From: Fengnan Chang <changfengnan@bytedance.com>
To: Gabriel Krisman Bertazi <krisman@suse.de>
Cc: axboe@kernel.dk, xiaobing.li@samsung.com, asml.silence@gmail.com,
io-uring@vger.kernel.org, Diangang Li <lidiangang@bytedance.com>
Subject: Re: [External] Re: [PATCH v2] io_uring: add IORING_SETUP_SQTHREAD_STATS flag to enable sqthread stats collection
Date: Tue, 21 Oct 2025 16:50:33 +0800 [thread overview]
Message-ID: <CAPFOzZsYa=x9hS1uw8dLNZjvdiDwtNHzi1BUThOjwT+uJ6XMpQ@mail.gmail.com> (raw)
In-Reply-To: <87ldl539hi.fsf@mailhost.krisman.be>
Gabriel Krisman Bertazi <krisman@suse.de> 于2025年10月20日周一 22:59写道:
>
> Fengnan Chang <changfengnan@bytedance.com> writes:
>
> > In previous versions, getrusage was always called in sqrthread
> > to count work time, but this could incur some overhead.
> > This patch turn off stats by default, and introduces a new flag
> > IORING_SETUP_SQTHREAD_STATS that allows user to enable the
> > collection of statistics in the sqthread.
> >
> > ./t/io_uring -p1 -d128 -b4096 -s32 -c1 -F1 -B1 -R1 -X1 -n1 ./testfile
> > IOPS base: 570K, patch: 590K
> >
> > ./t/io_uring -p1 -d128 -b4096 -s32 -c1 -F1 -B1 -R1 -X1 -n1 /dev/nvme1n1
> > IOPS base: 826K, patch: 889K
> >
> > Signed-off-by: Fengnan Chang <changfengnan@bytedance.com>
> > Reviewed-by: Diangang Li <lidiangang@bytedance.com>
> > ---
> > include/uapi/linux/io_uring.h | 5 +++++
> > io_uring/fdinfo.c | 15 ++++++++++-----
> > io_uring/io_uring.h | 3 ++-
> > io_uring/sqpoll.c | 10 +++++++---
> > io_uring/sqpoll.h | 1 +
> > 5 files changed, 25 insertions(+), 9 deletions(-)
> >
> > diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> > index 263bed13473e..8c5cb9533950 100644
> > --- a/include/uapi/linux/io_uring.h
> > +++ b/include/uapi/linux/io_uring.h
> > @@ -231,6 +231,11 @@ enum io_uring_sqe_flags_bit {
> > */
> > #define IORING_SETUP_CQE_MIXED (1U << 18)
> >
> > +/*
> > + * Enable SQPOLL thread stats collection
> > + */
> > +#define IORING_SETUP_SQTHREAD_STATS (1U << 19)
> > +
> > enum io_uring_op {
> > IORING_OP_NOP,
> > IORING_OP_READV,
> > diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
> > index ff3364531c77..4c532e414255 100644
> > --- a/io_uring/fdinfo.c
> > +++ b/io_uring/fdinfo.c
> > @@ -154,13 +154,16 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
> > if (tsk) {
> > get_task_struct(tsk);
> > rcu_read_unlock();
> > - getrusage(tsk, RUSAGE_SELF, &sq_usage);
> > + if (sq->enable_work_time_stat)
> > + getrusage(tsk, RUSAGE_SELF, &sq_usage);
> > put_task_struct(tsk);
>
> If the usage statistics are disabled, you don't need to acquire and drop
> the task_struct reference any longer. you can move the get/put_task_struct
> into the if.
I'll fix this in next version.
>
> > sq_pid = sq->task_pid;
> > sq_cpu = sq->sq_cpu;
> > - sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
> > + if (sq->enable_work_time_stat) {
> > + sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
> > + sq_usage.ru_stime.tv_usec);
> > - sq_work_time = sq->work_time;
> > + sq_work_time = sq->work_time;
> > + }
> > } else {
> > rcu_read_unlock();
> > }
> > @@ -168,8 +171,10 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
> >
> > seq_printf(m, "SqThread:\t%d\n", sq_pid);
> > seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
> > - seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
> > - seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
> > + if (ctx->flags & IORING_SETUP_SQTHREAD_STATS) {
> > + seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
> > + seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
> > + }
>
> It works, but it is weird that you gate the writing of sq_total_time on
> (sq->enable_work_time_stat) and then, the display of it on (ctx->flags &
> IORING_SETUP_SQTHREAD_STATS). Since a sqpoll can attend to more than
> one ctx, I'd just check ctx->flags & IORING_SETUP_SQTHREAD_STATS
> in both places in this function.
