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

Use jemalloc to trace thread allocation #8844

Merged
merged 42 commits into from
Mar 18, 2024
Merged

Use jemalloc to trace thread allocation #8844

merged 42 commits into from
Mar 18, 2024

Conversation

CalvinNeo
Copy link
Member

@CalvinNeo CalvinNeo commented Mar 14, 2024 •
edited by JaySon-Huang
Loading

What problem does this PR solve?

Issue Number: close #8835, close #8589

Problem Summary:

  1. WITH_JEMALLOC to enable external-jemalloc
  2. Introduce reportThreadAllocInfo etc.

Basicly two modes:

  1. For everlasting threads, record allocated/deallocated ptr, update according to these ptrs.
  2. For non-everlasting threads, mostly comes from Proxy, update only when the thread is executing something.

We don't directly monitor at FFI boundary because:

  1. There are some threads like raftstore which can't be monitored through FFI boundary.
  2. Rust's thread id does not has a meaning.

See also https://github.com/pingcap/tidb-engine-ext/pull/366/files

What is changed and how it works?

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

None

@CalvinNeo
z
5987e73 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@ti-chi-bot ti-chi-bot bot added do-not-merge/needs-linked-issue release-note-none Denotes a PR that doesn't merit a release note. size/L Denotes a PR that changes 100-499 lines, ignoring generated files. labels Mar 14, 2024
@CalvinNeo
instant
79d847c 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
fix
279e7a9 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
fix
51aa25b 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
zzzzz
d8ea43b 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@ti-chi-bot ti-chi-bot bot added size/XL Denotes a PR that changes 500-999 lines, ignoring generated files. and removed size/L Denotes a PR that changes 100-499 lines, ignoring generated files. labels Mar 14, 2024
@CalvinNeo
Copy link
Member Author

image

CalvinNeo and others added 4 commits March 14, 2024 23:19
@CalvinNeo
fmt
e0705b1 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
h
c73606a 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
f
aede44c 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
Merge branch 'master' into jemalloc-alloc
eb416dc
Lloyd-Pottiger
Lloyd-Pottiger reviewed Mar 15, 2024
View reviewed changes
dbms/src/Storages/KVStore/KVStore.cpp Outdated Show resolved Hide resolved
dbms/src/Storages/KVStore/KVStore.cpp Outdated Show resolved Hide resolved
dbms/src/Storages/KVStore/FFI/ProxyFFI.cpp Outdated Show resolved Hide resolved
CMakeLists.txt Outdated Show resolved Hide resolved
dbms/src/Common/MemoryTrace.h Outdated Show resolved Hide resolved
CalvinNeo and others added 10 commits March 15, 2024 10:50
@CalvinNeo
co
33c06a9 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo @Lloyd-Pottiger
Update dbms/src/Storages/KVStore/FFI/ProxyFFI.cpp
c433699 
Co-authored-by: Lloyd-Pottiger <60744015+Lloyd-Pottiger@users.noreply.github.com>
@CalvinNeo
Merge branch 'jemalloc-alloc' of github.com:CalvinNeo/tics into jemal…
95cb885 
…loc-alloc
@CalvinNeo
fix
c2a78f7 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
t1
dc8159d 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
t1
8232c97 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
reset
b662e97 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
fix
c3fb1a4 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
z
f8f5039 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
update proxy
22f54b2 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
f
f9c4ed3 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
f
1050cdf 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
f
0f39d24 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
x
9a5a426 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
x
d9d141d 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
x
b15004a 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
JaySon-Huang
JaySon-Huang reviewed Mar 18, 2024
View reviewed changes
dbms/src/Common/TiFlashMetrics.cpp Outdated Show resolved Hide resolved
dbms/src/Storages/KVStore/KVStore.cpp Outdated Show resolved Hide resolved
dbms/src/Storages/KVStore/KVStore.cpp Outdated Show resolved Hide resolved
dbms/src/Common/TiFlashMetrics.h Outdated Show resolved Hide resolved
CalvinNeo and others added 3 commits March 18, 2024 11:27
@CalvinNeo @JaySon-Huang
Update dbms/src/Common/TiFlashMetrics.cpp
a97525b 
Co-authored-by: JaySon <tshent@qq.com>
@CalvinNeo
x
b45c47a 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
Merge branch 'jemalloc-alloc' of github.com:CalvinNeo/tics into jemal…
0d82b86 
…loc-alloc
JinheLin
JinheLin reviewed Mar 18, 2024
View reviewed changes
dbms/src/Common/MemoryTrace.cpp Outdated
@@ -0,0 +1,37 @@
// Copyright 2024 PingCAP, Inc.
Copy link
Contributor

