From 5235553d821433e1f4fa720fd025d2c4b7ee9994 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 5 Feb 2018 13:16:56 -0700 Subject: blk-wbt: account flush requests correctly Mikulas reported a workload that saw bad performance, and figured out what it was due to various other types of requests being accounted as reads. Flush requests, for instance. Due to the high latency of those, we heavily throttle the writes to keep the latencies in balance. But they really should be accounted as writes. Fix this by checking the exact type of the request. If it's a read, account as a read, if it's a write or a flush, account as a write. Any other request we disregard. Previously everything would have been mistakenly accounted as reads. Reported-by: Mikulas Patocka Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Jens Axboe --- block/blk-wbt.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-wbt.c b/block/blk-wbt.c index ae8de9780085..f92fc84b5e2c 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -697,7 +697,15 @@ u64 wbt_default_latency_nsec(struct request_queue *q) static int wbt_data_dir(const struct request *rq) { - return rq_data_dir(rq); + const int op = req_op(rq); + + if (op == REQ_OP_READ) + return READ; + else if (op == REQ_OP_WRITE || op == REQ_OP_FLUSH) + return WRITE; + + /* don't account */ + return -1; } int wbt_init(struct request_queue *q) -- cgit From 30abb3a67f4b2aa160feeb3c0b771f730cbcca67 Mon Sep 17 00:00:00 2001 From: Howard McLauchlan Date: Tue, 6 Feb 2018 14:05:39 -0800 Subject: block: Add should_fail_bio() for bpf error injection The classic error injection mechanism, should_fail_request() does not support use cases where more information is required (from the entire struct bio, for example). To that end, this patch introduces should_fail_bio(), which calls should_fail_request() under the hood but provides a convenient place for kprobes to hook into if they require the entire struct bio. This patch also replaces some existing calls to should_fail_request() with should_fail_bio() with no degradation in performance. Signed-off-by: Howard McLauchlan Signed-off-by: Jens Axboe --- block/blk-core.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index d0d104268f1a..2d1a7bbe0634 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -34,6 +34,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -2083,6 +2084,14 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) return false; } +static noinline int should_fail_bio(struct bio *bio) +{ + if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) + return -EIO; + return 0; +} +ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); + /* * Remap block n of partition p to block n+start(p) of the disk. */ @@ -2174,7 +2183,7 @@ generic_make_request_checks(struct bio *bio) if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q)) goto not_supported; - if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) + if (should_fail_bio(bio)) goto end_io; if (!bio->bi_partno) { -- cgit From a7877390614770965a6925dfed79cbd3eeeb61e0 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Wed, 7 Feb 2018 22:19:20 +0100 Subject: block, bfq: add requeue-request hook Commit 'a6a252e64914 ("blk-mq-sched: decide how to handle flush rq via RQF_FLUSH_SEQ")' makes all non-flush re-prepared requests for a device be re-inserted into the active I/O scheduler for that device. As a consequence, I/O schedulers may get the same request inserted again, even several times, without a finish_request invoked on that request before each re-insertion. This fact is the cause of the failure reported in [1]. For an I/O scheduler, every re-insertion of the same re-prepared request is equivalent to the insertion of a new request. For schedulers like mq-deadline or kyber, this fact causes no harm. In contrast, it confuses a stateful scheduler like BFQ, which keeps state for an I/O request, until the finish_request hook is invoked on the request. In particular, BFQ may get stuck, waiting forever for the number of request dispatches, of the same request, to be balanced by an equal number of request completions (while there will be one completion for that request). In this state, BFQ may refuse to serve I/O requests from other bfq_queues. The hang reported in [1] then follows. However, the above re-prepared requests undergo a requeue, thus the requeue_request hook of the active elevator is invoked for these requests, if set. This commit then addresses the above issue by properly implementing the hook requeue_request in BFQ. [1] https://marc.info/?l=linux-block&m=151211117608676 Reported-by: Ivan Kozik Reported-by: Alban Browaeys Tested-by: Mike Galbraith Signed-off-by: Paolo Valente Signed-off-by: Serena Ziviani Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 107 ++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 82 insertions(+), 25 deletions(-) (limited to 'block') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 47e6ec7427c4..aeca22d91101 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -3823,24 +3823,26 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) } /* - * We exploit the bfq_finish_request hook to decrement - * rq_in_driver, but bfq_finish_request will not be - * invoked on this request. So, to avoid unbalance, - * just start this request, without incrementing - * rq_in_driver. As a negative consequence, - * rq_in_driver is deceptively lower than it should be - * while this request is in service. This may cause - * bfq_schedule_dispatch to be invoked uselessly. + * We exploit the bfq_finish_requeue_request hook to + * decrement rq_in_driver, but + * bfq_finish_requeue_request will not be invoked on + * this request. So, to avoid unbalance, just start + * this request, without incrementing rq_in_driver. As + * a negative consequence, rq_in_driver is deceptively + * lower than it should be while this request is in + * service. This may cause bfq_schedule_dispatch to be + * invoked uselessly. * * As for implementing an exact solution, the - * bfq_finish_request hook, if defined, is probably - * invoked also on this request. So, by exploiting - * this hook, we could 1) increment rq_in_driver here, - * and 2) decrement it in bfq_finish_request. Such a - * solution would let the value of the counter be - * always accurate, but it would entail using an extra - * interface function. This cost seems higher than the - * benefit, being the frequency of non-elevator-private + * bfq_finish_requeue_request hook, if defined, is + * probably invoked also on this request. So, by + * exploiting this hook, we could 1) increment + * rq_in_driver here, and 2) decrement it in + * bfq_finish_requeue_request. Such a solution would + * let the value of the counter be always accurate, + * but it would entail using an extra interface + * function. This cost seems higher than the benefit, + * being the frequency of non-elevator-private * requests very low. */ goto start_rq; @@ -4515,6 +4517,8 @@ static inline void bfq_update_insert_stats(struct request_queue *q, unsigned int cmd_flags) {} #endif +static void bfq_prepare_request(struct request *rq, struct bio *bio); + static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { @@ -4541,6 +4545,18 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, else list_add_tail(&rq->queuelist, &bfqd->dispatch); } else { + if (WARN_ON_ONCE(!bfqq)) { + /* + * This should never happen. Most likely rq is + * a requeued regular request, being + * re-inserted without being first + * re-prepared. Do a prepare, to avoid + * failure. + */ + bfq_prepare_request(rq, rq->bio); + bfqq = RQ_BFQQ(rq); + } + idle_timer_disabled = __bfq_insert_request(bfqd, rq); /* * Update bfqq, because, if a queue merge has occurred @@ -4697,22 +4713,44 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) bfq_schedule_dispatch(bfqd); } -static void bfq_finish_request_body(struct bfq_queue *bfqq) +static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq) { bfqq->allocated--; bfq_put_queue(bfqq); } -static void bfq_finish_request(struct request *rq) +/* + * Handle either a requeue or a finish for rq. The things to do are + * the same in both cases: all references to rq are to be dropped. In + * particular, rq is considered completed from the point of view of + * the scheduler. + */ +static void bfq_finish_requeue_request(struct request *rq) { - struct bfq_queue *bfqq; + struct bfq_queue *bfqq = RQ_BFQQ(rq); struct bfq_data *bfqd; - if (!rq->elv.icq) + /* + * Requeue and finish hooks are invoked in blk-mq without + * checking whether the involved request is actually still + * referenced in the scheduler. To handle this fact, the + * following two checks make this function exit in case of + * spurious invocations, for which there is nothing to do. + * + * First, check whether rq has nothing to do with an elevator. + */ + if (unlikely(!(rq->rq_flags & RQF_ELVPRIV))) + return; + + /* + * rq either is not associated with any icq, or is an already + * requeued request that has not (yet) been re-inserted into + * a bfq_queue. + */ + if (!rq->elv.icq || !bfqq) return; - bfqq = RQ_BFQQ(rq); bfqd = bfqq->bfqd; if (rq->rq_flags & RQF_STARTED) @@ -4727,13 +4765,14 @@ static void bfq_finish_request(struct request *rq) spin_lock_irqsave(&bfqd->lock, flags); bfq_completed_request(bfqq, bfqd); - bfq_finish_request_body(bfqq); + bfq_finish_requeue_request_body(bfqq); spin_unlock_irqrestore(&bfqd->lock, flags); } else { /* * Request rq may be still/already in the scheduler, - * in which case we need to remove it. And we cannot + * in which case we need to remove it (this should + * never happen in case of requeue). And we cannot * defer such a check and removal, to avoid * inconsistencies in the time interval from the end * of this function to the start of the deferred work. @@ -4748,9 +4787,26 @@ static void bfq_finish_request(struct request *rq) bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags); } - bfq_finish_request_body(bfqq); + bfq_finish_requeue_request_body(bfqq); } + /* + * Reset private fields. In case of a requeue, this allows + * this function to correctly do nothing if it is spuriously + * invoked again on this same request (see the check at the + * beginning of the function). Probably, a better general + * design would be to prevent blk-mq from invoking the requeue + * or finish hooks of an elevator, for a request that is not + * referred by that elevator. + * + * Resetting the following fields would break the + * request-insertion logic if rq is re-inserted into a bfq + * internal queue, without a re-preparation. Here we assume + * that re-insertions of requeued requests, without + * re-preparation, can happen only for pass_through or at_head + * requests (which are not re-inserted into bfq internal + * queues). + */ rq->elv.priv[0] = NULL; rq->elv.priv[1] = NULL; } @@ -5426,7 +5482,8 @@ static struct elevator_type iosched_bfq_mq = { .ops.mq = { .limit_depth = bfq_limit_depth, .prepare_request = bfq_prepare_request, - .finish_request = bfq_finish_request, + .requeue_request = bfq_finish_requeue_request, + .finish_request = bfq_finish_requeue_request, .exit_icq = bfq_exit_icq, .insert_requests = bfq_insert_requests, .dispatch_request = bfq_dispatch_request, -- cgit