tvl-depot/ops/pipelines/static-pipeline.yaml
Vincent Ambo abaa90c3ab fix(ops/pipelines): limit concurrency of 🦙
When pushing a large chain of CLs, builds can fail with OOM issues as
many Nix evaluations of the depot are happening simultaneously.

To work around this, we limit the concurrency of simultaneous Nix
evaluations (i.e. the `:llama` step). This can slow down the start of
builds in a large chain of small changes, but that is a better
tradeoff than failing the builds entirely and making people click
buttons.

Change-Id: If351aaad22d52e2bcf871377f22ab1df594c518d
Reviewed-on: https://cl.tvl.fyi/c/depot/+/7501
Reviewed-by: sterni <sternenseemann@systemli.org>
Autosubmit: tazjin <tazjin@tvl.su>
Tested-by: BuildkiteCI
2022-12-03 14:11:04 +00:00

119 lines
4.1 KiB
YAML

# This file defines the static Buildkite pipeline which attempts to
# create the dynamic pipeline of all depot targets.
#
# If something fails during the creation of the pipeline, the fallback
# is executed instead which will simply report an error to Gerrit.
---
env:
BUILDKITE_TOKEN_PATH: /run/agenix/buildkite-graphql-token
steps:
# Run pipeline for tvl-kit when new commits arrive on canon. Since
# it is not part of the depot build tree, this is a useful
# verification to ensure we don't break external things (too much).
- trigger: "tvl-kit"
async: true
label: ":fork:"
branches: "refs/heads/canon"
build:
message: "Verification triggered by ${BUILDKITE_COMMIT}"
# Create a revision number for the current commit for builds on
# canon.
#
# This writes data back to Gerrit using the Buildkite agent
# credentials injected through a git credentials helper.
#
# Revision numbers are defined as the number of commits in the
# lineage of HEAD, following only the first parent of merges.
- label: ":git:"
branches: "refs/heads/canon"
command: |
git -c 'credential.helper=gerrit-creds' \
push origin "HEAD:refs/r/$(git rev-list --count --first-parent HEAD)"
# Generate & upload dynamic build steps
- label: ":llama:"
key: "pipeline-gen"
concurrency_group: 'depot-nix-eval'
concurrency: 5 # much more than this and whitby will OOM
command: |
set -ue
if test -n "$${GERRIT_CHANGE_URL-}"; then
echo "This is a build of [cl/$$GERRIT_CHANGE_ID]($$GERRIT_CHANGE_URL) (at patchset #$$GERRIT_PATCHSET)" | \
buildkite-agent annotate
fi
# Attempt to fetch a target map from a parent commit on canon,
# except on builds of canon itself.
[ "${BUILDKITE_BRANCH}" != "refs/heads/canon" ] && \
nix/buildkite/fetch-parent-targets.sh
PIPELINE_ARGS=""
if [[ -f tmp/parent-target-map.json ]]; then
PIPELINE_ARGS="--arg parentTargetMap tmp/parent-target-map.json"
fi
nix-build --option restrict-eval true --include "depot=$${PWD}" \
--include "store=/nix/store" \
--allowed-uris 'https://' \
-A ops.pipelines.depot \
-o pipeline --show-trace $$PIPELINE_ARGS
# Steps need to be uploaded in reverse order because pipeline
# upload prepends instead of appending.
ls pipeline/build-chunk-*.json | tac | while read chunk; do
buildkite-agent pipeline upload $$chunk
done
buildkite-agent artifact upload "pipeline/*"
# Wait for all previous steps to complete.
- wait: null
continue_on_failure: true
# Exit with success or failure depending on whether any other steps
# failed.
#
# This information is checked by querying the Buildkite GraphQL API
# and fetching the count of failed steps.
#
# This step must be :duck: (yes, really!) because the post-command
# hook will inspect this name.
#
# Note that this step has requirements for the agent environment, which
# are enforced in our NixOS configuration:
#
# * curl and jq must be on the $PATH of build agents
# * besadii configuration must be readable to the build agents
- label: ":duck:"
key: ":duck:"
command: |
set -ueo pipefail
readonly FAILED_JOBS=$(curl 'https://graphql.buildkite.com/v1' \
--silent \
-H "Authorization: Bearer $(cat ${BUILDKITE_TOKEN_PATH})" \
-d "{\"query\": \"query BuildStatusQuery { build(uuid: \\\"$BUILDKITE_BUILD_ID\\\") { jobs(passed: false) { count } } }\"}" | \
jq -r '.data.build.jobs.count')
echo "$$FAILED_JOBS build jobs failed."
if (( $$FAILED_JOBS > 0 )); then
exit 1
fi
# After duck, on success, upload and run any release steps that were
# output by the dynamic pipeline.
- label: ":arrow_heading_down:"
depends_on:
- step: ":duck:"
allow_failure: false
command: |
set -ueo pipefail
buildkite-agent artifact download "pipeline/*" .
find ./pipeline -name 'release-chunk-*.json' | tac | while read chunk; do
buildkite-agent pipeline upload $$chunk
done