io_uring: only wake up sq thread while current task is in io worker context
PATCH v2 1/1 io_uring: only wake up sq thread while current task is in io worker context
If IORING_SETUP_SQPOLL is enabled, sqes are either handled in sq thread task context or in io worker task context. If current task context is sq thread, we don't need to check whether should wake up sq thread.
io_iopoll_req_issued() calls wq_has_sleeper(), which has smp_mb() memory barrier, before this patch, perf shows obvious overhead:
Samples: 481K of event 'cycles', Event count (approx.): 299807382878
Overhead Comma Shared Object Symbol
3.69% :9630 [kernel.vmlinux] [k] io_issue_sqeWith this patch, perf shows:
Samples: 482K of event 'cycles', Event count (approx.): 299929547283
Overhead Comma Shared Object Symbol
0.70% :4015 [kernel.vmlinux] [k] io_issue_sqeIt shows some obvious improvements.
--- fs/io_uring.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)
fs/io_uring.c +8 -3
@@ -2732,7 +2732,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)* find it from a io_iopoll_getevents() thread before the issuer is done * accessing the kiocb cookie. */ -static void io_iopoll_req_issued (struct io_kiocb *req) +static void io_iopoll_req_issued (struct io_kiocb *req,bool in_async) {struct io_ring_ctx *ctx = req->ctx;
@@ -2761,7 +2761,12 @@ static void io_iopoll_req_issued(struct io_kiocb *req)else list_add_tail (&req->inflight_entry, &ctx->iopoll_list); -if ((ctx->flags &IORING_SETUP_SQPOLL ) && +/* +* If IORING_SETUP_SQPOLL is enabled, sqes are either handled in sq thread +* task context or in io worker task context. If current task context is +* sq thread, we don't need to check whether should wake up sq thread. +*/ +if (in_async && (ctx->flags &IORING_SETUP_SQPOLL ) &&wq_has_sleeper (&ctx->sq_data->wait))wake_up (&ctx->sq_data->wait); }
@@ -6245,7 +6250,7 @@ static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock,if (in_async)mutex_lock (&ctx->uring_lock); -io_iopoll_req_issued (req); +io_iopoll_req_issued (req, in_async);if (in_async)mutex_unlock (&ctx->uring_lock);
Signature · 1 line
2.17.2
Quoted 10 lines · Xiaoguang Wang
If
IORING_SETUP_SQPOLLis enabled, sqes are either handled in sq thread task context or in io worker task context. If current task context is sq thread, we don't need to check whether should wake up sq thread.
io_iopoll_req_issued()callswq_has_sleeper(), which hassmp_mb()memory barrier, before this patch, perf shows obvious overhead:
Samples: 481K of event 'cycles', Event count (approx.): 299807382878Overhead Comma Shared Object Symbol 3.69% :9630 [kernel.vmlinux] [k] io_issue_sqe
Quoted 6 lines
With this patch, perf shows:
Samples: 482K of event 'cycles', Event count (approx.): 299929547283Overhead Comma Shared Object Symbol 0.70% :4015 [kernel.vmlinux] [k] io_issue_sqeIt shows some obvious improvements.
Applied, thanks.
Signature · 1 line
Jens Axboe