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

executor: optimize cursor read point get by reading through pessimistic lock cache #36149

Merged
merged 12 commits into from
Jul 13, 2022
Merged

executor: optimize cursor read point get by reading through pessimistic lock cache #36149

merged 12 commits into from
Jul 13, 2022

Conversation

you06
Copy link
Contributor

@you06 you06 commented Jul 12, 2022 •
edited
Loading

What problem does this PR solve?

Issue Number: ref #36162

Problem Summary:

What is changed and how it works?

For the point-get must lock the secondary key, lock it before reading, then later TiDB can read from pessimistic lock cache, this reduces one kv-get RPC.

I test it by an edited sysbench update-non-index(wrap it in pessimistic txns) with the following options:

  • clustered index off
  • 32 threads
  • 10,000,000 table size
  • 1 table

Before

  • TPS: 3174
  • Latency(avg): 10.08ms
  • Latency(.95): 16.71ms

Screen Shot 2022-07-12 at 10 11 01 PM

After

  • TPS: 3509
  • Latency(avg): 9.12ms
  • Latency(.95): 15.27ms

Screen Shot 2022-07-12 at 11 14 33 PM

There are no kv-get requests.

Check List

Tests

  • Unit test
  • Integration test
  • Manual test (add detailed scripts or steps below)
  • No code

Side effects

  • Performance regression: Consumes more CPU
  • Performance regression: Consumes more Memory
  • Breaking backward compatibility

Documentation

  • Affects user behaviors
  • Contains syntax changes
  • Contains variable changes
  • Contains experimental features
  • Changes MySQL compatibility

Release note

Please refer to Release Notes Language Style Guide to write a quality release note.

Optimize cursor read point get by reading through pessimistic lock cache.

@ti-chi-bot
Copy link
Member

ti-chi-bot commented Jul 12, 2022 •
edited
Loading

[REVIEW NOTIFICATION]

This pull request has been approved by:

  • cfzjywxk
  • sticnarf

To complete the pull request process, please ask the reviewers in the list to review by filling /cc @reviewer in the comment.
After your PR has acquired the required number of LGTMs, you can assign this pull request to the committer in the list by filling /assign @committer in the comment to help you merge this pull request.

The full list of commands accepted by this bot can be found here.

Reviewer can indicate their review by submitting an approval review.
Reviewer can cancel approval by submitting a request changes review.

@ti-chi-bot ti-chi-bot added do-not-merge/needs-linked-issue release-note Denotes a PR that will be considered when it comes time to generate release notes. size/S Denotes a PR that changes 10-29 lines, ignoring generated files. labels Jul 12, 2022
@sre-bot
Copy link
Contributor

sre-bot commented Jul 12, 2022 •
edited
Loading

Code Coverage Details: https://codecov.io/github/pingcap/tidb/commit/1d7e800c363388ca25936127d3d873a9a4d90bdb

@you06
Copy link
Contributor Author

you06 commented Jul 12, 2022

This optimization only works when the following conditions are hit:

  • pessimistic transaction(do not include pessimistic auto commit)
  • repeatable read
  • non-clustered PK or unique index

Maybe we can push down the lock-if-exist mechanism(RC mode) into TiKV, then it's able to reduce one round RPC for RC, cc @TonsnakeLin.

sticnarf
sticnarf reviewed Jul 13, 2022
View reviewed changes
executor/point_get.go Outdated Show resolved Hide resolved
executor/point_get.go Outdated Show resolved Hide resolved
sticnarf
sticnarf approved these changes Jul 13, 2022
View reviewed changes
Copy link
Contributor

@sticnarf sticnarf left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ti-chi-bot ti-chi-bot added the status/LGT1 Indicates that a PR has LGTM 1. label Jul 13, 2022
@sticnarf sticnarf requested a review from cfzjywxk July 13, 2022 06:50
@ti-chi-bot ti-chi-bot added status/LGT2 Indicates that a PR has LGTM 2. and removed status/LGT1 Indicates that a PR has LGTM 1. labels Jul 13, 2022
@cfzjywxk
Copy link
Contributor

/merge

@ti-chi-bot
Copy link
Member

This pull request has been accepted and is ready to merge.

Commit hash: 9852e8e

@ti-chi-bot ti-chi-bot added the status/can-merge Indicates a PR has been approved by a committer. label Jul 13, 2022
@ti-chi-bot ti-chi-bot merged commit 5eec739 into pingcap:master Jul 13, 2022
@you06 you06 deleted the opt-point-get branch July 13, 2022 14:50
@sre-bot
Copy link
Contributor

sre-bot commented Jul 13, 2022

TiDB MergeCI notify

🔴 Bad News! New failing [1] after this pr merged.
These new failed integration tests seem to be caused by the current PR, please try to fix these new failed integration tests, thanks!

CI Name Result Duration Compare with Parent commit
idc-jenkins-ci/integration-cdc-test 🟥 failed 1, success 35, total 36 25 min New failing
idc-jenkins-ci-tidb/integration-ddl-test ✅ all 6 tests passed 6 min 46 sec Fixed
idc-jenkins-ci-tidb/integration-common-test 🟢 all 11 tests passed 26 min Existing passed
idc-jenkins-ci-tidb/common-test 🟢 all 12 tests passed 13 min Existing passed
idc-jenkins-ci-tidb/sqllogic-test-2 🟢 all 28 tests passed 7 min 14 sec Existing passed
idc-jenkins-ci-tidb/sqllogic-test-1 🟢 all 26 tests passed 7 min 1 sec Existing passed
idc-jenkins-ci-tidb/tics-test 🟢 all 1 tests passed 5 min 5 sec Existing passed
idc-jenkins-ci-tidb/integration-compatibility-test 🟢 all 1 tests passed 3 min 14 sec Existing passed
idc-jenkins-ci-tidb/mybatis-test 🟢 all 1 tests passed 3 min 2 sec Existing passed
idc-jenkins-ci-tidb/plugin-test 🟢 build success, plugin test success 4min Existing passed

joycse06 added a commit to joycse06/tidb that referenced this pull request Jul 13, 2022
@joycse06
Merge branch 'master' into add-sql-require-primary-key
0e25f45 
* master: (27 commits)
  executor: parallel cancel mpp query (pingcap#36161)
  store/copr: adjust the cop cache admission process time for paging (pingcap#36157)
  log-backup: get can restored global-checkpoint-ts when support v3 checkpoint advance (pingcap#36197)
  executor: optimize cursor read point get by reading through pessimistic lock cache (pingcap#36149)
  *: add tidb_min_paging_size system variable (pingcap#36107)
  planner: handle the expected row count for pushed-down selection in mpp (pingcap#36195)
  *: support show ddl jobs for sub-jobs (pingcap#36168)
  table-filter: optimize table pattern message and unit tests (pingcap#36160)
  domain: fix unstable test TestAbnormalSessionPool (pingcap#36154)
  executor: check the error returned by `handleNoDelay` (pingcap#36105)
  log-backup: fix checkpoint display (pingcap#36166)
  store/mockstore/unistore: fix several issues of coprocessor paging in unistore (pingcap#36147)
  test: refactor restart test (pingcap#36174)
  ddl: support rename index and columns for multi-schema change (pingcap#36148)
  test: remove meaningless test and update bazel (pingcap#36136)
  planner: Reduce verbosity of logging unknown system variables (pingcap#36013)
  metrics/grafana: bring back the plan cache miss panel (pingcap#36081)
  ddl: implement table granularity DDL for SchemaTracker (pingcap#36077)
  *: bazel use jdk 17 (pingcap#36070)
  telemetry: add reviewer rule (pingcap#36084)
  ...
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@sticnarf sticnarf sticnarf approved these changes

@cfzjywxk cfzjywxk cfzjywxk approved these changes

Assignees
No one assigned
Labels
release-note Denotes a PR that will be considered when it comes time to generate release notes. size/S Denotes a PR that changes 10-29 lines, ignoring generated files. status/can-merge Indicates a PR has been approved by a committer. status/LGT2 Indicates that a PR has LGTM 2.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@you06 @ti-chi-bot @sre-bot @cfzjywxk @sticnarf