diff options
| author | Jan Kara <jack@suse.cz> | 2025-04-09 17:12:59 +0200 |
|---|---|---|
| committer | Christian Brauner <brauner@kernel.org> | 2025-09-19 13:11:00 +0200 |
| commit | e1b849cfa6b61f1c866a908c9e8dd9b5aaab820b (patch) | |
| tree | c4ec0f4d3e0ecfc88637d1ddb9fd5d4021890735 /include/linux/writeback.h | |
| parent | 8f5ae30d69d7543eee0d70083daf4de8fe15d585 (diff) | |
| download | lwn-e1b849cfa6b61f1c866a908c9e8dd9b5aaab820b.tar.gz lwn-e1b849cfa6b61f1c866a908c9e8dd9b5aaab820b.zip | |
writeback: Avoid contention on wb->list_lock when switching inodes
There can be multiple inode switch works that are trying to switch
inodes to / from the same wb. This can happen in particular if some
cgroup exits which owns many (thousands) inodes and we need to switch
them all. In this case several inode_switch_wbs_work_fn() instances will
be just spinning on the same wb->list_lock while only one of them makes
forward progress. This wastes CPU cycles and quickly leads to softlockup
reports and unusable system.
Instead of running several inode_switch_wbs_work_fn() instances in
parallel switching to the same wb and contending on wb->list_lock, run
just one work item per wb and manage a queue of isw items switching to
this wb.
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jan Kara <jack@suse.cz>
Diffstat (limited to 'include/linux/writeback.h')
| -rw-r--r-- | include/linux/writeback.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a2848d731a46..15a4bc4ab819 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -265,6 +265,8 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } +void inode_switch_wbs_work_fn(struct work_struct *work); + #else /* CONFIG_CGROUP_WRITEBACK */ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) |