[buildbot tests] [PR5062, PR5404, PR5449, PR5285, zvol: reduce linear list search] #5453
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
Use kernel ida to generate minor number, and use hash table to find zvol with name. Signed-off-by: Chunwei Chen <[email protected]>
After resume the suspend godfather I/O , if some child zio's io_reexecute flag assigned ZIO_REEXECUTE_NOW bit, but others assigned ZIO_REEXECUTE_SUSPEND bit, so the godfather I/O's io_reexecute flag will inherit both ZIO_REEXECUTE_NOW and ZIO_REEXECUTE_SUSPEND bit. However these child I/Os which io_reexecute flag assigned ZIO_REEXECUTE_SUSPEND will remove from current godfater I/O's child list and add to new spa_suspend_zio_root's child list, but others zio which io_reexecute flag assigned ZIO_REEXECUTE_NOW only notify godfater zio to execute and assigned self io_reexecute flag value to godfater zio. At last, the godfater I/O execute above code in zio_done function, and then godfather I/O execute done and destroy, and this lead to these child zio which io_reexecute flag assigned ZIO_REEXECUTE_NOW will lose monitor zio and have no chance to reexecute again. So fix zio_done() should only be clearing the ZIO_REEXECUTE_SUSPEND bit in this case.
This change introduces a new weighting algorithm to improve metaslab selection. The new weighting algorithm relies on the SPACEMAP_HISTOGRAM feature. As a result, the metaslab weight now encodes the type of weighting algorithm used (size-based vs segment-based). Authored by: George Wilson <[email protected]> Reviewed by: Alex Reece <[email protected]> Reviewed by: Chris Siden <[email protected]> Reviewed by: Dan Kimmel <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Reviewed by: Paul Dagnelie <[email protected]> Reviewed by: Pavel Zakharov [email protected] Reviewed by: Prakash Surya <[email protected]> Reviewed by: Don Brady <[email protected]> Approved by: Ported-by: Don Brady <[email protected]> OpenZFS-issue: https://www.illumos.org/issues/7303 OpenZFS-commit: openzfs/openzfs@8710fccea7 Porting Notes: The metaslab allocation tracing code is conditionally removed on linux (dependent on mdb debugger).
…ierarchy With OpenZFS 6111 we lost the ability to create replication send streams when we're missing even a single snapshot in the whole hierarchy: this commit restore this functionality. Add also relative zfs_send_008_pos.ksh script to ZFS test suite. Signed-off-by: loli10K <[email protected]>
|
@kernelOfTruth, thanks for your PR! By analyzing the history of the files in this pull request, we identified @grwilson, @behlendorf and @don-brady to be potential reviewers. |
This reverts commit 4d1ae43. [erroneously used the wrong commit]
Use it for spa_deadman, zpl_posix_acl_free, snapentry_expire. This free system_taskq from the above long delay tasks, and allow us to do taskq_wait_outstanding on system_taskq without being blocked forever, making system_taskq more generic and useful. Signed-off-by: Chunwei Chen <[email protected]>
Use kernel ida to generate minor number, and use hash table to find zvol with name. Signed-off-by: Chunwei Chen <[email protected]>
Do parallel prefetch all zvol dnodes before actually creating each individual. This will greatly reduce the import time when having a lot of zvols and disk is slow. Signed-off-by: Chunwei Chen <[email protected]>
On some kernel version, blk_cleanup_queue and put_disk will wait for more then 10ms. So a pool with a lot of zvols will easily wait for more then 1 min if we do zvol_free sequentially. Signed-off-by: Chunwei Chen <[email protected]> Requires-spl: refs/pull/588/head
|
pushing additionally the changes from #5433 , want to make sure this works fine before I test it with an rt-kernel [https://github.com/openzfs/spl/pull/589] ... |
The introduction of parallel zvol prefetch causes deadlock when using vdev_file. spa_async->(spa_namespace_lock)->txg_wait_synced->(wait for txg_sync) txg_sync->zio_wait->(wait for vdev_file_io_fsync on system_taskq) zvol_prefetch_minors_impl (on system_taskq)->spa_open_common->(wait for spa_namespace_lock) We fix this by using dedicated taskq for vdev_file. This same change was originally made in commit bc25c93 but reverted in commit aa9af22 when dynamic taskqs were added. Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Chunwei Chen <[email protected]> Closes openzfs#5506 Closes openzfs#5495
|
adding the fix for deadlock [haven't run into it yet], preparing usage & testing of 4.9-rt kernel |
|
Closing to cut down on the number of open PRs. The test results will remain available as always. |
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.
The following pull-requests are tested on top of latest master which includes ABD changes,
pushing this through a battery of tests to make sure it's stable for my "primetime" (bleeding edge production) testing
#5062 Godfather's child I/Os that may can't done and lost chance to reexecute again
#5404 OpenZFS 7303 - dynamic metaslab selection
#5449 OpenZFS 6569 - large file delete can starve out write ops
#5285 Allow zfs to send replication streams when missing snapshots in the hierarchy
tuxoko/zfs@0a7c4b7 zvol: reduce linear list search
Since there's an issue with the LRU for ABD patch and I'll most likely update my kernel + zfs tomorrow,
opening this branch/PR for a test run without it
[closing https://github.com//pull/5451 for now]