[Hammer] Make failed leaves be stickier #650
Merged
Conversation
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
Previously if a leaf failed on a write, we would discard it and try again with another leaf. This was useful in the event that we generated an invalid leaf, because it would be temporary and the worker could continue. But in reality, we don't generate invalid leaves. So what happened is that in the event of the log temporarily pushing back to the user, leaves would be dropped. This meant that the tree size could be much smaller than the seed index that any indices that leaves had been generated from. All of this meant that on restarting the hammer against a populated log, it could spend a long time resubmitting duplicates because of this index mismatch. This is still possible, but the drift is much smaller now (at most N indices are leaked per hammer run, where N is the number of write workers).
roger2hk
approved these changes
May 19, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Previously if a leaf failed on a write, we would discard it and try again with another leaf. This was useful in the event that we generated an invalid leaf, because it would be temporary and the worker could continue. But in reality, we don't generate invalid leaves. So what happened is that in the event of the log temporarily pushing back to the user, leaves would be dropped. This meant that the tree size could be much smaller than the seed index that any indices that leaves had been generated from. All of this meant that on restarting the hammer against a populated log, it could spend a long time resubmitting duplicates because of this index mismatch. This is still possible, but the drift is much smaller now (at most N indices are leaked per hammer run, where N is the number of write workers).