block, dm: don't copy bios for request clones
Currently dm-multipath has to clone the bios for every request sent
to the lower devices, which wastes cpu cycles and ties down memory.
This patch instead adds a new REQ_CLONE flag that instructs req_bio_endio
to not complete bios attached to a request, which we set on clone
requests similar to bios in a flush sequence. With this change I/O
errors on a path failure only get propagated to dm-multipath, which
can then either resubmit the I/O or complete the bios on the original
request.
I've done some basic testing of this on a Linux target with ALUA support,
and it survives path failures during I/O nicely.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-core.c b/block/blk-core.c
index de474b5d..aa819a5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -117,7 +117,7 @@
static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, int error)
{
- if (error)
+ if (error && !(rq->cmd_flags & REQ_CLONE))
clear_bit(BIO_UPTODATE, &bio->bi_flags);
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
@@ -128,7 +128,8 @@
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
- if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+ if (bio->bi_iter.bi_size == 0 &&
+ !(rq->cmd_flags & (REQ_FLUSH_SEQ|REQ_CLONE)))
bio_endio(bio, error);
}
@@ -2909,95 +2910,22 @@
}
EXPORT_SYMBOL_GPL(blk_lld_busy);
-/**
- * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
- * @rq: the clone request to be cleaned up
- *
- * Description:
- * Free all bios in @rq for a cloned request.
- */
-void blk_rq_unprep_clone(struct request *rq)
-{
- struct bio *bio;
-
- while ((bio = rq->bio) != NULL) {
- rq->bio = bio->bi_next;
-
- bio_put(bio);
- }
-}
-EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
-
-/*
- * Copy attributes of the original request to the clone request.
- * The actual data parts (e.g. ->cmd, ->sense) are not copied.
- */
-static void __blk_rq_prep_clone(struct request *dst, struct request *src)
+void blk_rq_prep_clone(struct request *dst, struct request *src)
{
dst->cpu = src->cpu;
- dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+ dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK);
+ dst->cmd_flags |= REQ_NOMERGE | REQ_CLONE;
dst->cmd_type = src->cmd_type;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
dst->nr_phys_segments = src->nr_phys_segments;
dst->ioprio = src->ioprio;
dst->extra_len = src->extra_len;
-}
-
-/**
- * blk_rq_prep_clone - Helper function to setup clone request
- * @rq: the request to be setup
- * @rq_src: original request to be cloned
- * @bs: bio_set that bios for clone are allocated from
- * @gfp_mask: memory allocation mask for bio
- * @bio_ctr: setup function to be called for each clone bio.
- * Returns %0 for success, non %0 for failure.
- * @data: private data to be passed to @bio_ctr
- *
- * Description:
- * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- * The actual data parts of @rq_src (e.g. ->cmd, ->sense)
- * are not copied, and copying such parts is the caller's responsibility.
- * Also, pages which the original bios are pointing to are not copied
- * and the cloned bios just point same pages.
- * So cloned bios must be completed before original bios, which means
- * the caller must complete @rq before @rq_src.
- */
-int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
- struct bio_set *bs, gfp_t gfp_mask,
- int (*bio_ctr)(struct bio *, struct bio *, void *),
- void *data)
-{
- struct bio *bio, *bio_src;
-
- if (!bs)
- bs = fs_bio_set;
-
- __rq_for_each_bio(bio_src, rq_src) {
- bio = bio_clone_fast(bio_src, gfp_mask, bs);
- if (!bio)
- goto free_and_out;
-
- if (bio_ctr && bio_ctr(bio, bio_src, data))
- goto free_and_out;
-
- if (rq->bio) {
- rq->biotail->bi_next = bio;
- rq->biotail = bio;
- } else
- rq->bio = rq->biotail = bio;
- }
-
- __blk_rq_prep_clone(rq, rq_src);
-
- return 0;
-
-free_and_out:
- if (bio)
- bio_put(bio);
- blk_rq_unprep_clone(rq);
-
- return -ENOMEM;
+ dst->bio = src->bio;
+ dst->biotail = src->biotail;
+ dst->cmd = src->cmd;
+ dst->cmd_len = src->cmd_len;
+ dst->sense = src->sense;
}
EXPORT_SYMBOL_GPL(blk_rq_prep_clone);