Use im

.config/hakari.toml

@@ -4,7 +4,7 @@
 hakari-package = "workspace_hack"
 
 # Format for `workspace-hack = ...` lines in other Cargo.tomls. Requires cargo-hakari 0.9.8 or above.
-dep-format-version = "3"
+dep-format-version = "2"
 
 # Setting workspace.resolver = "2" in the root Cargo.toml is HIGHLY recommended.
 # Hakari works much better with the new feature resolver.

.github/PULL_REQUEST_TEMPLATE/pull_request_template.md

@@ -1,10 +0,0 @@
-## Describe your changes
-
-## Issue ticket number and link
-
-## Checklist before requesting a review
-- [ ] I have performed a self-review of my code.
-- [ ] If it is a core feature, I have added thorough tests.
-- [ ] Do we need to implement analytics? if so did you add the relevant metrics to the dashboard?
-- [ ] If this PR requires public announcement, mark it with /release-notes label and add several sentences in this section.
-

.github/PULL_REQUEST_TEMPLATE/release-pr.md

@@ -14,7 +14,7 @@
 - [ ] Check [#dev-production-stream](https://neondb.slack.com/archives/C03F5SM1N02) Slack channel
 - [ ] Check [stuck projects page](https://console.neon.tech/admin/projects?sort=last_active&order=desc&stuck=true)
 - [ ] Check [recent operation failures](https://console.neon.tech/admin/operations?action=create_timeline%2Cstart_compute%2Cstop_compute%2Csuspend_compute%2Capply_config%2Cdelete_timeline%2Cdelete_tenant%2Ccreate_branch%2Ccheck_availability&sort=updated_at&order=desc&had_retries=some)
-- [ ] Check [cloud SLO dashboard](https://neonprod.grafana.net/d/_oWcBMJ7k/cloud-slos?orgId=1)
-- [ ] Check [compute startup metrics dashboard](https://neonprod.grafana.net/d/5OkYJEmVz/compute-startup-time)
+- [ ] Check [cloud SLO dashboard](https://observer.zenith.tech/d/_oWcBMJ7k/cloud-slos?orgId=1)
+- [ ] Check [compute startup metrics dashboard](https://observer.zenith.tech/d/5OkYJEmVz/compute-startup-time)
 
 <!-- List everything that should be done **after** release, any admin UI configuration / Grafana dashboard / alert changes / setting changes / etc -->

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

@@ -5,12 +5,12 @@ inputs:
   api_key:
     desctiption: 'Neon API key'
     required: true
+  environment:
+    desctiption: 'dev (aka captest) or staging'
+    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)'
@@ -22,6 +22,27 @@ outputs:
 runs:
   using: "composite"
   steps:
+    - name: Parse Input
+      id: parse-input
+      shell: bash -euxo pipefail {0}
+      run: |
+        case "${ENVIRONMENT}" in
+          dev)
+            API_HOST=console.dev.neon.tech
+            ;;
+          staging)
+            API_HOST=console.stage.neon.tech
+            ;;
+          *)
+            echo 2>&1 "Unknown environment=${ENVIRONMENT}. Allowed 'dev' or 'staging' only"
+            exit 1
+            ;;
+        esac
+
+        echo "api_host=${API_HOST}" >> $GITHUB_OUTPUT
+      env:
+        ENVIRONMENT: ${{ inputs.environment }}
+
     - name: Create New Branch
       id: create-branch
       shell: bash -euxo pipefail {0}
@@ -35,12 +56,7 @@ runs:
             --data "{
               \"branch\": {
                 \"name\": \"Created by actions/neon-branch-create; GITHUB_RUN_ID=${GITHUB_RUN_ID} at $(date +%s)\"
-              },
-              \"endpoints\": [
-                {
-                  \"type\": \"read_write\"
-                }
-              ]
+              }
             }")
 
           if [ -z "${branch}" ]; then
@@ -68,8 +84,8 @@ runs:
         host=$(echo $branch | jq --raw-output '.endpoints[0].host')
         echo "host=${host}" >> $GITHUB_OUTPUT
       env:
-        API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
+        API_HOST: ${{ steps.parse-input.outputs.api_host }}
         PROJECT_ID: ${{ inputs.project_id }}
 
     - name: Get Role name
@@ -87,8 +103,8 @@ runs:
         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 }}
+        API_HOST: ${{ steps.parse-input.outputs.api_host }}
         PROJECT_ID: ${{ inputs.project_id }}
         BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
 
@@ -130,8 +146,8 @@ runs:
         echo "::add-mask::${dsn}"
         echo "dsn=${dsn}" >> $GITHUB_OUTPUT
       env:
-        API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
+        API_HOST: ${{ steps.parse-input.outputs.api_host }}
         PROJECT_ID: ${{ inputs.project_id }}
         BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
         ROLE_NAME: ${{ steps.role-name.outputs.role_name }}

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

@@ -5,19 +5,40 @@ inputs:
   api_key:
     desctiption: 'Neon API key'
     required: true
+  environment:
+    desctiption: 'dev (aka captest) or staging'
+    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: Parse Input
+      id: parse-input
+      shell: bash -euxo pipefail {0}
+      run: |
+        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 Branch
       # Do not try to delete a branch if .github/actions/neon-project-create
       # or .github/actions/neon-branch-create failed before
@@ -52,7 +73,7 @@ runs:
           exit 1
         fi
       env:
-        API_HOST: ${{ inputs.api_host }}
         API_KEY: ${{ inputs.api_key }}
         PROJECT_ID: ${{ inputs.project_id }}
         BRANCH_ID: ${{ inputs.branch_id }}
+        API_HOST: ${{ steps.parse-input.outputs.api_host }}

.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 staging'
+    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)'
@@ -26,6 +22,31 @@ 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:-aws-eu-west-1}
+            ;;
+          staging)
+            API_HOST=console.stage.neon.tech
+            REGION_ID=${REGION_ID:-aws-us-east-2}
+            ;;
+          *)
+            echo 2>&1 "Unknown environment=${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: ${{ inputs.region_id }}
+
     - name: Create Neon Project
       id: create-neon-project
       # A shell without `set -x` to not to expose password/dsn in logs
@@ -40,7 +61,6 @@ runs:
           --data "{
             \"project\": {
               \"name\": \"Created by actions/neon-project-create; GITHUB_RUN_ID=${GITHUB_RUN_ID}\",
-              \"pg_version\": ${POSTGRES_VERSION},
               \"region_id\": \"${REGION_ID}\",
               \"settings\": { }
             }
@@ -55,10 +75,7 @@ runs:
 
         project_id=$(echo $project | jq --raw-output '.project.id')
         echo "project_id=${project_id}" >> $GITHUB_OUTPUT
-
-        echo "Project ${project_id} has been created"
       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

@@ -5,16 +5,37 @@ inputs:
   api_key:
     desctiption: 'Neon API key'
     required: true
+  environment:
+    desctiption: 'dev (aka captest) or staging'
+    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: Parse Input
+      id: parse-input
+      shell: bash -euxo pipefail {0}
+      run: |
+        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
       # Do not try to delete a project if .github/actions/neon-project-create failed before
       if: ${{ inputs.project_id != '' }}
@@ -27,9 +48,7 @@ runs:
           --header "Accept: application/json" \
           --header "Content-Type: application/json" \
           --header "Authorization: Bearer ${API_KEY}"
-
-        echo "Project ${PROJECT_ID} has been deleted"
       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/ansible/ansible.cfg

@@ -3,6 +3,7 @@
 localhost_warning = False
 host_key_checking = False
 timeout = 30
+collections_paths = ./collections
 
 [ssh_connection]
 ssh_args   = -F ./ansible.ssh.cfg

.github/ansible/deploy.yaml

@@ -117,8 +117,7 @@
       shell:
         cmd: |
           INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/pageservers
+          curl -sfS -d '{"version": {{ current_version }} }' -X PATCH {{ console_mgmt_base_url }}/api/v1/pageservers/$INSTANCE_ID
       tags:
       - pageserver
 
@@ -187,7 +186,6 @@
       shell:
         cmd: |
           INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/safekeepers
+          curl -sfS -d '{"version": {{ current_version }} }' -X PATCH {{ console_mgmt_base_url }}/api/v1/safekeepers/$INSTANCE_ID
       tags:
       - safekeeper

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

@@ -0,0 +1,31 @@
+storage:
+  vars:
+    bucket_name: neon-storage-ireland
+    bucket_region: eu-west-1
+    console_mgmt_base_url: http://neon-stress-console.local
+    etcd_endpoints: neon-stress-etcd.local:2379
+    safekeeper_enable_s3_offload: 'false'
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      remote_storage:
+        bucket_name: "{{ bucket_name }}"
+        bucket_region: "{{ bucket_region }}"
+        prefix_in_bucket: "{{ inventory_hostname }}"
+    safekeeper_s3_prefix: neon-stress/wal
+    hostname_suffix: ".local"
+    remote_user: admin
+  children:
+    pageservers:
+      hosts:
+        neon-stress-ps-1:
+          console_region_id: aws-eu-west-1
+        neon-stress-ps-2:
+          console_region_id: aws-eu-west-1
+    safekeepers:
+      hosts:
+        neon-stress-sk-1:
+          console_region_id: aws-eu-west-1
+        neon-stress-sk-2:
+          console_region_id: aws-eu-west-1
+        neon-stress-sk-3:
+          console_region_id: aws-eu-west-1

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

@@ -3,11 +3,9 @@ storage:
     bucket_name: neon-prod-storage-ap-southeast-1
     bucket_region: ap-southeast-1
     console_mgmt_base_url: http://console-release.local
-    broker_endpoint: http://storage-broker-lb.epsilon.ap-southeast-1.internal.aws.neon.tech:50051
+    etcd_endpoints: etcd-0.ap-southeast-1.aws.neon.tech:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -18,7 +16,6 @@ storage:
     ansible_aws_ssm_region: ap-southeast-1
     ansible_aws_ssm_bucket_name: neon-prod-storage-ap-southeast-1
     console_region_id: aws-ap-southeast-1
-    sentry_environment: production
 
   children:
     pageservers:

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

@@ -3,11 +3,9 @@ storage:
     bucket_name: neon-prod-storage-eu-central-1
     bucket_region: eu-central-1
     console_mgmt_base_url: http://console-release.local
-    broker_endpoint: http://storage-broker-lb.gamma.eu-central-1.internal.aws.neon.tech:50051
+    etcd_endpoints: etcd-0.eu-central-1.aws.neon.tech:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -18,7 +16,6 @@ storage:
     ansible_aws_ssm_region: eu-central-1
     ansible_aws_ssm_bucket_name: neon-prod-storage-eu-central-1
     console_region_id: aws-eu-central-1
-    sentry_environment: production
 
   children:
     pageservers:

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

@@ -3,11 +3,9 @@ storage:
     bucket_name: neon-prod-storage-us-east-2
     bucket_region: us-east-2
     console_mgmt_base_url: http://console-release.local
-    broker_endpoint: http://storage-broker-lb.delta.us-east-2.internal.aws.neon.tech:50051
+    etcd_endpoints: etcd-0.us-east-2.aws.neon.tech:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -18,7 +16,6 @@ storage:
     ansible_aws_ssm_region: us-east-2
     ansible_aws_ssm_bucket_name: neon-prod-storage-us-east-2
     console_region_id: aws-us-east-2
-    sentry_environment: production
 
   children:
     pageservers:
@@ -36,4 +33,4 @@ storage:
           ansible_host:  i-06d113fb73bfddeb0
         safekeeper-2.us-east-2.aws.neon.tech:
           ansible_host:  i-09f66c8e04afff2e8
-
+          

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

@@ -1,41 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-prod-storage-us-west-2
-    bucket_region: us-west-2
-    console_mgmt_base_url: http://console-release.local
-    broker_endpoint: http://storage-broker-lb.eta.us-west-2.internal.aws.neon.tech:50051
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
-      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: us-west-2
-    ansible_aws_ssm_bucket_name: neon-prod-storage-us-west-2
-    console_region_id: aws-us-west-2-new
-    sentry_environment: production
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.us-west-2.aws.neon.tech:
-          ansible_host: i-0d9f6dfae0e1c780d 
-        pageserver-1.us-west-2.aws.neon.tech:
-          ansible_host: i-0c834be1dddba8b3f
-        pageserver-2.us-west-2.aws.neon.tech:
-          ansible_host: i-051642d372c0a4f32
-
-    safekeepers:
-      hosts:
-        safekeeper-0.us-west-2.aws.neon.tech:
-          ansible_host: i-00719d8a74986fda6
-        safekeeper-1.us-west-2.aws.neon.tech:
-          ansible_host: i-074682f9d3c712e7c
-        safekeeper-2.us-west-2.aws.neon.tech:
-          ansible_host: i-042b7efb1729d7966 
-          

.github/ansible/production.hosts.yaml

@@ -4,11 +4,9 @@ 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
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -16,7 +14,6 @@ storage:
     safekeeper_s3_prefix: prod-1/wal
     hostname_suffix: ".local"
     remote_user: admin
-    sentry_environment: production
 
   children:
     pageservers:
@@ -36,5 +33,5 @@ storage:
           console_region_id: aws-us-west-2
         zenith-1-sk-2:
           console_region_id: aws-us-west-2
-        zenith-1-sk-4:
+        zenith-1-sk-3:
           console_region_id: aws-us-west-2

.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

@@ -3,11 +3,9 @@ storage:
     bucket_name: neon-dev-storage-eu-west-1
     bucket_region: eu-west-1
     console_mgmt_base_url: http://console-staging.local
-    broker_endpoint: http://storage-broker-lb.zeta.eu-west-1.internal.aws.neon.build:50051
+    etcd_endpoints: etcd-0.eu-west-1.aws.neon.build:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-staging.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -18,7 +16,6 @@ storage:
     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
-    sentry_environment: staging
 
   children:
     pageservers:

.github/ansible/staging.hosts.yaml

@@ -0,0 +1,34 @@
+storage:
+  vars:
+    bucket_name: zenith-staging-storage-us-east-1
+    bucket_region: us-east-1
+    console_mgmt_base_url: http://console-staging.local
+    etcd_endpoints: etcd-0.us-east-2.aws.neon.build:2379
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      remote_storage:
+        bucket_name: "{{ bucket_name }}"
+        bucket_region: "{{ bucket_region }}"
+        prefix_in_bucket: "{{ inventory_hostname }}"
+    safekeeper_s3_prefix: us-stage/wal
+    hostname_suffix: ".local"
+    remote_user: admin
+
+  children:
+    pageservers:
+      hosts:
+        zenith-us-stage-ps-2:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-ps-3:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-ps-4:
+          console_region_id: aws-us-east-1
+
+    safekeepers:
+      hosts:
+        zenith-us-stage-sk-4:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-sk-5:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-sk-6:
+          console_region_id: aws-us-east-1

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

@@ -3,11 +3,9 @@ storage:
     bucket_name: neon-staging-storage-us-east-2
     bucket_region: us-east-2
     console_mgmt_base_url: http://console-staging.local
-    broker_endpoint: http://storage-broker-lb.beta.us-east-2.internal.aws.neon.build:50051
+    etcd_endpoints: etcd-0.us-east-2.aws.neon.build:2379
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-staging.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -18,7 +16,6 @@ storage:
     ansible_aws_ssm_region: us-east-2
     ansible_aws_ssm_bucket_name: neon-staging-storage-us-east-2
     console_region_id: aws-us-east-2
-    sentry_environment: staging
 
   children:
     pageservers:
@@ -27,10 +24,6 @@ storage:
           ansible_host: i-0c3e70929edb5d691
         pageserver-1.us-east-2.aws.neon.build:
           ansible_host: i-0565a8b4008aa3f40
-        pageserver-2.us-east-2.aws.neon.build:
-          ansible_host: i-01e31cdf7e970586a
-        pageserver-3.us-east-2.aws.neon.build:
-          ansible_host: i-0602a0291365ef7cc
 
     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 }} SENTRY_ENVIRONMENT={{ sentry_environment }}
-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 }} SENTRY_ENVIRONMENT={{ sentry_environment }}
-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

@@ -8,10 +8,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-staging.local/management/api/v2"
   domain: "*.eu-west-1.aws.neon.build"
-  sentryEnvironment: "staging"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +22,6 @@ exposedService:
     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
-  httpsPort: 443
 
 #metrics:
 #  enabled: true
@@ -34,28 +29,3 @@ exposedService:
 #    enabled: true
 #    selector:
 #      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -1,52 +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-lb.zeta.eu-west-1.internal.aws.neon.build
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-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 }}"
-
-settings:
-  sentryEnvironment: "staging"

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

@@ -8,9 +8,6 @@ settings:
   authBackend: "link"
   authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
   uri: "https://console.stage.neon.tech/psql_session/"
-  sentryEnvironment: "staging"
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
 
 # -- Additional labels for neon-proxy-link pods
 podLabels:
@@ -40,28 +37,3 @@ exposedService:
 #    enabled: true
 #    selector:
 #      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -8,10 +8,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-staging.local/management/api/v2"
   domain: "*.cloud.stage.neon.tech"
-  sentryEnvironment: "staging"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +22,6 @@ exposedService:
     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
-  httpsPort: 443
 
 #metrics:
 #  enabled: true
@@ -34,28 +29,3 @@ exposedService:
 #    enabled: true
 #    selector:
 #      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -8,10 +8,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-staging.local/management/api/v2"
   domain: "*.us-east-2.aws.neon.build"
-  sentryEnvironment: "staging"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +22,6 @@ exposedService:
     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-east-2.aws.neon.build
-  httpsPort: 443
 
 #metrics:
 #  enabled: true
@@ -34,28 +29,3 @@ exposedService:
 #    enabled: true
 #    selector:
 #      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -1,52 +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-lb.beta.us-east-2.internal.aws.neon.build
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-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 }}"
-
-settings:
-  sentryEnvironment: "staging"

.github/helm-values/neon-stress.proxy-scram.yaml

@@ -0,0 +1,26 @@
+fullnameOverride: "neon-stress-proxy-scram"
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-stress-console.local/management/api/v2"
+  domain: "*.stress.neon.tech"
+
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: staging
+  zenith_region: eu-west-1
+  zenith_region_slug: ireland
+
+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: '*.stress.neon.tech'
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack

.github/helm-values/neon-stress.proxy.yaml

@@ -0,0 +1,35 @@
+fullnameOverride: "neon-stress-proxy"
+
+settings:
+  authBackend: "link"
+  authEndpoint: "https://console.dev.neon.tech/authenticate_proxy_request/"
+  uri: "https://console.dev.neon.tech/psql_session/"
+
+# -- Additional labels for zenith-proxy pods
+podLabels:
+  zenith_service: proxy
+  zenith_env: staging
+  zenith_region: eu-west-1
+  zenith_region_slug: ireland
+
+service:
+  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-stress-proxy.local
+  type: LoadBalancer
+
+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: connect.dev.neon.tech
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack

.github/helm-values/prod-ap-southeast-1-epsilon.neon-proxy-scram.yaml

@@ -8,10 +8,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.ap-southeast-1.aws.neon.tech"
-  sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +22,6 @@ exposedService:
     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: ap-southeast-1.aws.neon.tech
-  httpsPort: 443
 
 #metrics:
 #  enabled: true
@@ -34,28 +29,3 @@ exposedService:
 #    enabled: true
 #    selector:
 #      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -1,52 +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-lb.epsilon.ap-southeast-1.internal.aws.neon.tech
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-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 }}"
-
-settings:
-  sentryEnvironment: "production"

.github/helm-values/prod-eu-central-1-gamma.neon-proxy-scram.yaml

@@ -8,10 +8,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.eu-central-1.aws.neon.tech"
-  sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +22,6 @@ exposedService:
     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-central-1.aws.neon.tech
-  httpsPort: 443
 
 #metrics:
 #  enabled: true
@@ -34,28 +29,3 @@ exposedService:
 #    enabled: true
 #    selector:
 #      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -1,52 +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-lb.gamma.eu-central-1.internal.aws.neon.tech
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-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 }}"
-
-settings:
-  sentryEnvironment: "production"

.github/helm-values/prod-us-east-2-delta.neon-proxy-scram.yaml

@@ -8,10 +8,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.us-east-2.aws.neon.tech"
-  sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +22,6 @@ exposedService:
     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-east-2.aws.neon.tech
-  httpsPort: 443
 
 #metrics:
 #  enabled: true
@@ -34,28 +29,3 @@ exposedService:
 #    enabled: true
 #    selector:
 #      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -1,52 +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-lb.delta.us-east-2.internal.aws.neon.tech
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-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 }}"
-
-settings:
-  sentryEnvironment: "production"

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

@@ -1,61 +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"
-  sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
-
-# -- 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
-  httpsPort: 443
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

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

@@ -1,52 +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-lb.eta.us-west-2.internal.aws.neon.tech
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-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 }}"
-
-settings:
-  sentryEnvironment: "production"

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

@@ -1,56 +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 }}"
-
-settings:
-  sentryEnvironment: "production"

.github/helm-values/production.proxy-scram.yaml

@@ -2,10 +2,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.cloud.neon.tech"
-  sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 podLabels:
   zenith_service: proxy-scram
@@ -19,7 +15,6 @@ exposedService:
     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: '*.cloud.neon.tech'
-  httpsPort: 443
 
 metrics:
   enabled: true
@@ -27,28 +22,3 @@ metrics:
     enabled: true
     selector:
       release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

.github/helm-values/production.proxy.yaml

@@ -2,7 +2,6 @@ settings:
   authBackend: "link"
   authEndpoint: "https://console.neon.tech/authenticate_proxy_request/"
   uri: "https://console.neon.tech/psql_session/"
-  sentryEnvironment: "production"
 
 # -- Additional labels for zenith-proxy pods
 podLabels:
@@ -32,28 +31,3 @@ metrics:
     enabled: true
     selector:
       release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

.github/helm-values/staging.proxy-scram.yaml

@@ -0,0 +1,31 @@
+# Helm chart values for zenith-proxy.
+# 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 zenith-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: staging
+  zenith_region: us-east-1
+  zenith_region_slug: virginia
+
+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: cloud.stage.neon.tech
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack

.github/helm-values/staging.proxy.yaml

@@ -0,0 +1,31 @@
+# Helm chart values for zenith-proxy.
+# 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 zenith-proxy pods
+podLabels:
+  zenith_service: proxy
+  zenith_env: staging
+  zenith_region: us-east-1
+  zenith_region_slug: virginia
+
+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: connect.stage.neon.tech
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack

.github/workflows/benchmarking.yml

@@ -15,10 +15,12 @@ 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
-        default: 'aws-us-east-2'
       save_perf_report:
         type: boolean
         description: 'Publish perf report or not. If not set, the report is published only for the main branch'
@@ -35,69 +37,103 @@ 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: ${{ steps.create-neon-project.outputs.dsn }}
+        REMOTE_ENV: "1" # indicate to test harness that we do not have zenith binaries locally
+      run: |
+        # just to be sure that no data was cached on self hosted runner
+        # since it might generate duplicates when calling ingest_perf_test_result.py
+        rm -rf perf-report-staging
+        mkdir -p perf-report-staging
+        # Set --sparse-ordering option of pytest-order plugin to ensure tests are running in order of appears in the file,
+        # it's important for test_perf_pgbench.py::test_pgbench_remote_* tests.
+        # Do not run tests from test_runner/performance/test_perf_olap.py because they require a prepared DB. We run them separately in `clickbench-compare` job.
+        ./scripts/pytest test_runner/performance/ -v \
+          -m "remote_cluster" \
+          --sparse-ordering \
+          --out-dir perf-report-staging \
+          --timeout 5400 \
+          --ignore test_runner/performance/test_perf_olap.py
+
+    - name: Submit result
+      env:
         VIP_VAP_ACCESS_TOKEN: "${{ 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
@@ -116,16 +152,15 @@ jobs:
         # 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-reuse, neon-captest-prefetch, rds-postgres ]
+        platform: [ neon-captest-new, neon-captest-reuse, neon-captest-prefetch, rds-postgres ]
         db_size: [ 10gb ]
-        runner: [ us-east-2 ]
         include:
+          - platform: neon-captest-new
+            db_size: 50gb
           - 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"
@@ -137,9 +172,9 @@ 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: [ self-hosted, dev, x64 ]
     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
@@ -164,9 +199,8 @@ 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
@@ -197,11 +231,8 @@ 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 neondb SET enable_seqscan_prefetch=on"
+        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE neondb SET seqscan_prefetch_buffers=10"
       env:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
 
@@ -244,13 +275,6 @@ 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()
       uses: ./.github/actions/allure-report
@@ -258,6 +282,14 @@ jobs:
         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
@@ -294,9 +326,9 @@ jobs:
       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 ]
+    runs-on: [ self-hosted, dev, x64 ]
     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
@@ -342,15 +374,12 @@ 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 }}
 
-    - name: ClickBench benchmark
+    - name: Benchmark clickbench
       uses: ./.github/actions/run-python-test-set
       with:
         build_type: ${{ env.BUILD_TYPE }}
@@ -378,219 +407,3 @@ jobs:
         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: ${{ matrix.platform }}
-
-    runs-on: [ self-hosted, us-east-2, x64 ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
-
-    timeout-minutes: 360 # 6h
-
-    steps:
-    - uses: actions/checkout@v3
-
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ 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=${{ secrets.BENCHMARK_CAPTEST_TPCH_S10_CONNSTR }}
-            ;;
-          rds-aurora)
-            CONNSTR=${{ 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 }}
-
-  user-examples-compare:
-    if: success() || failure()
-    needs: [ tpch-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=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
-            ;;
-          rds-aurora)
-            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_AURORA_CONNSTR }}
-            ;;
-          rds-postgres)
-            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_POSTGRES_CONNSTR }}
-            ;;
-          *)
-            echo 2>&1 "Unknown PLATFORM=${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 user examples
-      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: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
-      env:
-        VIP_VAP_ACCESS_TOKEN: "${{ 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' }}
@@ -49,89 +45,6 @@ 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
-
-      # https://github.com/EmbarkStudios/cargo-deny
-      - name: Check rust licenses/bans/advisories/sources
-        if: ${{ !cancelled() }}
-        run: cargo deny check
-
   build-neon:
     runs-on: [ self-hosted, dev, x64 ]
     container:
@@ -166,10 +79,12 @@ jobs:
       - name: Set pg 14 revision for caching
         id: pg_v14_rev
         run: echo pg_rev=$(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.
       #
@@ -183,17 +98,19 @@ jobs:
       # corresponding Cargo.toml files for their descriptions.
       - name: Set env variables
         run: |
-          CARGO_FEATURES="--features testing"
           if [[ $BUILD_TYPE == "debug" ]]; then
             cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
-            CARGO_FLAGS="--locked $CARGO_FEATURES"
+            CARGO_FEATURES="--features testing"
+            CARGO_FLAGS="--locked --timings $CARGO_FEATURES"
           elif [[ $BUILD_TYPE == "release" ]]; then
             cov_prefix=""
-            CARGO_FLAGS="--locked --release $CARGO_FEATURES"
+            CARGO_FEATURES="--features testing,profiling"
+            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
@@ -210,8 +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
@@ -230,21 +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: |
@@ -285,9 +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
@@ -295,6 +219,17 @@ 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'
@@ -315,7 +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
@@ -349,7 +284,7 @@ jobs:
         uses: actions/checkout@v3
         with:
           submodules: true
-          fetch-depth: 1
+          fetch-depth: 2
 
       - name: Pytest benchmarks
         uses: ./.github/actions/run-python-test-set
@@ -370,7 +305,7 @@ jobs:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
     needs: [ regress-tests, benchmarks ]
-    if: ${{ !cancelled() }}
+    if: success() || failure()
     strategy:
       fail-fast: false
       matrix:
@@ -395,6 +330,7 @@ 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 ${REPORT_URL%/index.html}/data/suites.json
           ./scripts/pysync
@@ -427,7 +363,7 @@ jobs:
             !~/.cargo/registry/src
             ~/.cargo/git/
             target/
-          key: v1-${{ 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
@@ -443,6 +379,7 @@ 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: |
@@ -475,6 +412,7 @@ jobs:
               \"description\": \"Coverage report is ready\",
               \"target_url\": \"$REPORT_URL\"
             }"
+        shell: bash -euxo pipefail {0}
 
   trigger-e2e-tests:
     runs-on: [ self-hosted, dev, x64 ]
@@ -525,9 +463,6 @@ jobs:
     runs-on: [ self-hosted, dev, x64 ]
     needs: [ tag ]
     container: gcr.io/kaniko-project/executor:v1.9.0-debug
-    defaults:
-      run:
-        shell: sh -eu {0}
 
     steps:
       - name: Checkout
@@ -546,9 +481,6 @@ jobs:
     runs-on: [ self-hosted, dev, x64 ]
     needs: [ tag ]
     container: gcr.io/kaniko-project/executor:v1.9.0-debug
-    defaults:
-      run:
-        shell: sh -eu {0}
 
     steps:
       - name: Checkout
@@ -560,18 +492,10 @@ 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:
+  compute-node-image-v14:
     runs-on: [ self-hosted, dev, x64 ]
     container: gcr.io/kaniko-project/executor:v1.9.0-debug
     needs: [ tag ]
-    strategy:
-      fail-fast: false
-      matrix:
-        version: [ v14, v15 ]
-    defaults:
-      run:
-        shell: sh -eu {0}
-
     steps:
       - name: Checkout
         uses: actions/checkout@v1 # v3 won't work with kaniko
@@ -582,55 +506,28 @@ jobs:
       - name: Configure ECR login
         run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
-      - name: Kaniko build compute node with extensions
-        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=${{ github.sha }} --dockerfile Dockerfile.compute-node-${{ matrix.version }} --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+      - 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}}
 
-  vm-compute-node-image:
+  compute-node-image-v15:
     runs-on: [ self-hosted, dev, x64 ]
-    needs: [ tag, compute-node-image ]
-    strategy:
-      fail-fast: false
-      matrix:
-        version: [ v14, v15 ]
-    defaults:
-      run:
-        shell: sh -eu {0}
-    env:
-      VM_INFORMANT_VERSION: 0.1.1
-
+    container: gcr.io/kaniko-project/executor:v1.9.0-debug
+    needs: [ tag ]
     steps:
-      - name: Downloading latest vm-builder
-        run: |
-          curl -L https://github.com/neondatabase/neonvm/releases/latest/download/vm-builder -o vm-builder
-          chmod +x vm-builder
+      - name: Checkout
+        uses: actions/checkout@v1 # v3 won't work with kaniko
+        with:
+          submodules: true
+          fetch-depth: 0
 
-      - name: Pulling compute-node image
-        run: |
-          docker pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+      - name: Configure ECR login
+        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
-      - name: Downloading VM informant version ${{ env.VM_INFORMANT_VERSION }}
-        run: |
-          curl -fL https://github.com/neondatabase/autoscaling/releases/download/${{ env.VM_INFORMANT_VERSION }}/vm-informant -o vm-informant
-          chmod +x vm-informant
-
-      - name: Adding VM informant to compute-node image
-        run: |
-          ID=$(docker create 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}})
-          docker cp vm-informant $ID:/bin/vm-informant
-          docker commit $ID temp-vm-compute-node
-          docker rm -f $ID
-
-      - name: Build vm image
-        run: |
-          # note: as of 2023-01-12, vm-builder requires a trailing ":latest" for local images
-          ./vm-builder -src=temp-vm-compute-node:latest -dst=369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
-
-      - name: Pushing vm-compute-node image
-        run: |
-          docker push 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+      - name: Kaniko build compute node with extensions v15
+        run: /kaniko/executor --skip-unused-stages --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --build-arg GIT_VERSION=${{ 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, compute-tools-image ]
+    needs: [ tag, neon-image, compute-node-image-v14, compute-node-image-v15, compute-tools-image ]
     runs-on: [ self-hosted, dev, x64 ]
 
     steps:
@@ -674,13 +571,13 @@ jobs:
 
   promote-images:
     runs-on: [ self-hosted, dev, x64 ]
-    needs: [ tag, test-images, vm-compute-node-image ]
+    needs: [ tag, test-images ]
     if: github.event_name != 'workflow_dispatch'
     container: amazon/aws-cli
     strategy:
       fail-fast: false
       matrix:
-        name: [ neon, compute-node-v14, vm-compute-node-v14, compute-node-v15, vm-compute-node-v15, compute-tools]
+        name: [ neon, compute-node-v14, compute-node-v15, compute-tools ]
 
     steps:
       - name: Promote image to latest
@@ -713,15 +610,9 @@ jobs:
       - 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
 
-      - name: Pull vm compute node v14 image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} vm-compute-node-v14
-
       - name: Pull compute node v15 image from ECR
         run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} compute-node-v15
 
-      - name: Pull vm compute node v15 image from ECR
-        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} vm-compute-node-v15
-
       - name: Pull rust image from ECR
         run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned rust
 
@@ -733,9 +624,7 @@ jobs:
           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-v14:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:latest
-          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:latest
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:latest
-          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:latest
 
       - name: Configure Docker Hub login
         run: |
@@ -752,15 +641,9 @@ jobs:
       - name: Push compute node v14 image to Docker Hub
         run: crane push compute-node-v14 neondatabase/compute-node-v14:${{needs.tag.outputs.build-tag}}
 
-      - name: Push vm compute node v14 image to Docker Hub
-        run: crane push vm-compute-node-v14 neondatabase/vm-compute-node-v14:${{needs.tag.outputs.build-tag}}
-
       - name: Push compute node v15 image to Docker Hub
         run: crane push compute-node-v15 neondatabase/compute-node-v15:${{needs.tag.outputs.build-tag}}
 
-      - name: Push vm compute node v15 image to Docker Hub
-        run: crane push vm-compute-node-v15 neondatabase/vm-compute-node-v15:${{needs.tag.outputs.build-tag}}
-
       - name: Push rust image to Docker Hub
         run: crane push rust neondatabase/rust:pinned
 
@@ -772,36 +655,38 @@ jobs:
           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-v14:${{needs.tag.outputs.build-tag}} latest
-          crane tag neondatabase/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-node-v15:${{needs.tag.outputs.build-tag}} latest
-          crane tag neondatabase/vm-compute-node-v15:${{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 == 'release' &&
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
       github.event_name != 'workflow_dispatch'
     outputs:
       matrix-include: ${{ steps.set-matrix.outputs.include }}
     steps:
       - id: set-matrix
         run: |
-          if [[ "$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"}'
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            STAGING='{"env_name": "staging", "proxy_job": "neon-proxy", "proxy_config": "staging.proxy", "kubeconfig_secret": "STAGING_KUBECONFIG_DATA", "console_api_key_secret": "NEON_STAGING_API_KEY"}'
+            NEON_STRESS='{"env_name": "neon-stress", "proxy_job": "neon-stress-proxy", "proxy_config": "neon-stress.proxy", "kubeconfig_secret": "NEON_STRESS_KUBECONFIG_DATA", "console_api_key_secret": "NEON_CAPTEST_API_KEY"}'
+            echo "include=[$STAGING, $NEON_STRESS]" >> $GITHUB_OUTPUT
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            PRODUCTION='{"env_name": "production", "proxy_job": "neon-proxy", "proxy_config": "production.proxy", "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 'release'"
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
             exit 1
           fi
 
   deploy:
-    runs-on: [ self-hosted, dev, x64 ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible: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 ]
     if: |
-      github.ref_name == 'release' &&
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
       github.event_name != 'workflow_dispatch'
     defaults:
       run:
@@ -809,8 +694,6 @@ jobs:
     strategy:
       matrix:
         include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
-    environment:
-      name: prod-old
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -818,6 +701,16 @@ jobs:
           submodules: true
           fetch-depth: 0
 
