DAOS-18524 object: fix EC checksum in rebuild, aggregation#17908
Merged
gnailzenh merged 1 commit intorelease/2.8from Apr 8, 2026
Merged
DAOS-18524 object: fix EC checksum in rebuild, aggregation#17908gnailzenh merged 1 commit intorelease/2.8from
gnailzenh merged 1 commit intorelease/2.8from
Conversation
Fix two bugs causing -DER_CSUM failures with non-power-of-2 checksum chunk sizes on EC objects: 1. In __migrate_fetch_update_bulk(), checksums were computed while IOD recxs were still in DAOS-space (needed for the preceding fetch), but stored at VOS-space offsets. When cksum_size does not evenly divide ec_cell_sz, chunk boundaries differ between coordinate spaces, producing mismatched checksums. Move mrone_recx_daos2_vos() before migrate_csum_calc() so checksums align with VOS storage offsets. 2. In vos_csum_recalc.c, calc_csum_params() and csum_agg_verify() used unsigned int for extent offsets, truncating the PARITY_INDICATOR bit (0x8000000000000000) on parity extents. With non-power-of-2 chunk sizes, this truncation shifts chunk boundaries, causing aggregation checksum verification to always fail. Widen to uint64_t. Allow-unstable-test: true Features: checksum rebuild ec aggregation Signed-off-by: Kenneth Cain <kenneth.cain@hpe.com>
|
Ticket title is 'Observe DER_CSUM -2021 errors and "Data corruption found for recx" engine logging during reintegration and client data verify read-back' |
github-actions
Bot
added
the
priority
kccain
added
the
clean-cherry-pick
wangshilong
approved these changes
Apr 7, 2026
gnailzenh
approved these changes
Apr 8, 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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 two bugs causing -DER_CSUM failures with non-power-of-2 checksum chunk sizes on EC objects:
In __migrate_fetch_update_bulk(), checksums were computed while IOD recxs were still in DAOS-space (needed for the preceding fetch), but stored at VOS-space offsets. When cksum_size does not evenly divide ec_cell_sz, chunk boundaries differ between coordinate spaces, producing mismatched checksums. Move mrone_recx_daos2_vos() before migrate_csum_calc() so checksums align with VOS storage offsets.
In vos_csum_recalc.c, calc_csum_params() and csum_agg_verify() used unsigned int for extent offsets, truncating the PARITY_INDICATOR bit (0x8000000000000000) on parity extents. With non-power-of-2 chunk sizes, this truncation shifts chunk boundaries, causing aggregation checksum verification to always fail. Widen to uint64_t.
Allow-unstable-test: true
Features: checksum rebuild ec aggregation
Steps for the author:
After all prior steps are complete: