Concurrent insertable vector #188
Merged
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
Codecov Report
❗ Your organization needs to install the Codecov GitHub app to enable full functionality. Additional details and impacted files@@ Coverage Diff @@
## master #188 +/- ##
==========================================
- Coverage 64.14% 63.41% -0.73%
==========================================
Files 70 71 +1
Lines 4287 4319 +32
Branches 538 543 +5
==========================================
- Hits 2750 2739 -11
- Misses 1301 1336 +35
- Partials 236 244 +8
|
szmyd
reviewed
Oct 27, 2023
sanebay
reviewed
Oct 27, 2023
hkadayam
force-pushed
the
concurrent_vector
branch
from
815f022 to
9f43022
Compare
szmyd
reviewed
Oct 30, 2023
szmyd
approved these changes
Oct 30, 2023
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Outdated suggestions cannot be applied.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.
This data structure provides a vector where concurrent threads can safely emplace or push back the data into. However, it does not guarantee any access or iterations happen during the insertion. It is the responsibility of the user to synchronize this behavior. This data structure is useful when the user wants to insert data into a vector concurrently in a fast manner and then iterate over the data later. If the user wants a vector implementation which reads concurrently with writer, they can use sisl::ThreadVector. This data structure is provided as a replacement for simplistic cases where insertion and iteration never happen concurrently. As a result it provides better performance than even sisl::ThreadVector and better debuggability.
Benchmark shows atleast 10x better performance on more than 4 threads concurrently inserting with mutex.
Justification for this data structure: As mentioned sisl::ThreadVector uses RCU to protect concurrent read and write. However if the caller already guarantees that with RCU it is faster and less issues to chase down (and more simpler). That is the case for Homestore writeback cache dirty buffer accumulation.