+      - name: Setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Setup ansible
+        run: |
+          export PATH="/root/.local/bin:$PATH"
+          pip install --progress-bar off --user ansible boto3 toml
+
       - name: Redeploy
         run: |
           export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
@@ -838,8 +731,8 @@ jobs:
           chmod 0600 ssh-key
           ssh-add ssh-key
           rm -f ssh-key ssh-key-cert.pub
-          ANSIBLE_CONFIG=./ansible.cfg ansible-galaxy collection install sivel.toiletwater
-          ANSIBLE_CONFIG=./ansible.cfg 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-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] }}
           rm -f neon_install.tar.gz .neon_current_version
 
   deploy-new:
@@ -847,7 +740,7 @@ jobs:
     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 ]
+    needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
     if: |
       (github.ref_name == 'main') &&
       github.event_name != 'workflow_dispatch'
@@ -856,9 +749,7 @@ jobs:
         shell: bash
     strategy:
       matrix:
-        target_region: [ eu-west-1, us-east-2 ]
-    environment:
-      name: dev-${{ matrix.target_region }}
+        target_region: [ us-east-2 ]
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -879,7 +770,7 @@ jobs:
             exit 1
           fi
           ansible-galaxy collection install sivel.toiletwater
-          ansible-playbook deploy.yaml -i staging.${{ 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=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          ansible-playbook deploy.yaml -i staging.${{ 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-pr-test-new:
@@ -889,7 +780,7 @@ jobs:
     # 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') &&
+      contains(github.event.pull_request.labels.*.name, 'deploy-test-storage') && 
       github.event_name != 'workflow_dispatch'
     defaults:
       run:
@@ -912,7 +803,7 @@ jobs:
           ./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:
@@ -929,9 +820,7 @@ jobs:
         shell: bash
     strategy:
       matrix:
-        target_region: [ us-east-2, us-west-2, eu-central-1, ap-southeast-1 ]
-    environment:
-      name: prod-${{ matrix.target_region }}
+        target_region: [ us-east-2, eu-central-1, ap-southeast-1 ]
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -954,16 +843,16 @@ 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
+    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: |
-      github.ref_name == 'release' &&
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
       github.event_name != 'workflow_dispatch'
     defaults:
       run:
@@ -971,8 +860,6 @@ jobs:
     strategy:
       matrix:
         include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
-    environment:
-      name: prod-old
     env:
       KUBECONFIG: .kubeconfig
     steps:
@@ -998,51 +885,8 @@ jobs:
       - name: Re-deploy proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade ${{ matrix.proxy_job }}       neondatabase/neon-proxy --namespace neon-proxy --install --atomic -f .github/helm-values/${{ matrix.proxy_config }}.yaml       --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-          helm upgrade ${{ matrix.proxy_job }}-scram neondatabase/neon-proxy --namespace neon-proxy --install --atomic -f .github/helm-values/${{ matrix.proxy_config }}-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --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
-    # 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 == 'release' &&
-      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
-    environment:
-      name: prod-old
-    env:
-      KUBECONFIG: .kubeconfig
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-
-      - name: Add curl
-        run: apt update && apt install curl -y
-
-      - name: Store kubeconfig file
-        run: |
-          echo "${{ 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
+          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-proxy-new:
     runs-on: [ self-hosted, dev, x64 ]
@@ -1066,8 +910,6 @@ jobs:
             target_cluster: dev-eu-west-1-zeta
             deploy_link_proxy: false
             deploy_legacy_scram_proxy: false
-    environment:
-      name: dev-${{ matrix.target_region }}
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -1083,55 +925,19 @@ jobs:
       - name: Re-deploy scram proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -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
 
       - name: Re-deploy link proxy
         if: matrix.deploy_link_proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+          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} --wait --timeout 15m0s
 
       - name: Re-deploy legacy scram proxy
         if: matrix.deploy_legacy_scram_proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ 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
-    environment:
-      name: dev-${{ matrix.target_region }}
-    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  ${{ matrix.target_cluster }}
-
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ 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-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} --wait --timeout 15m0s
 
   deploy-proxy-prod-new:
     runs-on: prod
@@ -1149,14 +955,10 @@ 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
             target_cluster: prod-ap-southeast-1-epsilon
-    environment:
-      name: prod-${{ matrix.target_region }}
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -1172,47 +974,7 @@ jobs:
       - name: Re-deploy proxy
         run: |
           DOCKER_TAG=${{needs.tag.outputs.build-tag}}
-          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-
-  deploy-storage-broker-prod-new:
-    runs-on: prod
-    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
-    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
-    needs: [ push-docker-hub, tag, regress-tests ]
-    if: |
-      (github.ref_name == 'release') &&
-      github.event_name != 'workflow_dispatch'
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  us-east-2
-            target_cluster: prod-us-east-2-delta
-          - target_region:  us-west-2
-            target_cluster: prod-us-west-2-eta
-          - target_region: eu-central-1
-            target_cluster: prod-eu-central-1-gamma
-          - target_region: ap-southeast-1
-            target_cluster: prod-ap-southeast-1-epsilon
-    environment:
-      name: prod-${{ matrix.target_region }}
-    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  ${{ matrix.target_cluster }}
-
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ 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
 
   promote-compatibility-data:
     runs-on: [ self-hosted, dev, x64 ]
@@ -1223,6 +985,7 @@ 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

.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: ${{ matrix.os }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 2
+
+      - name: Check formatting
+        run: cargo fmt --all -- --check
+
+      - name: Install Ubuntu postgres dependencies
+        if: matrix.os == 'ubuntu-latest'
+        run: |
+          sudo apt update
+          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev protobuf-compiler
+
+      - name: Install macOS postgres dependencies
+        if: matrix.os == 'macos-latest'
+        run: brew install flex bison openssl protobuf
+
+      - name: Set pg 14 revision for caching
+        id: pg_v14_rev
+        run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
+        shell: bash -euxo pipefail {0}
+
+      - name: Set pg 15 revision for caching
+        id: pg_v15_rev
+        run: echo pg_rev=$(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-${{ hashFiles('./Cargo.lock') }}-rust
+
+      - name: Run cargo clippy
+        run: ./run_clippy.sh
+
+      - name: Ensure all project builds
+        run: cargo build --locked --all --all-targets
+
+  check-rust-dependencies:
+    runs-on: [ self-hosted, dev, x64 ]
+    container:
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      options: --init
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: false
+          fetch-depth: 1
+
+      # https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
+      - name: Check every project module is covered by Hakari
+        run: |
+          cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
+          cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack
+        shell: bash -euxo pipefail {0}
+
+  check-codestyle-python:
+    runs-on: [ self-hosted, Linux, k8s-runner ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: false
+          fetch-depth: 1
+
+      - name: Cache poetry deps
+        id: cache_poetry
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pypoetry/virtualenvs
+          key: v1-codestyle-python-deps-${{ 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 }}
 

Cargo.toml

@@ -1,3 +1,14 @@
+# 'named-profiles' feature was stabilized in cargo 1.57. This line makes the
+# build work with older cargo versions.
+#
+# We have this because as of this writing, the latest cargo Debian package
+# that's available is 1.56. (Confusingly, the Debian package version number
+# is 0.57, whereas 'cargo --version' says 1.56.)
+#
+# See https://tracker.debian.org/pkg/cargo for the current status of the
+# package. When that gets updated, we can remove this.
+cargo-features = ["named-profiles"]
+
 [workspace]
 members = [
     "compute_tools",
@@ -10,140 +21,6 @@ members = [
     "libs/*",
 ]
 
-[workspace.package]
-edition = "2021"
-license = "Apache-2.0"
-
-## All dependency versions, used in the project
-[workspace.dependencies]
-anyhow = { version = "1.0", features = ["backtrace"] }
-async-stream = "0.3"
-async-trait = "0.1"
-atty = "0.2.14"
-aws-config = { version = "0.51.0", default-features = false, features=["rustls"] }
-aws-sdk-s3 = "0.21.0"
-aws-smithy-http = "0.51.0"
-aws-types = "0.51.0"
-base64 = "0.13.0"
-bincode = "1.3"
-bindgen = "0.61"
-bstr = "1.0"
-byteorder = "1.4"
-bytes = "1.0"
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
-clap = "4.0"
-close_fds = "0.3.2"
-comfy-table = "6.1"
-const_format = "0.2"
-crc32c = "0.6"
-crossbeam-utils = "0.8.5"
-fail = "0.5.0"
-fs2 = "0.4.3"
-futures = "0.3"
-futures-core = "0.3"
-futures-util = "0.3"
-git-version = "0.3"
-hashbrown = "0.13"
-hex = "0.4"
-hex-literal = "0.3"
-hmac = "0.12.1"
-hostname = "0.3.1"
-humantime = "2.1"
-humantime-serde = "1.1.1"
-hyper = "0.14"
-hyper-tungstenite = "0.9"
-itertools = "0.10"
-jsonwebtoken = "8"
-libc = "0.2"
-md5 = "0.7.0"
-memoffset = "0.8"
-nix = "0.26"
-notify = "5.0.0"
-num-traits = "0.2.15"
-once_cell = "1.13"
-parking_lot = "0.12"
-pin-project-lite = "0.2"
-prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency
-prost = "0.11"
-rand = "0.8"
-regex = "1.4"
-reqwest = { version = "0.11", default-features = false, features = ["rustls-tls"] }
-routerify = "3"
-rpds = "0.12.0"
-rustls = "0.20"
-rustls-pemfile = "1"
-rustls-split = "0.3"
-scopeguard = "1.1"
-sentry = { version = "0.29", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
-serde = { version = "1.0", features = ["derive"] }
-serde_json = "1"
-serde_with = "2.0"
-sha2 = "0.10.2"
-signal-hook = "0.3"
-socket2 = "0.4.4"
-strum = "0.24"
-strum_macros = "0.24"
-svg_fmt = "0.4.1"
-tar = "0.4"
-thiserror = "1.0"
-tls-listener = { version = "0.6", features = ["rustls", "hyper-h1"] }
-tokio = { version = "1.17", features = ["macros"] }
-tokio-postgres-rustls = "0.9.0"
-tokio-rustls = "0.23"
-tokio-stream = "0.1"
-tokio-util = { version = "0.7", features = ["io"] }
-toml = "0.5"
-toml_edit = { version = "0.17", features = ["easy"] }
-tonic = {version = "0.8", features = ["tls", "tls-roots"]}
-tracing = "0.1"
-tracing-subscriber = { version = "0.3", features = ["env-filter"] }
-url = "2.2"
-uuid = { version = "1.2", features = ["v4", "serde"] }
-walkdir = "2.3.2"
-webpki-roots = "0.22.5"
-x509-parser = "0.14"
-
-## TODO replace this with tracing
-env_logger = "0.10"
-log = "0.4"
-
-## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-tokio-tar = { git = "https://github.com/neondatabase/tokio-tar.git", rev="404df61437de0feef49ba2ccdbdd94eb8ad6e142" }
-
-## Local libraries
-consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
-metrics = { version = "0.1", path = "./libs/metrics/" }
-pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
-postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
-postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
-pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
-remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
-safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
-storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
-tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
-utils = { version = "0.1", path = "./libs/utils/" }
-
-## Common library dependency
-workspace_hack = { version = "0.1", path = "./workspace_hack/" }
-
-## Build dependencies
-criterion = "0.4"
-rcgen = "0.10"
-rstest = "0.16"
-tempfile = "3.2"
-tonic-build = "0.8"
-
-# This is only needed for proxy's tests.
-# TODO: we should probably fork `tokio-postgres-rustls` instead.
-[patch.crates-io]
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-
-################# Binary contents sections
-
 [profile.release]
 # This is useful for profiling and, to some extent, debug.
 # Besides, debug info should not affect the performance.
@@ -204,3 +81,9 @@ inherits = "release"
 debug = false # true = 2 = all symbols, 1 = line only
 opt-level = "z"
 lto = true
+
+
+# This is only needed for proxy's tests.
+# TODO: we should probably fork `tokio-postgres-rustls` instead.
+[patch.crates-io]
+tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }

Dockerfile

@@ -79,7 +79,7 @@ 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

@@ -29,13 +29,7 @@ RUN cd postgres && \
     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 && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install && \
-    # Enable some of contrib extensions
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/bloom.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
 
 #########################################################################################
 #
@@ -61,9 +55,7 @@ RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
 
 #########################################################################################
 #
@@ -178,6 +170,9 @@ RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgto
 # Remove headers that we won't need anymore - we've completed installation of all extensions
 RUN rm -r /usr/local/pgsql/include
 
+# Remove now-useless PGXS src infrastructure
+RUN rm -r /usr/local/pgsql/lib/pgxs/src
+
 # Remove static postgresql libraries - all compilation is finished, so we
 # can now remove these files - they must be included in other binaries by now
 # if they were to be used by other libraries.
@@ -212,8 +207,7 @@ RUN apt update &&  \
         libgeos-c1v5 \
         libgdal28 \
         libproj19 \
-        libprotobuf-c1 \
-        gdb && \
+        libprotobuf-c1 && \
     rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
 USER postgres

Dockerfile.compute-node-v15

@@ -29,13 +29,7 @@ RUN cd postgres && \
     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 && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install && \
-    # Enable some of contrib extensions
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/bloom.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
 
 #########################################################################################
 #
@@ -61,9 +55,7 @@ RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
 
 #########################################################################################
 #
@@ -178,6 +170,9 @@ RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgto
 # Remove headers that we won't need anymore - we've completed installation of all extensions
 RUN rm -r /usr/local/pgsql/include
 
+# Remove now-useless PGXS src infrastructure
+RUN rm -r /usr/local/pgsql/lib/pgxs/src
+
 # Remove static postgresql libraries - all compilation is finished, so we
 # can now remove these files - they must be included in other binaries by now
 # if they were to be used by other libraries.
@@ -212,8 +207,7 @@ RUN apt update &&  \
         libgeos-c1v5 \
         libgdal28 \
         libproj19 \
-        libprotobuf-c1 \
-        gdb && \
+        libprotobuf-c1 && \
     rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
 USER postgres

Makefile

@@ -61,115 +61,146 @@ all: neon postgres neon-pg-ext
 #
 # The 'postgres_ffi' depends on the Postgres headers.
 .PHONY: neon
-neon: postgres-headers
+neon: postgres-v14-headers postgres-v15-headers
 	+@echo "Compiling Neon"
 	$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
 
 ### PostgreSQL parts
-# Some rules are duplicated for Postgres v14 and 15. We may want to refactor
+# The rules are duplicated for Postgres v14 and 15. We may want to refactor
 # to avoid the duplication in the future, but it's tolerable for now.
 #
-$(POSTGRES_INSTALL_DIR)/build/%/config.status:
-	+@echo "Configuring Postgres $* build"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/$*
-	(cd $(POSTGRES_INSTALL_DIR)/build/$* && \
-	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$*/configure \
+$(POSTGRES_INSTALL_DIR)/build/v14/config.status:
+	+@echo "Configuring Postgres v14 build"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/v14
+	(cd $(POSTGRES_INSTALL_DIR)/build/v14 && \
+	env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-v14/configure \
 		CFLAGS='$(PG_CFLAGS)' \
 		$(PG_CONFIGURE_OPTS) \
-		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/$* > configure.log)
+		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/v14 > configure.log)
+
+$(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)' \
+		$(PG_CONFIGURE_OPTS) \
+		--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/v15 > configure.log)
 
 # nicer alias to run 'configure'
-# Note: I've been unable to use templates for this part of our configuration.
-# I'm not sure why it wouldn't work, but this is the only place (apart from
-# the "build-all-versions" entry points) where direct mention of PostgreSQL
-# versions is used.
-.PHONY: postgres-configure-v15
-postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
-.PHONY: postgres-configure-v14
-postgres-configure-v14: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
+.PHONY: postgres-v14-configure
+postgres-v14-configure: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
+
+.PHONY: postgres-v15-configure
+postgres-v15-configure: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
 
 # Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
-.PHONY: postgres-headers-%
-postgres-headers-%: postgres-configure-%
-	+@echo "Installing PostgreSQL $* headers"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/include MAKELEVEL=0 install
+.PHONY: postgres-v14-headers
+postgres-v14-headers: postgres-v14-configure
+	+@echo "Installing PostgreSQL v14 headers"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/include MAKELEVEL=0 install
+
+.PHONY: postgres-v15-headers
+postgres-v15-headers: postgres-v15-configure
+	+@echo "Installing PostgreSQL v15 headers"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/src/include MAKELEVEL=0 install
 
 # Compile and install PostgreSQL
-.PHONY: postgres-%
-postgres-%: postgres-configure-% \
-		  postgres-headers-% # to prevent `make install` conflicts with neon's `postgres-headers`
-	+@echo "Compiling PostgreSQL $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 install
-	+@echo "Compiling libpq $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq install
-	+@echo "Compiling pg_prewarm $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_prewarm install
-	+@echo "Compiling pg_buffercache $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache install
-	+@echo "Compiling pageinspect $*"
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect install
+.PHONY: postgres-v14
+postgres-v14: postgres-v14-configure \
+		  postgres-v14-headers # to prevent `make install` conflicts with neon's `postgres-headers`
+	+@echo "Compiling PostgreSQL v14"
+	$(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"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pageinspect install
 
-.PHONY: postgres-clean-%
-postgres-clean-%:
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
-
-.PHONY: neon-pg-ext-%
-neon-pg-ext-%: postgres-%
-	+@echo "Compiling neon $*"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
-	+@echo "Compiling neon_walredo $*"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
-	+@echo "Compiling neon_test_utils $*"
-	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
-	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-		-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-		-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
-
-.PHONY: neon-pg-ext-clean-%
-neon-pg-ext-clean-%:
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon_walredo-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
-	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon_test_utils-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
-
-.PHONY: neon-pg-ext
-neon-pg-ext: \
-	neon-pg-ext-v14 \
-	neon-pg-ext-v15
-
-.PHONY: neon-pg-ext-clean
-neon-pg-ext-clean: \
-	neon-pg-ext-clean-v14 \
-	neon-pg-ext-clean-v15
+.PHONY: postgres-v15
+postgres-v15: postgres-v15-configure \
+		  postgres-v15-headers # to prevent `make install` conflicts with neon's `postgres-headers`
+	+@echo "Compiling PostgreSQL v15"
+	$(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"
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pageinspect install
 
 # shorthand to build all Postgres versions
-.PHONY: postgres
-postgres: \
-	postgres-v14 \
-	postgres-v15
+postgres: postgres-v14 postgres-v15
 
-.PHONY: postgres-headers
-postgres-headers: \
-	postgres-headers-v14 \
-	postgres-headers-v15
+.PHONY: postgres-v14-clean
+postgres-v14-clean:
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14 MAKELEVEL=0 clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pg_buffercache clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/contrib/pageinspect clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v14/src/interfaces/libpq clean
 
-.PHONY: postgres-clean
-postgres-clean: \
-	postgres-clean-v14 \
-	postgres-clean-v15
+.PHONY: postgres-v15-clean
+postgres-v15-clean:
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15 MAKELEVEL=0 clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pg_buffercache clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/contrib/pageinspect clean
+	$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/v15/src/interfaces/libpq clean
+
+neon-pg-ext-v14: postgres-v14
+	+@echo "Compiling neon v14"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-v14
+	(cd $(POSTGRES_INSTALL_DIR)/build/neon-v14 && \
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v14/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install)
+	+@echo "Compiling neon_walredo v14"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v14
+	(cd $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v14 && \
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v14/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install)
+	+@echo "Compiling neon_test_utils" v14
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v14
+	(cd $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v14 && \
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v14/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install)
+
+neon-pg-ext-v15: postgres-v15
+	+@echo "Compiling neon v15"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-v15
+	(cd $(POSTGRES_INSTALL_DIR)/build/neon-v15 && \
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v15/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install)
+	+@echo "Compiling neon_walredo v15"
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v15
+	(cd $(POSTGRES_INSTALL_DIR)/build/neon-walredo-v15 && \
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v15/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install)
+	+@echo "Compiling neon_test_utils" v15
+	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v15
+	(cd $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-v15 && \
+	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v15/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
+		-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install)
+
+.PHONY: neon-pg-ext-clean
+	$(MAKE) -C $(ROOT_PROJECT_DIR)/pgxn/neon clean
+	$(MAKE) -C $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils clean
+
+neon-pg-ext: neon-pg-ext-v14 neon-pg-ext-v15
+postgres-headers: postgres-v14-headers postgres-v15-headers
+postgres-clean: postgres-v14-clean postgres-v15-clean
 
