daos icon indicating copy to clipboard operation
daos copied to clipboard
verified publisher icon daos-stack

DAOS-15914 dtx: control DTX RPC to reduce network load

Open Nasf-Fan opened this issue 1 year ago • 33 comments

  1. Send DTX batched commit RPCs step by step

Currently, for each DTX batched commit operation, it will handle at most 512 DTX entries that may generate DTX commit RPCs to thousands of DAOS targets. We will not send out the batched RPCs all together, instead, we will send them step by step. After each step, the logic will yield and wait until replied, and then next batched RPCs. That can avoid holding too much system resources for relative long time. It is also helpful to reduce the whole system network peak load and the pressure on related targets.

  1. Cleanup stale DTX based on global RPC timeout

Originally, DTX cleanup logic will be triggered if the life for some stale DTX exceeds the fixed threshold DTX_CLEANUP_THD_AGE_UP (90 sec) that maybe smaller than global default RPC timeout, as to related DTX refresh RPC for cleanup logic maybe send out too early before related modification RPC(s) timeout. It increases network load unnecessarily.

Then we adjust the DTX cleanup threshold based on global default RPC timeout value, and give related DTX leader sometime after default RPC timeout to commit or abort the DTX. If the DTX is still prepared after that, then trigger DTX cleanup to handle potential stale DTX entries.

  1. Reorg DTX CoS logic

Reduce the RPCs caused by potential repeated DTX commit. More clear names for DTX CoS API.

Before requesting gatekeeper:

  • [ ] Two review approvals and any prior change requests have been resolved.
  • [ ] Testing is complete and all tests passed or there is a reason documented in the PR why it should be force landed and forced-landing tag is set.
  • [ ] Features: (or Test-tag*) commit pragma was used or there is a reason documented that there are no appropriate tags for this PR.
  • [ ] Commit messages follows the guidelines outlined here.
  • [ ] Any tests skipped by the ticket being addressed have been run and passed in the PR.

Gatekeeper:

  • [ ] You are the appropriate gatekeeper to be landing the patch.
  • [ ] The PR has 2 reviews by people familiar with the code, including appropriate owners.
  • [ ] Githooks were used. If not, request that user install them and check copyright dates.
  • [ ] Checkpatch issues are resolved. Pay particular attention to ones that will show up on future PRs.
  • [ ] All builds have passed. Check non-required builds for any new compiler warnings.
  • [ ] Sufficient testing is done. Check feature pragmas and test tags and that tests skipped for the ticket are run and now pass with the changes.
  • [ ] If applicable, the PR has addressed any potential version compatibility issues.
  • [ ] Check the target branch. If it is master branch, should the PR go to a feature branch? If it is a release branch, does it have merge approval in the JIRA ticket.
  • [ ] Extra checks if forced landing is requested
    • [ ] Review comments are sufficiently resolved, particularly by prior reviewers that requested changes.
    • [ ] No new NLT or valgrind warnings. Check the classic view.
    • [ ] Quick-build or Quick-functional is not used.
  • [ ] Fix the commit message upon landing. Check the standard here. Edit it to create a single commit. If necessary, ask submitter for a new summary.

Nasf-Fan avatar May 30 '24 05:05 Nasf-Fan

Ticket title is 'Aurora ECB testing: 256ECB:105 servers - ior with MPIIO/DFS EC_16P2GX hung' Status is 'In Progress' Labels: 'daos_ecb_issue,daos_ecb_scale,scrubbed_2.8,triaged' https://daosio.atlassian.net/browse/DAOS-15914

github-actions[bot] avatar May 30 '24 05:05 github-actions[bot]

Test stage Python Bandit check completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/3/execution/node/145/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/3/execution/node/365/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/3/execution/node/360/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/3/execution/node/303/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/3/execution/node/300/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Python Bandit check completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/4/execution/node/145/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/4/execution/node/371/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/4/execution/node/379/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/4/execution/node/331/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/4/execution/node/303/log

daosbuild1 avatar May 31 '24 03:05 daosbuild1

Test stage Python Bandit check completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/5/execution/node/145/log

daosbuild1 avatar May 31 '24 05:05 daosbuild1

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/5/execution/node/352/log

daosbuild1 avatar May 31 '24 05:05 daosbuild1

Test stage Python Bandit check completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/6/execution/node/146/log

daosbuild1 avatar May 31 '24 05:05 daosbuild1

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/6/execution/node/323/log

daosbuild1 avatar May 31 '24 05:05 daosbuild1

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/6/execution/node/363/log

daosbuild1 avatar May 31 '24 05:05 daosbuild1

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/6/execution/node/326/log

daosbuild1 avatar May 31 '24 05:05 daosbuild1

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/6/execution/node/320/log

daosbuild1 avatar May 31 '24 05:05 daosbuild1

Test stage Python Bandit check completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/7/execution/node/145/log

daosbuild1 avatar May 31 '24 08:05 daosbuild1

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/7/execution/node/348/log

daosbuild1 avatar May 31 '24 08:05 daosbuild1

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/7/execution/node/365/log

daosbuild1 avatar May 31 '24 08:05 daosbuild1

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/7/execution/node/326/log

daosbuild1 avatar May 31 '24 08:05 daosbuild1

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/7/execution/node/352/log

daosbuild1 avatar May 31 '24 08:05 daosbuild1

Test stage NLT on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-14476/11/testReport/

daosbuild1 avatar Jun 02 '24 17:06 daosbuild1

Test stage NLT on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-14476/13/testReport/

daosbuild1 avatar Jun 03 '24 04:06 daosbuild1

Test stage NLT on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-14476/15/testReport/

daosbuild1 avatar Jun 03 '24 06:06 daosbuild1

FYI a fix for the DEB build just landed to master

daltonbohning avatar Jun 05 '24 17:06 daltonbohning

Test stage Build on Leap 15.5 with Intel-C and TARGET_PREFIX completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/22/execution/node/387/log

daosbuild1 avatar Jun 14 '24 07:06 daosbuild1

Test stage Build on Leap 15.5 with Intel-C and TARGET_PREFIX completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-14476/23/execution/node/389/log

daosbuild1 avatar Jun 14 '24 07:06 daosbuild1

Test stage Test RPMs on EL 8.6 completed with status FAILURE. https://build.hpdd.intel.com/job/daos-stack/job/daos/job/PR-14476/27/display/redirect

daosbuild1 avatar Jun 17 '24 09:06 daosbuild1