From 76aaa5101fffaef12b45b4c01ed0d0528f23dedf Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 14 Jun 2012 09:04:07 +0200 Subject: block: Drop dead function blk_abort_queue() This function was only used by btrfs code in btrfs_abort_devices() (seems in a wrong way). It was removed in commit d07eb9117050c9ed3f78296ebcc06128b52693be, So, Let's remove the dead code to avoid any confusion. Changes in v2: update commit log, btrfs_abort_devices() was removed already. Cc: Jens Axboe Cc: linux-kernel@vger.kernel.org Cc: Chris Mason Cc: linux-btrfs@vger.kernel.org Cc: David Sterba Signed-off-by: Asias He Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba43f408baa3..07954b05b86c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -827,7 +827,6 @@ extern bool __blk_end_request_err(struct request *rq, int error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); -extern void blk_abort_queue(struct request_queue *); extern void blk_unprep_request(struct request *); /* -- cgit v1.2.3 From 8a5ecdd42862bf87ceab00bf2a15d7eabf58c02d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Jun 2012 20:40:58 -0700 Subject: block: add q->nr_rqs[] and move q->rq.elvpriv to q->nr_rqs_elvpriv Add q->nr_rqs[] which currently behaves the same as q->rq.count[] and move q->rq.elvpriv to q->nr_rqs_elvpriv. blk_drain_queue() is updated to use q->nr_rqs[] instead of q->rq.count[]. These counters separates queue-wide request statistics from the request list and allow implementation of per-queue request allocation. While at it, properly indent fields of struct request_list. Signed-off-by: Tejun Heo Acked-by: Vivek Goyal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 07954b05b86c..7e44ed93f84b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -51,11 +51,10 @@ struct request_list { * count[], starved[], and wait[] are indexed by * BLK_RW_SYNC/BLK_RW_ASYNC */ - int count[2]; - int starved[2]; - int elvpriv; - mempool_t *rq_pool; - wait_queue_head_t wait[2]; + int count[2]; + int starved[2]; + mempool_t *rq_pool; + wait_queue_head_t wait[2]; }; /* @@ -282,6 +281,8 @@ struct request_queue { struct list_head queue_head; struct request *last_merge; struct elevator_queue *elevator; + int nr_rqs[2]; /* # allocated [a]sync rqs */ + int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ /* * the queue request freelist, one for reads and one for writes -- cgit v1.2.3 From 5b788ce3e2acac9bf109743b1281d77347cf2101 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Jun 2012 20:40:59 -0700 Subject: block: prepare for multiple request_lists Request allocation is about to be made per-blkg meaning that there'll be multiple request lists. * Make queue full state per request_list. blk_*queue_full() functions are renamed to blk_*rl_full() and takes @rl instead of @q. * Rename blk_init_free_list() to blk_init_rl() and make it take @rl instead of @q. Also add @gfp_mask parameter. * Add blk_exit_rl() instead of destroying rl directly from blk_release_queue(). * Add request_list->q and make request alloc/free functions - blk_free_request(), [__]freed_request(), __get_request() - take @rl instead of @q. This patch doesn't introduce any functional difference. Signed-off-by: Tejun Heo Acked-by: Vivek Goyal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7e44ed93f84b..f2385ee7c7b2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -46,7 +46,12 @@ struct blkcg_gq; struct request; typedef void (rq_end_io_fn)(struct request *, int); +#define BLK_RL_SYNCFULL (1U << 0) +#define BLK_RL_ASYNCFULL (1U << 1) + struct request_list { + struct request_queue *q; /* the queue this rl belongs to */ + /* * count[], starved[], and wait[] are indexed by * BLK_RW_SYNC/BLK_RW_ASYNC @@ -55,6 +60,7 @@ struct request_list { int starved[2]; mempool_t *rq_pool; wait_queue_head_t wait[2]; + unsigned int flags; }; /* @@ -562,27 +568,25 @@ static inline bool rq_is_sync(struct request *rq) return rw_is_sync(rq->cmd_flags); } -static inline int blk_queue_full(struct request_queue *q, int sync) +static inline bool blk_rl_full(struct request_list *rl, bool sync) { - if (sync) - return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags); - return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + return rl->flags & flag; } -static inline void blk_set_queue_full(struct request_queue *q, int sync) +static inline void blk_set_rl_full(struct request_list *rl, bool sync) { - if (sync) - queue_flag_set(QUEUE_FLAG_SYNCFULL, q); - else - queue_flag_set(QUEUE_FLAG_ASYNCFULL, q); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags |= flag; } -static inline void blk_clear_queue_full(struct request_queue *q, int sync) +static inline void blk_clear_rl_full(struct request_list *rl, bool sync) { - if (sync) - queue_flag_clear(QUEUE_FLAG_SYNCFULL, q); - else - queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags &= ~flag; } -- cgit v1.2.3 From a051661ca6d134c18599498b185b667859d4339b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 26 Jun 2012 15:05:44 -0700 Subject: blkcg: implement per-blkg request allocation Currently, request_queue has one request_list to allocate requests from regardless of blkcg of the IO being issued. When the unified request pool is used up, cfq proportional IO limits become