On Wed, Sep 20, 2017 at 06:24:33AM +0800, Coly Li wrote: > When bcache does read I/Os, for example in writeback or writethrough mode, > if a read request on cache device is failed, bcache will try to recovery > the request by reading from cached device. If the data on cached device is > not synced with cache device, then requester will get a stale data. > > For critical storage system like database, providing stale data from > recovery may result an application level data corruption, which is > unacceptible. But for some other situation like multi-media stream cache, > continuous service may be more important and it is acceptible to fetch > a chunk of stale data. > > This patch tries to solve the above conflict by adding a sysfs option > /sys/block/bcache<idx>/bcache/allow_stale_data_on_failure > which is defaultly cleared (to 0) as disabled. Now people can make choices > for different situations.
IMO this is just a bug, I'd rather not have an option to keep the buggy behaviour. How about this patch: commit 2746f9c1f962288d8c5d7dabe698bf7b3fddd405 Author: Kent Overstreet <[email protected]> Date: Wed Sep 20 18:06:37 2017 +0200 bcache: Don't recover from IO errors when reading dirty data Signed-off-by: Kent Overstreet <[email protected]> diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 382397772a..c2d57ef953 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -532,8 +532,10 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k) PTR_BUCKET(b->c, k, ptr)->prio = INITIAL_PRIO; - if (KEY_DIRTY(k)) + if (KEY_DIRTY(k)) { s->read_dirty_data = true; + s->recoverable = false; + } n = bio_next_split(bio, min_t(uint64_t, INT_MAX, KEY_OFFSET(k) - bio->bi_iter.bi_sector),