 # This doesn't remove the effects of 'configure'.
 .PHONY: clean
-clean: postgres-clean neon-pg-ext-clean
+clean:
+	cd $(POSTGRES_INSTALL_DIR)/build/v14 && $(MAKE) clean
+	cd $(POSTGRES_INSTALL_DIR)/build/v15 && $(MAKE) clean
 	$(CARGO_CMD_PREFIX) cargo clean
+	cd pgxn/neon && $(MAKE) clean
+	cd pgxn/neon_test_utils && $(MAKE) clean
 
 # This removes everything
 .PHONY: distclean

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
 
@@ -26,13 +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 protobuf-compiler
 ```
 * 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 \
-  protobuf-devel
+  libseccomp-devel perl clang cmake etcd postgresql postgresql-contrib protobuf-compiler
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -45,7 +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 flex bison
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -118,21 +126,18 @@ Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (r
 # 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
 
-# start pageserver, safekeeper, and broker for their intercommunication
+# start pageserver and safekeeper
 > ./target/debug/neon_local start
-Starting neon broker at 127.0.0.1:50051
-storage_broker started, pid: 2918372
+Starting etcd broker using "/usr/bin/etcd"
+etcd started, pid: 2545996
 Starting pageserver at '127.0.0.1:64000' in '.neon'.
-pageserver started, pid: 2918386
+pageserver started, pid: 2546005
 Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'.
-safekeeper 1 started, pid: 2918437
-
-# create initial tenant and use it as a default for every future neon_local invocation
-> ./target/debug/neon_local tenant create --set-default
-tenant 9ef87a5bf0d92544f6fafeeb3239695c successfully created on the pageserver
-Created an initial timeline 'de200bd42b49cc1814412c7e592dd6e9' at Lsn 0/16B5A50 for tenant: 9ef87a5bf0d92544f6fafeeb3239695c
-Setting tenant 9ef87a5bf0d92544f6fafeeb3239695c as a default one
+safekeeper 1 started, pid: 2546041
 
 # start postgres compute node
 > ./target/debug/neon_local pg start main
@@ -224,20 +229,12 @@ 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.

compute_tools/Cargo.toml

@@ -1,25 +1,23 @@
 [package]
 name = "compute_tools"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-anyhow.workspace = true
-chrono.workspace = true
-clap.workspace = true
-futures.workspace = true
-hyper = { workspace = true, features = ["full"] }
-notify.workspace = true
-postgres.workspace = true
-regex.workspace = true
-serde.workspace = true
-serde_json.workspace = true
-tar.workspace = true
-tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
-tokio-postgres.workspace = true
-tracing.workspace = true
-tracing-subscriber.workspace = true
-url.workspace = true
-
-workspace_hack.workspace = true
+anyhow = "1.0"
+chrono = "0.4"
+clap = "4.0"
+env_logger = "0.9"
+futures = "0.3.13"
+hyper = { version = "0.14", features = ["full"] }
+log = { version = "0.4", features = ["std", "serde"] }
+notify = "5.0.0"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+regex = "1"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1"
+tar = "0.4"
+tokio = { version = "1.17", features = ["macros", "rt", "rt-multi-thread"] }
+tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+url = "2.2.2"
+workspace_hack = { version = "0.1", path = "../workspace_hack" }

compute_tools/README.md

@@ -19,10 +19,6 @@ Also `compute_ctl` spawns two separate service threads:
 - `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
   last activity requests.
 
-If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
-compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
-downscaling and (eventually) will request immediate upscaling under resource pressure.
-
 Usage example:
 ```sh
 compute_ctl -D /var/db/postgres/compute \

compute_tools/src/bin/compute_ctl.rs

@@ -18,10 +18,6 @@
 //! - `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
 //!   last activity requests.
 //!
-//! If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
-//! compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
-//! downscaling and (eventually) will request immediate upscaling under resource pressure.
-//!
 //! Usage example:
 //! ```sh
 //! compute_ctl -D /var/db/postgres/compute \
@@ -40,11 +36,10 @@ use std::{thread, time::Duration};
 use anyhow::{Context, Result};
 use chrono::Utc;
 use clap::Arg;
-use tracing::{error, info};
+use log::{error, info};
 
 use compute_tools::compute::{ComputeMetrics, ComputeNode, ComputeState, ComputeStatus};
 use compute_tools::http::api::launch_http_server;
-use compute_tools::informant::spawn_vm_informant_if_present;
 use compute_tools::logger::*;
 use compute_tools::monitor::launch_monitor;
 use compute_tools::params::*;
@@ -53,6 +48,7 @@ use compute_tools::spec::*;
 use url::Url;
 
 fn main() -> Result<()> {
+    // TODO: re-use `utils::logging` later
     init_logger(DEFAULT_LOG_LEVEL)?;
 
     let matches = cli().get_matches();
@@ -109,7 +105,7 @@ fn main() -> Result<()> {
         tenant,
         timeline,
         pageserver_connstr,
-        metrics: ComputeMetrics::default(),
+        metrics: ComputeMetrics::new(),
         state: RwLock::new(ComputeState::new()),
     };
     let compute = Arc::new(compute_state);
@@ -118,48 +114,30 @@ fn main() -> Result<()> {
     // requests, while configuration is still in progress.
     let _http_handle = launch_http_server(&compute).expect("cannot launch http endpoint thread");
     let _monitor_handle = launch_monitor(&compute).expect("cannot launch compute monitor thread");
-    // Also spawn the thread responsible for handling the VM informant -- if it's present
-    let _vm_informant_handle = spawn_vm_informant_if_present().expect("cannot launch VM informant");
 
-    // Start Postgres
-    let mut delay_exit = false;
-    let mut exit_code = None;
-    let pg = match compute.start_compute() {
-        Ok(pg) => Some(pg),
-        Err(err) => {
-            error!("could not start the compute node: {:?}", err);
+    // Run compute (Postgres) and hang waiting on it.
+    match compute.prepare_and_run() {
+        Ok(ec) => {
+            let code = ec.code().unwrap_or(1);
+            info!("Postgres exited with code {}, shutting down", code);
+            exit(code)
+        }
+        Err(error) => {
+            error!("could not start the compute node: {:?}", error);
+
             let mut state = compute.state.write().unwrap();
-            state.error = Some(format!("{:?}", err));
+            state.error = Some(format!("{:?}", error));
             state.status = ComputeStatus::Failed;
             drop(state);
-            delay_exit = true;
-            None
+
+            // Keep serving HTTP requests, so the cloud control plane was able to
+            // get the actual error.
+            info!("giving control plane 30s to collect the error before shutdown");
+            thread::sleep(Duration::from_secs(30));
+            info!("shutting down");
+            Err(error)
         }
-    };
-
-    // Wait for the child Postgres process forever. In this state Ctrl+C will
-    // propagate to Postgres and it will be shut down as well.
-    if let Some(mut pg) = pg {
-        let ecode = pg
-            .wait()
-            .expect("failed to start waiting on Postgres process");
-        info!("Postgres exited with code {}, shutting down", ecode);
-        exit_code = ecode.code()
     }
-
-    if let Err(err) = compute.check_for_core_dumps() {
-        error!("error while checking for core dumps: {err:?}");
-    }
-
-    // If launch failed, keep serving HTTP requests for a while, so the cloud
-    // control plane can get the actual error.
-    if delay_exit {
-        info!("giving control plane 30s to collect the error before shutdown");
-        thread::sleep(Duration::from_secs(30));
-        info!("shutting down");
-    }
-
-    exit(exit_code.unwrap_or(1))
 }
 
 fn cli() -> clap::Command {

compute_tools/src/checker.rs

@@ -1,12 +1,11 @@
 use anyhow::{anyhow, Result};
+use log::error;
 use postgres::Client;
 use tokio_postgres::NoTls;
-use tracing::{error, instrument};
 
 use crate::compute::ComputeNode;
 
-#[instrument(skip_all)]
-pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
+pub fn create_writablity_check_data(client: &mut Client) -> Result<()> {
     let query = "
     CREATE TABLE IF NOT EXISTS health_check (
         id serial primary key,
@@ -22,7 +21,6 @@ pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
     Ok(())
 }
 
-#[instrument(skip_all)]
 pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
     let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
     if client.is_closed() {

compute_tools/src/compute.rs

@@ -17,17 +17,17 @@
 use std::fs;
 use std::os::unix::fs::PermissionsExt;
 use std::path::Path;
-use std::process::{Command, Stdio};
+use std::process::{Command, ExitStatus, Stdio};
 use std::sync::atomic::{AtomicU64, Ordering};
 use std::sync::RwLock;
 
 use anyhow::{Context, Result};
 use chrono::{DateTime, Utc};
+use log::info;
 use postgres::{Client, NoTls};
 use serde::{Serialize, Serializer};
-use tracing::{info, instrument, warn};
 
-use crate::checker::create_writability_check_data;
+use crate::checker::create_writablity_check_data;
 use crate::config;
 use crate::pg_helpers::*;
 use crate::spec::*;
@@ -91,7 +91,7 @@ pub enum ComputeStatus {
     Failed,
 }
 
-#[derive(Default, Serialize)]
+#[derive(Serialize)]
 pub struct ComputeMetrics {
     pub sync_safekeepers_ms: AtomicU64,
     pub basebackup_ms: AtomicU64,
@@ -99,6 +99,23 @@ pub struct ComputeMetrics {
     pub total_startup_ms: AtomicU64,
 }
 
+impl ComputeMetrics {
+    pub fn new() -> Self {
+        Self {
+            sync_safekeepers_ms: AtomicU64::new(0),
+            basebackup_ms: AtomicU64::new(0),
+            config_ms: AtomicU64::new(0),
+            total_startup_ms: AtomicU64::new(0),
+        }
+    }
+}
+
+impl Default for ComputeMetrics {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl ComputeNode {
     pub fn set_status(&self, status: ComputeStatus) {
         self.state.write().unwrap().status = status;
@@ -121,7 +138,6 @@ impl ComputeNode {
 
     // Get basebackup from the libpq connection to pageserver using `connstr` and
     // unarchive it to `pgdata` directory overriding all its previous content.
-    #[instrument(skip(self))]
     fn get_basebackup(&self, lsn: &str) -> Result<()> {
         let start_time = Utc::now();
 
@@ -155,12 +171,11 @@ impl ComputeNode {
 
     // Run `postgres` in a special mode with `--sync-safekeepers` argument
     // and return the reported LSN back to the caller.
-    #[instrument(skip(self))]
     fn sync_safekeepers(&self) -> Result<String> {
         let start_time = Utc::now();
 
         let sync_handle = Command::new(&self.pgbin)
-            .args(["--sync-safekeepers"])
+            .args(&["--sync-safekeepers"])
             .env("PGDATA", &self.pgdata) // we cannot use -D in this mode
             .stdout(Stdio::piped())
             .spawn()
@@ -198,7 +213,6 @@ impl ComputeNode {
 
     /// Do all the preparations like PGDATA directory creation, configuration,
     /// safekeepers sync, basebackup, etc.
-    #[instrument(skip(self))]
     pub fn prepare_pgdata(&self) -> Result<()> {
         let spec = &self.spec;
         let pgdata_path = Path::new(&self.pgdata);
@@ -232,27 +246,23 @@ impl ComputeNode {
 
     /// Start Postgres as a child process and manage DBs/roles.
     /// After that this will hang waiting on the postmaster process to exit.
-    #[instrument(skip(self))]
-    pub fn start_postgres(&self) -> Result<std::process::Child> {
+    pub fn run(&self) -> Result<ExitStatus> {
+        let start_time = Utc::now();
+
         let pgdata_path = Path::new(&self.pgdata);
 
         // Run postgres as a child process.
         let mut pg = Command::new(&self.pgbin)
-            .args(["-D", &self.pgdata])
+            .args(&["-D", &self.pgdata])
             .spawn()
             .expect("cannot start postgres process");
 
         wait_for_postgres(&mut pg, pgdata_path)?;
 
-        Ok(pg)
-    }
-
-    #[instrument(skip(self))]
-    pub fn apply_config(&self) -> Result<()> {
         // If connection fails,
         // it may be the old node with `zenith_admin` superuser.
         //
-        // In this case we need to connect with old `zenith_admin` name
+        // In this case we need to connect with old `zenith_admin`name
         // and create new user. We cannot simply rename connected user,
         // but we can create a new one and grant it all privileges.
         let mut client = match Client::connect(self.connstr.as_str(), NoTls) {
@@ -278,43 +288,16 @@ impl ComputeNode {
             Ok(client) => client,
         };
 
-        // Proceed with post-startup configuration. Note, that order of operations is important.
         handle_roles(&self.spec, &mut client)?;
         handle_databases(&self.spec, &mut client)?;
         handle_role_deletions(self, &mut client)?;
         handle_grants(self, &mut client)?;
-        create_writability_check_data(&mut client)?;
+        create_writablity_check_data(&mut client)?;
 
         // 'Close' connection
         drop(client);
-
-        info!(
-            "finished configuration of compute for project {}",
-            self.spec.cluster.cluster_id
-        );
-
-        Ok(())
-    }
-
-    #[instrument(skip(self))]
-    pub fn start_compute(&self) -> Result<std::process::Child> {
-        info!(
-            "starting compute for project {}, operation {}, tenant {}, timeline {}",
-            self.spec.cluster.cluster_id,
-            self.spec.operation_uuid.as_ref().unwrap(),
-            self.tenant,
-            self.timeline,
-        );
-
-        self.prepare_pgdata()?;
-
-        let start_time = Utc::now();
-
-        let pg = self.start_postgres()?;
-
-        self.apply_config()?;
-
         let startup_end_time = Utc::now();
+
         self.metrics.config_ms.store(
             startup_end_time
                 .signed_duration_since(start_time)
@@ -334,70 +317,30 @@ impl ComputeNode {
 
         self.set_status(ComputeStatus::Running);
 
-        Ok(pg)
+        info!(
+            "finished configuration of compute for project {}",
+            self.spec.cluster.cluster_id
+        );
+
+        // Wait for child Postgres process basically forever. In this state Ctrl+C
+        // will propagate to Postgres and it will be shut down as well.
+        let ecode = pg
+            .wait()
+            .expect("failed to start waiting on Postgres process");
+
+        Ok(ecode)
     }
 
-    // Look for core dumps and collect backtraces.
-    //
-    // EKS worker nodes have following core dump settings:
-    //   /proc/sys/kernel/core_pattern -> core
-    //   /proc/sys/kernel/core_uses_pid -> 1
-    //   ulimint -c -> unlimited
-    // which results in core dumps being written to postgres data directory as core.<pid>.
-    //
-    // Use that as a default location and pattern, except macos where core dumps are written
-    // to /cores/ directory by default.
-    pub fn check_for_core_dumps(&self) -> Result<()> {
-        let core_dump_dir = match std::env::consts::OS {
-            "macos" => Path::new("/cores/"),
-            _ => Path::new(&self.pgdata),
-        };
+    pub fn prepare_and_run(&self) -> Result<ExitStatus> {
+        info!(
+            "starting compute for project {}, operation {}, tenant {}, timeline {}",
+            self.spec.cluster.cluster_id,
+            self.spec.operation_uuid.as_ref().unwrap(),
+            self.tenant,
+            self.timeline,
+        );
 
-        // Collect core dump paths if any
-        info!("checking for core dumps in {}", core_dump_dir.display());
-        let files = fs::read_dir(core_dump_dir)?;
-        let cores = files.filter_map(|entry| {
-            let entry = entry.ok()?;
-            let _ = entry.file_name().to_str()?.strip_prefix("core.")?;
-            Some(entry.path())
-        });
-
-        // Print backtrace for each core dump
-        for core_path in cores {
-            warn!(
-                "core dump found: {}, collecting backtrace",
-                core_path.display()
-            );
-
-            // Try first with gdb
-            let backtrace = Command::new("gdb")
-                .args(["--batch", "-q", "-ex", "bt", &self.pgbin])
-                .arg(&core_path)
-                .output();
-
-            // Try lldb if no gdb is found -- that is handy for local testing on macOS
-            let backtrace = match backtrace {
-                Err(ref e) if e.kind() == std::io::ErrorKind::NotFound => {
-                    warn!("cannot find gdb, trying lldb");
-                    Command::new("lldb")
-                        .arg("-c")
-                        .arg(&core_path)
-                        .args(["--batch", "-o", "bt all", "-o", "quit"])
-                        .output()
-                }
-                _ => backtrace,
-            }?;
-
-            warn!(
-                "core dump backtrace: {}",
-                String::from_utf8_lossy(&backtrace.stdout)
-            );
-            warn!(
-                "debugger stderr: {}",
-                String::from_utf8_lossy(&backtrace.stderr)
-            );
-        }
-
-        Ok(())
+        self.prepare_pgdata()?;
+        self.run()
     }
 }

compute_tools/src/http/api.rs

@@ -6,14 +6,32 @@ use std::thread;
 use anyhow::Result;
 use hyper::service::{make_service_fn, service_fn};
 use hyper::{Body, Method, Request, Response, Server, StatusCode};
+use log::{error, info};
 use serde_json;
-use tracing::{error, info};
 
-use crate::compute::ComputeNode;
+use crate::compute::{ComputeNode, ComputeStatus};
 
 // Service function to handle all available routes.
 async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body> {
     match (req.method(), req.uri().path()) {
+        // Timestamp of the last Postgres activity in the plain text.
+        // DEPRECATED in favour of /status
+        (&Method::GET, "/last_activity") => {
+            info!("serving /last_active GET request");
+            let state = compute.state.read().unwrap();
+
+            // Use RFC3339 format for consistency.
+            Response::new(Body::from(state.last_active.to_rfc3339()))
+        }
+
+        // Has compute setup process finished? -> true/false.
+        // DEPRECATED in favour of /status
+        (&Method::GET, "/ready") => {
+            info!("serving /ready GET request");
+            let status = compute.get_status();
+            Response::new(Body::from(format!("{}", status == ComputeStatus::Running)))
+        }
+
         // Serialized compute state.
         (&Method::GET, "/status") => {
             info!("serving /status GET request");
@@ -28,6 +46,16 @@ async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body>
             Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
         }
 
