onnxruntime/tools/ci_build/github/azure-pipelines/templates/c-api-linux-cpu.yml
Yi Zhang 0d1da41ca8
Fix docker image layer caching to avoid redundant docker building and transient connection exceptions. (#21612)
### Description
Improve docker commands to make docker image layer caching works.
It can make docker building faster and more stable.
So far, A100 pool's system disk is too small to use docker cache.
We won't use pipeline cache for docker image and remove some legacy
code.

### Motivation and Context
There are often an exception of
```
64.58 + curl https://nodejs.org/dist/v18.17.1/node-v18.17.1-linux-x64.tar.gz -sSL --retry 5 --retry-delay 30 --create-dirs -o /tmp/src/node-v18.17.1-linux-x64.tar.gz --fail
286.4 curl: (92) HTTP/2 stream 0 was not closed cleanly: INTERNAL_ERROR (err 2)
```
Because Onnxruntime pipeline have been sending too many requests to
download Nodejs in docker building.
Which is the major reason of pipeline failing now

In fact, docker image layer caching never works.
We can always see the scrips are still running
```
#9 [3/5] RUN cd /tmp/scripts && /tmp/scripts/install_centos.sh && /tmp/scripts/install_deps.sh && rm -rf /tmp/scripts
#9 0.234 /bin/sh: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8)
#9 0.235 /bin/sh: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8)
#9 0.235 /tmp/scripts/install_centos.sh: line 1: !/bin/bash: No such file or directory
#9 0.235 ++ '[' '!' -f /etc/yum.repos.d/microsoft-prod.repo ']'
#9 0.236 +++ tr -dc 0-9.
#9 0.236 +++ cut -d . -f1
#9 0.238 ++ os_major_version=8
....
#9 60.41 + curl https://nodejs.org/dist/v18.17.1/node-v18.17.1-linux-x64.tar.gz -sSL --retry 5 --retry-delay 30 --create-dirs -o /tmp/src/node-v18.17.1-linux-x64.tar.gz --fail
#9 60.59 + return 0
...
```

This PR is improving the docker command to make image layer caching
work.
Thus, CI won't send so many redundant request of downloading NodeJS.
```
#9 [2/5] ADD scripts /tmp/scripts
#9 CACHED

#10 [3/5] RUN cd /tmp/scripts && /tmp/scripts/install_centos.sh && /tmp/scripts/install_deps.sh && rm -rf /tmp/scripts
#10 CACHED

#11 [4/5] RUN adduser --uid 1000 onnxruntimedev
#11 CACHED

#12 [5/5] WORKDIR /home/onnxruntimedev
#12 CACHED
```

