Before this patch, if cache device missing, cached_dev_submit_bio return io err
to fs during cache detach, randomly lead to xfs do force shutdown.
This patch delay the cache io submit in cached_dev_submit_bio
and wait for cache set detach finish.
So if the cache device become missing, bcache detach cache set automatically,
and the io will sumbit normally.
Feb 2 20:59:23 kernel: bcache: bch_count_io_errors() nvme0n1p56: IO error on writing btree.
Feb 2 20:59:23 kernel: bcache: bch_count_io_errors() nvme0n1p57: IO error on writing btree.
Feb 2 20:59:23 kernel: bcache: bch_count_io_errors() nvme0n1p56: IO error on writing btree.
Feb 2 20:59:23 kernel: bcache: bch_btree_insert() error -5
Feb 2 20:59:23 kernel: XFS (bcache43): metadata I/O error in "xfs_buf_iodone_callback_error" at daddr 0x80034658 len 32 error 12
Feb 2 20:59:23 kernel: bcache: bch_btree_insert() error -5
Feb 2 20:59:23 kernel: bcache: bch_btree_insert() error -5
Feb 2 20:59:23 kernel: bcache: bch_btree_insert() error -5
Feb 2 20:59:23 kernel: bcache: bch_btree_insert() error -5
Feb 2 20:59:23 kernel: bcache: bch_cache_set_error() bcache: error on 004f8aa7-561a-4ba7-bf7b-292e461d3f18:
Feb 2 20:59:23 kernel: journal io error
Feb 2 20:59:23 kernel: bcache: bch_cache_set_error() , disabling caching
Feb 2 20:59:23 kernel: bcache: bch_btree_insert() error -5
Feb 2 20:59:23 kernel: bcache: conditional_stop_bcache_device() stop_when_cache_set_failed of bcache43 is "auto" and cache is clean, keep it alive.
Feb 2 20:59:23 kernel: XFS (bcache43): metadata I/O error in "xlog_iodone" at daddr 0x400123e60 len 64 error 12
Feb 2 20:59:23 kernel: XFS (bcache43): xfs_do_force_shutdown(0x2) called from line 1298 of file fs/xfs/xfs_log.c. Return address = 00000000c1c8077f
Feb 2 20:59:23 kernel: XFS (bcache43): Log I/O Error Detected. Shutting down filesystem
Feb 2 20:59:23 kernel: XFS (bcache43): Please unmount the filesystem and rectify the problem(s)
Signed-off-by: Zhen Zhang <zhangzhen.email@xxxxxxxxx>
---
drivers/md/bcache/bcache.h | 5 -----
drivers/md/bcache/request.c | 8 ++++----
drivers/md/bcache/super.c | 3 ++-
3 files changed, 6 insertions(+), 10 deletions(-)
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 9ed9c955add7..e5227dd08e3a 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -928,11 +928,6 @@ static inline void closure_bio_submit(struct cache_set *c,
struct closure *cl)
{
closure_get(cl);
- if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags))) {
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
- return;
- }
submit_bio_noacct(bio);
}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index d15aae6c51c1..36f0ee95b51f 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -13,6 +13,7 @@
#include "request.h"
#include "writeback.h"
+#include <linux/delay.h>
#include <linux/module.h>
#include <linux/hash.h>
#include <linux/random.h>
@@ -1172,11 +1173,10 @@ void cached_dev_submit_bio(struct bio *bio)
unsigned long start_time;
int rw = bio_data_dir(bio);
- if (unlikely((d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags)) ||
+ while (unlikely((d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags)) ||
dc->io_disable)) {
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
- return;
+ /* wait for detach finish and d->c == NULL. */
+ msleep(2);
}
if (likely(d->c)) {
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 140f35dc0c45..8d9a5e937bc8 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -661,7 +661,8 @@ int bch_prio_write(struct cache *ca, bool wait)
p->csum = bch_crc64(&p->magic, meta_bucket_bytes(&ca->sb) - 8);
bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait);
- BUG_ON(bucket == -1);
+ if (bucket == -1)
+ return -1;
mutex_unlock(&ca->set->bucket_lock);
prio_io(ca, bucket, REQ_OP_WRITE, 0);
--
2.25.1
