Compare commits

..

11 Commits

Author SHA1 Message Date
Egor Suvorov
8261455019 persistent_range_query: add layer_map_test 2022-11-24 04:47:19 +02:00
Egor Suvorov
aad88d6c39 persistent_range_query: add stress test 2022-11-24 03:50:18 +02:00
Egor Suvorov
6188315b51 persistent_range_query: more refs 2022-11-24 03:45:02 +02:00
Egor Suvorov
3a4b932d8a Draft generic persistent segment tree 2022-11-24 02:31:48 +02:00
Egor Suvorov
cc2b3c986c Simplify code: fewer lifetimes, auto-impl VecFrozenVersion 2022-11-24 02:11:06 +02:00
Egor Suvorov
c250c2664b Always require Clone for RangeQueryResult 2022-11-24 01:42:14 +02:00
Egor Suvorov
e5550a01b0 VecVersion: make it read-only, only the latest version can be modified 2022-11-24 01:28:13 +02:00
Egor Suvorov
45617ceaef RangeModification: add is_no_op/is_reinitialization 2022-11-24 00:12:05 +02:00
Egor Suvorov
29b39301fe RangeQueryResult: do not require Clone and do not provide default combine/add implementations 2022-11-24 00:11:52 +02:00
Egor Suvorov
b01a93be60 persistent_range_query: second draft
Move same generic parameters to associated types.
Work around private fields of SumResult<T>
2022-11-23 23:09:25 +02:00
Egor Suvorov
4c68d019e3 persistent_range_query: first draft 2022-11-23 20:52:34 +02:00
322 changed files with 21455 additions and 54736 deletions

View File

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

View File

@@ -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 -->

View File

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

View File

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

View File

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

View File

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

View File

@@ -5,31 +5,50 @@ inputs:
api_key:
desctiption: 'Neon API key'
required: true
environment:
desctiption: 'dev (aka captest) or stage'
required: true
project_id:
desctiption: 'ID of the Project to delete'
required: true
api_host:
desctiption: 'Neon API host'
default: console.stage.neon.tech
runs:
using: "composite"
steps:
- name: Delete Neon Project
# Do not try to delete a project if .github/actions/neon-project-create failed before
if: ${{ inputs.project_id != '' }}
- name: Parse Input
id: parse-input
shell: bash -euxo pipefail {0}
run: |
curl \
"https://${API_HOST}/api/v2/projects/${PROJECT_ID}" \
--fail \
--request DELETE \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}"
case "${ENVIRONMENT}" in
dev)
API_HOST=console.dev.neon.tech
;;
staging)
API_HOST=console.stage.neon.tech
;;
*)
echo 2>&1 "Unknown environment=${ENVIRONMENT}. Allowed 'dev' or 'staging' only"
exit 1
;;
esac
echo "Project ${PROJECT_ID} has been deleted"
echo "api_host=${API_HOST}" >> $GITHUB_OUTPUT
env:
ENVIRONMENT: ${{ inputs.environment }}
- name: Delete Neon Project
shell: bash -euxo pipefail {0}
run: |
# Allow PROJECT_ID to be empty/null for cases when .github/actions/neon-project-create failed
if [ -n "${PROJECT_ID}" ]; then
curl -X "POST" \
"https://${API_HOST}/api/v1/projects/${PROJECT_ID}/delete" \
--fail \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}"
fi
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
PROJECT_ID: ${{ inputs.project_id }}
API_HOST: ${{ steps.parse-input.outputs.api_host }}

View File

@@ -123,8 +123,8 @@ runs:
exit 1
fi
if [[ "${{ inputs.run_in_parallel }}" == "true" ]]; then
# -n8 uses eight processes to run tests via pytest-xdist
EXTRA_PARAMS="-n8 $EXTRA_PARAMS"
# -n4 uses four processes to run tests via pytest-xdist
EXTRA_PARAMS="-n4 $EXTRA_PARAMS"
# --dist=loadgroup points tests marked with @pytest.mark.xdist_group
# to the same worker to make @pytest.mark.order work with xdist

View File

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

View File

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

31
.github/ansible/neon-stress.hosts.yaml vendored Normal file
View File

@@ -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

View File

@@ -3,7 +3,7 @@ storage:
bucket_name: neon-prod-storage-ap-southeast-1
bucket_region: ap-southeast-1
console_mgmt_base_url: http://console-release.local
broker_endpoint: 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
remote_storage:
@@ -16,7 +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:

View File

@@ -3,7 +3,7 @@ storage:
bucket_name: neon-prod-storage-eu-central-1
bucket_region: eu-central-1
console_mgmt_base_url: http://console-release.local
broker_endpoint: 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
remote_storage:
@@ -16,7 +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:

View File

@@ -3,7 +3,7 @@ storage:
bucket_name: neon-prod-storage-us-east-2
bucket_region: us-east-2
console_mgmt_base_url: http://console-release.local
broker_endpoint: 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
remote_storage:
@@ -16,7 +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:

View File

@@ -1,39 +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
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

View File

@@ -4,7 +4,7 @@ storage:
console_mgmt_base_url: http://console-release.local
bucket_name: zenith-storage-oregon
bucket_region: us-west-2
broker_endpoint: http://storage-broker.prod.local:50051
etcd_endpoints: zenith-1-etcd.local:2379
pageserver_config_stub:
pg_distrib_dir: /usr/local
remote_storage:
@@ -14,7 +14,6 @@ storage:
safekeeper_s3_prefix: prod-1/wal
hostname_suffix: ".local"
remote_user: admin
sentry_environment: production
children:
pageservers:
@@ -34,5 +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

View File

@@ -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

View File

@@ -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: development
children:
pageservers:

34
.github/ansible/staging.hosts.yaml vendored Normal file
View File

@@ -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

View File

@@ -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: development
children:
pageservers:
@@ -27,8 +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
safekeepers:
hosts:

View File

@@ -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

View File

@@ -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

View File

@@ -8,7 +8,6 @@ settings:
authBackend: "console"
authEndpoint: "http://console-staging.local/management/api/v2"
domain: "*.eu-west-1.aws.neon.build"
sentryEnvironment: "development"
# -- Additional labels for neon-proxy pods
podLabels:
@@ -30,28 +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 }}"

View File

@@ -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: "development"

View File

@@ -1,65 +0,0 @@
# Helm chart values for neon-proxy-link.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "link"
authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
uri: "https://console.stage.neon.tech/psql_session/"
sentryEnvironment: "development"
# -- Additional labels for neon-proxy-link pods
podLabels:
zenith_service: proxy
zenith_env: dev
zenith_region: us-east-2
zenith_region_slug: us-east-2
service:
type: LoadBalancer
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal
external-dns.alpha.kubernetes.io/hostname: neon-proxy-link-mgmt.beta.us-east-2.aws.neon.build
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: neon-proxy-link.beta.us-east-2.aws.neon.build
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
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 }}"

View File

@@ -1,57 +0,0 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-staging.local/management/api/v2"
domain: "*.cloud.stage.neon.tech"
sentryEnvironment: "development"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram-legacy
zenith_env: dev
zenith_region: us-east-2
zenith_region_slug: us-east-2
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: neon-proxy-scram-legacy.beta.us-east-2.aws.neon.build
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
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 }}"

View File

@@ -8,7 +8,6 @@ settings:
authBackend: "console"
authEndpoint: "http://console-staging.local/management/api/v2"
domain: "*.us-east-2.aws.neon.build"
sentryEnvironment: "development"
# -- Additional labels for neon-proxy pods
podLabels:
@@ -30,28 +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 }}"

View File

@@ -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: "development"

View File

@@ -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

View File

@@ -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

View File

@@ -8,7 +8,6 @@ settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.ap-southeast-1.aws.neon.tech"
sentryEnvironment: "production"
# -- Additional labels for neon-proxy pods
podLabels:
@@ -30,28 +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 }}"

View File

@@ -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"

View File

@@ -8,7 +8,6 @@ settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.eu-central-1.aws.neon.tech"
sentryEnvironment: "production"
# -- Additional labels for neon-proxy pods
podLabels:
@@ -30,28 +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 }}"

View File

@@ -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"

View File

@@ -8,7 +8,6 @@ settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.us-east-2.aws.neon.tech"
sentryEnvironment: "production"
# -- Additional labels for neon-proxy pods
podLabels:
@@ -30,28 +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 }}"

View File

@@ -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"

View File

@@ -1,57 +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"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: prod
zenith_region: us-west-2
zenith_region_slug: us-west-2
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: us-west-2.aws.neon.tech
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
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 }}"

View File

@@ -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"

View File

@@ -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"

View File

@@ -2,7 +2,6 @@ settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.cloud.neon.tech"
sentryEnvironment: "production"
podLabels:
zenith_service: proxy-scram
@@ -23,28 +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 }}"

View File

@@ -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 }}"

View File

@@ -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

31
.github/helm-values/staging.proxy.yaml vendored Normal file
View File

@@ -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

View File

@@ -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 +37,97 @@ concurrency:
jobs:
bench:
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "300"
TEST_PG_BENCH_SCALES_MATRIX: "10,100"
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: "neon-staging"
# this workflow runs on self hosteed runner
# it's environment is quite different from usual guthub runner
# probably the most important difference is that it doesn't start from clean workspace each time
# e g if you install system packages they are not cleaned up since you install them directly in host machine
# not a container or something
# See documentation for more info: https://docs.github.com/en/actions/hosting-your-own-runners/about-self-hosted-runners
runs-on: [self-hosted, zenith-benchmarker]
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
env:
POSTGRES_DISTRIB_DIR: /usr/pgsql
DEFAULT_PG_VERSION: 14
steps:
- uses: actions/checkout@v3
- name: Checkout zenith repo
uses: actions/checkout@v3
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-release-artifact
path: /tmp/neon/
prefix: latest
# actions/setup-python@v2 is not working correctly on self-hosted runners
# see https://github.com/actions/setup-python/issues/162
# and probably https://github.com/actions/setup-python/issues/162#issuecomment-865387976 in particular
# so the simplest solution to me is to use already installed system python and spin virtualenvs for job runs.
# there is Python 3.7.10 already installed on the machine so use it to install poetry and then use poetry's virtuealenvs
- name: Install poetry & deps
run: |
python3 -m pip install --upgrade poetry wheel
# since pip/poetry caches are reused there shouldn't be any troubles with install every time
./scripts/pysync
- name: Show versions
run: |
echo Python
python3 --version
poetry run python3 --version
echo Poetry
poetry --version
echo Pgbench
${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
- name: Create Neon Project
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
postgres_version: ${{ env.DEFAULT_PG_VERSION }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
environment: ${{ github.event.inputs.environment || 'staging' }}
api_key: ${{ ( github.event.inputs.environment || 'staging' ) == 'staging' && secrets.NEON_STAGING_API_KEY || secrets.NEON_CAPTEST_API_KEY }}
- name: Run benchmark
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
# Set --sparse-ordering option of pytest-order plugin
# to ensure tests are running in order of appears in the file.
# It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
extra_params: -m remote_cluster --sparse-ordering --timeout 5400 --ignore test_runner/performance/test_perf_olap.py
# pgbench is installed system wide from official repo
# https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
# via
# sudo tee /etc/yum.repos.d/pgdg.repo<<EOF
# [pgdg13]
# name=PostgreSQL 13 for RHEL/CentOS 7 - x86_64
# baseurl=https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
# enabled=1
# gpgcheck=0
# EOF
# sudo yum makecache
# sudo yum install postgresql13-contrib
# actual binaries are located in /usr/pgsql-13/bin/
env:
# The pgbench test runs two tests of given duration against each scale.
# So the total runtime with these parameters is 2 * 2 * 300 = 1200, or 20 minutes.
# Plus time needed to initialize the test databases.
TEST_PG_BENCH_DURATIONS_MATRIX: "300"
TEST_PG_BENCH_SCALES_MATRIX: "10,100"
PLATFORM: "neon-staging"
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
REMOTE_ENV: "1" # indicate to test harness that we do not have zenith binaries locally
run: |
# just to be sure that no data was cached on self hosted runner
# since it might generate duplicates when calling ingest_perf_test_result.py
rm -rf perf-report-staging
mkdir -p perf-report-staging
# Set --sparse-ordering option of pytest-order plugin to ensure tests are running in order of appears in the file,
# it's important for test_perf_pgbench.py::test_pgbench_remote_* tests
./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --sparse-ordering --out-dir perf-report-staging --timeout 5400
- name: Submit result
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
run: |
REPORT_FROM=$(realpath perf-report-staging) REPORT_TO=staging scripts/generate_and_push_perf_report.sh
- name: Delete Neon Project
if: ${{ always() }}
uses: ./.github/actions/neon-project-delete
with:
environment: staging
project_id: ${{ steps.create-neon-project.outputs.project_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Create Allure report
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
@@ -116,16 +146,15 @@ 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 +166,9 @@ 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 +193,8 @@ 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: ${{ ( github.event.inputs.environment || 'dev' ) == 'staging' && secrets.NEON_STAGING_API_KEY || secrets.NEON_CAPTEST_API_KEY }}
- name: Set up Connection String
id: set-up-connstr
@@ -179,7 +207,7 @@ jobs:
CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
;;
rds-aurora)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
CONNSTR=${{ secrets.BENCHMARK_RDS_CONNSTR }}
;;
rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
@@ -197,11 +225,8 @@ jobs:
- name: Set database options
if: matrix.platform == 'neon-captest-prefetch'
run: |
DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET enable_seqscan_prefetch=on"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE main SET seqscan_prefetch_buffers=10"
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
@@ -244,13 +269,6 @@ jobs:
VIP_VAP_ACCESS_TOKEN: "${{ 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 +276,14 @@ 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
@@ -266,226 +292,3 @@ jobs:
slack-message: "Periodic perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
clickbench-compare:
# ClichBench DB for rds-aurora and rds-Postgres deployed to the same clusters
# we use for performance testing in pgbench-compare.
# Run this job only when pgbench-compare is finished to avoid the intersection.
# We might change it after https://github.com/neondatabase/neon/issues/2900.
#
# *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
# *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
if: success() || failure()
needs: [ pgbench-compare ]
strategy:
fail-fast: false
matrix:
# neon-captest-prefetch: We have pre-created projects with prefetch enabled
# rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
# rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-release-artifact
path: /tmp/neon/
prefix: latest
- name: Add Postgres binaries to PATH
run: |
${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
- name: Set up Connection String
id: set-up-connstr
run: |
case "${PLATFORM}" in
neon-captest-prefetch)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
;;
rds-aurora)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
;;
rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
;;
*)
echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
exit 1
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
psql ${CONNSTR} -c "SELECT version();"
- name: Set database options
if: matrix.platform == 'neon-captest-prefetch'
run: |
DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: ClickBench benchmark
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance/test_perf_olap.py
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_clickbench
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: Create Allure report
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: "Periodic OLAP perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
tpch-compare:
# TCP-H DB for rds-aurora and rds-Postgres deployed to the same clusters
# we use for performance testing in pgbench-compare & clickbench-compare.
# Run this job only when clickbench-compare is finished to avoid the intersection.
# We might change it after https://github.com/neondatabase/neon/issues/2900.
#
# *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
if: success() || failure()
needs: [ clickbench-compare ]
strategy:
fail-fast: false
matrix:
# neon-captest-prefetch: We have pre-created projects with prefetch enabled
# rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
# rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ 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 }}

View File

@@ -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
@@ -582,40 +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}
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: Build vm image
run: |
./vm-builder -src=369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}} -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:
@@ -659,13 +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
@@ -698,15 +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
@@ -718,9 +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: |
@@ -737,15 +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
@@ -757,36 +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 '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
exit 1
fi
deploy:
runs-on: [ self-hosted, dev, x64 ]
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
runs-on: [ self-hosted, Linux, k8s-runner ]
#container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:latest
# We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
# If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
if: |
github.ref_name == 'release' &&
(github.ref_name == 'main' || github.ref_name == 'release') &&
github.event_name != 'workflow_dispatch'
defaults:
run:
@@ -801,6 +701,16 @@ jobs:
submodules: true
fetch-depth: 0
- name: Setup python
uses: actions/setup-python@v4
with:
python-version: '3.10'
- name: Setup ansible
run: |
export PATH="/root/.local/bin:$PATH"
pip install --progress-bar off --user ansible boto3 toml
- name: Redeploy
run: |
export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
@@ -821,8 +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:
@@ -830,7 +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'
@@ -860,7 +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:
@@ -870,7 +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:
@@ -893,7 +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:
@@ -910,7 +820,7 @@ jobs:
shell: bash
strategy:
matrix:
target_region: [ us-east-2, us-west-2, eu-central-1, ap-southeast-1 ]
target_region: [ us-east-2, eu-central-1, ap-southeast-1 ]
steps:
- name: Checkout
uses: actions/checkout@v3
@@ -933,16 +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:
@@ -975,102 +885,10 @@ jobs:
- name: Re-deploy proxy
run: |
DOCKER_TAG=${{needs.tag.outputs.build-tag}}
helm upgrade ${{ matrix.proxy_job }} neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
helm upgrade ${{ matrix.proxy_job }}-scram neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
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: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
env:
KUBECONFIG: .kubeconfig
steps:
- name: Checkout
uses: actions/checkout@v3
with:
submodules: true
fetch-depth: 0
- name: Add curl
run: apt update && apt install curl -y
- name: Store kubeconfig file
run: |
echo "${{ 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 ]
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
deploy_link_proxy: true
deploy_legacy_scram_proxy: true
- target_region: eu-west-1
target_cluster: dev-eu-west-1-zeta
deploy_link_proxy: false
deploy_legacy_scram_proxy: false
steps:
- name: Checkout
uses: actions/checkout@v3
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 ${{ matrix.target_cluster }}
- name: Re-deploy scram proxy
run: |
DOCKER_TAG=${{needs.tag.outputs.build-tag}}
helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
- name: Re-deploy link proxy
if: matrix.deploy_link_proxy
run: |
DOCKER_TAG=${{needs.tag.outputs.build-tag}}
helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
- name: Re-deploy legacy scram proxy
if: matrix.deploy_legacy_scram_proxy
run: |
DOCKER_TAG=${{needs.tag.outputs.build-tag}}
helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram-legacy.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
deploy-storage-broker-dev-new:
runs-on: [ self-hosted, dev, x64 ]
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
# Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
@@ -1100,9 +918,10 @@ jobs:
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
- name: Re-deploy proxy
run: |
DOCKER_TAG=${{needs.tag.outputs.build-tag}}
helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --wait --timeout 15m0s
deploy-proxy-prod-new:
runs-on: prod
@@ -1120,8 +939,6 @@ jobs:
include:
- target_region: us-east-2
target_cluster: prod-us-east-2-delta
- target_region: us-west-2
target_cluster: prod-us-west-2-eta
- target_region: eu-central-1
target_cluster: prod-eu-central-1-gamma
- target_region: ap-southeast-1
@@ -1141,45 +958,7 @@ jobs:
- name: Re-deploy proxy
run: |
DOCKER_TAG=${{needs.tag.outputs.build-tag}}
helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -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
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 ]
@@ -1190,6 +969,7 @@ 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

166
.github/workflows/codestyle.yml vendored Normal file
View File

@@ -0,0 +1,166 @@
name: Check code style and build
on:
push:
branches:
- main
pull_request:
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
cancel-in-progress: true
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
jobs:
check-codestyle-rust:
strategy:
fail-fast: false
matrix:
# XXX: both OSes have rustup
# * https://github.com/actions/runner-images/blob/main/images/macos/macos-12-Readme.md#rust-tools
# * https://github.com/actions/runner-images/blob/main/images/linux/Ubuntu2204-Readme.md#rust-tools
# this is all we need to install our toolchain later via rust-toolchain.toml
# so don't install any toolchain explicitly.
os: [ubuntu-latest, macos-latest]
timeout-minutes: 90
name: check codestyle rust and postgres
runs-on: ${{ matrix.os }}
steps:
- name: Checkout
uses: actions/checkout@v3
with:
submodules: true
fetch-depth: 2
- name: Check formatting
run: cargo fmt --all -- --check
- name: Install Ubuntu postgres dependencies
if: matrix.os == 'ubuntu-latest'
run: |
sudo apt update
sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev
- name: Install macOS postgres dependencies
if: matrix.os == 'macos-latest'
run: brew install flex bison openssl
- name: Set pg 14 revision for caching
id: pg_v14_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
shell: bash -euxo pipefail {0}
- name: Set pg 15 revision for caching
id: pg_v15_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
shell: bash -euxo pipefail {0}
- name: Cache postgres v14 build
id: cache_pg_14
uses: actions/cache@v3
with:
path: pg_install/v14
key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v15 build
id: cache_pg_15
uses: actions/cache@v3
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Set extra env for macOS
if: matrix.os == 'macos-latest'
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: make postgres-v14
shell: bash -euxo pipefail {0}
- name: Build postgres v15
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: make postgres-v15
shell: bash -euxo pipefail {0}
- name: Build neon extensions
run: make neon-pg-ext
- name: Cache cargo deps
id: cache_cargo
uses: actions/cache@v3
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v6-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust
- name: Run cargo clippy
run: ./run_clippy.sh
- name: Ensure all project builds
run: cargo build --locked --all --all-targets
check-rust-dependencies:
runs-on: [ self-hosted, dev, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
steps:
- name: Checkout
uses: actions/checkout@v3
with:
submodules: false
fetch-depth: 1
# https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
- name: Check every project module is covered by Hakari
run: |
cargo hakari generate --diff # workspace-hack Cargo.toml is up-to-date
cargo hakari manage-deps --dry-run # all workspace crates depend on workspace-hack
shell: bash -euxo pipefail {0}
check-codestyle-python:
runs-on: [ self-hosted, Linux, k8s-runner ]
steps:
- name: Checkout
uses: actions/checkout@v3
with:
submodules: false
fetch-depth: 1
- name: Cache poetry deps
id: cache_poetry
uses: actions/cache@v3
with:
path: ~/.cache/pypoetry/virtualenvs
key: v1-codestyle-python-deps-${{ 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 .

View File

@@ -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/

View File

@@ -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 }}

1923
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -16,7 +16,6 @@ members = [
"pageserver",
"proxy",
"safekeeper",
"storage_broker",
"workspace_hack",
"libs/*",
]
@@ -86,4 +85,4 @@ 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="43e6db254a97fdecbce33d8bc0890accfd74495e" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }

View File

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

View File

@@ -170,6 +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.
@@ -197,6 +200,9 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
# libreadline8 for psql
# libossp-uuid16 for extension ossp-uuid
# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
#
# Lastly, link compute_ctl into zenith_ctl while we're at it,
# so that we don't need to put this in another layer.
RUN apt update && \
apt install --no-install-recommends -y \
libreadline8 \
@@ -204,9 +210,9 @@ RUN apt update && \
libgeos-c1v5 \
libgdal28 \
libproj19 \
libprotobuf-c1 \
gdb && \
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
libprotobuf-c1 && \
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
ln /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
USER postgres
ENTRYPOINT ["/usr/local/bin/compute_ctl"]

View File

@@ -170,6 +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.
@@ -197,6 +200,9 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
# libreadline8 for psql
# libossp-uuid16 for extension ossp-uuid
# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
#
# Lastly, link compute_ctl into zenith_ctl while we're at it,
# so that we don't need to put this in another layer.
RUN apt update && \
apt install --no-install-recommends -y \
libreadline8 \
@@ -204,9 +210,9 @@ RUN apt update && \
libgeos-c1v5 \
libgdal28 \
libproj19 \
libprotobuf-c1 \
gdb && \
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
libprotobuf-c1 && \
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
ln /usr/local/bin/compute_ctl /usr/local/bin/zenith_ctl
USER postgres
ENTRYPOINT ["/usr/local/bin/compute_ctl"]

203
Makefile
View File

@@ -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

View File

@@ -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
```
* 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
```
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)
@@ -124,12 +132,12 @@ Stopped pageserver 1 process with pid 2545906
# 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
safekeeper 1 started, pid: 2546041
# start postgres compute node
> ./target/debug/neon_local pg start main
@@ -221,20 +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.

View File

@@ -2,23 +2,22 @@
name = "compute_tools"
version = "0.1.0"
edition = "2021"
license = "Apache-2.0"
[dependencies]
anyhow = "1.0"
chrono = { version = "0.4", default-features = false, features = ["clock"] }
chrono = "0.4"
clap = "4.0"
env_logger = "0.9"
futures = "0.3.13"
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="43e6db254a97fdecbce33d8bc0890accfd74495e" }
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="43e6db254a97fdecbce33d8bc0890accfd74495e" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
url = "2.2.2"
workspace_hack = { version = "0.1", path = "../workspace_hack" }

View File

@@ -105,7 +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);

View File

@@ -5,7 +5,7 @@ use tokio_postgres::NoTls;
use crate::compute::ComputeNode;
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,

View File

@@ -23,11 +23,11 @@ use std::sync::RwLock;
use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use log::{info, warn};
use log::info;
use postgres::{Client, NoTls};
use serde::{Serialize, Serializer};
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;
@@ -158,7 +175,7 @@ impl ComputeNode {
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()
@@ -236,7 +253,7 @@ impl ComputeNode {
// 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");
@@ -275,7 +292,7 @@ impl ComputeNode {
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);
@@ -311,9 +328,6 @@ impl ComputeNode {
.wait()
.expect("failed to start waiting on Postgres process");
self.check_for_core_dumps()
.expect("failed to check for core dumps");
Ok(ecode)
}
@@ -329,68 +343,4 @@ impl ComputeNode {
self.prepare_pgdata()?;
self.run()
}
// 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.
fn check_for_core_dumps(&self) -> Result<()> {
let core_dump_dir = match std::env::consts::OS {
"macos" => Path::new("/cores/"),
_ => Path::new(&self.pgdata),
};
// 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(())
}
}

View File

@@ -9,11 +9,29 @@ use hyper::{Body, Method, Request, Response, Server, StatusCode};
use log::{error, info};
use serde_json;
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;

View File

@@ -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"

View File

@@ -74,8 +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;
}
}

View File

@@ -119,9 +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,
}
}
}
@@ -154,14 +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
@@ -220,7 +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)

View File

@@ -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);
}
}

View File

@@ -2,7 +2,6 @@
name = "control_plane"
version = "0.1.0"
edition = "2021"
license = "Apache-2.0"
[dependencies]
anyhow = "1.0"
@@ -11,7 +10,7 @@ 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 = "43e6db254a97fdecbce33d8bc0890accfd74495e" }
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"] }
@@ -24,9 +23,6 @@ url = "2.2.2"
# Note: Do not directly depend on pageserver or safekeeper; use pageserver_api or safekeeper_api
# instead, so that recompile times are better.
pageserver_api = { path = "../libs/pageserver_api" }
postgres_connection = { path = "../libs/postgres_connection" }
safekeeper_api = { path = "../libs/safekeeper_api" }
# Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
storage_broker = { version = "0.1", path = "../storage_broker" }
utils = { path = "../libs/utils" }
workspace_hack = { version = "0.1", path = "../workspace_hack" }

View File

@@ -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']