+        // DEPRECATED, use POST instead
+        (&Method::GET, "/check_writability") => {
+            info!("serving /check_writability GET request");
+            let res = crate::checker::check_writability(&compute).await;
+            match res {
+                Ok(_) => Response::new(Body::from("true")),
+                Err(e) => Response::new(Body::from(e.to_string())),
+            }
+        }
+
         (&Method::POST, "/check_writability") => {
             info!("serving /check_writability POST request");
             let res = crate::checker::check_writability(&compute).await;

compute_tools/src/http/openapi_spec.yaml

@@ -37,7 +37,58 @@ paths:
               schema:
                 $ref: "#/components/schemas/ComputeMetrics"
 
+  /ready:
+    get:
+      deprecated: true
+      tags:
+      - "info"
+      summary: Check whether compute startup process finished successfully
+      description: ""
+      operationId: computeIsReady
+      responses:
+        "200":
+          description: Compute is ready ('true') or not ('false')
+          content:
+            text/plain:
+              schema:
+                type: string
+                example: "true"
+
+  /last_activity:
+    get:
+      deprecated: true
+      tags:
+      - "info"
+      summary: Get timestamp of the last compute activity
+      description: ""
+      operationId: getLastComputeActivityTS
+      responses:
+        "200":
+          description: Timestamp of the last compute activity
+          content:
+            text/plain:
+              schema:
+                type: string
+                example: "2022-10-12T07:20:50.52Z"
+
   /check_writability:
+    get:
+      deprecated: true
+      tags:
+      - "check"
+      summary: Check that we can write new data on this compute
+      description: ""
+      operationId: checkComputeWritabilityDeprecated
+      responses:
+        "200":
+          description: Check result
+          content:
+            text/plain:
+              schema:
+                type: string
+                description: Error text or 'true' if check passed
+                example: "true"
+
     post:
       tags:
       - "check"

compute_tools/src/informant.rs

@@ -1,50 +0,0 @@
-use std::path::Path;
-use std::process;
-use std::thread;
-use std::time::Duration;
-use tracing::{info, warn};
-
-use anyhow::{Context, Result};
-
-const VM_INFORMANT_PATH: &str = "/bin/vm-informant";
-const RESTART_INFORMANT_AFTER_MILLIS: u64 = 5000;
-
-/// Launch a thread to start the VM informant if it's present (and restart, on failure)
-pub fn spawn_vm_informant_if_present() -> Result<Option<thread::JoinHandle<()>>> {
-    let exists = Path::new(VM_INFORMANT_PATH)
-        .try_exists()
-        .context("could not check if path exists")?;
-
-    if !exists {
-        return Ok(None);
-    }
-
-    Ok(Some(
-        thread::Builder::new()
-            .name("run-vm-informant".into())
-            .spawn(move || run_informant())?,
-    ))
-}
-
-fn run_informant() -> ! {
-    let restart_wait = Duration::from_millis(RESTART_INFORMANT_AFTER_MILLIS);
-
-    info!("starting VM informant");
-
-    loop {
-        let mut cmd = process::Command::new(VM_INFORMANT_PATH);
-        // Block on subprocess:
-        let result = cmd.status();
-
-        match result {
-            Err(e) => warn!("failed to run VM informant at {VM_INFORMANT_PATH:?}: {e}"),
-            Ok(status) if !status.success() => {
-                warn!("{VM_INFORMANT_PATH} exited with code {status:?}, retrying")
-            }
-            Ok(_) => info!("{VM_INFORMANT_PATH} ended gracefully (unexpectedly). Retrying"),
-        }
-
-        // Wait before retrying
-        thread::sleep(restart_wait);
-    }
-}

compute_tools/src/lib.rs

@@ -8,7 +8,6 @@ pub mod http;
 #[macro_use]
 pub mod logger;
 pub mod compute;
-pub mod informant;
 pub mod monitor;
 pub mod params;
 pub mod pg_helpers;

compute_tools/src/logger.rs

@@ -1,20 +1,42 @@
+use std::io::Write;
+
 use anyhow::Result;
-use tracing_subscriber::layer::SubscriberExt;
-use tracing_subscriber::prelude::*;
+use chrono::Utc;
+use env_logger::{Builder, Env};
+
+macro_rules! info_println {
+    ($($tts:tt)*) => {
+        if log_enabled!(Level::Info) {
+            println!($($tts)*);
+        }
+    }
+}
+
+macro_rules! info_print {
+    ($($tts:tt)*) => {
+        if log_enabled!(Level::Info) {
+            print!($($tts)*);
+        }
+    }
+}
 
 /// Initialize `env_logger` using either `default_level` or
 /// `RUST_LOG` environment variable as default log level.
 pub fn init_logger(default_level: &str) -> Result<()> {
-    let env_filter = tracing_subscriber::EnvFilter::try_from_default_env()
-        .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new(default_level));
+    let env = Env::default().filter_or("RUST_LOG", default_level);
 
-    let fmt_layer = tracing_subscriber::fmt::layer()
-        .with_target(false)
-        .with_writer(std::io::stderr);
-
-    tracing_subscriber::registry()
-        .with(env_filter)
-        .with(fmt_layer)
+    Builder::from_env(env)
+        .format(|buf, record| {
+            let thread_handle = std::thread::current();
+            writeln!(
+                buf,
+                "{} [{}] {}: {}",
+                Utc::now().format("%Y-%m-%d %H:%M:%S%.3f %Z"),
+                thread_handle.name().unwrap_or("main"),
+                record.level(),
+                record.args()
+            )
+        })
         .init();
 
     Ok(())

compute_tools/src/monitor.rs

@@ -3,8 +3,8 @@ use std::{thread, time};
 
 use anyhow::Result;
 use chrono::{DateTime, Utc};
+use log::{debug, info};
 use postgres::{Client, NoTls};
-use tracing::{debug, info};
 
 use crate::compute::ComputeNode;
 
@@ -52,16 +52,10 @@ fn watch_compute_activity(compute: &ComputeNode) {
                     let mut idle_backs: Vec<DateTime<Utc>> = vec![];
 
                     for b in backs.into_iter() {
-                        let state: String = match b.try_get("state") {
-                            Ok(state) => state,
-                            Err(_) => continue,
-                        };
+                        let state: String = b.get("state");
+                        let change: String = b.get("state_change");
 
                         if state == "idle" {
-                            let change: String = match b.try_get("state_change") {
-                                Ok(state_change) => state_change,
-                                Err(_) => continue,
-                            };
                             let change = DateTime::parse_from_rfc3339(&change);
                             match change {
                                 Ok(t) => idle_backs.push(t.with_timezone(&Utc)),
@@ -80,8 +74,10 @@ fn watch_compute_activity(compute: &ComputeNode) {
                         }
                     }
 
-                    // Get idle backend `state_change` with the max timestamp.
-                    if let Some(last) = idle_backs.iter().max() {
+                    // Sort idle backend `state_change` timestamps. The last one corresponds
+                    // to the last activity.
+                    idle_backs.sort();
+                    if let Some(last) = idle_backs.last() {
                         last_active = *last;
                     }
                 }

compute_tools/src/params.rs

@@ -1,9 +1,3 @@
 pub const DEFAULT_LOG_LEVEL: &str = "info";
-// From Postgres docs:
-//   To ease transition from the md5 method to the newer SCRAM method, if md5 is specified
-//   as a method in pg_hba.conf but the user's password on the server is encrypted for SCRAM
-//   (see below), then SCRAM-based authentication will automatically be chosen instead.
-//   https://www.postgresql.org/docs/15/auth-password.html
-//
-// So it's safe to set md5 here, as `control-plane` anyway uses SCRAM for all roles.
+pub const DEFAULT_CONNSTRING: &str = "host=localhost user=postgres";
 pub const PG_HBA_ALL_MD5: &str = "host\tall\t\tall\t\t0.0.0.0/0\t\tmd5";

compute_tools/src/pg_helpers.rs

@@ -11,7 +11,6 @@ use anyhow::{bail, Result};
 use notify::{RecursiveMode, Watcher};
 use postgres::{Client, Transaction};
 use serde::Deserialize;
-use tracing::{debug, instrument};
 
 const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
 
@@ -120,9 +119,16 @@ pub trait GenericOptionsSearch {
 impl GenericOptionsSearch for GenericOptions {
     /// Lookup option by name
     fn find(&self, name: &str) -> Option<String> {
-        let ops = self.as_ref()?;
-        let op = ops.iter().find(|s| s.name == name)?;
-        op.value.clone()
+        match &self {
+            Some(ops) => {
+                let op = ops.iter().find(|s| s.name == name);
+                match op {
+                    Some(op) => op.value.clone(),
+                    None => None,
+                }
+            }
+            None => None,
+        }
     }
 }
 
@@ -130,8 +136,8 @@ impl Role {
     /// Serialize a list of role parameters into a Postgres-acceptable
     /// string of arguments.
     pub fn to_pg_options(&self) -> String {
-        // XXX: consider putting LOGIN as a default option somewhere higher, e.g. in control-plane.
-        // For now, we do not use generic `options` for roles. Once used, add
+        // XXX: consider putting LOGIN as a default option somewhere higher, e.g. in Rails.
+        // For now we do not use generic `options` for roles. Once used, add
         // `self.options.as_pg_options()` somewhere here.
         let mut params: String = "LOGIN".to_string();
 
@@ -155,14 +161,6 @@ impl Role {
 }
 
 impl Database {
-    pub fn new(name: PgIdent, owner: PgIdent) -> Self {
-        Self {
-            name,
-            owner,
-            options: None,
-        }
-    }
-
     /// Serialize a list of database parameters into a Postgres-acceptable
     /// string of arguments.
     /// NB: `TEMPLATE` is actually also an identifier, but so far we only need
@@ -221,7 +219,11 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
             &[],
         )?
         .iter()
-        .map(|row| Database::new(row.get("datname"), row.get("owner")))
+        .map(|row| Database {
+            name: row.get("datname"),
+            owner: row.get("owner"),
+            options: None,
+        })
         .collect();
 
     Ok(postgres_dbs)
@@ -230,7 +232,6 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
 /// Wait for Postgres to become ready to accept connections. It's ready to
 /// accept connections when the state-field in `pgdata/postmaster.pid` says
 /// 'ready'.
-#[instrument(skip(pg))]
 pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
     let pid_path = pgdata.join("postmaster.pid");
 
@@ -289,18 +290,18 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
         }
 
         let res = rx.recv_timeout(Duration::from_millis(100));
-        debug!("woken up by notify: {res:?}");
+        log::debug!("woken up by notify: {res:?}");
         // If there are multiple events in the channel already, we only need to be
         // check once. Swallow the extra events before we go ahead to check the
         // pid file.
         while let Ok(res) = rx.try_recv() {
-            debug!("swallowing extra event: {res:?}");
+            log::debug!("swallowing extra event: {res:?}");
         }
 
         // Check that we can open pid file first.
         if let Ok(file) = File::open(&pid_path) {
             if !postmaster_pid_seen {
-                debug!("postmaster.pid appeared");
+                log::debug!("postmaster.pid appeared");
                 watcher
                     .unwatch(pgdata)
                     .expect("Failed to remove pgdata dir watch");
@@ -316,7 +317,7 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
             // Pid file could be there and we could read it, but it could be empty, for example.
             if let Some(Ok(line)) = last_line {
                 let status = line.trim();
-                debug!("last line of postmaster.pid: {status:?}");
+                log::debug!("last line of postmaster.pid: {status:?}");
 
                 // Now Postgres is ready to accept connections
                 if status == "ready" {
@@ -332,7 +333,7 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
         }
     }
 
-    tracing::info!("PostgreSQL is now running, continuing to configure it");
+    log::info!("PostgreSQL is now running, continuing to configure it");
 
     Ok(())
 }

compute_tools/src/spec.rs

@@ -2,10 +2,10 @@ use std::path::Path;
 use std::str::FromStr;
 
 use anyhow::Result;
+use log::{info, log_enabled, warn, Level};
 use postgres::config::Config;
 use postgres::{Client, NoTls};
 use serde::Deserialize;
-use tracing::{info, info_span, instrument, span_enabled, warn, Level};
 
 use crate::compute::ComputeNode;
 use crate::config;
@@ -79,25 +79,23 @@ pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
 
 /// Given a cluster spec json and open transaction it handles roles creation,
 /// deletion and update.
-#[instrument(skip_all)]
 pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     let mut xact = client.transaction()?;
     let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
 
     // Print a list of existing Postgres roles (only in debug mode)
-    if span_enabled!(Level::INFO) {
-        info!("postgres roles:");
-        for r in &existing_roles {
-            info!(
-                "    - {}:{}",
-                r.name,
-                if r.encrypted_password.is_some() {
-                    "[FILTERED]"
-                } else {
-                    "(null)"
-                }
-            );
-        }
+    info!("postgres roles:");
+    for r in &existing_roles {
+        info_println!(
+            "{} - {}:{}",
+            " ".repeat(27 + 5),
+            r.name,
+            if r.encrypted_password.is_some() {
+                "[FILTERED]"
+            } else {
+                "(null)"
+            }
+        );
     }
 
     // Process delta operations first
@@ -138,80 +136,58 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     info!("cluster spec roles:");
     for role in &spec.cluster.roles {
         let name = &role.name;
-        // XXX: with a limited number of roles it is fine, but consider making it a HashMap
-        let pg_role = existing_roles.iter().find(|r| r.name == *name);
 
-        enum RoleAction {
-            None,
-            Update,
-            Create,
-        }
-        let action = if let Some(r) = pg_role {
-            if (r.encrypted_password.is_none() && role.encrypted_password.is_some())
-                || (r.encrypted_password.is_some() && role.encrypted_password.is_none())
-            {
-                RoleAction::Update
-            } else if let Some(pg_pwd) = &r.encrypted_password {
-                // Check whether password changed or not (trim 'md5' prefix first if any)
-                //
-                // This is a backward compatibility hack, which comes from the times when we were using
-                // md5 for everyone and hashes were stored in the console db without md5 prefix. So when
-                // role comes from the control-plane (json spec) `Role.encrypted_password` doesn't have md5 prefix,
-                // but when role comes from Postgres (`get_existing_roles` / `existing_roles`) it has this prefix.
-                // Here is the only place so far where we compare hashes, so it seems to be the best candidate
-                // to place this compatibility layer.
-                let pg_pwd = if let Some(stripped) = pg_pwd.strip_prefix("md5") {
-                    stripped
-                } else {
-                    pg_pwd
-                };
-                if pg_pwd != *role.encrypted_password.as_ref().unwrap() {
-                    RoleAction::Update
-                } else {
-                    RoleAction::None
-                }
-            } else {
-                RoleAction::None
-            }
-        } else {
-            RoleAction::Create
-        };
-
-        match action {
-            RoleAction::None => {}
-            RoleAction::Update => {
-                let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
-                query.push_str(&role.to_pg_options());
-                xact.execute(query.as_str(), &[])?;
-            }
-            RoleAction::Create => {
-                let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
-                info!("role create query: '{}'", &query);
-                query.push_str(&role.to_pg_options());
-                xact.execute(query.as_str(), &[])?;
-
-                let grant_query = format!(
-                    "GRANT pg_read_all_data, pg_write_all_data TO {}",
-                    name.pg_quote()
-                );
-                xact.execute(grant_query.as_str(), &[])?;
-                info!("role grant query: '{}'", &grant_query);
-            }
-        }
-
-        if span_enabled!(Level::INFO) {
-            let pwd = if role.encrypted_password.is_some() {
+        info_print!(
+            "{} - {}:{}",
+            " ".repeat(27 + 5),
+            name,
+            if role.encrypted_password.is_some() {
                 "[FILTERED]"
             } else {
                 "(null)"
-            };
-            let action_str = match action {
-                RoleAction::None => "",
-                RoleAction::Create => " -> create",
-                RoleAction::Update => " -> update",
-            };
-            info!("   - {}:{}{}", name, pwd, action_str);
+            }
+        );
+
+        // XXX: with a limited number of roles it is fine, but consider making it a HashMap
+        let pg_role = existing_roles.iter().find(|r| r.name == *name);
+
+        if let Some(r) = pg_role {
+            let mut update_role = false;
+
+            if (r.encrypted_password.is_none() && role.encrypted_password.is_some())
+                || (r.encrypted_password.is_some() && role.encrypted_password.is_none())
+            {
+                update_role = true;
+            } else if let Some(pg_pwd) = &r.encrypted_password {
+                // Check whether password changed or not (trim 'md5:' prefix first)
+                update_role = pg_pwd[3..] != *role.encrypted_password.as_ref().unwrap();
+            }
+
+            if update_role {
+                let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
+                info_print!(" -> update");
+
+                query.push_str(&role.to_pg_options());
+                xact.execute(query.as_str(), &[])?;
+            }
+        } else {
+            info!("role name: '{}'", &name);
+            let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
+            info!("role create query: '{}'", &query);
+            info_print!(" -> create");
+
+            query.push_str(&role.to_pg_options());
+            xact.execute(query.as_str(), &[])?;
+
+            let grant_query = format!(
+                "GRANT pg_read_all_data, pg_write_all_data TO {}",
+                name.pg_quote()
+            );
+            xact.execute(grant_query.as_str(), &[])?;
+            info!("role grant query: '{}'", &grant_query);
         }
+
+        info_print!("\n");
     }
 
     xact.commit()?;
@@ -220,32 +196,23 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 }
 
 /// Reassign all dependent objects and delete requested roles.
-#[instrument(skip_all)]
 pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<()> {
-    if let Some(ops) = &node.spec.delta_operations {
-        // First, reassign all dependent objects to db owners.
+    let spec = &node.spec;
+
+    // First, reassign all dependent objects to db owners.
+    if let Some(ops) = &spec.delta_operations {
         info!("reassigning dependent objects of to-be-deleted roles");
-
-        // Fetch existing roles. We could've exported and used `existing_roles` from
-        // `handle_roles()`, but we only make this list there before creating new roles.
-        // Which is probably fine as we never create to-be-deleted roles, but that'd
-        // just look a bit untidy. Anyway, the entire `pg_roles` should be in shared
-        // buffers already, so this shouldn't be a big deal.
-        let mut xact = client.transaction()?;
-        let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
-        xact.commit()?;
-
         for op in ops {
-            // Check that role is still present in Postgres, as this could be a
-            // restart with the same spec after role deletion.
-            if op.action == "delete_role" && existing_roles.iter().any(|r| r.name == op.name) {
+            if op.action == "delete_role" {
                 reassign_owned_objects(node, &op.name)?;
             }
         }
+    }
 