meaningless - whoever grabs the next request being freed wins the race regardless of the configured weights. This can be easily demonstrated by creating a blkio cgroup w/ very low weight, put a program which can issue a lot of random direct IOs there and running a sequential IO from a different cgroup. As soon as the request pool is used up, the sequential IO bandwidth crashes. This patch implements per-blkg request_list. Each blkg has its own request_list and any IO allocates its request from the matching blkg making blkcgs completely isolated in terms of request allocation. * Root blkcg uses the request_list embedded in each request_queue, which was renamed to @q->root_rl from @q->rq. While making blkcg rl handling a bit harier, this enables avoiding most overhead for root blkcg. * Queue fullness is properly per request_list but bdi isn't blkcg aware yet, so congestion state currently just follows the root blkcg. As writeback isn't aware of blkcg yet, this works okay for async congestion but readahead may get the wrong signals. It's better than blkcg completely collapsing with shared request_list but needs to be improved with future changes. * After this change, each block cgroup gets a full request pool making resource consumption of each cgroup higher. This makes allowing non-root users to create cgroups less desirable; however, note that allowing non-root users to directly manage cgroups is already severely broken regardless of this patch - each block cgroup consumes kernel memory and skews IO weight (IO weights are not hierarchical). v2: queue-sysfs.txt updated and patch description udpated as suggested by Vivek. v3: blk_get_rl() wasn't checking error return from blkg_lookup_create() and may cause oops on lookup failure. Fix it by falling back to root_rl on blkg lookup failures. This problem was spotted by Rakesh Iyer . v4: Updated to accomodate 458f27a982 "block: Avoid missed wakeup in request waitqueue". blk_drain_queue() now wakes up waiters on all blkg->rl on the target queue. Signed-off-by: Tejun Heo Acked-by: Vivek Goyal Cc: Wu Fengguang Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f2385ee7c7b2..3816ce8a08fc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -51,7 +51,9 @@ typedef void (rq_end_io_fn)(struct request *, int); struct request_list { struct request_queue *q; /* the queue this rl belongs to */ - +#ifdef CONFIG_BLK_CGROUP + struct blkcg_gq *blkg; /* blkg this request pool belongs to */ +#endif /* * count[], starved[], and wait[] are indexed by * BLK_RW_SYNC/BLK_RW_ASYNC @@ -143,6 +145,7 @@ struct request { struct hd_struct *part; unsigned long start_time; #ifdef CONFIG_BLK_CGROUP + struct request_list *rl; /* rl this rq is alloced from */ unsigned long long start_time_ns; unsigned long long io_start_time_ns; /* when passed to hardware */ #endif @@ -291,9 +294,12 @@ struct request_queue { int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ /* - * the queue request freelist, one for reads and one for writes + * If blkcg is not used, @q->root_rl serves all requests. If blkcg + * is used, root blkg allocates from @q->root_rl and all other + * blkgs from their own blkg->rl. Which one to use should be + * determined using bio_request_list(). */ - struct request_list rq; + struct request_list root_rl; request_fn_proc *request_fn; make_request_fn *make_request_fn; -- cgit v1.2.3 From 9cbb17508808f8a6bdd83354b61e126ac4fa6fed Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Jul 2012 09:08:14 +0200 Subject: blk: centralize non-request unplug handling. Both md and umem has similar code for getting notified on an blk_finish_plug event. Centralize this code in block/ and allow each driver to provide its distinctive difference. Signed-off-by: NeilBrown Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3816ce8a08fc..607ca228f47e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -922,11 +922,15 @@ struct blk_plug { }; #define BLK_MAX_REQUEST_COUNT 16 +struct blk_plug_cb; +typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *); struct blk_plug_cb { struct list_head list; - void (*callback)(struct blk_plug_cb *); + blk_plug_cb_fn callback; + void *data; }; - +extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, + void *data, int size); extern void blk_start_plug(struct blk_plug *); extern void blk_finish_plug(struct blk_plug *); extern void blk_flush_plug_list(struct blk_plug *, bool); -- cgit v1.2.3 From 74018dc3063a2c729fc73041c0a9f03aac995920 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Jul 2012 09:08:15 +0200 Subject: blk: pass from_schedule to non-request unplug functions. This will allow md/raid to know why the unplug was called, and will be able to act according - if !from_schedule it is safe to perform tasks which could themselves schedule. Signed-off-by: NeilBrown Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 607ca228f47e..4e72a9d48232 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -923,7 +923,7 @@ struct blk_plug { #define BLK_MAX_REQUEST_COUNT 16 struct blk_plug_cb; -typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *); +typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); struct blk_plug_cb { struct list_head list; blk_plug_cb_fn callback; -- cgit v1.2.3