        &mut self,
-        branch: &Q,
-        op: Cow<'static, str>,
-        lsn_bytes: u64,
-        size_bytes: i64,
-    ) where
-        K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq,
-    {
-        let lastseg_id = *self.branches.get(branch).unwrap();
-        let newseg_id = self.segments.len();
-        let lastseg = &mut self.segments[lastseg_id];
-
-        let newseg = Segment {
-            op,
-            parent: Some(lastseg_id),
-            start_lsn: lastseg.end_lsn,
-            end_lsn: lastseg.end_lsn + lsn_bytes,
-            start_size: lastseg.end_size.unwrap(),
-            end_size: Some((lastseg.end_size.unwrap() as i64 + size_bytes) as u64),
-            children_after: Vec::new(),
-            needed: false,
-        };
-        lastseg.children_after.push(newseg_id);
-
-        self.segments.push(newseg);
-        *self.branches.get_mut(branch).expect("read already") = newseg_id;
-    }
-
-    pub fn insert<Q: ?Sized>(&mut self, branch: &Q, bytes: u64)
-    where
-        K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq,
-    {
-        self.modify_branch(branch, "insert".into(), bytes, bytes as i64);
-    }
-
-    pub fn update<Q: ?Sized>(&mut self, branch: &Q, bytes: u64)
-    where
-        K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq,
-    {
-        self.modify_branch(branch, "update".into(), bytes, 0i64);
-    }
-
-    pub fn delete<Q: ?Sized>(&mut self, branch: &Q, bytes: u64)
-    where
-        K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq,
-    {
-        self.modify_branch(branch, "delete".into(), bytes, -(bytes as i64));
-    }
-
-    /// Panics if the parent branch cannot be found.
-    pub fn branch<Q: ?Sized>(&mut self, parent: &Q, name: K)
-    where
-        K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq,
-    {
-        // Find the right segment
-        let branchseg_id = *self
-            .branches
-            .get(parent)
-            .expect("should had found the parent by key");
-        let _branchseg = &mut self.segments[branchseg_id];
-
-        // Create branch name for it
-        self.branches.insert(name, branchseg_id);
-    }
-
-    pub fn calculate(&mut self, retention_period: u64) -> SegmentSize {
-        // Phase 1: Mark all the segments that need to be retained
-        for (_branch, &last_seg_id) in self.branches.iter() {
-            let last_seg = &self.segments[last_seg_id];
-            let cutoff_lsn = last_seg.start_lsn.saturating_sub(retention_period);
-            let mut seg_id = last_seg_id;
-            loop {
-                let seg = &mut self.segments[seg_id];
-                if seg.end_lsn < cutoff_lsn {
-                    break;
-                }
-                seg.needed = true;
-                if let Some(prev_seg_id) = seg.parent {
-                    seg_id = prev_seg_id;
-                } else {
-                    break;
-                }
-            }
-        }
-
-        // Phase 2: For each oldest segment in a chain that needs to be retained,
-        // calculate if we should store snapshot or WAL
-        self.size_from_snapshot_later(0)
-    }
-
-    fn size_from_wal(&self, seg_id: usize) -> SegmentSize {
-        let seg = &self.segments[seg_id];
-
-        let this_size = seg.end_lsn - seg.start_lsn;
-
-        let mut children = Vec::new();
-
-        // try both ways
-        for &child_id in seg.children_after.iter() {
-            // try each child both ways
-            let child = &self.segments[child_id];
-            let p1 = self.size_from_wal(child_id);
-
-            let p = if !child.needed {
-                let p2 = self.size_from_snapshot_later(child_id);
-                if p1.total() < p2.total() {
-                    p1
-                } else {
-                    p2
-                }
-            } else {
-                p1
-            };
-            children.push(p);
-        }
-        SegmentSize {
-            seg_id,
-            method: if seg.needed { WalNeeded } else { Wal },
-            this_size,
-            children,
-        }
-    }
-
-    fn size_from_snapshot_later(&self, seg_id: usize) -> SegmentSize {
-        // If this is needed, then it's time to do the snapshot and continue
-        // with wal method.