View File

@@ -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 +49,16 @@ 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>>(
process_name: &str,
datadir: &Path,
command: &Path,
args: AI,
envs: EI,
args: &[S],
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()
@@ -86,15 +79,6 @@ where
.stderr(same_file_for_stderr)
.args(args);
let filled_cmd = fill_aws_secrets_vars(fill_rust_env_vars(background_command));
filled_cmd.envs(envs);
let pid_file_to_check = match initial_pid_file {
InitialPidFile::Create(path) => {
pre_exec_create_pidfile(filled_cmd, path);
path
}
InitialPidFile::Expect(path) => path,
};
let mut spawned_process = filled_cmd.spawn().with_context(|| {
format!("Could not spawn {process_name}, see console output and log files for details.")
@@ -105,8 +89,29 @@ 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);
@@ -136,45 +141,14 @@ 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
@@ -186,9 +160,8 @@ 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(());
}
@@ -200,6 +173,11 @@ pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> any
match process_has_stopped(pid) {
Ok(true) => {
println!("\n{process_name} stopped");
if let Err(e) = fs::remove_file(pid_file) {
if e.kind() != io::ErrorKind::NotFound {
eprintln!("Failed to remove pid file {pid_file:?} after stopping the process: {e:#}");
}
}
return Ok(());
}
Ok(false) => {
@@ -225,14 +203,7 @@ pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> any
}
fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
// If RUST_BACKTRACE is set, pass it through. But if it's not set, default
// to RUST_BACKTRACE=1.
let backtrace_setting = std::env::var_os("RUST_BACKTRACE");
let backtrace_setting = backtrace_setting
.as_deref()
.unwrap_or_else(|| OsStr::new("1"));
let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", backtrace_setting);
let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", "1");
// Pass through these environment variables to the command
for var in ["LLVM_PROFILE_FILE", "FAILPOINTS", "RUST_LOG"] {
@@ -257,69 +228,6 @@ fn fill_aws_secrets_vars(mut cmd: &mut Command) -> &mut Command {
cmd
}
/// Add a `pre_exec` to the cmd that, inbetween fork() and exec(),
/// 1. Claims a pidfile with a fcntl lock on it and
/// 2. Sets up the pidfile's file descriptor so that it (and the lock)
/// will remain held until the cmd exits.
fn pre_exec_create_pidfile<P>(cmd: &mut Command, path: P) -> &mut Command
where
P: Into<PathBuf>,
{
let path: PathBuf = path.into();
// SAFETY
// pre_exec is marked unsafe because it runs between fork and exec.
// Why is that dangerous in various ways?
// Long answer: https://github.com/rust-lang/rust/issues/39575
// Short answer: in a multi-threaded program, other threads may have
// been inside of critical sections at the time of fork. In the
// original process, that was allright, assuming they protected
// the critical sections appropriately, e.g., through locks.
// Fork adds another process to the mix that
// 1. Has a single thread T
// 2. In an exact copy of the address space at the time of fork.
// A variety of problems scan occur now:
// 1. T tries to grab a lock that was locked at the time of fork.
// It will wait forever since in its address space, the lock
// is in state 'taken' but the thread that would unlock it is
// not there.
// 2. A rust object that represented some external resource in the
// parent now got implicitly copied by the the fork, even though
// the object's type is not `Copy`. The parent program may use
// non-copyability as way to enforce unique ownership of an
// external resource in the typesystem. The fork breaks that
// assumption, as now both parent and child process have an
// owned instance of the object that represents the same
// underlying resource.
// While these seem like niche problems, (1) in particular is
// highly relevant. For example, `malloc()` may grab a mutex internally,
// and so, if we forked while another thread was mallocing' and our
// pre_exec closure allocates as well, it will block on the malloc
// mutex forever
//
// The proper solution is to only use C library functions that are marked
// "async-signal-safe": https://man7.org/linux/man-pages/man7/signal-safety.7.html
//
// With this specific pre_exec() closure, the non-error path doesn't allocate.
// The error path uses `anyhow`, and hence does allocate.
// We take our chances there, hoping that any potential disaster is constrained
// to the child process (e.g., malloc has no state ourside of the child process).
// Last, `expect` prints to stderr, and stdio is not async-signal-safe.
// Again, we take our chances, making the same assumptions as for malloc.
unsafe {
cmd.pre_exec(move || {
let file = pid_file::claim_for_current_process(&path).expect("claim pid file");
// Remove the FD_CLOEXEC flag on the pidfile descriptor so that the pidfile
// remains locked after exec.
nix::fcntl::fcntl(file.as_raw_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
.expect("remove FD_CLOEXEC");
// Don't run drop(file), it would close the file before we actually exec.
std::mem::forget(file);
Ok(())
});
}
cmd
}
fn process_started<F>(
pid: Pid,
pid_file_to_check: Option<&Path>,
@@ -330,11 +238,14 @@ where
{
match status_check() {
Ok(true) => match pid_file_to_check {
Some(pid_file_path) => match pid_file::read(pid_file_path)? {
PidFileRead::NotExist => Ok(false),
PidFileRead::LockedByOtherProcess(pid_in_file) => Ok(pid_in_file == pid),
PidFileRead::NotHeldByAnyProcess(_) => Ok(false),
},
Some(pid_file_path) => {
if pid_file_path.exists() {
let pid_in_file = read_pidfile(pid_file_path)?;
Ok(pid_in_file == pid)
} else {
Ok(false)
}
}
None => Ok(true),
},
Ok(false) => Ok(false),
@@ -342,6 +253,21 @@ 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

View File

@@ -8,10 +8,10 @@
use anyhow::{anyhow, bail, Context, Result};
use clap::{value_parser, Arg, ArgAction, ArgMatches, Command};
use control_plane::compute::ComputeControlPlane;
use control_plane::local_env::LocalEnv;
use control_plane::local_env::{EtcdBroker, LocalEnv};
use control_plane::pageserver::PageServerNode;
use control_plane::safekeeper::SafekeeperNode;
use control_plane::{broker, local_env};
use control_plane::{etcd, local_env};
use pageserver_api::models::TimelineInfo;
use pageserver_api::{
DEFAULT_HTTP_LISTEN_ADDR as DEFAULT_PAGESERVER_HTTP_ADDR,
@@ -22,10 +22,9 @@ use safekeeper_api::{
DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT,
};
use std::collections::{BTreeSet, HashMap};
use std::path::PathBuf;
use std::path::{Path, PathBuf};
use std::process::exit;
use std::str::FromStr;
use storage_broker::DEFAULT_LISTEN_ADDR as DEFAULT_BROKER_ADDR;
use utils::{
auth::{Claims, Scope},
id::{NodeId, TenantId, TenantTimelineId, TimelineId},
@@ -42,12 +41,13 @@ project_git_version!(GIT_VERSION);
const DEFAULT_PG_VERSION: &str = "14";
fn default_conf() -> String {
fn default_conf(etcd_binary_path: &Path) -> String {
format!(
r#"
# Default built-in configuration, defined in main.rs
[broker]
listen_addr = '{DEFAULT_BROKER_ADDR}'
[etcd_broker]
broker_endpoints = ['http://localhost:2379']
etcd_binary_path = '{etcd_binary_path}'
[pageserver]
id = {DEFAULT_PAGESERVER_ID}
@@ -60,6 +60,7 @@ id = {DEFAULT_SAFEKEEPER_ID}
pg_port = {DEFAULT_SAFEKEEPER_PG_PORT}
http_port = {DEFAULT_SAFEKEEPER_HTTP_PORT}
"#,
etcd_binary_path = etcd_binary_path.display(),
pageserver_auth_type = AuthType::Trust,
)
}
@@ -297,7 +298,7 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
})?
} else {
// Built-in default config
default_conf()
default_conf(&EtcdBroker::locate_etcd()?)
};
let pg_version = init_match
@@ -323,7 +324,7 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
pg_version,
)
.unwrap_or_else(|e| {
eprintln!("pageserver init failed: {e:?}");
eprintln!("pageserver init failed: {e}");
exit(1);
});
@@ -341,7 +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()
}
@@ -549,7 +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",
@@ -584,7 +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(),
@@ -747,7 +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)
}
}
@@ -806,22 +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);
}
}
@@ -832,41 +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}");
}
}
@@ -906,7 +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");

View File

@@ -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")
}

View File

@@ -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 $ZENITH_AUTH_TOKEN
// We parse this string and build it back with token from env var, and for simplicity rebuild
// uses only needed variables namely host, port, user, password.
format!("postgresql://no_user:{password}@{host}:{port}")
@@ -322,9 +322,6 @@ impl PostgresNode {
conf.append("shared_preload_libraries", "neon");
conf.append_line("");
conf.append("neon.pageserver_connstring", &pageserver_connstr);
if let AuthType::NeonJWT = auth_type {
conf.append("neon.safekeeper_token_env", "$NEON_AUTH_TOKEN");
}
conf.append("neon.tenant_id", &self.tenant_id.to_string());
conf.append("neon.timeline_id", &self.timeline_id.to_string());
if let Some(lsn) = self.lsn {
@@ -448,7 +445,7 @@ 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 +475,7 @@ 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 +511,7 @@ 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)?;
}

View File

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

77
control_plane/src/etcd.rs Normal file
View File

@@ -0,0 +1,77 @@
use std::{fs, path::PathBuf};
use anyhow::Context;
use crate::{background_process, local_env};
pub fn start_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
let etcd_broker = &env.etcd_broker;
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")
}

View File

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

View File

@@ -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")
}
@@ -404,7 +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
@@ -413,7 +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()
@@ -430,10 +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")?;
@@ -478,8 +511,8 @@ mod tests {
"failed to parse simple config {simple_conf_toml}, reason: {simple_conf_parse_result:?}"
);
let string_to_replace = "listen_addr = '127.0.0.1:50051'";
let spoiled_url_str = "listen_addr = '!@$XOXO%^&'";
let string_to_replace = "broker_endpoints = ['http://127.0.0.1:2379']";
let spoiled_url_str = "broker_endpoints = ['!@$XOXO%^&']";
let spoiled_url_toml = simple_conf_toml.replace(string_to_replace, spoiled_url_str);
assert!(
spoiled_url_toml.contains(spoiled_url_str),

