[improve](load) limit flush thread num proportional to CPU count #33325
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thank you for your contribution to Apache Doris. Since 2024-03-18, the Document has been moved to doris-website. |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
kaijchen
force-pushed
the
max-flush-thread-limit
branch
from
ff22068
to
902dc00
Compare
kaijchen
changed the title
|
clang-tidy review says "All clean, LGTM! 👍" |
1 similar comment
|
clang-tidy review says "All clean, LGTM! 👍" |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
kaijchen
changed the title
|
run buildall |
1 similar comment
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
2 similar comments
|
clang-tidy review says "All clean, LGTM! 👍" |
|
clang-tidy review says "All clean, LGTM! 👍" |
dataroaring
force-pushed
the
max-flush-thread-limit
branch
from
b4cccc6
to
2028ebf
Compare
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
TPC-H: Total hot run time: 38504 ms |
|
TeamCity be ut coverage result: |
TPC-DS: Total hot run time: 185557 ms |
ClickBench: Total hot run time: 29.8 s |
|
Load test result on machine: 'aliyun_ecs.c7a.8xlarge_32C64G' |
liaoxin01
reviewed
Apr 18, 2024
| @@ -203,15 +203,18 @@ void FlushToken::_flush_memtable(std::unique_ptr<MemTable> memtable_ptr, int32_t | |||
|
|
|||
| void MemTableFlushExecutor::init(int num_disk) { | |||
| num_disk = std::max(1, num_disk); | |||
| size_t min_threads = std::max(1, config::flush_thread_num_per_store); | |||
| size_t max_threads = num_disk * min_threads; | |||
| int num_cpus = static_cast<int>(std::thread::hardware_concurrency()); | |||
There was a problem hiding this comment.
If the value is not well defined or not computable，hardware_concurrency may return 0. We should process this case.
be/src/common/config.cpp
Outdated
| @@ -662,6 +662,12 @@ DEFINE_mInt64(storage_flood_stage_left_capacity_bytes, "1073741824"); // 1GB | |||
| DEFINE_Int32(flush_thread_num_per_store, "6"); | |||
| // number of thread for flushing memtable per store, for high priority load task | |||
| DEFINE_Int32(high_priority_flush_thread_num_per_store, "6"); | |||
| // number of threads = min(flush_thread_num_per_store * num_store, | |||
| // max_flush_thread_num_per_cpu * num_cpu) | |||
| DEFINE_Int32(max_flush_thread_num_per_cpu, "8"); | |||
There was a problem hiding this comment.
The default value of 8 is a bit large, and 2 or 4 may be more suitable.
kaijchen
commented
Apr 19, 2024
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
TeamCity be ut coverage result: |
kaijchen
commented
Apr 25, 2024
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
4 similar comments
|
clang-tidy review says "All clean, LGTM! 👍" |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
TeamCity be ut coverage result: |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
TeamCity be ut coverage result: |
kaijchen
commented
Apr 26, 2024
|
clang-tidy review says "All clean, LGTM! 👍" |
kaijchen
force-pushed
the
max-flush-thread-limit
branch
from
b63c5b7
to
cb7bba6
Compare
|
clang-tidy review says "All clean, LGTM! 👍" |
github-actions
bot
added
the
approved
|
PR approved by at least one committer and no changes requested. |
|
PR approved by anyone and no changes requested. |
|
run buildall |
TPC-H: Total hot run time: 41718 ms |
TPC-DS: Total hot run time: 185330 ms |
|
TeamCity be ut coverage result: |
|
PR approved by anyone and no changes requested. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Proposed changes
Add BE config
max_flush_thread_num_per_cpuandmax_high_priority_flush_thread_num_per_cpu.The default value is
8.The max threads for flush thread pool will be:
This is for preventing the flush thread pool to be too large when the machine has a lot of disks.
Further comments
If this is a relatively large or complex change, kick off the discussion at dev@doris.apache.org by explaining why you chose the solution you did and what alternatives you considered, etc...