feat: parallel digest and compression stage during log import#66
Open
doudou wants to merge 11 commits into
Open
feat: parallel digest and compression stage during log import#66doudou wants to merge 11 commits into
doudou wants to merge 11 commits into
Conversation
…el of normalization This allows to extract more parallelism, and simplifies the overall logic
"-19" is really really a lot slower
Otherwise it gets queued on the main executor. If zstd/sha256sum is a bit slow, it leads to freeing space only a lot later than we can (and needing a lot more space on disk) With this change it is executed right away as soon as both computation futures finish
Does not change performance.
It was not so far, so don't
Empty or truncated files
Given that we use a `while` block, the variable is not redefined, and the block was always using the last set value
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A significant amount of CPU is spent on digest calculation and on compression (profiling on some of our logs showed around 40%). This PR runs them as separate processes to make both parallel.
In addition to all of that, zstd is stupidly well optimized even on the I/O side, which leads to even more savings on huge logs.