-        let seg = &self.segments[seg_id];
-        //eprintln!("snap: seg{}: {} needed: {}", seg_id, seg.children_after.len(), seg.needed);
-        if seg.needed {
-            let mut children = Vec::new();
-
-            for &child_id in seg.children_after.iter() {
-                // try each child both ways
-                let child = &self.segments[child_id];
-                let p1 = self.size_from_wal(child_id);
-
-                let p = if !child.needed {
-                    let p2 = self.size_from_snapshot_later(child_id);
-                    if p1.total() < p2.total() {
-                        p1
-                    } else {
-                        p2
-                    }
-                } else {
-                    p1
-                };
-                children.push(p);
-            }
-            SegmentSize {
-                seg_id,
-                method: WalNeeded,
-                this_size: seg.start_size,
-                children,
-            }
-        } else {
-            // If any of the direct children are "needed", need to be able to reconstruct here
-            let mut children_needed = false;
-            for &child in seg.children_after.iter() {
-                let seg = &self.segments[child];
-                if seg.needed {
-                    children_needed = true;
-                    break;
-                }
-            }
-
-            let method1 = if !children_needed {
-                let mut children = Vec::new();
-                for child in seg.children_after.iter() {
-                    children.push(self.size_from_snapshot_later(*child));
-                }
-                Some(SegmentSize {
-                    seg_id,
-                    method: Skipped,
-                    this_size: 0,
-                    children,
-                })
-            } else {
-                None
-            };
-
-            // If this a junction, consider snapshotting here
-            let method2 = if children_needed || seg.children_after.len() >= 2 {
-                let mut children = Vec::new();
-                for child in seg.children_after.iter() {
-                    children.push(self.size_from_wal(*child));
-                }
-                Some(SegmentSize {
-                    seg_id,
-                    method: SnapshotAfter,
-                    this_size: seg.end_size.unwrap(),
-                    children,
-                })
-            } else {
-                None
-            };
-
-            match (method1, method2) {
-                (None, None) => panic!(),
-                (Some(method), None) => method,
-                (None, Some(method)) => method,
-                (Some(method1), Some(method2)) => {
-                    if method1.total() < method2.total() {
-                        method1
-                    } else {
-                        method2
-                    }
-                }
-            }
-        }
-    }
-
-    pub fn into_segments(self) -> Vec<Segment> {
-        self.segments
-    }
-}

libs/tenant_size_model/src/main.rs

@@ -1,268 +0,0 @@
-//! Tenant size model testing ground.
-//!
-//! Has a number of scenarios and a `main` for invoking these by number, calculating the history
-//! size, outputs graphviz graph. Makefile in directory shows how to use graphviz to turn scenarios
-//! into pngs.
-
-use tenant_size_model::{Segment, SegmentSize, Storage};
-
-// Main branch only. Some updates on it.
-fn scenario_1() -> (Vec<Segment>, SegmentSize) {
-    // Create main branch
-    let mut storage = Storage::new("main");
-
-    // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000);
-
-    // Stream of updates
-    for _ in 0..5 {
-        storage.update("main", 1_000);
-    }
-
-    let size = storage.calculate(1000);
-
-    (storage.into_segments(), size)
-}
-
-// Main branch only. Some updates on it.
-fn scenario_2() -> (Vec<Segment>, SegmentSize) {
-    // Create main branch
-    let mut storage = Storage::new("main");
-
-    // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000);
-
-    // Stream of updates
-    for _ in 0..5 {
-        storage.update("main", 1_000);
-    }
-
-    // Branch
-    storage.branch("main", "child");
-    storage.update("child", 1_000);
-
-    // More updates on parent
-    storage.update("main", 1_000);
-
-    let size = storage.calculate(1000);
-
-    (storage.into_segments(), size)
-}
-
-// Like 2, but more updates on main
-fn scenario_3() -> (Vec<Segment>, SegmentSize) {
-    // Create main branch
-    let mut storage = Storage::new("main");
-
-    // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000);
-
-    // Stream of updates
-    for _ in 0..5 {
-        storage.update("main", 1_000);
-    }
-
-    // Branch
-    storage.branch("main", "child");
-    storage.update("child", 1_000);
-
-    // More updates on parent
-    for _ in 0..5 {
-        storage.update("main", 1_000);
-    }
-
-    let size = storage.calculate(1000);
-
-    (storage.into_segments(), size)
-}
-
-// Diverged branches
-fn scenario_4() -> (Vec<Segment>, SegmentSize) {
-    // Create main branch
-    let mut storage = Storage::new("main");
-
-    // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000);
-
-    // Stream of updates
-    for _ in 0..5 {
-        storage.update("main", 1_000);
-    }
-
-    // Branch
-    storage.branch("main", "child");
-    storage.update("child", 1_000);
-
-    // More updates on parent
-    for _ in 0..8 {
-        storage.update("main", 1_000);