View File

@@ -1,21 +1,19 @@
use std::borrow::Cow;
use std::collections::HashMap;
use std::fs::File;
use std::fs::{self, File};
use std::io::{BufReader, Write};
use std::num::NonZeroU64;
use std::path::PathBuf;
use std::process::{Child, Command};
use std::path::{Path, PathBuf};
use std::process::Child;
use std::{io, result};
use anyhow::{bail, ensure, Context};
use crate::connection::PgConnectionConfig;
use anyhow::{bail, Context};
use pageserver_api::models::{
TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
};
use postgres_connection::{parse_host_port, PgConnectionConfig};
use reqwest::blocking::{Client, RequestBuilder, Response};
use reqwest::{IntoUrl, Method};
use thiserror::Error;
use utils::auth::{Claims, Scope};
use utils::{
http::error::HttpErrorBody,
id::{TenantId, TimelineId},
@@ -79,26 +77,37 @@ pub struct PageServerNode {
impl PageServerNode {
pub fn from_env(env: &LocalEnv) -> PageServerNode {
let (host, port) = parse_host_port(&env.pageserver.listen_pg_addr)
.expect("Unable to parse listen_pg_addr");
let port = port.unwrap_or(5432);
let password = if env.pageserver.auth_type == AuthType::NeonJWT {
Some(env.pageserver.auth_token.clone())
&env.pageserver.auth_token
} else {
None
""
};
Self {
pg_connection_config: PgConnectionConfig::new_host_port(host, port)
.set_password(password),
pg_connection_config: Self::pageserver_connection_config(
password,
&env.pageserver.listen_pg_addr,
),
env: env.clone(),
http_client: Client::new(),
http_base_url: format!("http://{}/v1", env.pageserver.listen_http_addr),
}
}
// pageserver conf overrides defined by neon_local configuration.
fn neon_local_overrides(&self) -> Vec<String> {
/// Construct libpq connection string for connecting to the pageserver.
fn pageserver_connection_config(password: &str, listen_addr: &str) -> PgConnectionConfig {
format!("postgresql://no_user:{password}@{listen_addr}/no_db")
.parse()
.unwrap()
}
pub fn initialize(
&self,
create_tenant: Option<TenantId>,
initial_timeline_id: Option<TimelineId>,
config_overrides: &[&str],
pg_version: u32,
) -> anyhow::Result<TimelineId> {
let id = format!("id={}", self.env.pageserver.id);
// FIXME: the paths should be shell-escaped to handle paths with spaces, quotas etc.
let pg_distrib_dir_param = format!(
@@ -113,54 +122,44 @@ 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
}
/// Initializes a pageserver node by creating its config with the overrides provided,
/// and creating an initial tenant and timeline afterwards.
pub fn initialize(
&self,
create_tenant: Option<TenantId>,
initial_timeline_id: Option<TimelineId>,
config_overrides: &[&str],
pg_version: u32,
) -> anyhow::Result<TimelineId> {
// 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,
)
})?;
// Then, briefly start it fully to run HTTP commands on it,
// to create initial tenant and timeline.
// We disable the remote storage, since we stop pageserver right after the timeline creation,
// hence most of the uploads will either aborted or not started: no point to start them at all.
let disabled_remote_storage_override = "remote_storage={}";
let mut pageserver_process = self
.start_node(
&[disabled_remote_storage_override],
// Previous overrides will be taken from the config created before, don't overwrite them.
false,
)
.start_node(&init_config_overrides, &self.env.base_data_dir, true)
.with_context(|| {
format!(
"Failed to start a process for pageserver node {}",
"Failed to start a process for pageserver {}",
self.env.pageserver.id,
)
})?;
@@ -174,21 +173,29 @@ impl PageServerNode {
}
Err(e) => eprintln!("{e:#}"),
}
background_process::send_stop_child_process(&pageserver_process)?;
let exit_code = pageserver_process.wait()?;
ensure!(
exit_code.success(),
format!(
"pageserver init failed with exit code {:?}",
exit_code.code()
)
);
println!(
"Stopped pageserver {} process with pid {}",
self.env.pageserver.id,
pageserver_process.id(),
);
match pageserver_process.kill() {
Err(e) => {
eprintln!(
"Failed to stop pageserver {} process with pid {}: {e:#}",
self.env.pageserver.id,
pageserver_process.id(),
)
}
Ok(()) => {
println!(
"Stopped pageserver {} process with pid {}",
self.env.pageserver.id,
pageserver_process.id(),
);
// cleanup after pageserver startup, since we do not call regular `stop_process` during init
let pid_file = self.pid_file();
if let Err(e) = fs::remove_file(&pid_file) {
if e.kind() != io::ErrorKind::NotFound {
eprintln!("Failed to remove pid file {pid_file:?} after stopping the process: {e:#}");
}
}
}
}
init_result
}
@@ -221,73 +228,42 @@ 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]);
}
background_process::start_process(
"pageserver",
&datadir,
datadir,
&self.env.pageserver_bin(),
args.iter().map(Cow::as_ref),
self.pageserver_env_variables()?,
&args,
background_process::InitialPidFile::Expect(&self.pid_file()),
|| match self.check_status() {
Ok(()) => Ok(true),
@@ -297,35 +273,6 @@ 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.
///

View File

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

View File

@@ -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 = []

View File

@@ -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:

View File

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

View File

@@ -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...)
```

View File

@@ -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

View File

@@ -2,11 +2,6 @@
Below you will find a brief overview of each subdir in the source tree in alphabetical order.
`storage_broker`:
Neon storage broker, providing messaging between safekeepers and pageservers.
[storage_broker.md](./storage_broker.md)
`/control_plane`:
Local control plane.
@@ -45,9 +40,9 @@ and create new databases and accounts (control plane API in our case).
Integration tests, written in Python using the `pytest` framework.
`/vendor/postgres-v14` and `/vendor/postgres-v15`:
`/vendor/postgres-v14`:
PostgreSQL source tree per version, with the modifications needed for Neon.
PostgreSQL source tree, with the modifications needed for Neon.
`/pgxn/neon`:

View File

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

View File

@@ -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"

209
libs/etcd_broker/src/lib.rs Normal file
View File

@@ -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)))
}

View File

@@ -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
}
)
}
}

View File

@@ -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>,
}

View File

@@ -2,7 +2,6 @@
name = "metrics"
version = "0.1.0"
edition = "2021"
license = "Apache-2.0"
[dependencies]
prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency

View File

@@ -2,7 +2,6 @@
name = "pageserver_api"
version = "0.1.0"
edition = "2021"
license = "Apache-2.0"
[dependencies]
serde = { version = "1.0", features = ["derive"] }

View File

@@ -15,37 +15,19 @@ use bytes::{BufMut, Bytes, BytesMut};
/// A state of a tenant in pageserver's memory.
#[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
pub enum TenantState {
// This tenant is being loaded from local disk
Loading,
// This tenant is being downloaded from cloud storage.
Attaching,
/// Tenant is fully operational
Active,
/// A tenant is recognized by pageserver, but it is being detached or the
/// system is being shut down.
Stopping,
/// A tenant is recognized by the pageserver, but can no longer be used for
/// any operations, because it failed to be activated.
/// Tenant is fully operational, its background jobs might be running or not.
Active { background_jobs_running: bool },
/// A tenant is recognized by pageserver, but not yet ready to operate:
/// e.g. not present locally and being downloaded or being read into memory from the file system.
Paused,
/// A tenant is recognized by the pageserver, but no longer used for any operations, as failed to get activated.
Broken,
}
impl TenantState {
pub fn has_in_progress_downloads(&self) -> bool {
match self {
Self::Loading => true,
Self::Attaching => true,
Self::Active => false,
Self::Stopping => false,
Self::Broken => false,
}
}
}
/// A state of a timeline in pageserver's memory.
#[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
pub enum TimelineState {
/// Timeline is fully operational. If the containing Tenant is Active, the timeline's
/// background jobs are running otherwise they will be launched when the tenant is activated.
/// Timeline is fully operational, its background jobs are running.
Active,
/// A timeline is recognized by pageserver, but not yet ready to operate.
/// The status indicates, that the timeline could eventually go back to Active automatically:
@@ -53,9 +35,8 @@ pub enum TimelineState {
Suspended,
/// A timeline is recognized by pageserver, but not yet ready to operate and not allowed to
/// automatically become Active after certain events: only a management call can change this status.
Stopping,
/// A timeline is recognized by the pageserver, but can no longer be used for
/// any operations, because it failed to be activated.
Paused,
/// A timeline is recognized by the pageserver, but no longer used for any operations, as failed to get activated.
Broken,
}
@@ -117,7 +98,6 @@ 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>")]
@@ -163,8 +143,6 @@ 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>,
}
@@ -190,15 +168,10 @@ pub struct TimelineInfo {
pub latest_gc_cutoff_lsn: Lsn,
#[serde_as(as = "DisplayFromStr")]
pub disk_consistent_lsn: Lsn,
#[serde_as(as = "DisplayFromStr")]
pub remote_consistent_lsn: Lsn,
pub current_logical_size: Option<u64>, // is None when timeline is Unloaded
/// 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>")]
@@ -207,23 +180,34 @@ pub struct TimelineInfo {
pub last_received_msg_ts: Option<u128>,
pub pg_version: u32,
#[serde_as(as = "Option<DisplayFromStr>")]
pub remote_consistent_lsn: Option<Lsn>,
pub awaits_download: bool,
pub state: TimelineState,
// Some of the above fields are duplicated in 'local' and 'remote', for backwards-
// compatility with older clients.
pub local: LocalTimelineInfo,
pub remote: RemoteTimelineInfo,
}
#[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>;
@@ -323,7 +307,7 @@ 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);
@@ -333,7 +317,7 @@ 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);
@@ -343,7 +327,7 @@ 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);
@@ -354,7 +338,7 @@ 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);
}

View File

@@ -0,0 +1,12 @@
[package]
name = "persistent_range_query"
version = "0.1.0"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
workspace_hack = { version = "0.1", path = "../../workspace_hack" }
[dev-dependencies]
rand = "0.8.3"

View File

@@ -0,0 +1,78 @@
use std::ops::Range;
pub mod naive;
pub mod ops;
pub mod segment_tree;
/// Should be a monoid:
/// * Identity element: for all a: combine(new_for_empty_range(), a) = combine(a, new_for_empty_range()) = a
/// * Associativity: for all a, b, c: combine(combine(a, b), c) == combine(a, combine(b, c))
pub trait RangeQueryResult<Key>: Sized + Clone {
// Clone is equivalent to combine with an empty range.
fn new_for_empty_range() -> Self;
// Contract: left_range.end == right_range.start
// left_range.start == left_range.end == right_range.start == right_range.end is still possible
fn combine(
left: &Self,
left_range: &Range<Key>,
right: &Self,
right_range: &Range<Key>,
) -> Self;
fn add(left: &mut Self, left_range: &Range<Key>, right: &Self, right_range: &Range<Key>);
}
pub trait LazyRangeInitializer<Result: RangeQueryResult<Key>, Key> {
fn get(&self, range: &Range<Key>) -> Result;
}
/// Should be a monoid:
/// * Identity element: for all op: compose(no_op(), op) == compose(op, no_op()) == op
/// * Associativity: for all op_1, op_2, op_3: compose(compose(op_1, op_2), op_3) == compose(op_1, compose(op_2, op_3))
///
/// Should left act on Result:
/// * Identity operation: for all r: no_op().apply(r) == r
/// * Compatibility: for all op_1, op_2, r: op_1.apply(op_2.apply(r)) == compose(op_1, op_2).apply(r)
pub trait RangeModification<Key> {
type Result: RangeQueryResult<Key>;
fn no_op() -> Self;
fn is_no_op(&self) -> bool;
fn is_reinitialization(&self) -> bool;
fn apply(&self, result: &mut Self::Result, range: &Range<Key>);
fn compose(later: &Self, earlier: &mut Self);
}
pub trait VecReadableVersion<Modification: RangeModification<Key>, Key> {
fn get(&self, keys: &Range<Key>) -> Modification::Result;
}
// TODO: use trait alias when stabilized
pub trait VecFrozenVersion<Modification: RangeModification<Key>, Key>:
Clone + VecReadableVersion<Modification, Key>
{
}
impl<
T: Clone + VecReadableVersion<Modification, Key>,
Modification: RangeModification<Key>,
Key,
> VecFrozenVersion<Modification, Key> for T
{
}
pub trait PersistentVecStorage<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key,
>: VecReadableVersion<Modification, Key>
{
fn new(all_keys: Range<Key>, initializer: Initializer) -> Self;
type FrozenVersion: VecFrozenVersion<Modification, Key>;
fn modify(&mut self, keys: &Range<Key>, modification: &Modification);
fn freeze(&mut self) -> Self::FrozenVersion;
}

View File

@@ -0,0 +1,115 @@
use crate::{
LazyRangeInitializer, PersistentVecStorage, RangeModification, RangeQueryResult,
VecReadableVersion,
};
use std::marker::PhantomData;
use std::ops::Range;
use std::rc::Rc;
pub struct NaiveFrozenVersion<Modification: RangeModification<Key>, Key> {
all_keys: Range<Key>,
values: Rc<Box<Vec<Modification::Result>>>,
}
pub trait IndexableKey: Clone {
fn index(all_keys: &Range<Self>, key: &Self) -> usize;
fn element_range(all_keys: &Range<Self>, index: usize) -> Range<Self>;
}
fn get<Modification: RangeModification<Key>, Key: IndexableKey>(
all_keys: &Range<Key>,
values: &Vec<Modification::Result>,
keys: &Range<Key>,
) -> Modification::Result {
let mut result = Modification::Result::new_for_empty_range();
let mut result_range = keys.start.clone()..keys.start.clone();
for index in
IndexableKey::index(&all_keys, &keys.start)..IndexableKey::index(&all_keys, &keys.end)
{
let element_range = IndexableKey::element_range(&all_keys, index);
Modification::Result::add(&mut result, &result_range, &values[index], &element_range);
result_range.end = element_range.end;
}
result
}
impl<Modification: RangeModification<Key>, Key: IndexableKey> VecReadableVersion<Modification, Key>
for NaiveFrozenVersion<Modification, Key>
{
fn get(&self, keys: &Range<Key>) -> Modification::Result {
get::<Modification, Key>(&self.all_keys, &self.values, keys)
}
}
// Manual implementation of `Clone` becase `derive` requires `Modification: Clone`
impl<Modification: RangeModification<Key>, Key: Clone> Clone
for NaiveFrozenVersion<Modification, Key>
{
fn clone(&self) -> Self {
Self {
all_keys: self.all_keys.clone(),
values: self.values.clone(),
}
}
}
// TODO: is it at all possible to store previous versions in this struct,
// without any Rc<>?
pub struct NaiveVecStorage<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: IndexableKey,
> {
all_keys: Range<Key>,
last_version: Vec<Modification::Result>,
_initializer: PhantomData<Initializer>,
}
impl<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: IndexableKey,
> VecReadableVersion<Modification, Key> for NaiveVecStorage<Modification, Initializer, Key>
{
fn get(&self, keys: &Range<Key>) -> Modification::Result {
get::<Modification, Key>(&self.all_keys, &self.last_version, keys)
}
}
impl<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: IndexableKey,
> PersistentVecStorage<Modification, Initializer, Key>
for NaiveVecStorage<Modification, Initializer, Key>
{
fn new(all_keys: Range<Key>, initializer: Initializer) -> Self {
let mut values = Vec::with_capacity(IndexableKey::index(&all_keys, &all_keys.end));
