Push json-data to Git
Christophe Benz
1Running with gitlab-runner 17.8.3 (690ce25c)2 on Run fetchers JBzuiMazz, system ID: s_33ef491069c64Using Docker executor with image git.nomics.world:4567/dbnomics/dbnomics-fetcher-pipeline/git-job:latest ...5Authenticating with credentials from job payload (GitLab Registry)6Pulling docker image git.nomics.world:4567/dbnomics/dbnomics-fetcher-pipeline/git-job:latest ...7Using docker image sha256:afc3785ac7a4f3a034a20e87914f55a0bb100a12dc045e546d87be3a982d698a for git.nomics.world:4567/dbnomics/dbnomics-fetcher-pipeline/git-job:latest with digest git.nomics.world:4567/dbnomics/dbnomics-fetcher-pipeline/git-job@sha256:76b884efa708d8842c7a5310996ba87a6995d4cf2c5629b5e0f6cd69081003e1 ...9Running on runner-jbzuimazz-project-106-concurrent-1 via tyche...11Skipping Git repository setup12Skipping Git checkout13Skipping Git submodules setup15Using docker image sha256:afc3785ac7a4f3a034a20e87914f55a0bb100a12dc045e546d87be3a982d698a for git.nomics.world:4567/dbnomics/dbnomics-fetcher-pipeline/git-job:latest with digest git.nomics.world:4567/dbnomics/dbnomics-fetcher-pipeline/git-job@sha256:76b884efa708d8842c7a5310996ba87a6995d4cf2c5629b5e0f6cd69081003e1 ...16$ mkdir -p $PROVIDER_GIT_DIR17$ git config --global push.default simple18$ git config --global user.email "${PROVIDER_SLUG}-fetcher@localhost"19$ git config --global user.name "${PROVIDER_SLUG} fetcher"20$ eval $(ssh-agent -s)21Agent pid 1922$ echo "$SSH_PRIVATE_KEY" | tr -d '\r' | ssh-add -23Identity added: (stdin) (lbma-fetcher@localhost)24$ mkdir -p ~/.ssh25$ chmod 700 ~/.ssh26$ ssh-keyscan -t rsa $CI_SERVER_HOST >> ~/.ssh/known_hosts27# git.nomics.world:22 SSH-2.0-OpenSSH_9.2p1 Debian-2+deb12u528$ chmod 644 ~/.ssh/known_hosts29$ PIPELINE_STATE_DIR="${PIPELINE_DIR}/state" # collapsed multi-line command30$ if [ "$START_FROM" == "deploy" ] && [ ! -d "$WORKSPACE_JSON_DATA_DIR" ]; then # collapsed multi-line command31$ cd "$PROVIDER_GIT_DIR"32$ if [ $RM_GIT_LOCK == "1" ] && [ -f json-data/$GIT_LOCK_FILE ]; then # collapsed multi-line command33$ echo "Updating json-data Git repository clone..."34Updating json-data Git repository clone...35$ time git-pull-or-clone -v --clone-url "$JSON_DATA_REMOTE_SSH_URL" json-data362025-03-23 00:35:55,075 [27] INFO cli.py: 'json-data' already exists, pulling...37Warning: Permanently added the RSA host key for IP address '51.159.101.244' to the list of known hosts.38Auto packing the repository in background for optimum performance.39See "git help gc" for manual housekeeping.40 Command being timed: "git fetch"41 User time (seconds): 0.0142 System time (seconds): 0.0343 Percent of CPU this job got: 2%44 Elapsed (wall clock) time (h:mm:ss or m:ss): 0:01.7845 Average shared text size (kbytes): 046 Average unshared data size (kbytes): 047 Average stack size (kbytes): 048 Average total size (kbytes): 049 Maximum resident set size (kbytes): 652850 Average resident set size (kbytes): 051 Major (requiring I/O) page faults: 6052 Minor (reclaiming a frame) page faults: 193853 Voluntary context switches: 22954 Involuntary context switches: 9655 Swaps: 056 File system inputs: 814457 File system outputs: 12058 Socket messages sent: 059 Socket messages received: 060 Signals delivered: 061 Page size (bytes): 409662 Exit status: 063 Command being timed: "git reset --hard @{upstream} --quiet"64 User time (seconds): 0.0065 System time (seconds): 0.0066 Percent of CPU this job got: 3%67 Elapsed (wall clock) time (h:mm:ss or m:ss): 0:00.2068 Average shared text size (kbytes): 069 Average unshared data size (kbytes): 070 Average stack size (kbytes): 071 Average total size (kbytes): 072 Maximum resident set size (kbytes): 508873 Average resident set size (kbytes): 074 Major (requiring I/O) page faults: 1375 Minor (reclaiming a frame) page faults: 23176 Voluntary context switches: 4077 Involuntary context switches: 2678 Swaps: 079 File system inputs: 56880 File system outputs: 4881 Socket messages sent: 082 Socket messages received: 083 Signals delivered: 084 Page size (bytes): 409685 Exit status: 086real 0m2.253s87user 0m0.203s88sys 0m0.084s89$ echo "Synchronizing converted data to json-data Git repository..."90Synchronizing converted data to json-data Git repository...91$ time dbnomics-update-storage -v "$WORKSPACE_JSON_DATA_DIR" json-data922025-03-23 00:35:58,081 [42] INFO dbnomics_data_model.storage.storage: Updating category tree of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) with the one of FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'merge'932025-03-23 00:35:58,097 [42] INFO dbnomics_data_model.storage.storage: Updating releases metadata