mirror of
https://github.com/neondatabase/neon.git
synced 2025-12-22 21:59:59 +00:00
Increase tenant size for large tenant oltp workload (#12260)
## Problem - We run the large tenant oltp workload with a fixed size (larger than existing customers' workloads). Our customer's workloads are continuously growing and our testing should stay ahead of the customers' production workloads. - we want to touch all tables in the tenant's database (updates) so that we simulate a continuous change in layer files like in a real production workload - our current oltp benchmark uses a mixture of read and write transactions, however we also want a separate test run with read-only transactions only ## Summary of changes - modify the existing workload to have a separate run with pgbench custom scripts that are read-only - create a new workload that - grows all large tables in each run (for the reuse branch in the large oltp tenant's project) - updates a percentage of rows in all large tables in each run (to enforce table bloat and auto-vacuum runs and layer rebuild in pageservers Each run of the new workflow increases the logical database size about 16 GB. We start with 6 runs per day which will give us about 96-100 GB growth per day. --------- Co-authored-by: Alexander Lakhin <alexander.lakhin@neon.tech>
This commit is contained in:
Peter Bendel
GitHub
11
.github/workflows/large_oltp_benchmark.yml
vendored
11
.github/workflows/large_oltp_benchmark.yml
vendored
@@ -33,11 +33,19 @@ jobs:
|
||||
fail-fast: false # allow other variants to continue even if one fails
|
||||
matrix:
|
||||
include:
|
||||
# test only read-only custom scripts in new branch without database maintenance
|
||||
- target: new_branch
|
||||
custom_scripts: select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3
|
||||
test_maintenance: false
|
||||
# test all custom scripts in new branch with database maintenance
|
||||
- target: new_branch
|
||||
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
|
||||
test_maintenance: true
|
||||
# test all custom scripts in reuse branch with database maintenance
|
||||
- target: reuse_branch
|
||||
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
|
||||
max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
|
||||
test_maintenance: true
|
||||
max-parallel: 1 # we want to run each benchmark sequentially to not have noisy neighbors on shared storage (PS, SK)
|
||||
permissions:
|
||||
contents: write
|
||||
statuses: write
|
||||
@@ -145,6 +153,7 @@ jobs:
|
||||
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
|
||||
|
||||
- name: Benchmark database maintenance
|
||||
if: ${{ matrix.test_maintenance == 'true' }}
|
||||
uses: ./.github/actions/run-python-test-set
|
||||
with:
|
||||
build_type: ${{ env.BUILD_TYPE }}
|
||||
|
||||
175
.github/workflows/large_oltp_growth.yml
vendored
Normal file
175
.github/workflows/large_oltp_growth.yml
vendored
Normal file
@@ -0,0 +1,175 @@
|
||||
name: large oltp growth
|
||||
# workflow to grow the reuse branch of large oltp benchmark continuously (about 16 GB per run)
|
||||
|
||||
on:
|
||||
# uncomment to run on push for debugging your PR
|
||||
# push:
|
||||
# branches: [ bodobolero/increase_large_oltp_workload ]
|
||||
|
||||
schedule:
|
||||
# * is a special character in YAML so you have to quote this string
|
||||
# ┌───────────── minute (0 - 59)
|
||||
# │ ┌───────────── hour (0 - 23)
|
||||
# │ │ ┌───────────── day of the month (1 - 31)
|
||||
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
|
||||
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
|
||||
- cron: '0 6 * * *' # 06:00 UTC
|
||||
- cron: '0 8 * * *' # 08:00 UTC
|
||||
- cron: '0 10 * * *' # 10:00 UTC
|
||||
- cron: '0 12 * * *' # 12:00 UTC
|
||||
- cron: '0 14 * * *' # 14:00 UTC
|
||||
- cron: '0 16 * * *' # 16:00 UTC
|
||||
workflow_dispatch: # adds ability to run this manually
|
||||
|
||||
defaults:
|
||||
run:
|
||||
shell: bash -euxo pipefail {0}
|
||||
|
||||
concurrency:
|
||||
# Allow only one workflow globally because we need dedicated resources which only exist once
|
||||
group: large-oltp-growth
|
||||
cancel-in-progress: true
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
oltp:
|
||||
strategy:
|
||||
fail-fast: false # allow other variants to continue even if one fails
|
||||
matrix:
|
||||
include:
|
||||
# for now only grow the reuse branch, not the other branches.
|
||||
- target: reuse_branch
|
||||
custom_scripts:
|
||||
- grow_action_blocks.sql
|
||||
- grow_action_kwargs.sql
|
||||
- grow_device_fingerprint_event.sql
|
||||
- grow_edges.sql
|
||||
- grow_hotel_rate_mapping.sql
|
||||
- grow_ocr_pipeline_results_version.sql
|
||||
- grow_priceline_raw_response.sql
|
||||
- grow_relabled_transactions.sql
|
||||
- grow_state_values.sql
|
||||
- grow_values.sql
|
||||
- grow_vertices.sql
|
||||
- update_accounting_coding_body_tracking_category_selection.sql
|
||||
- update_action_blocks.sql
|
||||
- update_action_kwargs.sql
|
||||
- update_denormalized_approval_workflow.sql
|
||||
- update_device_fingerprint_event.sql
|
||||
- update_edges.sql
|
||||
- update_heron_transaction_enriched_log.sql
|
||||
- update_heron_transaction_enrichment_requests.sql
|
||||
- update_hotel_rate_mapping.sql
|
||||
- update_incoming_webhooks.sql
|
||||
- update_manual_transaction.sql
|
||||
- update_ml_receipt_matching_log.sql
|
||||
- update_ocr_pipeine_results_version.sql
|
||||
- update_orc_pipeline_step_results.sql
|
||||
- update_orc_pipeline_step_results_version.sql
|
||||
- update_priceline_raw_response.sql
|
||||
- update_quickbooks_transactions.sql
|
||||
- update_raw_finicity_transaction.sql
|
||||
- update_relabeled_transactions.sql
|
||||
- update_state_values.sql
|
||||
- update_stripe_authorization_event_log.sql
|
||||
- update_transaction.sql
|
||||
- update_values.sql
|
||||
- update_vertices.sql
|
||||
max-parallel: 1 # we want to run each growth workload sequentially (for now there is just one)
|
||||
permissions:
|
||||
contents: write
|
||||
statuses: write
|
||||
id-token: write # aws-actions/configure-aws-credentials
|
||||
env:
|
||||
TEST_PG_BENCH_DURATIONS_MATRIX: "1h"
|
||||
TEST_PGBENCH_CUSTOM_SCRIPTS: ${{ join(matrix.custom_scripts, ' ') }}
|
||||
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
|
||||
PG_VERSION: 16 # pre-determined by pre-determined project
|
||||
TEST_OUTPUT: /tmp/test_output
|
||||
BUILD_TYPE: remote
|
||||
PLATFORM: ${{ matrix.target }}
|
||||
|
||||
runs-on: [ self-hosted, us-east-2, x64 ]
|
||||
container:
|
||||
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
|
||||
credentials:
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
options: --init
|
||||
|
||||
steps:
|
||||
- name: Harden the runner (Audit all outbound calls)
|
||||
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
||||
|
||||
- name: Configure AWS credentials # necessary to download artefacts
|
||||
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
|
||||
with:
|
||||
aws-region: eu-central-1
|
||||
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
|
||||
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
|
||||
|
||||
- name: Download Neon artifact
|
||||
uses: ./.github/actions/download
|
||||
with:
|
||||
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
|
||||
path: /tmp/neon/
|
||||
prefix: latest
|
||||
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
|
||||
|
||||
- name: Set up Connection String
|
||||
id: set-up-connstr
|
||||
run: |
|
||||
case "${{ matrix.target }}" in
|
||||
reuse_branch)
|
||||
CONNSTR=${{ secrets.BENCHMARK_LARGE_OLTP_REUSE_CONNSTR }}
|
||||
;;
|
||||
*)
|
||||
echo >&2 "Unknown target=${{ matrix.target }}"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
CONNSTR_WITHOUT_POOLER="${CONNSTR//-pooler/}"
|
||||
|
||||
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
|
||||
echo "connstr_without_pooler=${CONNSTR_WITHOUT_POOLER}" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: pgbench with custom-scripts
|
||||
uses: ./.github/actions/run-python-test-set
|
||||
with:
|
||||
build_type: ${{ env.BUILD_TYPE }}
|
||||
test_selection: performance
|
||||
run_in_parallel: false
|
||||
save_perf_report: true
|
||||
extra_params: -m remote_cluster --timeout 7200 -k test_perf_oltp_large_tenant_growth
|
||||
pg_version: ${{ env.PG_VERSION }}
|
||||
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
|
||||
env:
|
||||
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
|
||||
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
|
||||
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
|
||||
|
||||
- name: Create Allure report
|
||||
id: create-allure-report
|
||||
if: ${{ !cancelled() }}
|
||||
uses: ./.github/actions/allure-report-generate
|
||||
with:
|
||||
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
|
||||
|
||||
- name: Post to a Slack channel
|
||||
if: ${{ github.event.schedule && failure() }}
|
||||
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
|
||||
with:
|
||||
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
|
||||
slack-message: |
|
||||
Periodic large oltp tenant growth increase: ${{ job.status }}
|
||||
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
|
||||
<${{ steps.create-allure-report.outputs.report-url }}|Allure report>
|
||||
env:
|
||||
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
|
||||
Reference in New Issue
Block a user