for index in 0..values.capacity() {
values.push(initializer.get(&IndexableKey::element_range(&all_keys, index)));
}
NaiveVecStorage {
all_keys,
last_version: values,
_initializer: PhantomData,
}
}
type FrozenVersion = NaiveFrozenVersion<Modification, Key>;
fn modify(&mut self, keys: &Range<Key>, modification: &Modification) {
for index in IndexableKey::index(&self.all_keys, &keys.start)
..IndexableKey::index(&self.all_keys, &keys.end)
{
let element_range = IndexableKey::element_range(&self.all_keys, index);
modification.apply(&mut self.last_version[index], &element_range);
}
}
fn freeze(&mut self) -> Self::FrozenVersion {
NaiveFrozenVersion::<Modification, Key> {
all_keys: self.all_keys.clone(),
values: Rc::new(Box::new(self.last_version.clone())),
}
}
}

View File

@@ -0,0 +1,14 @@
pub mod rsq;
#[derive(Copy, Clone, Debug)]
pub struct SameElementsInitializer<T> {
initial_element_value: T,
}
impl<T> SameElementsInitializer<T> {
pub fn new(initial_element_value: T) -> Self {
SameElementsInitializer {
initial_element_value,
}
}
}

View File

@@ -0,0 +1,118 @@
//! # Range Sum Query
use crate::ops::SameElementsInitializer;
use crate::{LazyRangeInitializer, RangeModification, RangeQueryResult};
use std::borrow::Borrow;
use std::ops::{Add, AddAssign, Range};
// TODO: commutative Add
#[derive(Clone, Copy, Debug)]
pub struct SumResult<T> {
sum: T,
}
impl<T> SumResult<T> {
pub fn sum(&self) -> &T {
&self.sum
}
}
impl<T: Clone + for<'a> AddAssign<&'a T> + From<u8>, Key> RangeQueryResult<Key> for SumResult<T>
where
for<'a> &'a T: Add<&'a T, Output = T>,
{
fn new_for_empty_range() -> Self {
SumResult { sum: 0.into() }
}
fn combine(
left: &Self,
_left_range: &Range<Key>,
right: &Self,
_right_range: &Range<Key>,
) -> Self {
SumResult {
sum: &left.sum + &right.sum,
}
}
fn add(left: &mut Self, _left_range: &Range<Key>, right: &Self, _right_range: &Range<Key>) {
left.sum += &right.sum
}
}
pub trait SumOfSameElements<Key> {
fn sum(initial_element_value: &Self, keys: &Range<Key>) -> Self;
}
impl<T: SumOfSameElements<Key>, TB: Borrow<T>, Key> LazyRangeInitializer<SumResult<T>, Key>
for SameElementsInitializer<TB>
where
SumResult<T>: RangeQueryResult<Key>,
{
fn get(&self, range: &Range<Key>) -> SumResult<T> {
SumResult {
sum: SumOfSameElements::sum(self.initial_element_value.borrow(), range),
}
}
}
#[derive(Copy, Clone, Debug)]
pub enum AddAssignModification<T> {
None,
Add(T),
Assign(T),
}
impl<T: Clone + for<'a> AddAssign<&'a T>, Key> RangeModification<Key> for AddAssignModification<T>
where
SumResult<T>: RangeQueryResult<Key>,
for<'a> SameElementsInitializer<&'a T>: LazyRangeInitializer<SumResult<T>, Key>,
{
type Result = SumResult<T>;
fn no_op() -> Self {
AddAssignModification::None
}
fn is_no_op(&self) -> bool {
match self {
AddAssignModification::None => true,
_ => false,
}
}
fn is_reinitialization(&self) -> bool {
match self {
AddAssignModification::Assign(_) => true,
_ => false,
}
}
fn apply(&self, result: &mut SumResult<T>, range: &Range<Key>) {
use AddAssignModification::*;
match self {
None => {}
Add(x) | Assign(x) => {
let to_add = SameElementsInitializer::new(x).get(range).sum;
if let Assign(_) = self {
result.sum = to_add;
} else {
result.sum += &to_add;
}
}
}
}
fn compose(later: &Self, earlier: &mut Self) {
use AddAssignModification::*;
match (later, earlier) {
(_, e @ None) => *e = later.clone(),
(None, _) => {}
(Assign(_), e) => *e = later.clone(),
(Add(x), Add(y)) => *y += x,
(Add(x), Assign(value)) => *value += x,
}
}
}

View File

@@ -0,0 +1,255 @@
//! # Segment Tree
//! It is a competitive programming folklore data structure. Do not confuse with the interval tree.
use crate::{LazyRangeInitializer, PersistentVecStorage, RangeQueryResult, VecReadableVersion};
use std::ops::Range;
use std::rc::Rc;
pub trait MidpointableKey: Clone + Ord + Sized {
fn midpoint(range: &Range<Self>) -> Self;
}
pub trait RangeModification<Key>: Clone + crate::RangeModification<Key> {}
// TODO: use trait alias when stabilized
impl<T: Clone + crate::RangeModification<Key>, Key> RangeModification<Key> for T {}
#[derive(Debug)]
struct Node<Modification: RangeModification<Key>, Key> {
result: Modification::Result,
modify_children: Modification,
left: Option<Rc<Self>>,
right: Option<Rc<Self>>,
}
// Manual implementation because we don't need `Key: Clone` for this, unlike with `derive`.
impl<Modification: RangeModification<Key>, Key> Clone for Node<Modification, Key> {
fn clone(&self) -> Self {
Node {
result: self.result.clone(),
modify_children: self.modify_children.clone(),
left: self.left.clone(),
right: self.right.clone(),
}
}
}
impl<Modification: RangeModification<Key>, Key> Node<Modification, Key> {
fn new<Initializer: LazyRangeInitializer<Modification::Result, Key>>(
range: &Range<Key>,
initializer: &Initializer,
) -> Self {
Node {
result: initializer.get(range),
modify_children: Modification::no_op(),
left: None,
right: None,
}
}
pub fn apply(&mut self, modification: &Modification, range: &Range<Key>) {
modification.apply(&mut self.result, range);
Modification::compose(modification, &mut self.modify_children);
if self.modify_children.is_reinitialization() {
self.left = None;
self.right = None;
}
}
pub fn force_children<Initializer: LazyRangeInitializer<Modification::Result, Key>>(
&mut self,
initializer: &Initializer,
range_left: &Range<Key>,
range_right: &Range<Key>,
) {
let left = Rc::make_mut(
self.left
.get_or_insert_with(|| Rc::new(Node::new(&range_left, initializer))),
);
let right = Rc::make_mut(
self.right
.get_or_insert_with(|| Rc::new(Node::new(&range_right, initializer))),
);
left.apply(&self.modify_children, &range_left);
right.apply(&self.modify_children, &range_right);
self.modify_children = Modification::no_op();
}
pub fn recalculate_from_children(&mut self, range_left: &Range<Key>, range_right: &Range<Key>) {
assert!(self.modify_children.is_no_op());
assert!(self.left.is_some());
assert!(self.right.is_some());
self.result = Modification::Result::combine(
&self.left.as_ref().unwrap().result,
&range_left,
&self.right.as_ref().unwrap().result,
&range_right,
);
}
}
fn split_range<Key: MidpointableKey>(range: &Range<Key>) -> (Range<Key>, Range<Key>) {
let range_left = range.start.clone()..MidpointableKey::midpoint(range);
let range_right = range_left.end.clone()..range.end.clone();
(range_left, range_right)
}
pub struct PersistentSegmentTreeVersion<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: Clone,
> {
root: Rc<Node<Modification, Key>>,
all_keys: Range<Key>,
initializer: Rc<Initializer>,
}
// Manual implementation because we don't need `Key: Clone` for this, unlike with `derive`.
impl<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: Clone,
> Clone for PersistentSegmentTreeVersion<Modification, Initializer, Key>
{
fn clone(&self) -> Self {
Self {
root: self.root.clone(),
all_keys: self.all_keys.clone(),
initializer: self.initializer.clone(),
}
}
}
fn get<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: MidpointableKey,
>(
node: &mut Rc<Node<Modification, Key>>,
node_keys: &Range<Key>,
initializer: &Initializer,
keys: &Range<Key>,
) -> Modification::Result {
if node_keys.end <= keys.start || keys.end <= node_keys.start {
return Modification::Result::new_for_empty_range();
}
if keys.start <= node_keys.start && node_keys.end <= keys.end {
return node.result.clone();
}
let node = Rc::make_mut(node);
let (left_keys, right_keys) = split_range(node_keys);
node.force_children(initializer, &left_keys, &right_keys);
let mut result = get(node.left.as_mut().unwrap(), &left_keys, initializer, keys);
Modification::Result::add(
&mut result,
&left_keys,
&get(node.right.as_mut().unwrap(), &right_keys, initializer, keys),
&right_keys,
);
result
}
fn modify<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: MidpointableKey,
>(
node: &mut Rc<Node<Modification, Key>>,
node_keys: &Range<Key>,
initializer: &Initializer,
keys: &Range<Key>,
modification: &Modification,
) {
if modification.is_no_op() || node_keys.end <= keys.start || keys.end <= node_keys.start {
return;
}
let node = Rc::make_mut(node);
if keys.start <= node_keys.start && node_keys.end <= keys.end {
node.apply(modification, node_keys);
return;
}
let (left_keys, right_keys) = split_range(node_keys);
node.force_children(initializer, &left_keys, &right_keys);
modify(
node.left.as_mut().unwrap(),
&left_keys,
initializer,
keys,
&modification,
);
modify(
node.right.as_mut().unwrap(),
&right_keys,
initializer,
keys,
&modification,
);
node.recalculate_from_children(&left_keys, &right_keys);
}
impl<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: MidpointableKey,
> VecReadableVersion<Modification, Key>
for PersistentSegmentTreeVersion<Modification, Initializer, Key>
{
fn get(&self, keys: &Range<Key>) -> Modification::Result {
get(
&mut self.root.clone(), // TODO: do not always force a branch
&self.all_keys,
self.initializer.as_ref(),
keys,
)
}
}
pub struct PersistentSegmentTree<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: MidpointableKey,
>(PersistentSegmentTreeVersion<Modification, Initializer, Key>);
impl<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: MidpointableKey,
> VecReadableVersion<Modification, Key>
for PersistentSegmentTree<Modification, Initializer, Key>
{
fn get(&self, keys: &Range<Key>) -> Modification::Result {
self.0.get(keys)
}
}
impl<
Modification: RangeModification<Key>,
Initializer: LazyRangeInitializer<Modification::Result, Key>,
Key: MidpointableKey,
> PersistentVecStorage<Modification, Initializer, Key>
for PersistentSegmentTree<Modification, Initializer, Key>
{
fn new(all_keys: Range<Key>, initializer: Initializer) -> Self {
PersistentSegmentTree(PersistentSegmentTreeVersion {
root: Rc::new(Node::new(&all_keys, &initializer)),
all_keys: all_keys,
initializer: Rc::new(initializer),
})
}
type FrozenVersion = PersistentSegmentTreeVersion<Modification, Initializer, Key>;
fn modify(&mut self, keys: &Range<Key>, modification: &Modification) {
modify(
&mut self.0.root, // TODO: do not always force a branch
&self.0.all_keys,
self.0.initializer.as_ref(),
keys,
modification,
)
}
fn freeze(&mut self) -> Self::FrozenVersion {
self.0.clone()
}
}

View File

@@ -0,0 +1,295 @@
use persistent_range_query::naive::{IndexableKey, NaiveVecStorage};
use persistent_range_query::ops::SameElementsInitializer;
use persistent_range_query::segment_tree::{MidpointableKey, PersistentSegmentTree};
use persistent_range_query::{
LazyRangeInitializer, PersistentVecStorage, RangeModification, RangeQueryResult,
VecReadableVersion,
};
use std::cmp::Ordering;
use std::ops::Range;
#[derive(Clone, Copy, Debug, Eq, PartialEq, Ord, PartialOrd)]
struct PageIndex(u32);
type LayerId = String;
impl IndexableKey for PageIndex {
fn index(all_keys: &Range<Self>, key: &Self) -> usize {
(key.0 as usize) - (all_keys.start.0 as usize)
}
fn element_range(all_keys: &Range<Self>, index: usize) -> Range<Self> {
PageIndex(all_keys.start.0 + index as u32)..PageIndex(all_keys.start.0 + index as u32 + 1)
}
}
impl MidpointableKey for PageIndex {
fn midpoint(range: &Range<Self>) -> Self {
PageIndex(range.start.0 + (range.end.0 - range.start.0) / 2)
}
}
#[derive(Clone, Debug, Eq, PartialEq)]
struct LayerMapInformation {
// Only make sense for a range of length 1.
last_layer: Option<LayerId>,
last_image_layer: Option<LayerId>,
// Work for all ranges
max_delta_layers: (usize, Range<PageIndex>),
}
impl LayerMapInformation {
fn last_layers(&self) -> (&Option<LayerId>, &Option<LayerId>) {
(&self.last_layer, &self.last_image_layer)
}
fn max_delta_layers(&self) -> &(usize, Range<PageIndex>) {
&self.max_delta_layers
}
}
fn merge_ranges(left: &Range<PageIndex>, right: &Range<PageIndex>) -> Range<PageIndex> {
if left.is_empty() {
right.clone()
} else if right.is_empty() {
left.clone()
} else if left.end == right.start {
left.start..right.end
} else {
left.clone()
}
}
impl RangeQueryResult<PageIndex> for LayerMapInformation {
fn new_for_empty_range() -> Self {
LayerMapInformation {
last_layer: None,
last_image_layer: None,
max_delta_layers: (0, PageIndex(0)..PageIndex(0)),
}
}
fn combine(
left: &Self,
_left_range: &Range<PageIndex>,
right: &Self,
_right_range: &Range<PageIndex>,
) -> Self {
// Note that either range may be empty.
LayerMapInformation {
last_layer: left
.last_layer
.as_ref()
.or_else(|| right.last_layer.as_ref())
.cloned(),
last_image_layer: left
.last_image_layer
.as_ref()
.or_else(|| right.last_image_layer.as_ref())
.cloned(),
max_delta_layers: match left.max_delta_layers.0.cmp(&right.max_delta_layers.0) {
Ordering::Less => right.max_delta_layers.clone(),
Ordering::Greater => left.max_delta_layers.clone(),
Ordering::Equal => (
left.max_delta_layers.0,
merge_ranges(&left.max_delta_layers.1, &right.max_delta_layers.1),
),
},
}
}
fn add(
left: &mut Self,
left_range: &Range<PageIndex>,
right: &Self,
right_range: &Range<PageIndex>,
) {
*left = Self::combine(&left, left_range, right, right_range);
}
}
#[derive(Clone, Debug)]
struct AddDeltaLayers {
last_layer: LayerId,
count: usize,
}
#[derive(Clone, Debug)]
struct LayerMapModification {
add_image_layer: Option<LayerId>,
add_delta_layers: Option<AddDeltaLayers>,
}
impl LayerMapModification {
fn add_image_layer(layer: impl Into<LayerId>) -> Self {
LayerMapModification {
add_image_layer: Some(layer.into()),
add_delta_layers: None,
}
}
fn add_delta_layer(layer: impl Into<LayerId>) -> Self {
LayerMapModification {
add_image_layer: None,
add_delta_layers: Some(AddDeltaLayers {
last_layer: layer.into(),
count: 1,
}),
}
}
}
impl RangeModification<PageIndex> for LayerMapModification {
type Result = LayerMapInformation;
fn no_op() -> Self {
LayerMapModification {
add_image_layer: None,
add_delta_layers: None,
}
}
fn is_no_op(&self) -> bool {
self.add_image_layer.is_none() && self.add_delta_layers.is_none()
}
fn is_reinitialization(&self) -> bool {
self.add_image_layer.is_some()
}
fn apply(&self, result: &mut Self::Result, range: &Range<PageIndex>) {
if let Some(layer) = &self.add_image_layer {
result.last_layer = Some(layer.clone());
result.last_image_layer = Some(layer.clone());
result.max_delta_layers = (0, range.clone());
}
if let Some(AddDeltaLayers { last_layer, count }) = &self.add_delta_layers {
result.last_layer = Some(last_layer.clone());
result.max_delta_layers.0 += count;
}
}
fn compose(later: &Self, earlier: &mut Self) {
if later.add_image_layer.is_some() {
*earlier = later.clone();
return;
}
if let Some(AddDeltaLayers { last_layer, count }) = &later.add_delta_layers {
let res = earlier.add_delta_layers.get_or_insert(AddDeltaLayers {
last_layer: LayerId::default(),
count: 0,
});
res.last_layer = last_layer.clone();
res.count += count;
}
}
}
impl LazyRangeInitializer<LayerMapInformation, PageIndex> for SameElementsInitializer<()> {
fn get(&self, range: &Range<PageIndex>) -> LayerMapInformation {
LayerMapInformation {
last_layer: None,
last_image_layer: None,
max_delta_layers: (0, range.clone()),
}
}
}
fn test_layer_map<
S: PersistentVecStorage<LayerMapModification, SameElementsInitializer<()>, PageIndex>,
>() {
let mut s = S::new(
PageIndex(0)..PageIndex(100),
SameElementsInitializer::new(()),
);
s.modify(
&(PageIndex(0)..PageIndex(70)),
&LayerMapModification::add_image_layer("Img0..70"),
);
s.modify(
&(PageIndex(50)..PageIndex(100)),
&LayerMapModification::add_image_layer("Img50..100"),
);
s.modify(
&(PageIndex(10)..PageIndex(60)),
&LayerMapModification::add_delta_layer("Delta10..60"),
);
let s_before_last_delta = s.freeze();
s.modify(
&(PageIndex(20)..PageIndex(80)),
&LayerMapModification::add_delta_layer("Delta20..80"),
);
assert_eq!(
s.get(&(PageIndex(5)..PageIndex(6))).last_layers(),
(&Some("Img0..70".to_owned()), &Some("Img0..70".to_owned()))
);
assert_eq!(
s.get(&(PageIndex(15)..PageIndex(16))).last_layers(),
(
&Some("Delta10..60".to_owned()),
&Some("Img0..70".to_owned())
)
);
assert_eq!(
s.get(&(PageIndex(25)..PageIndex(26))).last_layers(),
(
&Some("Delta20..80".to_owned()),
&Some("Img0..70".to_owned())
)
);
assert_eq!(
s.get(&(PageIndex(65)..PageIndex(66))).last_layers(),
(
&Some("Delta20..80".to_owned()),
&Some("Img50..100".to_owned())
)
);
assert_eq!(
s.get(&(PageIndex(95)..PageIndex(96))).last_layers(),
(
&Some("Img50..100".to_owned()),
&Some("Img50..100".to_owned())
)
);
assert_eq!(
s.get(&(PageIndex(0)..PageIndex(100))).max_delta_layers(),
&(2, PageIndex(20)..PageIndex(60)),
);
assert_eq!(
*s_before_last_delta
.get(&(PageIndex(0)..PageIndex(100)))
.max_delta_layers(),
(1, PageIndex(10)..PageIndex(60)),
);
assert_eq!(
*s.get(&(PageIndex(10)..PageIndex(30))).max_delta_layers(),
(2, PageIndex(20)..PageIndex(30))
);
assert_eq!(
*s.get(&(PageIndex(10)..PageIndex(20))).max_delta_layers(),
(1, PageIndex(10)..PageIndex(20))
);
assert_eq!(
*s.get(&(PageIndex(70)..PageIndex(80))).max_delta_layers(),
(1, PageIndex(70)..PageIndex(80))
);
assert_eq!(
*s_before_last_delta
.get(&(PageIndex(70)..PageIndex(80)))
.max_delta_layers(),
(0, PageIndex(70)..PageIndex(80))
);
}
#[test]
fn test_naive() {
test_layer_map::<NaiveVecStorage<_, _, _>>();
}
#[test]
fn test_segment_tree() {
test_layer_map::<PersistentSegmentTree<_, _, _>>();
}

View File

@@ -0,0 +1,116 @@
use persistent_range_query::naive::*;
use persistent_range_query::ops::rsq::AddAssignModification::Add;
use persistent_range_query::ops::rsq::*;
use persistent_range_query::ops::SameElementsInitializer;
use persistent_range_query::segment_tree::{MidpointableKey, PersistentSegmentTree};
use persistent_range_query::{PersistentVecStorage, VecReadableVersion};
use rand::{Rng, SeedableRng};
use std::ops::Range;
#[derive(Copy, Clone, Debug, Eq, PartialEq, Ord, PartialOrd)]
struct K(u16);
impl IndexableKey for K {
fn index(all_keys: &Range<Self>, key: &Self) -> usize {
(key.0 as usize) - (all_keys.start.0 as usize)
}
fn element_range(all_keys: &Range<Self>, index: usize) -> Range<Self> {
K(all_keys.start.0 + index as u16)..K(all_keys.start.0 + index as u16 + 1)
}
}
impl SumOfSameElements<K> for i32 {
fn sum(initial_element_value: &Self, keys: &Range<K>) -> Self {
initial_element_value * (keys.end.0 - keys.start.0) as Self
}
}
impl MidpointableKey for K {
fn midpoint(range: &Range<Self>) -> Self {
K(range.start.0 + (range.end.0 - range.start.0) / 2)
}
}
fn test_storage<
S: PersistentVecStorage<AddAssignModification<i32>, SameElementsInitializer<i32>, K>,
>() {
let mut s = S::new(K(0)..K(12), SameElementsInitializer::new(0i32));
assert_eq!(*s.get(&(K(0)..K(12))).sum(), 0);
s.modify(&(K(2)..K(5)), &AddAssignModification::Add(3));
assert_eq!(*s.get(&(K(0)..K(12))).sum(), 3 + 3 + 3);
let s_old = s.freeze();
s.modify(&(K(3)..K(6)), &AddAssignModification::Assign(10));
assert_eq!(*s.get(&(K(0)..K(12))).sum(), 3 + 10 + 10 + 10);
s.modify(&(K(4)..K(7)), &AddAssignModification::Add(2));
assert_eq!(*s.get(&(K(0)..K(12))).sum(), 3 + 10 + 12 + 12 + 2);
assert_eq!(*s.get(&(K(4)..K(6))).sum(), 12 + 12);
assert_eq!(*s_old.get(&(K(4)..K(6))).sum(), 3);
}
#[test]
fn test_naive() {
test_storage::<NaiveVecStorage<_, _, _>>();
}
#[test]
fn test_segment_tree() {
test_storage::<PersistentSegmentTree<_, _, _>>();
}
#[test]
fn test_stress() {
const LEN: u16 = 17_238;
const OPERATIONS: i32 = 20_000;
let mut rng = rand::rngs::StdRng::seed_from_u64(0);
let mut naive: NaiveVecStorage<AddAssignModification<i32>, _, _> =
NaiveVecStorage::new(K(0)..K(LEN), SameElementsInitializer::new(2i32));
let mut segm_tree: PersistentSegmentTree<AddAssignModification<i32>, _, _> =
PersistentSegmentTree::new(K(0)..K(LEN), SameElementsInitializer::new(2i32));
fn gen_range(rng: &mut impl Rng) -> Range<K> {
let l: u16 = rng.gen_range(0..LEN);
let r: u16 = rng.gen_range(0..LEN);
if l <= r {
K(l)..K(r)
} else {
K(r)..K(l)
}
}
for _ in 0..2 {
let checksum_range = gen_range(&mut rng);
let checksum_before: i32 = *naive.get(&checksum_range).sum();
assert_eq!(checksum_before, *segm_tree.get(&checksum_range).sum());
let naive_before = naive.freeze();
let segm_tree_before = segm_tree.freeze();
assert_eq!(checksum_before, *naive_before.get(&checksum_range).sum());
assert_eq!(checksum_before, *segm_tree.get(&checksum_range).sum());
for _ in 0..OPERATIONS {
{
let range = gen_range(&mut rng);
assert_eq!(naive.get(&range).sum(), segm_tree.get(&range).sum());
}
{
let range = gen_range(&mut rng);
let val = rng.gen_range(-10i32..=10i32);
let op = Add(val);
naive.modify(&range, &op);
segm_tree.modify(&range, &op);
}
}
assert_eq!(checksum_before, *naive_before.get(&checksum_range).sum());
assert_eq!(
checksum_before,
*segm_tree_before.get(&checksum_range).sum()
);
}
}

View File

@@ -1,18 +0,0 @@
[package]
name = "postgres_connection"
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"
itertools = "0.10.3"
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "43e6db254a97fdecbce33d8bc0890accfd74495e" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
url = "2.2.2"
workspace_hack = { version = "0.1", path = "../../workspace_hack" }
[dev-dependencies]
once_cell = "1.13.0"

View File

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

Some files were not shown because too many files have changed in this diff Show More