Block layer used to merge requests and bios with different failfast settings. This caused regular IOs to fail prematurely when they were merged into failfast requests for readahead. Niel Lambrechts could trigger the problem semi-reliably on ext4 when resuming from STR. ext4 uses readahead when reading inodes and combined with the deterministic extra SATA PHY exception cycle during resume on the specific configuration, non-readahead inode read would fail causing ext4 errors. Please read the following thread for details. http://lkml.org/lkml/2009/5/23/21 This patch makes block layer reject merging if the failfast settings don't match. This is correct but likely to lower IO performance by preventing regular IOs from mingling into surrounding readahead requests. Changes to allow such mixed merges and handle errors correctly will be added later. Signed-off-by: Tejun Heo <tj@xxxxxxxxxx> Reported-by: Niel Lambrechts <niel.lambrechts@xxxxxxxxx> Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: Theodore Tso <tytso@xxxxxxx> --- block/blk-merge.c | 6 ++++++ block/elevator.c | 8 ++++++++ 2 files changed, 14 insertions(+), 0 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index 39ce644..e199967 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -350,6 +350,12 @@ static int attempt_merge(struct request_queue *q, struct request *req, if (blk_integrity_rq(req) != blk_integrity_rq(next)) return 0; + /* don't merge requests of different failfast settings */ + if (blk_failfast_dev(req) != blk_failfast_dev(next) || + blk_failfast_transport(req) != blk_failfast_transport(next) || + blk_failfast_driver(req) != blk_failfast_driver(next)) + return 0; + /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn diff --git a/block/elevator.c b/block/elevator.c index ca86192..6f23753 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -100,6 +100,14 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio) if (bio_integrity(bio) != blk_integrity_rq(rq)) return 0; + /* + * Don't merge if failfast settings don't match + */ + if (bio_failfast_dev(bio) != blk_failfast_dev(rq) || + bio_failfast_transport(bio) != blk_failfast_transport(rq) || + bio_failfast_driver(bio) != blk_failfast_driver(rq)) + return 0; + if (!elv_iosched_allow_merge(rq, bio)) return 0; -- 1.6.0.2 -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