-        // Second, proceed with role deletions.
+    // Second, proceed with role deletions.
+    let mut xact = client.transaction()?;
+    if let Some(ops) = &spec.delta_operations {
         info!("processing role deletions");
-        let mut xact = client.transaction()?;
         for op in ops {
             // We do not check either role exists or not,
             // Postgres will take care of it for us
@@ -256,7 +223,6 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
                 xact.execute(query.as_str(), &[])?;
             }
         }
-        xact.commit()?;
     }
 
     Ok(())
@@ -297,16 +263,13 @@ fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()>
 /// like `CREATE DATABASE` and `DROP DATABASE` do not support it. Statement-level
 /// atomicity should be enough here due to the order of operations and various checks,
 /// which together provide us idempotency.
-#[instrument(skip_all)]
 pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     let existing_dbs: Vec<Database> = get_existing_dbs(client)?;
 
     // Print a list of existing Postgres databases (only in debug mode)
-    if span_enabled!(Level::INFO) {
-        info!("postgres databases:");
-        for r in &existing_dbs {
-            info!("    {}:{}", r.name, r.owner);
-        }
+    info!("postgres databases:");
+    for r in &existing_dbs {
+        info_println!("{} - {}:{}", " ".repeat(27 + 5), r.name, r.owner);
     }
 
     // Process delta operations first
@@ -349,15 +312,12 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     for db in &spec.cluster.databases {
         let name = &db.name;
 
+        info_print!("{} - {}:{}", " ".repeat(27 + 5), db.name, db.owner);
+
         // XXX: with a limited number of databases it is fine, but consider making it a HashMap
         let pg_db = existing_dbs.iter().find(|r| r.name == *name);
 
-        enum DatabaseAction {
-            None,
-            Update,
-            Create,
-        }
-        let action = if let Some(r) = pg_db {
+        if let Some(r) = pg_db {
             // XXX: db owner name is returned as quoted string from Postgres,
             // when quoting is needed.
             let new_owner = if r.owner.starts_with('"') {
@@ -367,42 +327,24 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
             };
 
             if new_owner != r.owner {
-                // Update the owner
-                DatabaseAction::Update
-            } else {
-                DatabaseAction::None
-            }
-        } else {
-            DatabaseAction::Create
-        };
-
-        match action {
-            DatabaseAction::None => {}
-            DatabaseAction::Update => {
                 let query: String = format!(
                     "ALTER DATABASE {} OWNER TO {}",
                     name.pg_quote(),
                     db.owner.pg_quote()
                 );
-                let _ = info_span!("executing", query).entered();
-                client.execute(query.as_str(), &[])?;
-            }
-            DatabaseAction::Create => {
-                let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
-                query.push_str(&db.to_pg_options());
-                let _ = info_span!("executing", query).entered();
-                client.execute(query.as_str(), &[])?;
-            }
-        };
+                info_print!(" -> update");
 
-        if span_enabled!(Level::INFO) {
-            let action_str = match action {
-                DatabaseAction::None => "",
-                DatabaseAction::Create => " -> create",
-                DatabaseAction::Update => " -> update",
-            };
-            info!("   - {}:{}{}", db.name, db.owner, action_str);
+                client.execute(query.as_str(), &[])?;
+            }
+        } else {
+            let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
+            info_print!(" -> create");
+
+            query.push_str(&db.to_pg_options());
+            client.execute(query.as_str(), &[])?;
         }
+
+        info_print!("\n");
     }
 
     Ok(())
@@ -410,7 +352,6 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 
 /// Grant CREATE ON DATABASE to the database owner and do some other alters and grants
 /// to allow users creating trusted extensions and re-creating `public` schema, for example.
-#[instrument(skip_all)]
 pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
     let spec = &node.spec;
 

compute_tools/tests/pg_helpers_tests.rs

@@ -38,33 +38,4 @@ mod pg_helpers_tests {
 
         assert_eq!(ident.pg_quote(), "\"\"\"name\"\";\\n select 1;\"");
     }
-
-    #[test]
-    fn generic_options_search() {
-        let generic_options: GenericOptions = Some(vec![
-            GenericOption {
-                name: "present_value".into(),
-                value: Some("value".into()),
-                vartype: "string".into(),
-            },
-            GenericOption {
-                name: "missed_value".into(),
-                value: None,
-                vartype: "int".into(),
-            },
-        ]);
-        assert_eq!(generic_options.find("present_value"), Some("value".into()));
-        assert_eq!(generic_options.find("missed_value"), None);
-        assert_eq!(generic_options.find("invalid_value"), None);
-
-        let empty_generic_options: GenericOptions = Some(vec![]);
-        assert_eq!(empty_generic_options.find("present_value"), None);
-        assert_eq!(empty_generic_options.find("missed_value"), None);
-        assert_eq!(empty_generic_options.find("invalid_value"), None);
-
-        let none_generic_options: GenericOptions = None;
-        assert_eq!(none_generic_options.find("present_value"), None);
-        assert_eq!(none_generic_options.find("missed_value"), None);
-        assert_eq!(none_generic_options.find("invalid_value"), None);
-    }
 }

control_plane/Cargo.toml

@@ -1,31 +1,29 @@
 [package]
 name = "control_plane"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-anyhow.workspace = true
-clap.workspace = true
-comfy-table.workspace = true
-git-version.workspace = true
-nix.workspace = true
-once_cell.workspace = true
-postgres.workspace = true
-regex.workspace = true
-reqwest = { workspace = true, features = ["blocking", "json"] }
-serde.workspace = true
-serde_with.workspace = true
-tar.workspace = true
-thiserror.workspace = true
-toml.workspace = true
-url.workspace = true
+anyhow = "1.0"
+clap = "4.0"
+comfy-table = "6.1"
+git-version = "0.3.5"
+nix = "0.25"
+once_cell = "1.13.0"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
+regex = "1"
+reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
+serde = { version = "1.0", features = ["derive"] }
+serde_with = "2.0"
+tar = "0.4.38"
+thiserror = "1"
+toml = "0.5"
+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.workspace = true
-safekeeper_api.workspace = true
-postgres_connection.workspace = true
-storage_broker.workspace = true
-utils.workspace = true
-
-workspace_hack.workspace = true
+pageserver_api = { path = "../libs/pageserver_api" }
+postgres_connection = { path = "../libs/postgres_connection" }
+safekeeper_api = { path = "../libs/safekeeper_api" }
+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

@@ -14,19 +14,17 @@
 
 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};
+
+use utils::lock_file;
 
 // These constants control the loop used to poll for process start / stop.
 //
@@ -51,21 +49,21 @@ pub enum InitialPidFile<'t> {
 }
 
 /// Start a background child process using the parameters given.
-pub fn start_process<F, AI, A, EI>(
+pub fn start_process<
+    F,
+    S: AsRef<OsStr>,
+    EI: IntoIterator<Item = (String, String)>, // Not generic AsRef<OsStr>, otherwise empty `envs` prevents type inference
+>(
     process_name: &str,
     datadir: &Path,
     command: &Path,
-    args: AI,
+    args: &[S],
     envs: EI,
     initial_pid_file: InitialPidFile,
     process_status_check: F,
 ) -> anyhow::Result<Child>
 where
     F: Fn() -> anyhow::Result<bool>,
-    AI: IntoIterator<Item = A>,
-    A: AsRef<OsStr>,
-    // Not generic AsRef<OsStr>, otherwise empty `envs` prevents type inference
-    EI: IntoIterator<Item = (String, String)>,
 {
     let log_path = datadir.join(format!("{process_name}.log"));
     let process_log_file = fs::OpenOptions::new()
@@ -88,14 +86,6 @@ where
     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.")
     })?;
@@ -105,8 +95,29 @@ 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);
@@ -136,29 +147,30 @@ where
     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}"),
+    }
+}
+
 /// 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
@@ -170,9 +182,8 @@ 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(());
         }
@@ -241,69 +252,6 @@ 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>,
@@ -314,11 +262,14 @@ 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),
@@ -326,6 +277,21 @@ 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,
     )
 }
@@ -263,7 +264,7 @@ fn get_tenant_id(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::R
     } else if let Some(default_id) = env.default_tenant_id {
         Ok(default_id)
     } else {
-        anyhow::bail!("No tenant id. Use --tenant-id, or set a default tenant");
+        bail!("No tenant id. Use --tenant-id, or set 'default_tenant_id' in the config file");
     }
 }
 
@@ -284,6 +285,8 @@ fn parse_timeline_id(sub_match: &ArgMatches) -> anyhow::Result<Option<TimelineId
 }
 
 fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
+    let initial_timeline_id_arg = parse_timeline_id(init_match)?;
+
     // Create config file
     let toml_file: String = if let Some(config_path) = init_match.get_one::<PathBuf>("config") {
         // load and parse the file
@@ -295,7 +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
@@ -307,16 +310,30 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
         LocalEnv::parse_config(&toml_file).context("Failed to create neon configuration")?;
     env.init(pg_version)
         .context("Failed to initialize neon repository")?;
+    let initial_tenant_id = env
+        .default_tenant_id
+        .expect("default_tenant_id should be generated by the `env.init()` call above");
 
     // Initialize pageserver, create initial tenant and timeline.
     let pageserver = PageServerNode::from_env(&env);
-    pageserver
-        .initialize(&pageserver_config_overrides(init_match))
+    let initial_timeline_id = pageserver
+        .initialize(
+            Some(initial_tenant_id),
+            initial_timeline_id_arg,
+            &pageserver_config_overrides(init_match),
+            pg_version,
+        )
         .unwrap_or_else(|e| {
-            eprintln!("pageserver init failed: {e:?}");
+            eprintln!("pageserver init failed: {e}");
             exit(1);
         });
 
+    env.register_branch_mapping(
+        DEFAULT_BRANCH_NAME.to_owned(),
+        initial_tenant_id,
+        initial_timeline_id,
+    )?;
+
     Ok(env)
 }
 
@@ -325,7 +342,7 @@ fn pageserver_config_overrides(init_match: &ArgMatches) -> Vec<&str> {
         .get_many::<String>("pageserver-config-override")
         .into_iter()
         .flatten()
-        .map(String::as_str)
+        .map(|s| s.as_str())
         .collect()
 }
 
@@ -372,17 +389,6 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
             println!(
                 "Created an initial timeline '{new_timeline_id}' at Lsn {last_record_lsn} for tenant: {new_tenant_id}",
             );
-
-            if create_match.get_flag("set-default") {
-                println!("Setting tenant {new_tenant_id} as a default one");
-                env.default_tenant_id = Some(new_tenant_id);
-            }
-        }
-        Some(("set-default", set_default_match)) => {
-            let tenant_id =
-                parse_tenant_id(set_default_match)?.context("No tenant id specified")?;
-            println!("Setting tenant {tenant_id} as a default one");
-            env.default_tenant_id = Some(tenant_id);
         }
         Some(("config", create_match)) => {
             let tenant_id = get_tenant_id(create_match, env)?;
@@ -544,7 +550,7 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
 
             table.load_preset(comfy_table::presets::NOTHING);
 
-            table.set_header([
+            table.set_header(&[
                 "NODE",
                 "ADDRESS",
                 "TIMELINE",
@@ -579,7 +585,7 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
                     .map(|name| name.as_str())
                     .unwrap_or("?");
 
-                table.add_row([
+                table.add_row(&[
                     node_name.as_str(),
                     &node.address.to_string(),
                     &node.timeline_id.to_string(),
@@ -742,7 +748,7 @@ fn get_safekeeper(env: &local_env::LocalEnv, id: NodeId) -> Result<SafekeeperNod
     if let Some(node) = env.safekeepers.iter().find(|node| node.id == id) {
         Ok(SafekeeperNode::from_env(env, node))
     } else {
-        bail!("could not find safekeeper {id}")
+        bail!("could not find safekeeper '{}'", id)
     }
 }
 
@@ -801,22 +807,22 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
 }
 
 fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    etcd::start_etcd_process(env)?;
+    let pageserver = PageServerNode::from_env(env);
+
     // Postgres nodes are not started automatically
 
-    broker::start_broker_process(env)?;
-
-    let pageserver = PageServerNode::from_env(env);
     if let Err(e) = pageserver.start(&pageserver_config_overrides(sub_match)) {
-        eprintln!("pageserver {} start failed: {:#}", env.pageserver.id, e);
-        try_stop_all(env, true);
+        eprintln!("pageserver start failed: {e}");
+        try_stop_etcd_process(env);
         exit(1);
     }
 
     for node in env.safekeepers.iter() {
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.start() {
-            eprintln!("safekeeper {} start failed: {:#}", safekeeper.id, e);
-            try_stop_all(env, false);
+            eprintln!("safekeeper '{}' start failed: {e}", safekeeper.id);
+            try_stop_etcd_process(env);
             exit(1);
         }
     }
@@ -827,41 +833,35 @@ fn handle_stop_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<
     let immediate =
         sub_match.get_one::<String>("stop-mode").map(|s| s.as_str()) == Some("immediate");
 
-    try_stop_all(env, immediate);
-
-    Ok(())
-}
-
-fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
     let pageserver = PageServerNode::from_env(env);
 
     // Stop all compute nodes
-    match ComputeControlPlane::load(env.clone()) {
-        Ok(cplane) => {
-            for (_k, node) in cplane.nodes {
-                if let Err(e) = node.stop(false) {
-                    eprintln!("postgres stop failed: {e:#}");
-                }
-            }
-        }
-        Err(e) => {
-            eprintln!("postgres stop failed, could not restore control plane data from env: {e:#}")
+    let cplane = ComputeControlPlane::load(env.clone())?;
+    for (_k, node) in cplane.nodes {
+        if let Err(e) = node.stop(false) {
+            eprintln!("postgres stop failed: {}", e);
         }
     }
 
     if let Err(e) = pageserver.stop(immediate) {
-        eprintln!("pageserver {} stop failed: {:#}", env.pageserver.id, e);
+        eprintln!("pageserver stop failed: {}", e);
     }
 
     for node in env.safekeepers.iter() {
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.stop(immediate) {
-            eprintln!("safekeeper {} stop failed: {:#}", safekeeper.id, e);
+            eprintln!("safekeeper '{}' stop failed: {}", safekeeper.id, e);
         }
     }
 
-    if let Err(e) = broker::stop_broker_process(env) {
-        eprintln!("neon broker stop failed: {e:#}");
+    try_stop_etcd_process(env);
+
+    Ok(())
+}
+
+fn try_stop_etcd_process(env: &local_env::LocalEnv) {
+    if let Err(e) = etcd::stop_etcd_process(env) {
+        eprintln!("etcd stop failed: {e}");
     }
 }
 
@@ -901,7 +901,6 @@ fn cli() -> Command {
     let stop_mode_arg = Arg::new("stop-mode")
         .short('m')
         .value_parser(["fast", "immediate"])
-        .default_value("fast")
         .help("If 'immediate', don't flush repository data at shutdown")
         .required(false)
         .value_name("stop-mode");
@@ -923,8 +922,9 @@ fn cli() -> Command {
         .version(GIT_VERSION)
         .subcommand(
             Command::new("init")
-                .about("Initialize a new Neon repository, preparing configs for services to start with")
+                .about("Initialize a new Neon repository")
                 .arg(pageserver_config_args.clone())
+                .arg(timeline_id_arg.clone().help("Use a specific timeline id when creating a tenant and its initial timeline"))
                 .arg(
                     Arg::new("config")
                         .long("config")
@@ -986,14 +986,11 @@ fn cli() -> Command {
                 .arg(timeline_id_arg.clone().help("Use a specific timeline id when creating a tenant and its initial timeline"))
                 .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false))
                 .arg(pg_version_arg.clone())
-                .arg(Arg::new("set-default").long("set-default").action(ArgAction::SetTrue).required(false)
-                    .help("Use this tenant in future CLI commands where tenant_id is needed, but not specified"))
                 )
-            .subcommand(Command::new("set-default").arg(tenant_id_arg.clone().required(true))
-                .about("Set a particular tenant as default in future CLI commands where tenant_id is needed, but not specified"))
             .subcommand(Command::new("config")
                 .arg(tenant_id_arg.clone())
-                .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false)))
+                .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false))
+                )
         )
         .subcommand(
             Command::new("pageserver")

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

@@ -44,7 +44,7 @@ impl ComputeControlPlane {
         let mut nodes = BTreeMap::default();
         let pgdatadirspath = &env.pg_data_dirs_path();
 
-        for tenant_dir in fs::read_dir(pgdatadirspath)
+        for tenant_dir in fs::read_dir(&pgdatadirspath)
             .with_context(|| format!("failed to list {}", pgdatadirspath.display()))?
         {
             let tenant_dir = tenant_dir?;
@@ -67,8 +67,8 @@ impl ComputeControlPlane {
     fn get_port(&mut self) -> u16 {
         1 + self
             .nodes
-            .values()
-            .map(|node| node.address.port())
+            .iter()
+            .map(|(_name, node)| node.address.port())
             .max()
             .unwrap_or(self.base_port)
     }
@@ -183,7 +183,7 @@ impl PostgresNode {
 
     fn sync_safekeepers(&self, auth_token: &Option<String>, pg_version: u32) -> Result<Lsn> {
         let pg_path = self.env.pg_bin_dir(pg_version)?.join("postgres");
-        let mut cmd = Command::new(pg_path);
+        let mut cmd = Command::new(&pg_path);
 
         cmd.arg("--sync-safekeepers")
             .env_clear()
@@ -201,7 +201,7 @@ impl PostgresNode {
             .stderr(Stdio::piped());
 
         if let Some(token) = auth_token {
-            cmd.env("NEON_AUTH_TOKEN", token);
+            cmd.env("ZENITH_AUTH_TOKEN", token);
         }
 
         let sync_handle = cmd
@@ -261,7 +261,7 @@ impl PostgresNode {
     }
 
     fn create_pgdata(&self) -> Result<()> {
-        fs::create_dir_all(self.pgdata()).with_context(|| {
+        fs::create_dir_all(&self.pgdata()).with_context(|| {
             format!(
                 "could not create data directory {}",
                 self.pgdata().display()
@@ -304,17 +304,17 @@ impl PostgresNode {
 
