From aa387cc895672b00f807ad7c734a2defaf677712 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 31 Jul 2011 22:05:09 +0200 Subject: block: add bsg helper library This moves the FC classes bsg code to the block layer and makes it a lib so that other classes like iscsi and SAS can use it. It is helpful because working with the request queue, bios, creating scatterlists, etc are a pain that the LLD does not have to worry about with normal IOs and should not have to worry about for bsg requests. Signed-off-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0e67c45b3bc9..847928546076 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -30,6 +30,7 @@ struct request_pm_state; struct blk_trace; struct request; struct sg_io_hdr; +struct bsg_job; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -209,6 +210,7 @@ typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *, typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); +typedef int (bsg_job_fn) (struct bsg_job *); enum blk_eh_timer_return { BLK_EH_NOT_HANDLED, @@ -375,6 +377,8 @@ struct request_queue { struct mutex sysfs_lock; #if defined(CONFIG_BLK_DEV_BSG) + bsg_job_fn *bsg_job_fn; + int bsg_job_size; struct bsg_class_device bsg_dev; #endif -- cgit v1.2.3 From 4853abaae7e4a2af938115ce9071ef8684fb7af4 Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Mon, 15 Aug 2011 21:37:25 +0200 Subject: block: fix flush machinery for stacking drivers with differring flush flags Commit ae1b1539622fb46e51b4d13b3f9e5f4c713f86ae, block: reimplement FLUSH/FUA to support merge, introduced a performance regression when running any sort of fsyncing workload using dm-multipath and certain storage (in our case, an HP EVA). The test I ran was fs_mark, and it dropped from ~800 files/sec on ext4 to ~100 files/sec. It turns out that dm-multipath always advertised flush+fua support, and passed commands on down the stack, where those flags used to get stripped off. The above commit changed that behavior: static inline struct request *__elv_next_request(struct request_queue *q) { struct request *rq; while (1) { - while (!list_empty(&q->queue_head)) { + if (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); - if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) || - (rq->cmd_flags & REQ_FLUSH_SEQ)) - return rq; - rq = blk_do_flush(q, rq); - if (rq) - return rq; + return rq; } Note that previously, a command would come in here, have REQ_FLUSH|REQ_FUA set, and then get handed off to blk_do_flush: struct request *blk_do_flush(struct request_queue *q, struct request *rq) { unsigned int fflags = q->flush_flags; /* may change, cache it */ bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA; bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH); bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA); unsigned skip = 0; ... if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) { rq->cmd_flags &= ~REQ_FLUSH; if (!has_fua) rq->cmd_flags &= ~REQ_FUA; return rq; } So, the flush machinery was bypassed in such cases (q->flush_flags == 0 && rq->cmd_flags & (REQ_FLUSH|REQ_FUA)). Now, however, we don't get into the flush machinery at all. Instead, __elv_next_request just hands a request with flush and fua bits set to the scsi_request_fn, even if the underlying request_queue does not support flush or fua. The agreed upon approach is to fix the flush machinery to allow stacking. While this isn't used in practice (since there is only one request-based dm target, and that target will now reflect the flush flags of the underlying device), it does future-proof the solution, and make it function as designed. In order to make this work, I had to add a field to the struct request, inside the flush structure (to store the original req->end_io). Shaohua had suggested overloading the union with rb_node and completion_data, but the completion data is used by device mapper and can also be used by other drivers. So, I didn't see a way around the additional field. I tested this patch on an HP EVA with both ext4 and xfs, and it recovers the lost performance. Comments and other testers, as always, are appreciated. Cheers, Jeff Signed-off-by: Jeff Moyer Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 847928546076..84b15d54f8c2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -118,6 +118,7 @@ struct request { struct { unsigned int seq; struct list_head list; + rq_end_io_fn *saved_end_io; } flush; }; -- cgit v1.2.3