Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Performance improvements for DQM startup #34837

Merged
merged 3 commits into from
Aug 13, 2021
Merged

Performance improvements for DQM startup #34837

merged 3 commits into from
Aug 13, 2021

Conversation

Dr15Jones
Copy link
Contributor

@Dr15Jones Dr15Jones commented Aug 11, 2021 •
edited
Loading

PR description:

Profiling workflow 1004.0 step2 showed > 30% of the short job time (just 10 events) was spent in two DQM routines

  • MonitorElementData::Path::set
  • DQMStore::findMEMonitorElementData::Path

In both cases, the routines were creating and destroying a very large number of temporary strings.

PR validation:

Code compiles and workflow 1004.0 step2 appears to run fine. The newly creates unit test for MonitorElementData::Path::set passes.

fixes cms-sw/framework-team#215

@Dr15Jones
Added unit test for MonitorElementData::Path::set
e86f5c0
@Dr15Jones
Improve performance of MonitorElementData::Path::set
f945679 
Profiling jobs showed this function taking 15% of the time for a
short job. The new version takes 0.5% by avoiding any unnecessary
memory allocations.
@Dr15Jones
Avoid creating temporary strings when doing comparisons
19b604e 
Profiling showed DQMStore::findME<MonitorElementData::Path> was
taking very long during beginRun because it was making lots of
temporary strings.
@cmsbuild cmsbuild added this to the CMSSW_12_1_X milestone Aug 11, 2021
@cmsbuild
Copy link
Contributor

+code-checks

Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-34837/24620

  • This PR adds an extra 24KB to repository

@cmsbuild
Copy link
Contributor

A new Pull Request was created by @Dr15Jones (Chris Jones) for master.

It involves the following packages:

  • DQMServices/Core (dqm)
  • DataFormats/Histograms (dqm, core)

@smuzaffar, @andrius-k, @Dr15Jones, @kmaeshima, @ErnestaP, @ahmad3213, @cmsbuild, @makortel, @jfernan2, @rvenditti can you please review it and eventually sign? Thanks.
@barvic, @rovere this is something you requested to watch as well.
@perrotta, @dpiparo, @qliphy you are the release manager for this.

cms-bot commands are listed here

@Dr15Jones
Copy link
Contributor Author

please test

@cmsbuild
Copy link
Contributor

-1

Failed Tests: RelVals-INPUT
Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-db7b0a/17680/summary.html
COMMIT: 19b604e
CMSSW: CMSSW_12_1_X_2021-08-10-2300/slc7_amd64_gcc900
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week1/cms-sw/cmssw/34837/17680/install.sh to create a dev area with all the needed externals and cmssw changes.

RelVals-INPUT

  • 23434.9923434.99_TTbar_14TeV+2026D49PU_PMXS1S2+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+HARVESTGlobalPU/step2_TTbar_14TeV+2026D49PU_PMXS1S2+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+HARVESTGlobalPU.log
  • 23434.2123434.21_TTbar_14TeV+2026D49PU_ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+DigiTriggerPU+RecoGlobalPU+MiniAODPU/step2_TTbar_14TeV+2026D49PU_ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+DigiTriggerPU+RecoGlobalPU+MiniAODPU.log
  • 23434.992123434.9921_TTbar_14TeV+2026D49PU_PMXS1S2ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+MiniAODPU/step2_TTbar_14TeV+2026D49PU_PMXS1S2ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+MiniAODPU.log
Expand to see more relval errors ...

Comparison Summary

Summary:

  • No significant changes to the logs found
  • Reco comparison results: 4 differences found in the comparisons
  • DQMHistoTests: Total files compared: 39
  • DQMHistoTests: Total histograms compared: 3001486
  • DQMHistoTests: Total failures: 6
  • DQMHistoTests: Total nulls: 1
  • DQMHistoTests: Total successes: 3001457
  • DQMHistoTests: Total skipped: 22
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 1.736 KiB( 38 files compared)
  • DQMHistoSizes: changed ( 1325.81,... ): 0.870 KiB Physics/NanoAODDQM
  • DQMHistoSizes: changed ( 312.0 ): -0.004 KiB MessageLogger/Warnings
  • Checked 165 log files, 37 edm output root files, 39 DQM output files
  • TriggerResults: no differences found

@Dr15Jones
Copy link
Contributor Author

Please test

I think the previous failures were from slow loading of the pileup files.

