block: implement mixed merge of different failfast requests
Failfast has characteristics from other attributes. When issuing,
executing and successuflly completing requests, failfast doesn't make
any difference. It only affects how a request is handled on failure.
Allowing requests with different failfast settings to be merged cause
normal IOs to fail prematurely while not allowing has performance
penalties as failfast is used for read aheads which are likely to be
located near in-flight or to-be-issued normal IOs.
This patch introduces the concept of 'mixed merge'. A request is a
mixed merge if it is merge of segments which require different
handling on failure. Currently the only mixable attributes are
failfast ones (or lack thereof).
When a bio with different failfast settings is added to an existing
request or requests of different failfast settings are merged, the
merged request is marked mixed. Each bio carries failfast settings
and the request always tracks failfast state of the first bio. When
the request fails, blk_rq_err_bytes() can be used to determine how
many bytes can be safely failed without crossing into an area which
requires further retrials.
This allows request merging regardless of failfast settings while
keeping the failure handling correct.
This patch only implements mixed merge but doesn't enable it. The
next one will update SCSI to make use of mixed merge.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Niel Lambrechts <niel.lambrechts@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
diff --git a/block/blk-core.c b/block/blk-core.c
index 4daae1e..c822239 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1157,6 +1157,7 @@
const unsigned short prio = bio_prio(bio);
const int sync = bio_sync(bio);
const int unplug = bio_unplug(bio);
+ const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
int rw_flags;
if (bio_barrier(bio) && bio_has_data(bio) &&
@@ -1186,6 +1187,9 @@
trace_block_bio_backmerge(q, bio);
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+ blk_rq_set_mixed_merge(req);
+
req->biotail->bi_next = bio;
req->biotail = bio;
req->__data_len += bytes;
@@ -1205,6 +1209,12 @@
trace_block_bio_frontmerge(q, bio);
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+ blk_rq_set_mixed_merge(req);
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= ff;
+ }
+
bio->bi_next = req->bio;
req->bio = bio;
@@ -1649,6 +1659,50 @@
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ * A request could be merge of IOs which require different failure
+ * handling. This function determines the number of bytes which
+ * can be failed from the beginning of the request without
+ * crossing into area which need to be retried further.
+ *
+ * Return:
+ * The number of bytes to fail.
+ *
+ * Context:
+ * queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+ unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+ unsigned int bytes = 0;
+ struct bio *bio;
+
+ if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+ return blk_rq_bytes(rq);
+
+ /*
+ * Currently the only 'mixing' which can happen is between
+ * different fastfail types. We can safely fail portions
+ * which have all the failfast bits that the first one has -
+ * the ones which are at least as eager to fail as the first
+ * one.
+ */
+ for (bio = rq->bio; bio; bio = bio->bi_next) {
+ if ((bio->bi_rw & ff) != ff)
+ break;
+ bytes += bio->bi_size;
+ }
+
+ /* this could lead to infinite loop */
+ BUG_ON(blk_rq_bytes(rq) && !bytes);
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (blk_do_io_stat(req)) {
@@ -1995,6 +2049,12 @@
if (blk_fs_request(req) || blk_discard_rq(req))
req->__sector += total_bytes >> 9;
+ /* mixed attributes always follow the first bio */
+ if (req->cmd_flags & REQ_MIXED_MERGE) {
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+ }
+
/*
* If total number of sectors is less than the first segment
* size, something has gone terribly wrong.
@@ -2174,6 +2234,25 @@
EXPORT_SYMBOL(blk_end_request_cur);
/**
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ * Complete @rq till the next failure boundary.
+ *
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
+{
+ WARN_ON(error >= 0);
+ return blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_err);
+
+/**
* __blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
* @error: %0 for success, < %0 for error
@@ -2232,6 +2311,26 @@
}
EXPORT_SYMBOL(__blk_end_request_cur);
+/**
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ * Complete @rq till the next failure boundary. Must be called
+ * with queue lock held.
+ *
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
+{
+ WARN_ON(error >= 0);
+ return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
+
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio)
{