From: Coly Li <colyli@suse.de>
To: linux-bcache@vger.kernel.org
Cc: linux-block@vger.kernel.org, Coly Li <colyli@suse.de>,
Junhui Tang <tang.junhui@zte.com.cn>,
Michael Lyle <mlyle@lyle.org>
Subject: [PATCH v2 10/12] bcache: add backing_request_endio() for bi_end_io of attached backing device I/O
Date: Sun, 14 Jan 2018 01:10:48 +0800 [thread overview]
Message-ID: <20180113171050.22467-11-colyli@suse.de> (raw)
In-Reply-To: <20180113171050.22467-1-colyli@suse.de>
In order to catch I/O error of backing device, a separate bi_end_io
call back is required. Then a per backing device counter can record I/O
errors number and retire the backing device if the counter reaches a
per backing device I/O error limit.
This patch adds backing_request_endio() to bcache backing device I/O code
path, this is a preparation for further complicated backing device failure
handling. So far there is no real code logic change, I make this change a
separate patch to make sure it is stable and reliable for further work.
Changelog:
v2: indeed this is new added in this patch set.
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Cc: Michael Lyle <mlyle@lyle.org>
---
drivers/md/bcache/request.c | 95 +++++++++++++++++++++++++++++++++++--------
drivers/md/bcache/super.c | 1 +
drivers/md/bcache/writeback.c | 1 +
3 files changed, 81 insertions(+), 16 deletions(-)
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index e09c5ae745be..ad4cf71f7eab 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -139,6 +139,7 @@ static void bch_data_invalidate(struct closure *cl)
}
op->insert_data_done = true;
+ /* get in bch_data_insert() */
bio_put(bio);
out:
continue_at(cl, bch_data_insert_keys, op->wq);
@@ -630,6 +631,38 @@ static void request_endio(struct bio *bio)
closure_put(cl);
}
+static void backing_request_endio(struct bio *bio)
+{
+ struct closure *cl = bio->bi_private;
+
+ if (bio->bi_status) {
+ struct search *s = container_of(cl, struct search, cl);
+ /*
+ * If a bio has REQ_PREFLUSH for writeback mode, it is
+ * speically assembled in cached_dev_write() for a non-zero
+ * write request which has REQ_PREFLUSH. we don't set
+ * s->iop.status by this failure, the status will be decided
+ * by result of bch_data_insert() operation.
+ */
+ if (unlikely(s->iop.writeback &&
+ bio->bi_opf & REQ_PREFLUSH)) {
+ char buf[BDEVNAME_SIZE];
+
+ bio_devname(bio, buf);
+ pr_err("Can't flush %s: returned bi_status %i",
+ buf, bio->bi_status);
+ } else {
+ /* set to orig_bio->bi_status in bio_complete() */
+ s->iop.status = bio->bi_status;
+ }
+ s->recoverable = false;
+ /* should count I/O error for backing device here */
+ }
+
+ bio_put(bio);
+ closure_put(cl);
+}
+
static void bio_complete(struct search *s)
{
if (s->orig_bio) {
@@ -644,13 +677,21 @@ static void bio_complete(struct search *s)
}
}
-static void do_bio_hook(struct search *s, struct bio *orig_bio)
+static void do_bio_hook(struct search *s,
+ struct bio *orig_bio,
+ bio_end_io_t *end_io_fn)
{
struct bio *bio = &s->bio.bio;
bio_init(bio, NULL, 0);
__bio_clone_fast(bio, orig_bio);
- bio->bi_end_io = request_endio;
+ /*
+ * bi_end_io can be set separately somewhere else, e.g. the
+ * variants in,
+ * - cache_bio->bi_end_io from cached_dev_cache_miss()
+ * - n->bi_end_io from cache_lookup_fn()
+ */
+ bio->bi_end_io = end_io_fn;
bio->bi_private = &s->cl;
bio_cnt_set(bio, 3);
@@ -676,7 +717,7 @@ static inline struct search *search_alloc(struct bio *bio,
s = mempool_alloc(d->c->search, GFP_NOIO);
closure_init(&s->cl, NULL);
- do_bio_hook(s, bio);
+ do_bio_hook(s, bio, request_endio);
s->orig_bio = bio;
s->cache_miss = NULL;
@@ -743,10 +784,11 @@ static void cached_dev_read_error(struct closure *cl)
trace_bcache_read_retry(s->orig_bio);
s->iop.status = 0;
- do_bio_hook(s, s->orig_bio);
+ do_bio_hook(s, s->orig_bio, backing_request_endio);
/* XXX: invalidate cache */
+ /* I/O request sent to backing device */
closure_bio_submit(s->iop.c, bio, cl);
}
@@ -859,7 +901,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
bio_copy_dev(cache_bio, miss);
cache_bio->bi_iter.bi_size = s->insert_bio_sectors << 9;
- cache_bio->bi_end_io = request_endio;
+ cache_bio->bi_end_io = backing_request_endio;
cache_bio->bi_private = &s->cl;
bch_bio_map(cache_bio, NULL);
@@ -872,14 +914,16 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
s->cache_miss = miss;
s->iop.bio = cache_bio;
bio_get(cache_bio);
+ /* I/O request sent to backing device */
closure_bio_submit(s->iop.c, cache_bio, &s->cl);
return ret;
out_put:
bio_put(cache_bio);
out_submit:
- miss->bi_end_io = request_endio;
+ miss->bi_end_io = backing_request_endio;
miss->bi_private = &s->cl;
+ /* I/O request sent to backing device */
closure_bio_submit(s->iop.c, miss, &s->cl);
return ret;
}
@@ -943,31 +987,48 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
s->iop.bio = s->orig_bio;
bio_get(s->iop.bio);
- if ((bio_op(bio) != REQ_OP_DISCARD) ||
- blk_queue_discard(bdev_get_queue(dc->bdev)))
- closure_bio_submit(s->iop.c, bio, cl);
+ if (bio_op(bio) == REQ_OP_DISCARD &&
+ !blk_queue_discard(bdev_get_queue(dc->bdev)))
+ goto insert_data;
+
+ /* I/O request sent to backing device */
+ bio->bi_end_io = backing_request_endio;
+ closure_bio_submit(s->iop.c, bio, cl);
+
} else if (s->iop.writeback) {
bch_writeback_add(dc);
s->iop.bio = bio;
if (bio->bi_opf & REQ_PREFLUSH) {
- /* Also need to send a flush to the backing device */
- struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0,
- dc->disk.bio_split);
-
+ /*
+ * Also need to send a flush to the backing
+ * device, if failed on backing device.
+ */
+ struct bio *flush;
+
+ flush = bio_alloc_bioset(GFP_NOIO, 0,
+ dc->disk.bio_split);
+ if (!flush) {
+ s->iop.status = BLK_STS_RESOURCE;
+ goto insert_data;
+ }
bio_copy_dev(flush, bio);
- flush->bi_end_io = request_endio;
+ flush->bi_end_io = backing_request_endio;
flush->bi_private = cl;
flush->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-
+ /* I/O request sent to backing device */
closure_bio_submit(s->iop.c, flush, cl);
}
+ bch_writeback_add(dc);
+
} else {
s->iop.bio = bio_clone_fast(bio, GFP_NOIO, dc->disk.bio_split);
-
+ /* I/O request sent to backing device */
+ bio->bi_end_io = backing_request_endio;
closure_bio_submit(s->iop.c, bio, cl);
}
+insert_data:
closure_call(&s->iop.cl, bch_data_insert, NULL, cl);
continue_at(cl, cached_dev_write_complete, NULL);
}
@@ -981,6 +1042,7 @@ static void cached_dev_nodata(struct closure *cl)
bch_journal_meta(s->iop.c, cl);
/* If it's a flush, we send the flush to the backing device too */
+ bio->bi_end_io = backing_request_endio;
closure_bio_submit(s->iop.c, bio, cl);
continue_at(cl, cached_dev_bio_complete, NULL);
@@ -1078,6 +1140,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
cached_dev_read(dc, s);
}
} else
+ /* I/O request sent to backing device */
detached_dev_do_request(d, bio);
return BLK_QC_T_NONE;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 97e3bb8e1aee..08a0b541a4da 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -265,6 +265,7 @@ void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent)
bio->bi_private = dc;
closure_get(cl);
+ /* I/O request sent to backing device */
__write_super(&dc->sb, bio);
closure_return_with_destructor(cl, bch_write_bdev_super_unlock);
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index e97e2afead3e..878103b9f2ec 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -289,6 +289,7 @@ static void write_dirty(struct closure *cl)
bio_set_dev(&io->bio, io->dc->bdev);
io->bio.bi_end_io = dirty_endio;
+ /* I/O request sent to backing device */
closure_bio_submit(io->dc->disk.c, &io->bio, cl);
}
--
2.15.1
next prev parent reply other threads:[~2018-01-13 17:13 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-13 17:10 [PATCH v2 00/12] bcache: device failure handling improvement Coly Li
2018-01-13 17:10 ` [PATCH v2 01/12] bcache: set writeback_rate_update_seconds in range [1, 60] seconds Coly Li
2018-01-13 17:10 ` [PATCH v2 02/12] bcache: properly set task state in bch_writeback_thread() Coly Li
2018-01-13 17:10 ` [PATCH v2 03/12] bcache: set task properly in allocator_wait() Coly Li
2018-01-13 17:10 ` [PATCH v2 04/12] bcache: fix cached_dev->count usage for bch_cache_set_error() Coly Li
2018-01-13 17:10 ` [PATCH v2 05/12] bcache: stop dc->writeback_rate_update properly Coly Li
2018-01-13 17:10 ` [PATCH v2 06/12] bcache: set error_limit correctly Coly Li
2018-01-13 17:10 ` [PATCH v2 07/12] bcache: add CACHE_SET_IO_DISABLE to struct cache_set flags Coly Li
2018-01-13 17:10 ` [PATCH v2 08/12] bcache: stop all attached bcache devices for a retired cache set Coly Li
2018-01-13 17:10 ` [PATCH v2 09/12] bcache: fix inaccurate io state for detached bcache devices Coly Li
2018-01-13 17:10 ` Coly Li [this message]
2018-01-13 17:10 ` [PATCH v2 11/12] bcache: add io_disable to struct cached_dev Coly Li
2018-01-13 17:10 ` [PATCH v2 12/12] bcache: stop bcache device when backing device is offline Coly Li
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180113171050.22467-11-colyli@suse.de \
--to=colyli@suse.de \
--cc=linux-bcache@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=mlyle@lyle.org \
--cc=tang.junhui@zte.com.cn \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.