Differential D7718

journalprocessor: re-enable subsharding per partition
ClosedPublic
Actions

Authored by seirl on Apr 29 2022, 5:38 PM.

Details

Reviewers

olasd

Group Reviewers

Reviewers

Commits

rDDATASETc2c2c21e081c: journalprocessor: re-enable subsharding per partition

Summary

Significantly improves performance by reducing the number of levels in
each DB, and thus reducing the amount of compaction.

Test Plan

Tested with a manual export

Diff Detail

Repository

rDDATASET Datasets

Branch

master

Lint

No Linters Available

Unit

No Unit Test Coverage

Build Status

Buildable 28979
Build 45301: Phabricator diff pipeline on jenkins	Jenkins console · Jenkins
Build 45300: arc lint + arc unit

Event Timeline

seirl created this revision.Apr 29 2022, 5:38 PM

Herald added a reviewer: Reviewers. · View Herald TranscriptApr 29 2022, 5:38 PM

Build is green

Patch application report for D7718 (id=27914)

Rebasing onto db331f27e8...

First, rewinding head to replay your work on top of it...
Applying: journalprocessor: re-enable subsharding per partition

Changes applied before test

commit 64bdfe68f337cb8a2185fc36ad891f4176a8531e
Author: Antoine Pietri <antoine.pietri1@gmail.com>
Date:   Fri Apr 29 15:36:35 2022 +0000

    journalprocessor: re-enable subsharding per partition
    
    Significantly improves performance by reducing the number of levels in
    each DB, and thus reducing the amount of compaction.

See https://jenkins.softwareheritage.org/job/DDATASET/job/tests-on-diff/143/ for more details.

Harbormaster completed remote builds in B28979: Diff 27914.Apr 29 2022, 5:40 PM

seirl requested review of this revision.Apr 29 2022, 5:40 PM

In the future this may warrant a config knob (or enablement only above a given threshold in the target offsets) to avoid thrashing on 16 indexes all the time even for small(er) topics.

This revision is now accepted and ready to land.Apr 29 2022, 5:46 PM

rebase

This revision was landed with ongoing or failed builds.Apr 29 2022, 5:49 PM

Closed by commit rDDATASETc2c2c21e081c: journalprocessor: re-enable subsharding per partition (authored by seirl). · Explain Why

This revision was automatically updated to reflect the committed changes.

seirl added a commit: rDDATASETc2c2c21e081c: journalprocessor: re-enable subsharding per partition.

Build is green

Patch application report for D7718 (id=27915)

Rebasing onto db331f27e8...

Current branch diff-target is up to date.

Changes applied before test

commit c2c2c21e081c6276c2ef29248b562ff55bd44604
Author: Antoine Pietri <antoine.pietri1@gmail.com>
Date:   Fri Apr 29 15:36:35 2022 +0000

    journalprocessor: re-enable subsharding per partition
    
    Significantly improves performance by reducing the number of levels in
    each DB, and thus reducing the amount of compaction.

See https://jenkins.softwareheritage.org/job/DDATASET/job/tests-on-diff/144/ for more details.

Harbormaster completed remote builds in B28980: Diff 27915.Apr 29 2022, 5:51 PM

seirl mentioned this in T3021: Investigate why reading the journal of the content table takes so long.Apr 29 2022, 6:20 PM