###Reference
https://docs.docker.com/build/drivers/

---------

Co-authored-by: Yi Zhang <your@email.com>
2024-08-06 21:37:09 +08:00

113 lines
4.5 KiB
YAML

# This file contains the ADO job that build libonnxruntime.so on Linux
parameters:
- name: AdditionalBuildFlags
displayName: Additional build flags for build.py
type: string
default: ''
- name: BaseImage
type: string
- name: OnnxruntimeArch
type: string
- name: OnnxruntimeNodejsBindingArch
type: string
values:
- arm64
- x64
- name: PoolName
type: string
default: 'onnxruntime-Ubuntu2204-AMD-CPU'
- name: ArtifactNamePrefix
type: string
default: "onnxruntime"
- name: PackageJava
type: boolean
default: true
- name: PackageNodejs
type: boolean
default: true
jobs:
- job: Linux_C_API_Packaging_CPU_${{parameters.OnnxruntimeArch}}
workspace:
clean: all
timeoutInMinutes: 210
pool: ${{parameters.PoolName}}
steps:
- checkout: self
clean: true
submodules: none
- template: set-version-number-variables-step.yml
- ${{ if eq(parameters.OnnxruntimeArch, 'x64') }}:
- template: get-docker-image-steps.yml
parameters:
Dockerfile: tools/ci_build/github/linux/docker/inference/x86_64/default/cpu/Dockerfile
Context: tools/ci_build/github/linux/docker/inference/x86_64/default/cpu
DockerBuildArgs: "--build-arg BUILD_UID=$( id -u ) --build-arg BASEIMAGE=${{parameters.BaseImage}}"
Repository: onnxruntimecpubuildcentos8${{parameters.OnnxruntimeArch}}_packaging
- ${{ if eq(parameters.OnnxruntimeArch, 'aarch64') }}:
- template: get-docker-image-steps.yml
parameters:
Dockerfile: tools/ci_build/github/linux/docker/inference/aarch64/default/cpu/Dockerfile
Context: tools/ci_build/github/linux/docker/inference/aarch64/default/cpu
DockerBuildArgs: "--build-arg BUILD_UID=$( id -u ) --build-arg BASEIMAGE=${{parameters.BaseImage}}"
Repository: onnxruntimecpubuildcentos8${{parameters.OnnxruntimeArch}}_packaging
UpdateDepsTxt: false
- task: CmdLine@2
inputs:
script: |
mkdir -p $HOME/.onnx
docker run --rm --volume /data/onnx:/data/onnx:ro --volume $(Build.SourcesDirectory):/onnxruntime_src --volume $(Build.BinariesDirectory):/build \
--volume $HOME/.onnx:/home/onnxruntimedev/.onnx -e NIGHTLY_BUILD onnxruntimecpubuildcentos8${{parameters.OnnxruntimeArch}}_packaging /bin/bash -c "python3.9 \
/onnxruntime_src/tools/ci_build/build.py --enable_lto --build_java --build_nodejs --build_dir /build --config Release \
--skip_submodule_sync --parallel --use_binskim_compliant_compile_flags --build_shared_lib ${{ parameters.AdditionalBuildFlags }} && cd /build/Release && make install DESTDIR=/build/installed"
workingDirectory: $(Build.SourcesDirectory)
displayName: 'Build'
- script: |
set -e -x
mkdir $(Build.ArtifactStagingDirectory)/testdata
cp $(Build.BinariesDirectory)/Release/libcustom_op_library.so* $(Build.ArtifactStagingDirectory)/testdata
ls -al $(Build.ArtifactStagingDirectory)
displayName: 'Create Artifacts'
- ${{ if eq(parameters.PackageJava, 'true') }}:
- template: java-api-artifacts-package-and-publish-steps-posix.yml
parameters:
arch: 'linux-${{parameters.OnnxruntimeArch}}'
buildConfig: 'Release'
artifactName: 'onnxruntime-java-linux-${{parameters.OnnxruntimeArch}}'
version: '$(OnnxRuntimeVersion)'
libraryName: 'libonnxruntime.so'
nativeLibraryName: 'libonnxruntime4j_jni.so'
- template: c-api-artifacts-package-and-publish-steps-posix.yml
parameters:
buildConfig: 'Release'
artifactName: '${{parameters.ArtifactNamePrefix}}-linux-${{parameters.OnnxruntimeArch}}-$(OnnxRuntimeVersion)'
artifactNameNoVersionString: '${{parameters.ArtifactNamePrefix}}-linux-${{parameters.OnnxruntimeArch}}'
libraryName: 'libonnxruntime.so.$(OnnxRuntimeVersion)'
- ${{ if eq(parameters.PackageNodejs, 'true') }}:
- template: nodejs-artifacts-package-and-publish-steps-posix.yml
parameters:
arch: '${{parameters.OnnxruntimeNodejsBindingArch}}'
os: 'linux'
artifactName: 'drop-onnxruntime-nodejs-linux-${{parameters.OnnxruntimeArch}}'
- ${{ if not(eq(parameters.OnnxruntimeNodejsBindingArch, 'arm64')) }}:
- template: component-governance-component-detection-steps.yml
parameters:
condition: 'succeeded'
- task: mspremier.PostBuildCleanup.PostBuildCleanup-task.PostBuildCleanup@3
displayName: 'Clean Agent Directories'
condition: always()