summaryrefslogtreecommitdiff
path: root/block/blk-timeout.c
diff options
context:
space:
mode:
authorJens Axboe <axboe@kernel.dk>2013-10-24 09:20:05 +0100
committerJens Axboe <axboe@kernel.dk>2013-10-25 11:56:00 +0100
commit320ae51feed5c2f13664aa05a76bec198967e04d (patch)
treead37ccbcc5ddb1c9c19e48965bf8fec1b05217dc /block/blk-timeout.c
parent1dddc01af0d42b21058e0cb9c1ca9e8d5204d9b0 (diff)
downloadlwn-320ae51feed5c2f13664aa05a76bec198967e04d.tar.gz
lwn-320ae51feed5c2f13664aa05a76bec198967e04d.zip
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices: - The classic request_fn based approach, where drivers use struct request units for IO. The block layer provides various helper functionalities to let drivers share code, things like tag management, timeout handling, queueing, etc. - The "stacked" approach, where a driver squeezes in between the block layer and IO submitter. Since this bypasses the IO stack, driver generally have to manage everything themselves. With drivers being written for new high IOPS devices, the classic request_fn based driver doesn't work well enough. The design dates back to when both SMP and high IOPS was rare. It has problems with scaling to bigger machines, and runs into scaling issues even on smaller machines when you have IOPS in the hundreds of thousands per device. The stacked approach is then most often selected as the model for the driver. But this means that everybody has to re-invent everything, and along with that we get all the problems again that the shared approach solved. This commit introduces blk-mq, block multi queue support. The design is centered around per-cpu queues for queueing IO, which then funnel down into x number of hardware submission queues. We might have a 1:1 mapping between the two, or it might be an N:M mapping. That all depends on what the hardware supports. blk-mq provides various helper functions, which include: - Scalable support for request tagging. Most devices need to be able to uniquely identify a request both in the driver and to the hardware. The tagging uses per-cpu caches for freed tags, to enable cache hot reuse. - Timeout handling without tracking request on a per-device basis. Basically the driver should be able to get a notification, if a request happens to fail. - Optional support for non 1:1 mappings between issue and submission queues. blk-mq can redirect IO completions to the desired location. - Support for per-request payloads. Drivers almost always need to associate a request structure with some driver private command structure. Drivers can tell blk-mq this at init time, and then any request handed to the driver will have the required size of memory associated with it. - Support for merging of IO, and plugging. The stacked model gets neither of these. Even for high IOPS devices, merging sequential IO reduces per-command overhead and thus increases bandwidth. For now, this is provided as a potential 3rd queueing model, with the hope being that, as it matures, it can replace both the classic and stacked model. That would get us back to having just 1 real model for block devices, leaving the stacked approach to dm/md devices (as it was originally intended). Contributions in this patch from the following people: Shaohua Li <shli@fusionio.com> Alexander Gordeev <agordeev@redhat.com> Christoph Hellwig <hch@infradead.org> Mike Christie <michaelc@cs.wisc.edu> Matias Bjorling <m@bjorling.me> Jeff Moyer <jmoyer@redhat.com> Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-timeout.c')
-rw-r--r--block/blk-timeout.c73
1 files changed, 46 insertions, 27 deletions
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 65f103563969..22846cf3595a 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -7,6 +7,7 @@
#include <linux/fault-inject.h>
#include "blk.h"
+#include "blk-mq.h"
#ifdef CONFIG_FAIL_IO_TIMEOUT
@@ -88,11 +89,18 @@ static void blk_rq_timed_out(struct request *req)
ret = q->rq_timed_out_fn(req);
switch (ret) {
case BLK_EH_HANDLED:
- __blk_complete_request(req);
+ /* Can we use req->errors here? */
+ if (q->mq_ops)
+ blk_mq_complete_request(req, req->errors);
+ else
+ __blk_complete_request(req);
break;
case BLK_EH_RESET_TIMER:
blk_clear_rq_complete(req);
- blk_add_timer(req);
+ if (q->mq_ops)
+ blk_mq_add_timer(req);
+ else
+ blk_add_timer(req);
break;
case BLK_EH_NOT_HANDLED:
/*
@@ -108,6 +116,23 @@ static void blk_rq_timed_out(struct request *req)
}
}
+void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
+ unsigned int *next_set)
+{
+ if (time_after_eq(jiffies, rq->deadline)) {
+ list_del_init(&rq->timeout_list);
+
+ /*
+ * Check if we raced with end io completion
+ */
+ if (!blk_mark_rq_complete(rq))
+ blk_rq_timed_out(rq);
+ } else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
+ *next_timeout = rq->deadline;
+ *next_set = 1;
+ }
+}
+
void blk_rq_timed_out_timer(unsigned long data)
{
struct request_queue *q = (struct request_queue *) data;
@@ -117,21 +142,8 @@ void blk_rq_timed_out_timer(unsigned long data)
spin_lock_irqsave(q->queue_lock, flags);
- list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list) {
- if (time_after_eq(jiffies, rq->deadline)) {
- list_del_init(&rq->timeout_list);
-
- /*
- * Check if we raced with end io completion
- */
- if (blk_mark_rq_complete(rq))
- continue;
- blk_rq_timed_out(rq);
- } else if (!next_set || time_after(next, rq->deadline)) {
- next = rq->deadline;
- next_set = 1;
- }
- }
+ list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
+ blk_rq_check_expired(rq, &next, &next_set);
if (next_set)
mod_timer(&q->timeout, round_jiffies_up(next));
@@ -157,15 +169,7 @@ void blk_abort_request(struct request *req)
}
EXPORT_SYMBOL_GPL(blk_abort_request);
-/**
- * blk_add_timer - Start timeout timer for a single request
- * @req: request that is about to start running.
- *
- * Notes:
- * Each request has its own timer, and as it is added to the queue, we
- * set up the timer. When the request completes, we cancel the timer.
- */
-void blk_add_timer(struct request *req)
+void __blk_add_timer(struct request *req, struct list_head *timeout_list)
{
struct request_queue *q = req->q;
unsigned long expiry;
@@ -184,7 +188,8 @@ void blk_add_timer(struct request *req)
req->timeout = q->rq_timeout;
req->deadline = jiffies + req->timeout;
- list_add_tail(&req->timeout_list, &q->timeout_list);
+ if (timeout_list)
+ list_add_tail(&req->timeout_list, timeout_list);
/*
* If the timer isn't already pending or this timeout is earlier
@@ -196,5 +201,19 @@ void blk_add_timer(struct request *req)
if (!timer_pending(&q->timeout) ||
time_before(expiry, q->timeout.expires))
mod_timer(&q->timeout, expiry);
+
+}
+
+/**
+ * blk_add_timer - Start timeout timer for a single request
+ * @req: request that is about to start running.
+ *
+ * Notes:
+ * Each request has its own timer, and as it is added to the queue, we
+ * set up the timer. When the request completes, we cancel the timer.
+ */
+void blk_add_timer(struct request *req)
+{
+ __blk_add_timer(req, &req->q->timeout_list);
}