DAOS-18541 rebuild: accumulate more OIDs per migrate RPC to reduce RPC count#17704
Open
wangshilong wants to merge 3 commits intomasterfrom
Open
DAOS-18541 rebuild: accumulate more OIDs per migrate RPC to reduce RPC count#17704wangshilong wants to merge 3 commits intomasterfrom
wangshilong wants to merge 3 commits intomasterfrom
Conversation
Fix yield-count accounting in the scanner: rebuild_object() is a pure in-memory btree insert and does not need to contribute yield pressure. A send-side batching policy is also introduced: the send ULT defers flushing until at least REBUILD_SEND_BATCH_MIN OIDs are queued or REBUILD_SEND_BATCH_TIMEOUT_SEC seconds have elapsed, preventing a flood of small migrate RPCs when the scanner runs faster than the sender — particularly under reintegration workloads. Signed-off-by: Wang Shilong <shilong.wang@hpe.com>
|
Ticket title is 'Rebuild stuck on Bear cluster' |
wangshilong
changed the title
wangshilong
changed the title
wangshilong
changed the title
gnailzenh
reviewed
Mar 15, 2026
Signed-off-by: Wang Shilong <shilong.wang@hpe.com>
liuxuezhao
previously approved these changes
Mar 16, 2026
Collaborator
|
Test stage Functional on EL 9 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-17704/2/execution/node/1096/log |
Signed-off-by: Wang Shilong <shilong.wang@hpe.com>
wangshilong
force-pushed
the
shilongw/DAOS-18541
branch
from
5ec1fbe to
f4154c1
Compare
liuxuezhao
approved these changes
Mar 16, 2026
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix yield-count accounting in the scanner, A send-side batching policy is also introduced: the send ULT defers flushing until at least REBUILD_SEND_BATCH_MIN OIDs are queued or REBUILD_SEND_BATCH_TIMEOUT_SEC seconds have elapsed.
Without batching, a fast scanner floods the destination rank with many small RPCs, exhausting IB receive buffers and triggering timeouts. This is especially severe during reintegration, where all OIDs are concentrated on a single target rank.
Steps for the author:
After all prior steps are complete: