| Message ID | 1474555980-2787-2-git-send-email-axboe@fb.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Thu, Sep 22, 2016 at 08:52:59AM -0600, Jens Axboe wrote: > Two cases: > > 1) blk_mq_alloc_request() needlessly re-runs the queue, after > calling into the tag allocation without NOWAIT set. We don't > need to do that. > > 2) blk_mq_map_request() should just use blk_mq_run_hw_queue() with > the async flag set to false. I had some very similar patches in my queue but never got around benchmarking them in enough setups to feel safe enough to post them. Assuming you found no reaosn to keep the odd old scheme either: Reviewed-by: Christoph Hellwig <hch@lst.de> -- To unsubscribe from this list: send the line "unsubscribe linux-block" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Looks good,
Reviewed-by: Sagi Grimberg <sagi@rimberg.me>
--
To unsubscribe from this list: send the line "unsubscribe linux-block" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/block/blk-mq.c b/block/blk-mq.c index e0a69daddbd8..c29700010b5c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -34,8 +34,6 @@ static DEFINE_MUTEX(all_q_mutex); static LIST_HEAD(all_q_list); -static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx); - /* * Check if any of the ctx's have pending work in this hardware queue */ @@ -228,19 +226,9 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); - rq = __blk_mq_alloc_request(&alloc_data, rw, 0); - if (!rq && !(flags & BLK_MQ_REQ_NOWAIT)) { - __blk_mq_run_hw_queue(hctx); - blk_mq_put_ctx(ctx); - - ctx = blk_mq_get_ctx(q); - hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); - rq = __blk_mq_alloc_request(&alloc_data, rw, 0); - ctx = alloc_data.ctx; - } blk_mq_put_ctx(ctx); + if (!rq) { blk_queue_exit(q); return ERR_PTR(-EWOULDBLOCK); @@ -1225,7 +1213,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, blk_mq_set_alloc_data(&alloc_data, q, BLK_MQ_REQ_NOWAIT, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, op, op_flags); if (unlikely(!rq)) { - __blk_mq_run_hw_queue(hctx); + blk_mq_run_hw_queue(hctx, false); blk_mq_put_ctx(ctx); trace_block_sleeprq(q, bio, op);
Two cases: 1) blk_mq_alloc_request() needlessly re-runs the queue, after calling into the tag allocation without NOWAIT set. We don't need to do that. 2) blk_mq_map_request() should just use blk_mq_run_hw_queue() with the async flag set to false. Signed-off-by: Jens Axboe <axboe@fb.com> --- block/blk-mq.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-)