From: Peter Zijlstra <peterz@infradead.org> To: Jens Axboe <axboe@kernel.dk> Cc: "Carter Li 李通洲" <carter.li@eoitek.com>, "Pavel Begunkov" <asml.silence@gmail.com>, io-uring <io-uring@vger.kernel.org> Subject: Re: [ISSUE] The time cost of IOSQE_IO_LINK Date: Mon, 17 Feb 2020 13:09:20 +0100 Message-ID: <20200217120920.GQ14914@hirez.programming.kicks-ass.net> (raw) In-Reply-To: <b8069e62-7ea4-c7f3-55a3-838241951068@kernel.dk> On Fri, Feb 14, 2020 at 01:44:32PM -0700, Jens Axboe wrote: I've not looked at git trees yet, but the below doesn't apply to anything I have at hand. Anyway, I think I can still make sense of it -- just a rename or two seems to be missing. A few notes on the below... > diff --git a/include/linux/sched.h b/include/linux/sched.h > index 04278493bf15..447b06c6bed0 100644 > --- a/include/linux/sched.h > +++ b/include/linux/sched.h > @@ -685,6 +685,11 @@ struct task_struct { > #endif > struct sched_dl_entity dl; > > +#ifdef CONFIG_IO_URING > + struct list_head uring_work; > + raw_spinlock_t uring_lock; > +#endif > + Could we pretty please use struct callback_head for this, just like task_work() and RCU ? Look at task_work_add() for inspiration. And maybe remove the uring naming form this. > #ifdef CONFIG_UCLAMP_TASK > /* Clamp values requested for a scheduling entity */ > struct uclamp_se uclamp_req[UCLAMP_CNT]; > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index 51ca491d99ed..170fefa1caf8 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -2717,6 +2717,11 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) > INIT_HLIST_HEAD(&p->preempt_notifiers); > #endif > > +#ifdef CONFIG_IO_URING > + INIT_LIST_HEAD(&p->uring_work); > + raw_spin_lock_init(&p->uring_lock); > +#endif > + > #ifdef CONFIG_COMPACTION > p->capture_control = NULL; > #endif > @@ -4104,6 +4109,20 @@ void __noreturn do_task_dead(void) > cpu_relax(); > } > > +#ifdef CONFIG_IO_URING > +extern void io_uring_task_handler(struct task_struct *tsk); > + > +static inline void io_uring_handler(struct task_struct *tsk) > +{ > + if (!list_empty(&tsk->uring_work)) > + io_uring_task_handler(tsk); > +} > +#else /* !CONFIG_IO_URING */ > +static inline void io_uring_handler(struct task_struct *tsk) > +{ > +} > +#endif > + > static void sched_out_update(struct task_struct *tsk) > { > /* > @@ -4121,6 +4140,7 @@ static void sched_out_update(struct task_struct *tsk) > io_wq_worker_sleeping(tsk); > preempt_enable_no_resched(); > } > + io_uring_handler(tsk); > } > > static void sched_in_update(struct task_struct *tsk) > @@ -4131,6 +4151,7 @@ static void sched_in_update(struct task_struct *tsk) > else > io_wq_worker_running(tsk); > } > + io_uring_handler(tsk); > } The problem I have here is that we have an unconditional load of the cacheline that has ->uring_work in. /me curses about how nobody seems interested in building useful cacheline analyis tools :/ Lemme see if I can find a spot for this... perhaps something like so? diff --git a/include/linux/sched.h b/include/linux/sched.h index 0918904c939d..4fba93293fa1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -649,6 +649,7 @@ struct task_struct { /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; + int on_rq; #ifdef CONFIG_SMP struct llist_node wake_entry; @@ -671,14 +672,16 @@ struct task_struct { int recent_used_cpu; int wake_cpu; #endif - int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; + struct callbach_head *sched_work; + const struct sched_class *sched_class; + struct sched_entity se; struct sched_rt_entity rt; #ifdef CONFIG_CGROUP_SCHED
next prev parent reply index Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-02-12 16:31 Carter Li 李通洲 2020-02-12 17:11 ` Jens Axboe 2020-02-12 17:22 ` Jens Axboe 2020-02-12 17:29 ` Jens Axboe 2020-02-13 0:33 ` Carter Li 李通洲 2020-02-13 15:08 ` Pavel Begunkov 2020-02-13 15:14 ` Jens Axboe 2020-02-13 15:51 ` Carter Li 李通洲 2020-02-14 1:25 ` Carter Li 李通洲 2020-02-14 2:45 ` Jens Axboe 2020-02-14 5:03 ` Jens Axboe 2020-02-14 15:32 ` Peter Zijlstra 2020-02-14 15:47 ` Jens Axboe 2020-02-14 16:18 ` Jens Axboe 2020-02-14 17:52 ` Jens Axboe 2020-02-14 20:44 ` Jens Axboe 2020-02-15 0:16 ` Carter Li 李通洲 2020-02-15 1:10 ` Jens Axboe 2020-02-15 1:25 ` Carter Li 李通洲 2020-02-15 1:27 ` Jens Axboe 2020-02-15 6:01 ` Jens Axboe 2020-02-15 6:32 ` Carter Li 李通洲 2020-02-15 15:11 ` Jens Axboe 2020-02-16 19:06 ` Pavel Begunkov 2020-02-16 22:23 ` Jens Axboe 2020-02-17 10:30 ` Pavel Begunkov 2020-02-17 19:30 ` Jens Axboe 2020-02-16 23:06 ` Jens Axboe 2020-02-16 23:07 ` Jens Axboe 2020-02-17 12:09 ` Peter Zijlstra [this message] 2020-02-17 16:12 ` Jens Axboe 2020-02-17 17:16 ` Jens Axboe 2020-02-17 17:46 ` Peter Zijlstra 2020-02-17 18:16 ` Jens Axboe 2020-02-18 13:13 ` Peter Zijlstra 2020-02-18 14:27 ` [PATCH] asm-generic/atomic: Add try_cmpxchg() fallbacks Peter Zijlstra 2020-02-18 14:40 ` Peter Zijlstra 2020-02-20 10:30 ` Will Deacon 2020-02-20 10:37 ` Peter Zijlstra 2020-02-20 10:39 ` Will Deacon 2020-02-18 14:56 ` [ISSUE] The time cost of IOSQE_IO_LINK Oleg Nesterov 2020-02-18 15:07 ` Oleg Nesterov 2020-02-18 15:38 ` Peter Zijlstra 2020-02-18 16:33 ` Jens Axboe 2020-02-18 15:07 ` Peter Zijlstra 2020-02-18 15:50 ` [PATCH] task_work_run: don't take ->pi_lock unconditionally Oleg Nesterov 2020-02-20 16:39 ` Peter Zijlstra 2020-02-20 17:22 ` Oleg Nesterov 2020-02-20 17:49 ` Peter Zijlstra 2020-02-21 14:52 ` Oleg Nesterov 2020-02-24 18:47 ` Jens Axboe 2020-02-28 19:17 ` Jens Axboe 2020-02-28 19:25 ` Peter Zijlstra 2020-02-28 19:28 ` Jens Axboe 2020-02-28 20:06 ` Peter Zijlstra 2020-02-28 20:15 ` Jens Axboe 2020-02-18 16:46 ` [ISSUE] The time cost of IOSQE_IO_LINK Jens Axboe 2020-02-18 16:52 ` Jens Axboe 2020-02-18 13:13 ` Peter Zijlstra
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=20200217120920.GQ14914@hirez.programming.kicks-ass.net \ --to=peterz@infradead.org \ --cc=asml.silence@gmail.com \ --cc=axboe@kernel.dk \ --cc=carter.li@eoitek.com \ --cc=io-uring@vger.kernel.org \ /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
IO-Uring Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/io-uring/0 io-uring/git/0.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 io-uring io-uring/ https://lore.kernel.org/io-uring \ io-uring@vger.kernel.org public-inbox-index io-uring Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.kernel.vger.io-uring AGPL code for this site: git clone https://public-inbox.org/public-inbox.git