             // Set up authentication
             //
-            // $NEON_AUTH_TOKEN will be replaced with value from environment
+            // $ZENITH_AUTH_TOKEN will be replaced with value from environment
             // variable during compute pg startup. It is done this way because
             // otherwise user will be able to retrieve the value using SHOW
             // command or pg_settings
             let password = if let AuthType::NeonJWT = auth_type {
-                "$NEON_AUTH_TOKEN"
+                "$ZENITH_AUTH_TOKEN"
             } else {
                 ""
             };
             // NOTE avoiding spaces in connection string, because it is less error prone if we forward it somewhere.
-            // Also note that not all parameters are supported here. Because in compute we substitute $NEON_AUTH_TOKEN
+            // Also note that not all parameters are supported here. Because in compute we substitute $ZENITH_AUTH_TOKEN
             // We parse this string and build it back with token from env var, and for simplicity rebuild
             // uses only needed variables namely host, port, user, password.
             format!("postgresql://no_user:{password}@{host}:{port}")
@@ -323,7 +323,7 @@ impl PostgresNode {
         conf.append_line("");
         conf.append("neon.pageserver_connstring", &pageserver_connstr);
         if let AuthType::NeonJWT = auth_type {
-            conf.append("neon.safekeeper_token_env", "$NEON_AUTH_TOKEN");
+            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());
@@ -448,7 +448,7 @@ impl PostgresNode {
             self.env.pg_lib_dir(self.pg_version)?.to_str().unwrap(),
         );
         if let Some(token) = auth_token {
-            cmd.env("NEON_AUTH_TOKEN", token);
+            cmd.env("ZENITH_AUTH_TOKEN", token);
         }
 
         let pg_ctl = cmd.output().context("pg_ctl failed")?;
@@ -478,7 +478,7 @@ impl PostgresNode {
                 postgresql_conf_path.to_str().unwrap()
             )
         })?;
-        fs::remove_dir_all(self.pgdata())?;
+        fs::remove_dir_all(&self.pgdata())?;
         self.create_pgdata()?;
 
         // 2. Bring back config files
@@ -514,7 +514,7 @@ impl PostgresNode {
                 "Destroying postgres data directory '{}'",
                 self.pgdata().to_str().unwrap()
             );
-            fs::remove_dir_all(self.pgdata())?;
+            fs::remove_dir_all(&self.pgdata())?;
         } else {
             self.pg_ctl(&["stop"], &None)?;
         }

control_plane/src/etcd.rs

@@ -0,0 +1,78 @@
+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;
+    print!(
+        "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 +8,8 @@
 //
 
 mod background_process;
-pub mod broker;
 pub mod compute;
+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")
     }
@@ -296,6 +329,11 @@ impl LocalEnv {
             env.neon_distrib_dir = env::current_exe()?.parent().unwrap().to_owned();
         }
 
+        // If no initial tenant ID was given, generate it.
+        if env.default_tenant_id.is_none() {
+            env.default_tenant_id = Some(TenantId::generate());
+        }
+
         env.base_data_dir = base_path();
 
         Ok(env)
@@ -399,7 +437,7 @@ impl LocalEnv {
             }
         }
 
-        fs::create_dir(base_path)?;
+        fs::create_dir(&base_path)?;
 
         // generate keys for jwt
         // openssl genrsa -out private_key.pem 2048
@@ -408,7 +446,7 @@ impl LocalEnv {
             private_key_path = base_path.join("auth_private_key.pem");
             let keygen_output = Command::new("openssl")
                 .arg("genrsa")
-                .args(["-out", private_key_path.to_str().unwrap()])
+                .args(&["-out", private_key_path.to_str().unwrap()])
                 .arg("2048")
                 .stdout(Stdio::null())
                 .output()
@@ -425,10 +463,10 @@ impl LocalEnv {
             // openssl rsa -in private_key.pem -pubout -outform PEM -out public_key.pem
             let keygen_output = Command::new("openssl")
                 .arg("rsa")
-                .args(["-in", private_key_path.to_str().unwrap()])
+                .args(&["-in", private_key_path.to_str().unwrap()])
                 .arg("-pubout")
-                .args(["-outform", "PEM"])
-                .args(["-out", public_key_path.to_str().unwrap()])
+                .args(&["-outform", "PEM"])
+                .args(&["-out", public_key_path.to_str().unwrap()])
                 .stdout(Stdio::null())
                 .output()
                 .context("failed to generate auth private key")?;
@@ -473,8 +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

@@ -1,13 +1,12 @@
-use std::borrow::Cow;
 use std::collections::HashMap;
 use std::fs::File;
 use std::io::{BufReader, Write};
 use std::num::NonZeroU64;
-use std::path::PathBuf;
-use std::process::{Child, Command};
+use std::path::{Path, PathBuf};
+use std::process::Child;
 use std::{io, result};
 
-use anyhow::{bail, Context};
+use anyhow::{bail, ensure, Context};
 use pageserver_api::models::{
     TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
 };
@@ -97,8 +96,13 @@ impl PageServerNode {
         }
     }
 
-    // pageserver conf overrides defined by neon_local configuration.
-    fn neon_local_overrides(&self) -> Vec<String> {
+    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!(
@@ -113,32 +117,90 @@ 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
+
+        let mut pageserver_process = self
+            .start_node(&init_config_overrides, &self.env.base_data_dir, true)
+            .with_context(|| {
+                format!(
+                    "Failed to start a process for pageserver {}",
+                    self.env.pageserver.id,
+                )
+            })?;
+
+        let init_result = self
+            .try_init_timeline(create_tenant, initial_timeline_id, pg_version)
+            .context("Failed to create initial tenant and timeline for pageserver");
+        match &init_result {
+            Ok(initial_timeline_id) => {
+                println!("Successfully initialized timeline {initial_timeline_id}")
+            }
+            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(),
+        );
+        init_result
     }
 
-    /// Initializes a pageserver node by creating its config with the overrides provided.
-    pub fn initialize(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
-        // First, run `pageserver --init` and wait for it to write a config into FS and exit.
-        self.pageserver_init(config_overrides).with_context(|| {
-            format!(
-                "Failed to run init for pageserver node {}",
-                self.env.pageserver.id,
-            )
-        })
+    fn try_init_timeline(
+        &self,
+        new_tenant_id: Option<TenantId>,
+        new_timeline_id: Option<TimelineId>,
+        pg_version: u32,
+    ) -> anyhow::Result<TimelineId> {
+        let initial_tenant_id = self.tenant_create(new_tenant_id, HashMap::new())?;
+        let initial_timeline_info = self.timeline_create(
+            initial_tenant_id,
+            new_timeline_id,
+            None,
+            None,
+            Some(pg_version),
+        )?;
+        Ok(initial_timeline_info.timeline_id)
     }
 
     pub fn repo_path(&self) -> PathBuf {
@@ -153,73 +215,52 @@ impl PageServerNode {
     }
 
     pub fn start(&self, config_overrides: &[&str]) -> anyhow::Result<Child> {
-        self.start_node(config_overrides, false)
+        self.start_node(config_overrides, &self.repo_path(), false)
     }
 
-    fn pageserver_init(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
-        let datadir = self.repo_path();
-        let node_id = self.env.pageserver.id;
-        println!(
-            "Initializing pageserver node {} at '{}' in {:?}",
-            node_id,
-            self.pg_connection_config.raw_address(),
-            datadir
-        );
-        io::stdout().flush()?;
-
-        let datadir_path_str = datadir.to_str().with_context(|| {
-            format!("Cannot start pageserver node {node_id} in path that has no string representation: {datadir:?}")
-        })?;
-        let mut args = self.pageserver_basic_args(config_overrides, datadir_path_str);
-        args.push(Cow::Borrowed("--init"));
-
-        let init_output = Command::new(self.env.pageserver_bin())
-            .args(args.iter().map(Cow::as_ref))
-            .envs(self.pageserver_env_variables()?)
-            .output()
-            .with_context(|| format!("Failed to run pageserver init for node {node_id}"))?;
-
-        anyhow::ensure!(
-            init_output.status.success(),
-            "Pageserver init for node {} did not finish successfully, stdout: {}, stderr: {}",
-            node_id,
-            String::from_utf8_lossy(&init_output.stdout),
-            String::from_utf8_lossy(&init_output.stderr),
-        );
-
-        Ok(())
-    }
-
-    fn start_node(&self, config_overrides: &[&str], update_config: bool) -> anyhow::Result<Child> {
-        let mut overrides = self.neon_local_overrides();
-        overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
-
-        let datadir = self.repo_path();
+    fn start_node(
+        &self,
+        config_overrides: &[&str],
+        datadir: &Path,
+        update_config: bool,
+    ) -> anyhow::Result<Child> {
         print!(
-            "Starting pageserver node {} at '{}' in {:?}",
-            self.env.pageserver.id,
+            "Starting pageserver at '{}' in '{}'",
             self.pg_connection_config.raw_address(),
-            datadir
+            datadir.display()
         );
         io::stdout().flush()?;
 
-        let datadir_path_str = datadir.to_str().with_context(|| {
-            format!(
-                "Cannot start pageserver node {} in path that has no string representation: {:?}",
-                self.env.pageserver.id, datadir,
-            )
-        })?;
-        let mut args = self.pageserver_basic_args(config_overrides, datadir_path_str);
+        let mut args = vec![
+            "-D",
+            datadir.to_str().with_context(|| {
+                format!("Datadir path {datadir:?} cannot be represented as a unicode string")
+            })?,
+        ];
+
         if update_config {
-            args.push(Cow::Borrowed("--update-config"));
+            args.push("--update-config");
         }
 
+        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,
+            datadir,
             &self.env.pageserver_bin(),
-            args.iter().map(Cow::as_ref),
-            self.pageserver_env_variables()?,
+            &args,
+            envs,
             background_process::InitialPidFile::Expect(&self.pid_file()),
             || match self.check_status() {
                 Ok(()) => Ok(true),
@@ -229,35 +270,6 @@ impl PageServerNode {
         )
     }
 
-    fn pageserver_basic_args<'a>(
-        &self,
-        config_overrides: &'a [&'a str],
-        datadir_path_str: &'a str,
-    ) -> Vec<Cow<'a, str>> {
-        let mut args = vec![Cow::Borrowed("-D"), Cow::Borrowed(datadir_path_str)];
-
-        let mut overrides = self.neon_local_overrides();
-        overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
-        for config_override in overrides {
-            args.push(Cow::Borrowed("-c"));
-            args.push(Cow::Owned(config_override));
-        }
-
-        args
-    }
-
-    fn pageserver_env_variables(&self) -> anyhow::Result<Vec<(String, String)>> {
-        Ok(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![("NEON_AUTH_TOKEN".to_owned(), token)]
-        } else {
-            Vec::new()
-        })
-    }
-
     ///
     /// Stop the server.
     ///

control_plane/src/safekeeper.rs

@@ -131,8 +131,13 @@ 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 {

deny.toml

@@ -1,90 +0,0 @@
-# This file was auto-generated using `cargo deny init`.
-# cargo-deny is a cargo plugin that lets you lint your project's
-# dependency graph to ensure all your dependencies conform
-# to your expectations and requirements.
-
-# Root options
-targets = []
-all-features = false
-no-default-features = false
-feature-depth = 1
-
-# This section is considered when running `cargo deny check advisories`
-# More documentation for the advisories section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/advisories/cfg.html
-[advisories]
-db-urls = ["https://github.com/rustsec/advisory-db"]
-vulnerability = "deny"
-unmaintained = "warn"
-yanked = "warn"
-notice = "warn"
-ignore = []
-
-# This section is considered when running `cargo deny check licenses`
-# More documentation for the licenses section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/licenses/cfg.html
-[licenses]
-unlicensed = "deny"
-allow = [
-    "Apache-2.0",
-    "Artistic-2.0",
-    "BSD-2-Clause",
-    "BSD-3-Clause",
-    "ISC",
-    "MIT",
-    "MPL-2.0",
-    "OpenSSL",
-    "Unicode-DFS-2016",
-]
-deny = []
-copyleft = "warn"
-allow-osi-fsf-free = "neither"
-default = "deny"
-confidence-threshold = 0.8
-exceptions = [
-    # Zlib license has some restrictions if we decide to change sth
-    { allow = ["Zlib"], name = "const_format_proc_macros", version = "*" },
-    { allow = ["Zlib"], name = "const_format", version = "*" },
-]
-
-[[licenses.clarify]]
-name = "ring"
-version = "*"
-expression = "MIT AND ISC AND OpenSSL"
-license-files = [
-    { path = "LICENSE", hash = 0xbd0eed23 }
-]
-
-[licenses.private]
-ignore = true
-registries = []
-
-# This section is considered when running `cargo deny check bans`.
-# More documentation about the 'bans' section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/bans/cfg.html
-[bans]
-multiple-versions = "warn"
-wildcards = "allow"
-highlight = "all"
-workspace-default-features = "allow"
-external-default-features = "allow"
-allow = []
-deny = []
-skip = []
-skip-tree = []
-
-# This section is considered when running `cargo deny check sources`.
-# More documentation about the 'sources' section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/sources/cfg.html
-[sources]
-unknown-registry = "warn"
-unknown-git = "warn"
-allow-registry = ["https://github.com/rust-lang/crates.io-index"]
-allow-git = []
-
-[sources.allow-org]
-github = [
-    "neondatabase",
-]
-gitlab = []
-bitbucket = []

docker-compose/docker-compose.yml

@@ -1,6 +1,29 @@
 version: '3'
 
 services:
+  etcd:
+    restart: always
+    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
@@ -33,7 +56,7 @@ services:
     restart: always
     image: ${REPOSITORY:-neondatabase}/neon:${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 +68,7 @@ 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',
@@ -53,7 +76,7 @@ services:
                                                         bucket_region='eu-north-1',
                                                         prefix_in_bucket='/pageserver/'}\""
     depends_on:
-      - storage_broker
+      - etcd
       - minio_create_buckets
 
   safekeeper1:
@@ -62,7 +85,7 @@ services:
     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
@@ -76,14 +99,14 @@ 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:
@@ -92,7 +115,7 @@ services:
     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
@@ -106,14 +129,14 @@ 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:
@@ -122,7 +145,7 @@ services:
     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
@@ -136,25 +159,16 @@ 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:

docs/authentication.md

@@ -2,7 +2,7 @@
 
 ### 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.
+Etcd 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.
@@ -65,7 +65,7 @@ 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:$NEON_AUTH_TOKEN@localhost:15028`.
+The connection string is configured by the `neon.pageserver_connstring` PostgreSQL GUC, e.g. `postgresql://no_user:$ZENITH_AUTH_TOKEN@localhost:15028`.
 The environment variable inside the connection string is substituted with
 the JWT token.
 
@@ -77,14 +77,14 @@ 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
-`$NEON_AUTH_TOKEN` environment variable.
+`$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
+in the Etcd, but they do not publish access tokens, otherwise what is
 the point of authentication.
 
 Pageserver keeps a connection to some set of Safekeepers, which
@@ -114,7 +114,7 @@ either of three values:
 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 `NEON_AUTH_TOKEN`
+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,

docs/consumption_metrics.md

@@ -1,115 +0,0 @@
-### Overview
-Pageserver and proxy periodically collect consumption metrics and push them to a HTTP endpoint.
-
-This doc describes current implementation details.
-For design details see [the RFC](./rfcs/021-metering.md) and [the discussion on Github](https://github.com/neondatabase/neon/pull/2884).
-
-- The metrics are collected in a separate thread, and the collection interval and endpoint are configurable.
-
-- Metrics are cached, so that we don't send unchanged metrics on every iteration.
-
-- Metrics are sent in batches of 1000 (see CHUNK_SIZE const) metrics max with no particular grouping guarantees.
-
-batch format is
-```json
-
-{ "events" : [metric1, metric2, ...]]}
-
-```
-See metric format examples below.
-
-- All metrics values are in bytes, unless otherwise specified.
-
-- Currently no retries are implemented.
-
-### Pageserver metrics
-
-#### Configuration
-The endpoint and the collection interval are specified in the pageserver config file (or can be passed as command line arguments):
-`metric_collection_endpoint` defaults to None, which means that metric collection is disabled by default.
-`metric_collection_interval` defaults to 10min
-
-#### Metrics
-
-Currently, the following metrics are collected:
-
-- `written_size`
-
-Amount of WAL produced , by a timeline, i.e. last_record_lsn
-This is an absolute, per-timeline metric.
-
-- `resident_size`
-
-Size of all the layer files in the tenant's directory on disk on the pageserver.
-This is an absolute, per-tenant metric.
-
-- `remote_storage_size`
-
-Size of the remote storage (S3) directory.
-This is an absolute, per-tenant metric.
-
-- `timeline_logical_size`
-Logical size of the data in the timeline
-This is an absolute, per-timeline metric.
-
-- `synthetic_storage_size`
-Size of all tenant's branches including WAL
-This is the same metric that `tenant/{tenant_id}/size` endpoint returns.
-This is an absolute, per-tenant metric.
-
-Synthetic storage size is calculated in a separate thread, so it might be slightly outdated.
-
-#### Format example
-
-```json
-{
-"metric": "remote_storage_size",
-"type": "absolute",
-"time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"tenant_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-"timeline_id": "a03ebb4f5922a1c56ff7485cc8854143",
-}
-```
-
-`idempotency_key` is a unique key for each metric, so that we can deduplicate metrics.
-It is a combination of the time, node_id and a random number.
-
-### Proxy consumption metrics
-
-#### Configuration
-The endpoint and the collection interval can be passed as command line arguments for proxy:
-`metric_collection_endpoint` no default, which means that metric collection is disabled by default.
-`metric_collection_interval` no default
-
-#### Metrics
-
-Currently, only one proxy metric is collected:
-
-- `proxy_io_bytes_per_client`
-Outbound traffic per client.
-This is an incremental, per-endpoint metric.
-
-#### Format example
-
-```json
-{
-"metric": "proxy_io_bytes_per_client",
-"type": "incremental",
-"start_time": "2022-12-28T11:07:19.317310284Z",
-"stop_time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"endpoint_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-}
-```
-
-The metric is incremental, so the value is the difference between the current and the previous value.
-If there is no previous value, the value, the value is the current value and the `start_time` equals `stop_time`.
-
-### TODO
-
-- [ ] Handle errors better: currently if one tenant fails to gather metrics, the whole iteration fails and metrics are not sent for any tenant.
-- [ ] Add retries
-- [ ] Tune the interval