Choose a reason for hiding this comment

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

This filename is easy to confuse with MemoryTracker.cpp.

Copy link
Member Author

Choose a reason for hiding this comment

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

Changed into MemoryAllocTracker

@CalvinNeo
df
5fa20a1 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
df2
b384af1 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
fix
0759459 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
proxy
25170e0 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
Merge remote-tracking branch 'upstream/master' into jemalloc-alloc
5d10880
@CalvinNeo
fix2
d3356ac 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
fix2
2eead98 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
Copy link
Member Author

/run-all-tests

@CalvinNeo
Copy link
Member Author

/unhold

@ti-chi-bot ti-chi-bot bot removed the do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. label Mar 18, 2024
@ti-chi-bot ti-chi-bot
Copy link
Contributor

ti-chi-bot bot commented Mar 18, 2024

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: JaySon-Huang, JinheLin, Lloyd-Pottiger

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

The pull request process is described here

Needs approval from an approver in each of these files:
  • OWNERS [JaySon-Huang,JinheLin,Lloyd-Pottiger]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@CalvinNeo
Copy link
Member Author 

[2024-03-18T09:33:57.596Z] 
Stopping fullstack-test_tiflash0_1 ... error

Stopping fullstack-test_tikv0_1    ... error

Stopping fullstack-test_pd0_1      ... error

Stopping fullstack-test_tidb0_1    ... done


[2024-03-18T09:33:57.596Z] ERROR: for fullstack-test_tiflash0_1  cannot stop container: 1f118e0614d4aac39cf246135f74a693a79197d56bb4142de62f0999daa734ca: tried to kill container, but did not receive an exit event

[2024-03-18T09:33:57.596Z] Removing fullstack-test_tidb0_1    ... 

[2024-03-18T09:33:57.596Z] Removing fullstack-test_tiflash0_1 ... 

[2024-03-18T09:33:57.851Z] 
Removing fullstack-test_tidb0_1    ... done

Removing fullstack-test_tiflash0_1 ... done
Removing network fullstack-test_default

[2024-03-18T09:33:57.852Z] error while removing network: network fullstack-test_default id c8d1b8608346fbdb325d6157808b9a71ad112ff4d6223204c15ac087a8c52973 has active endpoints

@CalvinNeo
ft
b41346b 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
Copy link
Member Author

/run-all-tests

@CalvinNeo
ft
a9aaafa 
Signed-off-by: CalvinNeo <calvinneo1995@gmail.com>
@CalvinNeo
Copy link
Member Author

/run-all-tests

@CalvinNeo
Copy link
Member Author

/run-unit-test

@ti-chi-bot ti-chi-bot bot merged commit f061a58 into pingcap:master Mar 18, 2024
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@JaySon-Huang JaySon-Huang JaySon-Huang approved these changes

@Lloyd-Pottiger Lloyd-Pottiger Lloyd-Pottiger approved these changes

@JinheLin JinheLin JinheLin approved these changes

Assignees
No one assigned
Labels
approved lgtm release-note-none Denotes a PR that doesn't merit a release note. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Support thread-wise memory alloc/dealloc monitor tiflash cn always crash after kill this tiflash cn
4 participants
@CalvinNeo @Lloyd-Pottiger @JaySon-Huang @JinheLin