Yeh, there's a bit of a problem here, I was going to use check
ctx->flags & IORING_SETUP_SQTHREAD_STATS, but in io_sq_thread, getrusage
is try to account multi ctx, and can't get ctx before getrusage, so I use
enable_work_time_stat, and I missed something. I would like to use
enable_work_time_stat in both places in this function.
>
> > seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr);
> > for (i = 0; i < ctx->file_table.data.nr; i++) {
> > struct file *f = NULL;
> > diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
> > index 46d9141d772a..949dc7cba111 100644
> > --- a/io_uring/io_uring.h
> > +++ b/io_uring/io_uring.h
> > @@ -54,7 +54,8 @@
> > IORING_SETUP_REGISTERED_FD_ONLY |\
> > IORING_SETUP_NO_SQARRAY |\
> > IORING_SETUP_HYBRID_IOPOLL |\
> > - IORING_SETUP_CQE_MIXED)
> > + IORING_SETUP_CQE_MIXED |\
> > + IORING_SETUP_SQTHREAD_STATS)
> >
> > #define IORING_ENTER_FLAGS (IORING_ENTER_GETEVENTS |\
> > IORING_ENTER_SQ_WAKEUP |\
> > diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
> > index a3f11349ce06..46bcd4854abc 100644
> > --- a/io_uring/sqpoll.c
> > +++ b/io_uring/sqpoll.c
> > @@ -161,6 +161,7 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
> > mutex_init(&sqd->lock);
> > init_waitqueue_head(&sqd->wait);
> > init_completion(&sqd->exited);
> > + sqd->enable_work_time_stat = false;
> > return sqd;
> > }
> >
> > @@ -317,7 +318,8 @@ static int io_sq_thread(void *data)
> > }
> >
> > cap_entries = !list_is_singular(&sqd->ctx_list);
> > - getrusage(current, RUSAGE_SELF, &start);
> > + if (sqd->enable_work_time_stat)
> > + getrusage(current, RUSAGE_SELF, &start);
> > list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
> > int ret = __io_sq_thread(ctx, cap_entries);
> >
> > @@ -333,7 +335,8 @@ static int io_sq_thread(void *data)
> >
> > if (sqt_spin || !time_after(jiffies, timeout)) {
> > if (sqt_spin) {
> > - io_sq_update_worktime(sqd, &start);
> > + if (sqd->enable_work_time_stat)
> > + io_sq_update_worktime(sqd, &start);
> > timeout = jiffies + sqd->sq_thread_idle;
> > }
> > if (unlikely(need_resched())) {
> > @@ -445,7 +448,8 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
> > ret = PTR_ERR(sqd);
> > goto err;
> > }
> > -
> > + if (ctx->flags & IORING_SETUP_SQTHREAD_STATS)
> > + sqd->enable_work_time_stat = true;
> > ctx->sq_creds = get_current_cred();
> > ctx->sq_data = sqd;
> > ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
> > diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
> > index b83dcdec9765..55f2e4d46d54 100644
> > --- a/io_uring/sqpoll.h
> > +++ b/io_uring/sqpoll.h
> > @@ -19,6 +19,7 @@ struct io_sq_data {
> > u64 work_time;
> > unsigned long state;
> > struct completion exited;
> > + bool enable_work_time_stat;
> > };
> >
> > int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p);
>
> --
> Gabriel Krisman Bertazi
next prev parent reply other threads:[~2025-10-21 8:50 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-20 11:30 [PATCH v2] io_uring: add IORING_SETUP_SQTHREAD_STATS flag to enable sqthread stats collection Fengnan Chang
2025-10-20 14:59 ` Gabriel Krisman Bertazi
2025-10-21 8:50 ` Fengnan Chang [this message]
2025-10-20 15:12 ` Jens Axboe
2025-10-21 8:54 ` [External] " Fengnan Chang
2025-10-21 17:54 ` Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAPFOzZsYa=x9hS1uw8dLNZjvdiDwtNHzi1BUThOjwT+uJ6XMpQ@mail.gmail.com' \
--to=changfengnan@bytedance.com \
--cc=asml.silence@gmail.com \
--cc=axboe@kernel.dk \
--cc=io-uring@vger.kernel.org \
--cc=krisman@suse.de \
--cc=lidiangang@bytedance.com \
--cc=xiaobing.li@samsung.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox