misc(memory) Allow exact buffer allocation #12594
Open
+62
−5
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
facebook-github-bot
added
the
CLA Signed
✅ Deploy Preview for meta-velox canceled.
|
|
This pull request was exported from Phabricator. Differential Revision: D70521769 |
|
This pull request was exported from Phabricator. Differential Revision: D70521769 |
joeg
changed the title
joeg
changed the title
joeg
added a commit
to joeg/velox
that referenced
this pull request
Mar 11, 2025
Summary: By default buffers are allocated up to 50% headroom : https://www.internalfb.com/code/fbsource/[cbb63d0a88c6]/fbcode/velox/common/memory/MemoryPool.cpp?lines=397 In the simple tpch demo this reduced overall data sizes by about ~6% - this scales to encoded vectors at the moment (dictionaries) and there is likely an equally large win for flat vectors given they are copied (vector copy also uses this same default buffer allocation logic). For scenarios that need to maintain long lived data this is wasteful, Enabling an optional exact allocation (size + padding) reduces this waste. Reviewed By: xiaoxmeng Differential Revision: D70521769
|
This pull request was exported from Phabricator. Differential Revision: D70521769 |
Summary: By default buffers are allocated up to 50% headroom : https://www.internalfb.com/code/fbsource/[cbb63d0a88c6]/fbcode/velox/common/memory/MemoryPool.cpp?lines=397 In the simple tpch demo this reduced overall data sizes by about ~6% - this scales to encoded vectors at the moment (dictionaries) and there is likely an equally large win for flat vectors given they are copied (vector copy also uses this same default buffer allocation logic). For scenarios that need to maintain long lived data this is wasteful, Enabling an optional exact allocation (size + padding) reduces this waste. Reviewed By: xiaoxmeng Differential Revision: D70521769
|
This pull request was exported from Phabricator. Differential Revision: D70521769 |
xiaoxmeng
approved these changes
Mar 12, 2025
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.
Summary:
By default buffers are allocated up to 50% headroom :
velox/velox/common/memory/MemoryPool.cpp
Line 397 in 89afec8
In the simple tpch demo this reduced overall data sizes by about ~6% - this scales to encoded vectors at the moment (dictionaries) and there is likely an equally large win for flat vectors given they are copied (vector copy also uses this same default buffer allocation logic).
For scenarios that need to maintain long lived data this is wasteful, Enabling an optional exact allocation (size + padding) reduces this waste.
Reviewed By: xiaoxmeng
Differential Revision: D70521769