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/rfcs/021-metering.md

@@ -1,186 +0,0 @@
-# Consumption tracking
-
-
-# Goals
-
-This proposal is made with two mostly but not entirely overlapping goals:
-
-* Collect info that is needed for consumption-based billing
-* Cross-check AWS bills
-
-
-# Metrics
-
-There are six metrics to collect:
-
-* CPU time. Wall clock seconds * the current number of cores. We have a fixed ratio of memory to cores, so the current memory size is the function of the number of cores. Measured per each `endpoint`.
-
-* Traffic. In/out traffic on the proxy. Measured per each `endpoint`.
-
-* Written size. Amount of data we write. That is different from both traffic and storage size, as only during the writing we
-
-  a) occupy some disk bandwidth on safekeepers
-
-  b) necessarily cross AZ boundaries delivering WAL to all safekeepers
-
-  Each timeline/branch has at most one writer, so the data is collected per branch.
-
-* Synthetic storage size. That is what is exposed now with pageserver's `/v1/tenant/{}/size`. Looks like now it is per-tenant. (Side note: can we make it per branch to show as branch physical size in UI?)
-
-* Real storage size. That is the size of the tenant directory on the pageservers disk. Per-tenant.
-
-* S3 storage size. That is the size of the tenant data on S3. Per-tenant.
-
-That info should be enough to build an internal model that predicts AWS price (hence tracking `written data` and `real storage size`). As for the billing model we probably can get away with mentioning only `CPU time`, `synthetic storage size`, and `traffic` consumption.
-
-# Services participating in metrics collection
-
-## Proxy
-
-For actual implementation details check `/docs/consumption_metrics.md`
-
-Proxy is the only place that knows about traffic flow, so it tracks it and reports it with quite a small interval, let's say 1 minute. A small interval is needed here since the proxy is stateless, and any restart will reset accumulated consumption. Also proxy should report deltas since the last report, not an absolute value of the counter. Such kind of events is easier to integrate over a period of time to get the amount of traffic during some time interval.
-
-Example event:
-
-```json
-{
-"metric": "proxy_io_bytes_per_client",
-"type": "incremental",
-"start_time": "2022-12-28T11:07:19.317310284Z",
-"stop_time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"endpoint_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-}
-```
-
-Since we report deltas over some period of time, it makes sense to include `event_start_time`/`event_stop_time` where `event_start_time` is the time of the previous report. That will allow us to identify metering gaps better (e.g., failed send/delivery).
-
-When there is no active connection proxy can avoid reporting anything. Also, deltas are additive, so several console instances serving the same user and endpoint can report traffic without coordination.
-
-## Console
-
-The console knows about start/stop events, so it knows the amount of CPU time allocated to each endpoint. It also knows about operation successes and failures and can avoid billing clients after unsuccessful 'suspend' events. The console doesn't know the current compute size within the allowed limits on the endpoint. So with CPU time, we do the following:
-
-* While we don't yet have the autoscaling console can report `cpu time` as the number of seconds since the last `start_compute` event.
-
-* When we have autoscaling, `autoscaler-agent` can report `cpu time`*`compute_units_count` in the same increments as the proxy reports traffic.
-
-Example event:
-
-```json
-{
-    "metric": "effective_compute_seconds",
-    "type": "increment",
-    "endpoint_id": "blazing-warrior-34",
-    "event_start_time": ...,
-    "event_stop_time": ...,
-    "value": 12345454,
-}
-```
-
-I'd also suggest reporting one value, `cpu time`*`compute_units_count`, instead of two separate fields as it makes event schema simpler (it is possible to treat it the same way as traffic) and preserves additivity.
-
-## Pageserver
-
-For actual implementation details check `/docs/consumption_metrics.md`
-
-Pageserver knows / has access to / can calculate the rest of the metrics:
-
-* Written size -- that is basically `last_received_lsn`,
-* Synthetic storage size -- there is a way to calculate it, albeit a costly one,
-* Real storage size -- there is a way to calculate it using a layer map or filesystem,
-* S3 storage size -- can calculate it by S3 API calls
-
-Some of those metrics are expensive to calculate, so the reporting period here is driven mainly by implementation details. We can set it to, for example, once per hour. Not a big deal since the pageserver is stateful, and all metrics can be reported as an absolute value, not increments. At the same time, a smaller reporting period improves UX, so it would be good to have something more real-time.
-
-`written size` is primarily a safekeeper-related metric, but since it is available on both pageserver and safekeeper, we can avoid reporting anything from the safekeeper.
-
-Example event:
-
-```json
-{
-"metric": "remote_storage_size",
-"type": "absolute",
-"time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"tenant_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-"timeline_id": "a03ebb4f5922a1c56ff7485cc8854143",
-}
-```
-
-# Data collection
-
-## Push vs. pull
-
-We already have pull-based Prometheus metrics, so it is tempting to use them here too. However, in our setup, it is hard to tell when some metric changes. For example, garbage collection will constantly free some disk space over a week, even if the project is down for that week. We could also iterate through all existing tenants/branches/endpoints, but that means some amount of code to do that properly and most likely we will end up with some per-metric hacks in the collector to cut out some of the tenants that are surely not changing that metric.
-
-With the push model, it is easier to publish data only about actively changing metrics -- pageserver knows when it performs s3 offloads, garbage collection and starts/stops consuming data from the safekeeper; proxy knows about connected clients; console / autoscaler-agent knows about active cpu time.
-
-Hence, let's go with a push-based model.
-
-## Common bus vs. proxying through the console
-
-We can implement such push systems in a few ways:
-
-a. Each component pushes its metrics to the "common bus", namely segment, Kafka, or something similar. That approach scales well, but it would be harder to test it locally, will introduce new dependencies, we will have to distribute secrets for that connection to all of the components, etc. We would also have to loop back some of the events and their aggregates to the console, as we want to show some that metrics to the user in real-time.
-
-b. Each component can call HTTP `POST` with its events to the console, and the console can forward it to the segment for later integration with metronome / orb / onebill / etc. With that approach, only the console has to speak with segment. Also since that data passes through the console, the console can save the latest metrics values, so there is no need for constant feedback of that events back from the segment.
-
-# Implementation
-
-Each (proxy|pageserver|autoscaler-agent) sends consumption events to the single endpoint in the console:
-
-```json
-POST /usage_events HTTP/1.1
-Content-Type: application/json
-
-[
-{
-"metric": "remote_storage_size",
-"type": "absolute",
-"time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"tenant_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-"timeline_id": "a03ebb4f5922a1c56ff7485cc8854143",
-},
-...
-]
-```
-
-![data flow](./images/metering.jpg)
-
-Events could be either:
-* `incremental` -- change in consumption since the previous event or service restart. That is `effective_cpu_seconds`, `traffic_in_bytes`, and `traffic_out_bytes`.
-* `absolute` -- that is the current value of a metric. All of the size-related metrics are absolute.
-
-Each service can post events at its own pace and bundle together data from different tenants/endpoints.
-
-The console algorithm upon receive of events could be the following:
-
-1. Create and send a segment event with the same content (possibly enriching it with tenant/timeline data for endpoint-based events).
-2. Update the latest state of per-tenant and per-endpoint metrics in the database.
-3. Check whether any of that metrics is above the allowed threshold and stop the project if necessary.
-
-Since all the data comes in batches, we can do the batch update to reduce the number of queries in the database. Proxy traffic is probably the most frequent metric, so with batching, we will have extra `number_of_proxies` requests to the database each minute. This is most likely fine for now but will generate many dead tuples in the console database. If that is the case, we can change step 2 to the following:
-
-2.1. Check if there $tenant_$metric / $endpoint_$metric key in Redis
-
-2.2. If no stored value is found and the metric is incremental, then fetch the current value from DWH (which keeps aggregated value for all the events) and publish it.
-
-2.3. Publish a new value (absolute metric) or add an increment to the stored value (incremental metric)
-
-## Consumption watchdog
-
-Since all the data goes through the console, we don't have to run any background thread/coroutines to check whether consumption is within the allowed limits. We only change consumption with `POST /usage_events`, so limit checks could be applied in the same handler.
-
-## Extensibility
-
-If we need to add a new metric (e.g. s3 traffic or something else), the console code should, by default, process it and publish segment event, even if the metric name is unknown to the console.
-
-## Naming & schema
-
-Each metric name should end up with units -- now `_seconds` and `_bytes`, and segment event should always have `tenant_id` and `timeline_id`/`endpoint_id` where applicable.

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

@@ -18,6 +18,10 @@ Intended to be used in integration tests and in CLI tools for local installation
 Documentation of the Neon features and concepts.
 Now it is mostly dev documentation.
 
+`/monitoring`:
+
+TODO
+
 `/pageserver`:
 
 Neon storage service.
@@ -41,9 +45,9 @@ 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`:
 
@@ -94,13 +98,6 @@ cargo hakari manage-deps
 
 If you don't have hakari installed (`error: no such subcommand: hakari`), install it by running `cargo install cargo-hakari`.
 
-### Checking Rust 3rd-parties
-[Cargo deny](https://embarkstudios.github.io/cargo-deny/index.html) is a cargo plugin that lets us lint project's dependency graph to ensure all dependencies conform to requirements. It detects security issues, matches licenses, and ensures crates only come from trusted sources.
-
-```bash
-cargo deny check
-```
-
 ## Using Python
 Note that Debian/Ubuntu Python packages are stale, as it commonly happens,
 so manual installation of dependencies is not recommended.

libs/consumption_metrics/Cargo.toml

@@ -1,16 +0,0 @@
-[package]
-name = "consumption_metrics"
-version = "0.1.0"
-edition = "2021"
-license = "Apache-2.0"
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-anyhow = "1.0.68"
-chrono = { version = "0.4", default-features = false, features = ["clock", "serde"] }
-rand = "0.8.3"
-serde = "1.0.152"
-serde_with = "2.1.0"
-utils = { version = "0.1.0", path = "../utils" }
-workspace_hack = { version = "0.1.0", path = "../../workspace_hack" }

libs/consumption_metrics/src/lib.rs

@@ -1,50 +0,0 @@
-//!
-//! Shared code for consumption metics collection
-//!
-use chrono::{DateTime, Utc};
-use rand::Rng;
-use serde::Serialize;
-
-#[derive(Serialize, Debug, Clone, Eq, PartialEq, Ord, PartialOrd)]
-#[serde(tag = "type")]
-pub enum EventType {
-    #[serde(rename = "absolute")]
-    Absolute { time: DateTime<Utc> },
-    #[serde(rename = "incremental")]
-    Incremental {
-        start_time: DateTime<Utc>,
-        stop_time: DateTime<Utc>,
-    },
-}
-
-#[derive(Serialize, Debug, Clone, Eq, PartialEq, Ord, PartialOrd)]
-pub struct Event<Extra> {
-    #[serde(flatten)]
-    #[serde(rename = "type")]
-    pub kind: EventType,
-
-    pub metric: &'static str,
-    pub idempotency_key: String,
-    pub value: u64,
-
-    #[serde(flatten)]
-    pub extra: Extra,
-}
-
-pub fn idempotency_key(node_id: String) -> String {
-    format!(
-        "{}-{}-{:04}",
-        Utc::now(),
-        node_id,
-        rand::thread_rng().gen_range(0..=9999)
-    )
-}
-
-pub const CHUNK_SIZE: usize = 1000;
-
-// Just a wrapper around a slice of events
-// to serialize it as `{"events" : [ ] }
-#[derive(serde::Serialize)]
-pub struct EventChunk<'a, T> {
-    pub events: &'a [T],
-}

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/metrics/Cargo.toml

@@ -1,12 +1,10 @@
 [package]
 name = "metrics"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-prometheus.workspace = true
-libc.workspace = true
-once_cell.workspace = true
-
-workspace_hack.workspace = true
+prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency
+libc = "0.2"
+once_cell = "1.13.0"
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/pageserver_api/Cargo.toml

@@ -1,17 +1,16 @@
 [package]
 name = "pageserver_api"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-serde.workspace = true
-serde_with.workspace = true
-const_format.workspace = true
-anyhow.workspace = true
-bytes.workspace = true
-byteorder.workspace = true
-utils.workspace = true
-postgres_ffi.workspace = true
+serde = { version = "1.0", features = ["derive"] }
+serde_with = "2.0"
+const_format = "0.2.21"
+anyhow = { version = "1.0", features = ["backtrace"] }
+bytes = "1.0.1"
+byteorder = "1.4.3"
 
-workspace_hack.workspace = true
+utils = { path = "../utils" }
+postgres_ffi = { path = "../postgres_ffi" }
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/pageserver_api/src/models.rs

@@ -1,4 +1,4 @@
-use std::num::{NonZeroU64, NonZeroUsize};
+use std::num::NonZeroU64;
 
 use byteorder::{BigEndian, ReadBytesExt};
 use serde::{Deserialize, Serialize};
@@ -44,17 +44,18 @@ impl TenantState {
 /// A state of a timeline in pageserver's memory.
 #[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 pub enum TimelineState {
-    /// The timeline is recognized by the pageserver but is not yet operational.
-    /// In particular, the walreceiver connection loop is not running for this timeline.
-    /// It will eventually transition to state Active or Broken.
-    Loading,
-    /// The timeline is fully operational.
-    /// It can be queried, and the walreceiver connection loop is running.
+    /// 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.
     Active,
-    /// The timeline was previously Loading or Active but is shutting down.
-    /// It cannot transition back into any other state.
+    /// 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:
+    /// for example, if the owning tenant goes back to Active again.
+    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,
-    /// The timeline is broken and not operational (previous states: Loading or Active).
+    /// A timeline is recognized by the pageserver, but can no longer be used for
+    /// any operations, because it failed to be activated.
     Broken,
 }
 
@@ -116,7 +117,6 @@ impl TenantCreateRequest {
 #[serde_as]
 #[derive(Serialize, Deserialize)]
 pub struct TenantConfigRequest {
-    #[serde_as(as = "DisplayFromStr")]
     pub tenant_id: TenantId,
     #[serde(default)]
     #[serde_as(as = "Option<DisplayFromStr>")]
@@ -162,8 +162,6 @@ pub struct TenantInfo {
     #[serde_as(as = "DisplayFromStr")]
     pub id: TenantId,
     pub state: TenantState,
-    /// Sum of the size of all layer files.
-    /// If a layer is present in both local FS and S3, it counts only once.
     pub current_physical_size: Option<u64>, // physical size is only included in `tenant_status` endpoint
     pub has_in_progress_downloads: Option<bool>,
 }
@@ -192,12 +190,9 @@ pub struct TimelineInfo {
     #[serde_as(as = "DisplayFromStr")]
     pub remote_consistent_lsn: Lsn,
     pub current_logical_size: Option<u64>, // is None when timeline is Unloaded
-    /// Sum of the size of all layer files.
-    /// If a layer is present in both local FS and S3, it counts only once.
     pub current_physical_size: Option<u64>, // is None when timeline is Unloaded
     pub current_logical_size_non_incremental: Option<u64>,
-
-    pub timeline_dir_layer_file_size_sum: Option<u64>,
+    pub current_physical_size_non_incremental: Option<u64>,
 
     pub wal_source_connstr: Option<String>,
     #[serde_as(as = "Option<DisplayFromStr>")]
@@ -206,28 +201,32 @@ pub struct TimelineInfo {
     pub last_received_msg_ts: Option<u128>,
     pub pg_version: u32,
 
+    pub awaits_download: bool,
+
     pub state: TimelineState,
+
+    // Some of the above fields are duplicated in 'local' and 'remote', for backwards-
+    // compatility with older clients.
+    pub local: LocalTimelineInfo,
+    pub remote: RemoteTimelineInfo,
 }
 
-#[derive(Debug, Serialize, Deserialize)]
-pub struct DownloadRemoteLayersTaskSpawnRequest {
-    pub max_concurrent_downloads: NonZeroUsize,
-}
-
+#[serde_as]
 #[derive(Debug, Serialize, Deserialize, Clone)]
-pub struct DownloadRemoteLayersTaskInfo {
-    pub task_id: String,
-    pub state: DownloadRemoteLayersTaskState,
-    pub total_layer_count: u64,         // stable once `completed`
-    pub successful_download_count: u64, // stable once `completed`
-    pub failed_download_count: u64,     // stable once `completed`
+pub struct LocalTimelineInfo {
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    pub ancestor_timeline_id: Option<TimelineId>,
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    pub ancestor_lsn: Option<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
 }
 
+#[serde_as]
 #[derive(Debug, Serialize, Deserialize, Clone)]
-pub enum DownloadRemoteLayersTaskState {
-    Running,
-    Completed,
-    ShutDown,
+pub struct RemoteTimelineInfo {
+    #[serde_as(as = "Option<DisplayFromStr>")]
+    pub remote_consistent_lsn: Option<Lsn>,
 }
 
 pub type ConfigureFailpointsRequest = Vec<FailpointConfig>;
@@ -327,7 +326,7 @@ impl PagestreamFeMessage {
         match self {
             Self::Exists(req) => {
                 bytes.put_u8(0);
-                bytes.put_u8(u8::from(req.latest));
+                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);
@@ -337,7 +336,7 @@ impl PagestreamFeMessage {
 
             Self::Nblocks(req) => {
                 bytes.put_u8(1);
-                bytes.put_u8(u8::from(req.latest));
+                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);
@@ -347,7 +346,7 @@ impl PagestreamFeMessage {
 
             Self::GetPage(req) => {
                 bytes.put_u8(2);
-                bytes.put_u8(u8::from(req.latest));
+                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);
@@ -358,7 +357,7 @@ impl PagestreamFeMessage {
 
             Self::DbSize(req) => {
                 bytes.put_u8(3);
-                bytes.put_u8(u8::from(req.latest));
+                bytes.put_u8(if req.latest { 1 } else { 0 });
                 bytes.put_u64(req.lsn.0);
                 bytes.put_u32(req.dbnode);
             }

libs/postgres_connection/Cargo.toml

@@ -1,17 +1,17 @@
 [package]
 name = "postgres_connection"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-anyhow.workspace = true
-itertools.workspace = true
-postgres.workspace = true
-tokio-postgres.workspace = true
-url.workspace = true
-
-workspace_hack.workspace = true
+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.workspace = true
+once_cell = "1.13.0"

libs/postgres_ffi/Cargo.toml

@@ -1,31 +1,29 @@
 [package]
 name = "postgres_ffi"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-rand.workspace = true
-regex.workspace = true
-bytes.workspace = true
-byteorder.workspace = true
-anyhow.workspace = true
-crc32c.workspace = true
-hex.workspace = true
-once_cell.workspace = true
-log.workspace = true
-memoffset.workspace = true
-thiserror.workspace = true
-serde.workspace = true
-utils.workspace = true
-
-workspace_hack.workspace = true
+rand = "0.8.3"
+regex = "1.4.5"
+bytes = "1.0.1"
+byteorder = "1.4.3"
+anyhow = "1.0"
+crc32c = "0.6.0"
+hex = "0.4.3"
+once_cell = "1.13.0"
+log = "0.4.14"
+memoffset = "0.7"
+thiserror = "1.0"
+serde = { version = "1.0", features = ["derive"] }
+utils = { path = "../utils" }
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }
 
 [dev-dependencies]
-env_logger.workspace = true
-postgres.workspace = true
+env_logger = "0.9"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
 wal_craft = { path = "wal_craft" }
 
 [build-dependencies]
-anyhow.workspace = true
-bindgen.workspace = true
+anyhow = "1.0"
+bindgen = "0.61"