From 36e765392e48e0322222347c4d21078c0b94758c Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 28 Sep 2018 16:42:20 +0800 Subject: [PATCH] blk-mq: complete req in softirq context in case of single queue Lot of controllers may have only one irq vector for completing IO request. And usually affinity of the only irq vector is all possible CPUs, however, on most of ARCH, there may be only one specific CPU for handling this interrupt. So if all IOs are completed in hardirq context, it is inevitable to degrade IO performance because of increased irq latency. This patch tries to address this issue by allowing to complete request in softirq context, like the legacy IO path. IOPS is observed as ~13%+ in the following randread test on raid0 over virtio-scsi. mdadm --create --verbose /dev/md0 --level=0 --chunk=1024 --raid-devices=8 /dev/sdb /dev/sdc /dev/sdd /dev/sde /dev/sdf /dev/sdg /dev/sdh /dev/sdi fio --time_based --name=benchmark --runtime=30 --filename=/dev/md0 --nrfiles=1 --ioengine=libaio --iodepth=32 --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=32 --rw=randread --blocksize=4k Cc: Dongli Zhang Cc: Zach Marano Cc: Christoph Hellwig Cc: Bart Van Assche Cc: Jianchao Wang Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq.c | 14 ++++++++++++++ block/blk-softirq.c | 5 ++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 1dc157c85a83..89bd9cb9defc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -568,6 +568,20 @@ static void __blk_mq_complete_request(struct request *rq) if (!blk_mq_mark_complete(rq)) return; + /* + * Most of single queue controllers, there is only one irq vector + * for handling IO completion, and the only irq's affinity is set + * as all possible CPUs. On most of ARCHs, this affinity means the + * irq is handled on one specific CPU. + * + * So complete IO reqeust in softirq context in case of single queue + * for not degrading IO performance by irqsoff latency. + */ + if (rq->q->nr_hw_queues == 1) { + __blk_complete_request(rq); + return; + } + if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { rq->q->softirq_done_fn(rq); return; diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 15c1f5e12eb8..e47a2f751884 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -97,8 +97,8 @@ static int blk_softirq_cpu_dead(unsigned int cpu) void __blk_complete_request(struct request *req) { - int ccpu, cpu; struct request_queue *q = req->q; + int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu; unsigned long flags; bool shared = false; @@ -110,8 +110,7 @@ void __blk_complete_request(struct request *req) /* * Select completion CPU */ - if (req->cpu != -1) { - ccpu = req->cpu; + if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) { if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) shared = cpus_share_cache(cpu, ccpu); } else