diff options
| author | Sergey Senozhatsky <senozhatsky@chromium.org> | 2024-12-18 15:34:24 +0900 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2025-01-25 20:22:20 -0800 |
| commit | 424d0e5828ada98130081b9846f6557158e3f9dd (patch) | |
| tree | 8912ab8b5232cdcad82e114127e42ed219bcef2c /drivers/block | |
| parent | b8d3ff7bb5111c6a88d5672469de445d9b46cf22 (diff) | |
zram: cond_resched() in writeback loop
zram writeback is a costly operation, because every target slot (unless
ZRAM_HUGE) is decompressed before it gets written to a backing device.
The writeback to a backing device uses submit_bio_wait() which may look
like a rescheduling point. However, if the backing device has
BD_HAS_SUBMIT_BIO bit set __submit_bio() calls directly
disk->fops->submit_bio(bio) on the backing device and so when
submit_bio_wait() calls blk_wait_io() the I/O is already done. On such
systems we effective end up in a loop
for_each (target slot) {
decompress(slot)
__submit_bio()
disk->fops->submit_bio(bio)
}
Which on PREEMPT_NONE systems triggers watchdogs (since there are no
explicit rescheduling points). Add cond_resched() to the zram writeback
loop.
Link: https://lkml.kernel.org/r/20241218063513.297475-8-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'drivers/block')
| -rw-r--r-- | drivers/block/zram/zram_drv.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index faa58d85cef8..70ecaee25c20 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -884,6 +884,8 @@ static ssize_t writeback_store(struct device *dev, next: zram_slot_unlock(zram, index); release_pp_slot(zram, pps); + + cond_resched(); } if (blk_idx) |