Files
nicktrn 9ecf07731a v3: small features and fixes for prod infra (#968)
* add checkpoint restore events

* fix retries.enabledInDev

* fix tsconfig paths

* fix provider build and dev

* update kubernetes provider and fix builds again

* upgrade prod base to node 20

* update infra publish workflow

* rethrow k8s errors after logging

* shorten index container names

* fix error type assertion

* rename type assertion

* remove resource limits for now

* add missing run id on create

* add push to deploy command for self-hosting

* checkpointing fixes

* update coordinator image

* ensure valid registry login

* delete checkpoint archive after successful push

* log options on error

* structured logs for socket connections

* fix structured log merge

* exit process after checkpointing

* update restore pull secret name

* append shortcode to restore names

* log handler payload

* disable post start lifecycle hook

* pass in coordinator host via volume

* replace dapi with taskinfo

* add missing restore label

* don't restart restored containers

* remove init container from create

* atomic post-completion checkpoints

* switch to run id for container names

* improve wait accuracy

* measure basic checkpoint perf

* always log disconnect reason

* use system clock to end wait spans

* checkpoint readiness and cancel signals

* restore from checkpoint events and fix statuses

* remove attempt id env var

* restore dependencies from events

* reconnect wip

* lifecycle hooks are back

* fix hooks and improve reconnect

* make docker send postStart hook

* only checkpoint for retry if large delay

* fix a few more resume issues

* lifecycle hook fixes

* skip connection handler when waiting for post start hook

---------

Co-authored-by: Eric Allam <eric@trigger.dev>
2024-03-25 16:28:56 +00:00

61 lines
1.9 KiB
Docker

# syntax=docker/dockerfile:labs
FROM node:18-bullseye-slim@sha256:a4edd54dcfdcacc8a4100fee71498e8671d99556a1acf5614539214a70092426 AS node-18
WORKDIR /app
FROM node-18 AS pruner
COPY --chown=node:node . .
RUN npx -q turbo@1.10.9 prune --scope=coordinator --docker
RUN find . -name "node_modules" -type d -prune -exec rm -rf '{}' +
FROM node-18 AS base
RUN apt-get update \
&& apt-get install -y buildah ca-certificates dumb-init \
&& rm -rf /var/lib/apt/lists/*
COPY --chown=node:node .gitignore .gitignore
COPY --from=pruner --chown=node:node /app/out/json/ .
COPY --from=pruner --chown=node:node /app/out/pnpm-lock.yaml ./pnpm-lock.yaml
COPY --from=pruner --chown=node:node /app/out/pnpm-workspace.yaml ./pnpm-workspace.yaml
FROM base AS dev-deps
RUN corepack enable
ENV NODE_ENV development
RUN --mount=type=cache,id=pnpm,target=/root/.local/share/pnpm/store pnpm fetch --no-frozen-lockfile
RUN --mount=type=cache,id=pnpm,target=/root/.local/share/pnpm/store pnpm install --ignore-scripts --no-frozen-lockfile
FROM base AS builder
RUN corepack enable
COPY --from=pruner --chown=node:node /app/out/full/ .
COPY --from=dev-deps --chown=node:node /app/ .
COPY --chown=node:node turbo.json turbo.json
RUN pnpm run -r --filter coordinator build:bundle
FROM alpine AS cri-tools
WORKDIR /cri-tools
ARG CRICTL_VERSION=v1.29.0
ARG CRICTL_CHECKSUM=sha256:d16a1ffb3938f5a19d5c8f45d363bd091ef89c0bc4d44ad16b933eede32fdcbb
ADD --checksum=${CRICTL_CHECKSUM} \
https://github.com/kubernetes-sigs/cri-tools/releases/download/${CRICTL_VERSION}/crictl-${CRICTL_VERSION}-linux-amd64.tar.gz .
RUN tar zxvf crictl-${CRICTL_VERSION}-linux-amd64.tar.gz
FROM base AS runner
RUN corepack enable
ENV NODE_ENV production
COPY --from=cri-tools --chown=node:node /cri-tools/crictl /usr/local/bin
COPY --from=builder --chown=node:node /app/apps/coordinator/dist/index.mjs ./index.mjs
EXPOSE 8000
CMD [ "/usr/bin/dumb-init", "--", "/usr/local/bin/node", "./index.mjs" ]