of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) with the one of FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'merge'942025-03-23 00:35:58,097 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'platinum_M' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'952025-03-23 00:35:58,298 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.20 seconds.962025-03-23 00:35:58,298 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied972025-03-23 00:35:58,298 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 982025-03-23 00:35:58,298 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'palladium_M' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'992025-03-23 00:35:58,344 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.04 seconds.1002025-03-23 00:35:58,344 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied1012025-03-23 00:35:58,344 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1022025-03-23 00:35:58,344 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'palladium_D' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'1032025-03-23 00:35:58,410 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.06 seconds.1042025-03-23 00:35:58,410 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied1052025-03-23 00:35:58,410 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1062025-03-23 00:35:58,410 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'silver_D' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'1072025-03-23 00:35:58,453 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.04 seconds.1082025-03-23 00:35:58,453 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied1092025-03-23 00:35:58,453 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1102025-03-23 00:35:58,453 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'gold_D' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'1112025-03-23 00:35:58,557 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.10 seconds.1122025-03-23 00:35:58,557 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied1132025-03-23 00:35:58,557 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1142025-03-23 00:35:58,558 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'gold_M' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'1152025-03-23 00:35:58,616 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.05 seconds.1162025-03-23 00:35:58,616 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied1172025-03-23 00:35:58,616 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1182025-03-23 00:35:58,616 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'platinum_D' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'1192025-03-23 00:35:58,887 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.27 seconds.1202025-03-23 00:35:58,887 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied1212025-03-23 00:35:58,887 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1222025-03-23 00:35:58,888 [42] INFO dbnomics_data_model.storage.storage: Updating dataset 'silver_M' of FileSystemStorage(storage_dir=PosixPath('json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) from the one in FileSystemStorage(storage_dir=PosixPath('/data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data'), get_series_offsets=None, storage_variant='detect', default_storage_variant='jsonl', warn_when_scanning_jsonl_series=False) using strategy 'replace'1232025-03-23 00:35:58,896 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: dirsync finished in 0.00 seconds.1242025-03-23 00:35:58,897 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 1 directories parsed, 0 files copied1252025-03-23 00:35:58,897 [42] INFO dbnomics_data_model.storage.adapters.filesystem.storage.dirsync: 126$ cd json-data127real 0m1.852s128user 0m0.403s129sys 0m0.082s130$ echo "Committing data from $WORKSPACE_JSON_DATA_DIR, and pushing"131Committing data from /data/dbnomics-prod/workspaces/lbma/pipelines/485466/json-data, and pushing132$ time git add -A133real 0m0.064s134user 0m0.000s135sys 0m0.004s136$ time git commit -m "Convert data from provider" -m "CI_PIPELINE_ID:$CI_PIPELINE_ID" -m "CI_JOB_ID:$CI_JOB_ID" --quiet || true137On branch master138Your branch is up to date with 'origin/master'.139nothing to commit, working tree clean140real 0m0.038s141user 0m0.003s142sys 0m0.003s143$ time git push144Everything up-to-date145real 0m0.398s146user 0m0.012s147sys 0m0.009s148$ PIPELINE_STATE_FILE="${PIPELINE_STATE_DIR}/state.json" # collapsed multi-line command149$ # bad strategy, to be removed # collapsed multi-line command150$ # used by IMF, ISTAT, to be removed # collapsed multi-line command152Job succeeded