@cmsbuild
Copy link
Contributor

-1

Failed Tests: RelVals-INPUT
Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-db7b0a/17704/summary.html
COMMIT: 19b604e
CMSSW: CMSSW_12_1_X_2021-08-10-2300/slc7_amd64_gcc900
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week1/cms-sw/cmssw/34837/17704/install.sh to create a dev area with all the needed externals and cmssw changes.

RelVals-INPUT

  • 23434.9923434.99_TTbar_14TeV+2026D49PU_PMXS1S2+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+HARVESTGlobalPU/step2_TTbar_14TeV+2026D49PU_PMXS1S2+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+HARVESTGlobalPU.log
  • 23434.2123434.21_TTbar_14TeV+2026D49PU_ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+DigiTriggerPU+RecoGlobalPU+MiniAODPU/step2_TTbar_14TeV+2026D49PU_ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+DigiTriggerPU+RecoGlobalPU+MiniAODPU.log
  • 23434.992123434.9921_TTbar_14TeV+2026D49PU_PMXS1S2ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+MiniAODPU/step2_TTbar_14TeV+2026D49PU_PMXS1S2ProdLike+TTbar_14TeV_TuneCP5_GenSimHLBeamSpot14INPUT+PREMIX_PremixHLBeamSpot14PU+DigiTriggerPU+RecoGlobalPU+MiniAODPU.log
Expand to see more relval errors ...

Comparison Summary

Summary:

  • No significant changes to the logs found
  • Reco comparison results: 4 differences found in the comparisons
  • DQMHistoTests: Total files compared: 39
  • DQMHistoTests: Total histograms compared: 3001486
  • DQMHistoTests: Total failures: 7
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 3001457
  • DQMHistoTests: Total skipped: 22
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 1.74 KiB( 38 files compared)
  • DQMHistoSizes: changed ( 1325.81,... ): 0.870 KiB Physics/NanoAODDQM
  • Checked 165 log files, 37 edm output root files, 39 DQM output files
  • TriggerResults: no differences found

@Dr15Jones
Copy link
Contributor Author

please test

@cmsbuild
Copy link
Contributor

+1

Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-db7b0a/17714/summary.html
COMMIT: 19b604e
CMSSW: CMSSW_12_1_X_2021-08-11-1900/slc7_amd64_gcc900
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week1/cms-sw/cmssw/34837/17714/install.sh to create a dev area with all the needed externals and cmssw changes.

Comparison Summary

Summary:

  • No significant changes to the logs found
  • Reco comparison results: 3 differences found in the comparisons
  • DQMHistoTests: Total files compared: 39
  • DQMHistoTests: Total histograms compared: 3001486
  • DQMHistoTests: Total failures: 6
  • DQMHistoTests: Total nulls: 1
  • DQMHistoTests: Total successes: 3001457
  • DQMHistoTests: Total skipped: 22
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 1.744 KiB( 38 files compared)
  • DQMHistoSizes: changed ( 1325.81,... ): 0.870 KiB Physics/NanoAODDQM
  • DQMHistoSizes: changed ( 312.0 ): 0.004 KiB MessageLogger/Warnings
  • Checked 165 log files, 37 edm output root files, 39 DQM output files
  • TriggerResults: no differences found

@Dr15Jones
Copy link
Contributor Author

+1

@jfernan2
Copy link
Contributor

+1

@cmsbuild
Copy link
Contributor

This pull request is fully signed and it will be integrated in one of the next master IBs (tests are also fine). This pull request will now be reviewed by the release team before it's merged. @perrotta, @dpiparo, @qliphy (and backports should be raised in the release meeting by the corresponding L2)

@qliphy
Copy link
Contributor

qliphy commented Aug 13, 2021

+1

@cmsbuild cmsbuild merged commit 5eb483c into cms-sw:master Aug 13, 2021
This was referenced Aug 13, 2021
Merged
Merged
Merged
@Dr15Jones Dr15Jones deleted the fasterMonitorElementData_Path_set branch August 17, 2021 15:20
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
code-checks-approved core-approved dqm-approved fully-signed orp-approved tests-approved
Projects
None yet
Milestone
CMSSW_12_1_X
Development

Successfully merging this pull request may close these issues.

Decrease startup time for DQM code
4 participants
@Dr15Jones @cmsbuild @jfernan2 @qliphy