-    }
-
-    let size = storage.calculate(1000);
-
-    (storage.into_segments(), size)
-}
-
-fn scenario_5() -> (Vec<Segment>, SegmentSize) {
-    let mut storage = Storage::new("a");
-    storage.insert("a", 5000);
-    storage.branch("a", "b");
-    storage.update("b", 4000);
-    storage.update("a", 2000);
-    storage.branch("a", "c");
-    storage.insert("c", 4000);
-    storage.insert("a", 2000);
-
-    let size = storage.calculate(5000);
-
-    (storage.into_segments(), size)
-}
-
-fn scenario_6() -> (Vec<Segment>, SegmentSize) {
-    use std::borrow::Cow;
-
-    const NO_OP: Cow<'static, str> = Cow::Borrowed("");
-
-    let branches = [
-        Some(0x7ff1edab8182025f15ae33482edb590a_u128),
-        Some(0xb1719e044db05401a05a2ed588a3ad3f),
-        Some(0xb68d6691c895ad0a70809470020929ef),
-    ];
-
-    // compared to other scenarios, this one uses bytes instead of kB
-
-    let mut storage = Storage::new(None);
-
-    storage.branch(&None, branches[0]); // at 0
-    storage.modify_branch(&branches[0], NO_OP, 108951064, 43696128); // at 108951064
-    storage.branch(&branches[0], branches[1]); // at 108951064
-    storage.modify_branch(&branches[1], NO_OP, 15560408, -1851392); // at 124511472
-    storage.modify_branch(&branches[0], NO_OP, 174464360, -1531904); // at 283415424
-    storage.branch(&branches[0], branches[2]); // at 283415424
-    storage.modify_branch(&branches[2], NO_OP, 15906192, 8192); // at 299321616
-    storage.modify_branch(&branches[0], NO_OP, 18909976, 32768); // at 302325400
-
-    let size = storage.calculate(100_000);
-
-    (storage.into_segments(), size)
-}
-
-fn main() {
-    let args: Vec<String> = std::env::args().collect();
-
-    let scenario = if args.len() < 2 { "1" } else { &args[1] };
-
-    let (segments, size) = match scenario {
-        "1" => scenario_1(),
-        "2" => scenario_2(),
-        "3" => scenario_3(),
-        "4" => scenario_4(),
-        "5" => scenario_5(),
-        "6" => scenario_6(),
-        other => {
-            eprintln!("invalid scenario {}", other);
-            std::process::exit(1);
-        }
-    };
-
-    graphviz_tree(&segments, &size);
-}
-
-fn graphviz_recurse(segments: &[Segment], node: &SegmentSize) {
-    use tenant_size_model::SegmentMethod::*;
-
-    let seg_id = node.seg_id;
-    let seg = segments.get(seg_id).unwrap();
-    let lsn = seg.end_lsn;
-    let size = seg.end_size.unwrap_or(0);
-    let method = node.method;
-
-    println!("  {{");
-    println!("    node [width=0.1 height=0.1 shape=oval]");
-
-    let tenant_size = node.total_children();
-
-    let penwidth = if seg.needed { 6 } else { 3 };
-    let x = match method {
-        SnapshotAfter =>
-            format!("label=\"lsn: {lsn}\\nsize: {size}\\ntenant_size: {tenant_size}\" style=filled penwidth={penwidth}"),
-        Wal =>
-            format!("label=\"lsn: {lsn}\\nsize: {size}\\ntenant_size: {tenant_size}\" color=\"black\" penwidth={penwidth}"),
-        WalNeeded =>
-            format!("label=\"lsn: {lsn}\\nsize: {size}\\ntenant_size: {tenant_size}\" color=\"black\" penwidth={penwidth}"),
-        Skipped =>
-            format!("label=\"lsn: {lsn}\\nsize: {size}\\ntenant_size: {tenant_size}\" color=\"gray\" penwidth={penwidth}"),
-    };
-
-    println!("    \"seg{seg_id}\" [{x}]");
-    println!("  }}");
-
-    // Recurse. Much of the data is actually on the edge
-    for child in node.children.iter() {
-        let child_id = child.seg_id;
-        graphviz_recurse(segments, child);
-
-        let edge_color = match child.method {
-            SnapshotAfter => "gray",
-            Wal => "black",
-            WalNeeded => "black",
-            Skipped => "gray",
-        };
-
-        println!("  {{");
-        println!("    edge [] ");
-        print!("    \"seg{seg_id}\" -> \"seg{child_id}\" [");
-        print!("color={edge_color}");
-        if child.method == WalNeeded {
-            print!(" penwidth=6");
-        }
-        if child.method == Wal {
-            print!(" penwidth=3");
-        }
-
-        let next = segments.get(child_id).unwrap();
-
-        if next.op.is_empty() {
-            print!(
-                " label=\"{} / {}\"",
-                next.end_lsn - seg.end_lsn,
-                (next.end_size.unwrap_or(0) as i128 - seg.end_size.unwrap_or(0) as i128)
-            );
-        } else {
-            print!(" label=\"{}: {}\"", next.op, next.end_lsn - seg.end_lsn);
-        }
-        println!("]");
-        println!("  }}");
-    }
-}
-
-fn graphviz_tree(segments: &[Segment], tree: &SegmentSize) {
-    println!("digraph G {{");
-    println!("  fontname=\"Helvetica,Arial,sans-serif\"");
-    println!("  node [fontname=\"Helvetica,Arial,sans-serif\"]");
-    println!("  edge [fontname=\"Helvetica,Arial,sans-serif\"]");
-    println!("  graph [center=1 rankdir=LR]");
-    println!("  edge [dir=none]");
-
-    graphviz_recurse(segments, tree);
-
-    println!("}}");
-}
-
-#[test]
-fn scenarios_return_same_size() {
-    type ScenarioFn = fn() -> (Vec<Segment>, SegmentSize);
-    let truths: &[(u32, ScenarioFn, _)] = &[
-        (line!(), scenario_1, 8000),
-        (line!(), scenario_2, 9000),
-        (line!(), scenario_3, 13000),
-        (line!(), scenario_4, 16000),
-        (line!(), scenario_5, 17000),
-        (line!(), scenario_6, 333_792_000),
-    ];
-
-    for (line, scenario, expected) in truths {
-        let (_, size) = scenario();
-        assert_eq!(*expected, size.total_children(), "scenario on line {line}");
-    }
-}