On 12/17/19 3:28 PM, Pavel Begunkov wrote:
> percpu_ref_tryget() has its own overhead. Instead getting a reference
> for each request, grab a bunch once per io_submit_sqes().
>
> basic benchmark with submit and wait 128 non-linked nops showed ~5%
> performance gain. (7044 KIOPS vs 7423)
>
> Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
> ---
>
> For notice: it could be done without @extra_refs variable,
> but looked too tangled because of gotos.
>
>
> fs/io_uring.c | 11 ++++++++---
> 1 file changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index cf4138f0e504..6c85dfc62224 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -845,9 +845,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
> gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
> struct io_kiocb *req;
>
> - if (!percpu_ref_tryget(&ctx->refs))
> - return NULL;
> -
> if (!state) {
> req = kmem_cache_alloc(req_cachep, gfp);
> if (unlikely(!req))
> @@ -3929,6 +3926,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
> struct io_submit_state state, *statep = NULL;
> struct io_kiocb *link = NULL;
> int i, submitted = 0;
> + unsigned int extra_refs;
> bool mm_fault = false;
>
> /* if we have a backlog and couldn't flush it all, return BUSY */
> @@ -3941,6 +3939,10 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
> statep = &state;
> }
>
> + if (!percpu_ref_tryget_many(&ctx->refs, nr))
> + return -EAGAIN;
> + extra_refs = nr;
> +
> for (i = 0; i < nr; i++) {
> struct io_kiocb *req = io_get_req(ctx, statep);
>
> @@ -3949,6 +3951,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
> submitted = -EAGAIN;
> break;
> }
> + --extra_refs;
> if (!io_get_sqring(ctx, req)) {
> __io_free_req(req);
> break;
> @@ -3976,6 +3979,8 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
> io_queue_link_head(link);
> if (statep)
> io_submit_state_end(&state);
> + if (extra_refs)
> + percpu_ref_put_many(&ctx->refs, extra_refs);
Might be cleaner to introduce a 'ret' variable, and leave submitted to be just
that, the number submitted. Then you could just do:
if (submitted != nr)
percpu_ref_put_many(&ctx->refs, nr - submitted);
and not need that weird extra_refs.
--
Jens Axboe
