L2ARC: Relax locking during write #16040

amotin · 2024-03-29T01:16:53Z

Previous code held ARC state sublist lock throughout all L2ARC write process, which included number of allocations and even ZIO issues. Being blocked in any of those places the code could also block ARC eviction, that could cause OOM activation or even deadlock if system is low on memory or one is too fragmented.

Fix it by dropping the lock as soon as we see a block eligible for L2ARC writing and pick it up later using earlier inserted marker. While there, also reduce scope of hash lock, moving ZIO allocation and other operations not requiring header access out of it. All operations requiring header access move under hash lock, since L2_WRITING flag does not prevent header eviction only transition to arc_l2c_only state without L1 header.

To be able to manipulate sublist lock and marker as needed add few more multilist functions and modify one.

Types of changes

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Performance enhancement (non-breaking change which improves efficiency)
Code cleanup (non-breaking change which makes code smaller or more readable)
Breaking change (fix or feature that would cause existing functionality to change)
Library ABI change (libzfs, libzfs_core, libnvpair, libuutil and libzfsbootenv)
Documentation (a change to man pages or other documentation)

Checklist:

My code follows the OpenZFS code style requirements.
I have updated the documentation accordingly.
I have read the contributing document.
I have added tests to cover my changes.
I have run the ZFS Test Suite with this change applied.
All commit messages are properly formatted and contain Signed-off-by.

Previous code held ARC state sublist lock throughout all L2ARC write process, which included number of allocations and even ZIO issues. Being blocked in any of those places the code could also block ARC eviction, that could cause OOM activation or even dead- lock if system is low on memory or one is too fragmented. Fix it by dropping the lock as soon as we see a block eligible for L2ARC writing and pick it up later using earlier inserted marker. While there, also reduce scope of hash lock, moving ZIO allocation and other operations not requiring header access out of it. All operations requiring header access move under hash lock, since L2_WRITING flag does not prevent header eviction only transition to arc_l2c_only state with L1 header. To be able to manipulate sublist lock and marker as needed add few more multilist functions and modify one. Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc.

Previous code held ARC state sublist lock throughout all L2ARC write process, which included number of allocations and even ZIO issues. Being blocked in any of those places the code could also block ARC eviction, that could cause OOM activation or even dead- lock if system is low on memory or one is too fragmented. Fix it by dropping the lock as soon as we see a block eligible for L2ARC writing and pick it up later using earlier inserted marker. While there, also reduce scope of hash lock, moving ZIO allocation and other operations not requiring header access out of it. All operations requiring header access move under hash lock, since L2_WRITING flag does not prevent header eviction only transition to arc_l2c_only state with L1 header. To be able to manipulate sublist lock and marker as needed add few more multilist functions and modify one. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes openzfs#16040

Previous code held ARC state sublist lock throughout all L2ARC write process, which included number of allocations and even ZIO issues. Being blocked in any of those places the code could also block ARC eviction, that could cause OOM activation or even dead- lock if system is low on memory or one is too fragmented. Fix it by dropping the lock as soon as we see a block eligible for L2ARC writing and pick it up later using earlier inserted marker. While there, also reduce scope of hash lock, moving ZIO allocation and other operations not requiring header access out of it. All operations requiring header access move under hash lock, since L2_WRITING flag does not prevent header eviction only transition to arc_l2c_only state with L1 header. To be able to manipulate sublist lock and marker as needed add few more multilist functions and modify one. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes #16040

Previous code held ARC state sublist lock throughout all L2ARC write process, which included number of allocations and even ZIO issues. Being blocked in any of those places the code could also block ARC eviction, that could cause OOM activation or even dead- lock if system is low on memory or one is too fragmented. Fix it by dropping the lock as soon as we see a block eligible for L2ARC writing and pick it up later using earlier inserted marker. While there, also reduce scope of hash lock, moving ZIO allocation and other operations not requiring header access out of it. All operations requiring header access move under hash lock, since L2_WRITING flag does not prevent header eviction only transition to arc_l2c_only state with L1 header. To be able to manipulate sublist lock and marker as needed add few more multilist functions and modify one. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes openzfs#16040

..., before we make the header or the log block visible to others. It should fix assertion on allocated space going negative if the header is freed once the lock is dropped, while the write is still going. Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Fixes openzfs#16040

..., before we make the header or the log block visible to others. It should fix assertion on allocated space going negative if the header is freed once the lock is dropped, while the write is still going. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Rob Norris <robn@despairlabs.com> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes #16040 Closes #16743

..., before we make the header or the log block visible to others. It should fix assertion on allocated space going negative if the header is freed once the lock is dropped, while the write is still going. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Rob Norris <robn@despairlabs.com> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes openzfs#16040 Closes openzfs#16743

amotin added the Status: Code Review Needed Ready for review and testing label Mar 29, 2024

behlendorf approved these changes Apr 8, 2024

View reviewed changes

behlendorf added Status: Accepted Ready to integrate (reviewed, tested) and removed Status: Code Review Needed Ready for review and testing labels Apr 8, 2024

behlendorf merged commit 997f85b into openzfs:master Apr 9, 2024
24 of 26 checks passed

amotin deleted the l2arc_lock branch April 9, 2024 23:27

amotin mentioned this pull request Nov 11, 2024

dsl_dataset: put IO-inducing frees on the pool deadlist #16722

Merged

13 tasks

amotin mentioned this pull request Nov 11, 2024

L2ARC: Move different stats updates earlier #16743

Merged

13 tasks

behlendorf mentioned this pull request Nov 12, 2024

CI tests for combined #16722 and #16040 #16744

Closed

7 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

L2ARC: Relax locking during write #16040

L2ARC: Relax locking during write #16040

amotin commented Mar 29, 2024 •

edited

Loading

L2ARC: Relax locking during write #16040

L2ARC: Relax locking during write #16040

Conversation

amotin commented Mar 29, 2024 • edited Loading

Types of changes

Checklist:

amotin commented Mar 29, 2024 •

edited

Loading