From: Peter Zijlstra <peterz@infradead.org>
To: Oleg Nesterov <oleg@redhat.com>
Cc: "Arjan van de Ven" <arjan@linux.intel.com>,
"Fernando Luis Vázquez Cao" <fernando_b1@lab.ntt.co.jp>,
"Frederic Weisbecker" <fweisbec@gmail.com>,
"Ingo Molnar" <mingo@kernel.org>,
"Thomas Gleixner" <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>,
"Tetsuo Handa" <penguin-kernel@I-love.SAKURA.ne.jp>,
"Andrew Morton" <akpm@linux-foundation.org>
Subject: Re: [PATCH 2/4] nohz: Synchronize sleep time stats with seqlock
Date: Wed, 21 Aug 2013 14:48:49 +0200 [thread overview]
Message-ID: <20130821124849.GB31370@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20130821113551.GA1472@redhat.com>
On Wed, Aug 21, 2013 at 01:35:51PM +0200, Oleg Nesterov wrote:
> > > Btw. Whatever we do, can't we unify io_schedule/io_schedule_timeout?
> >
> > I suppose we could, a timeout of MAX_SCHEDULE_TIMEOUT will act like a
> > regular schedule, but it gets all the overhead of doing
> > schedule_timeout(). So I don't think its a win.
>
> Well, the only overhead is "if(to == MAX_SCHEDULE_TIMEOUT)" at the start.
> I don't think it makes sense to copy-and-paste the identical code to
> avoid it. But please ignore, this is really minor and off-topic.
Ah, so the 'problem' is that schedule_timeout() doesn't live in
kernel/sched/core.c and we thus get an extra function call (which are
somewhat expensive on some archs).
That said, I suppose we could do something like the below, that should
allow the compiler to DTRT.
---
include/linux/sched.h | 35 ++++++++++++++++++++++---
kernel/sched/core.c | 22 +++++-----------
kernel/timer.c | 67 ++++++++++--------------------------------------
3 files changed, 52 insertions(+), 72 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 50d04b9..112960c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -303,10 +303,37 @@ extern char __sched_text_start[], __sched_text_end[];
extern int in_sched_functions(unsigned long addr);
#define MAX_SCHEDULE_TIMEOUT LONG_MAX
-extern signed long schedule_timeout(signed long timeout);
-extern signed long schedule_timeout_interruptible(signed long timeout);
-extern signed long schedule_timeout_killable(signed long timeout);
-extern signed long schedule_timeout_uninterruptible(signed long timeout);
+extern long __schedule_timeout(long timeout);
+
+static inline long schedule_timeout(long timeout)
+{
+ if (timeout == MAX_SCHEDULE_TIMEOUT) {
+ schedule();
+ return timeout;
+ }
+ return __schedule_timeout(timeout);
+}
+
+/*
+ * We can use __set_current_state() here because schedule_timeout() calls
+ * schedule() unconditionally.
+ */
+static inline long schedule_timeout_interruptible(long timeout)
+{
+ __set_current_state(TASK_INTERRUPTIBLE);
+ return schedule_timeout(timeout);
+}
+static inline long schedule_timeout_killable(long timeout)
+{
+ __set_current_state(TASK_KILLABLE);
+ return schedule_timeout(timeout);
+}
+static inline long schedule_timeout_uninterruptible(long timeout)
+{
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ return schedule_timeout(timeout);
+}
+
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f737871..ef2cddd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3937,21 +3937,6 @@ EXPORT_SYMBOL_GPL(yield_to);
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
*/
-void __sched io_schedule(void)
-{
- struct rq *rq = raw_rq();
-
- delayacct_blkio_start();
- atomic_inc(&rq->nr_iowait);
- blk_flush_plug(current);
- current->in_iowait = 1;
- schedule();
- current->in_iowait = 0;
- atomic_dec(&rq->nr_iowait);
- delayacct_blkio_end();
-}
-EXPORT_SYMBOL(io_schedule);
-
long __sched io_schedule_timeout(long timeout)
{
struct rq *rq = raw_rq();
@@ -3968,6 +3953,13 @@ long __sched io_schedule_timeout(long timeout)
return ret;
}
+void __sched io_schedule(void)
+{
+ io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
+}
+EXPORT_SYMBOL(io_schedule);
+
+
/**
* sys_sched_get_priority_max - return maximum RT priority.
* @policy: scheduling class.
diff --git a/kernel/timer.c b/kernel/timer.c
index 15bc1b4..8244ce0 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1429,38 +1429,24 @@ static void process_timeout(unsigned long __data)
*
* In all cases the return value is guaranteed to be non-negative.
*/
-signed long __sched schedule_timeout(signed long timeout)
+signed long __sched __schedule_timeout(signed long timeout)
{
struct timer_list timer;
unsigned long expire;
- switch (timeout)
- {
- case MAX_SCHEDULE_TIMEOUT:
- /*
- * These two special cases are useful to be comfortable
- * in the caller. Nothing more. We could take
- * MAX_SCHEDULE_TIMEOUT from one of the negative value
- * but I' d like to return a valid offset (>=0) to allow
- * the caller to do everything it want with the retval.
- */
- schedule();
- goto out;
- default:
- /*
- * Another bit of PARANOID. Note that the retval will be
- * 0 since no piece of kernel is supposed to do a check
- * for a negative retval of schedule_timeout() (since it
- * should never happens anyway). You just have the printk()
- * that will tell you if something is gone wrong and where.
- */
- if (timeout < 0) {
- printk(KERN_ERR "schedule_timeout: wrong timeout "
+ /*
+ * Another bit of PARANOID. Note that the retval will be 0 since no
+ * piece of kernel is supposed to do a check for a negative retval of
+ * schedule_timeout() (since it should never happens anyway). You just
+ * have the printk() that will tell you if something is gone wrong and
+ * where.
+ */
+ if (timeout < 0) {
+ printk(KERN_ERR "schedule_timeout: wrong timeout "
"value %lx\n", timeout);
- dump_stack();
- current->state = TASK_RUNNING;
- goto out;
- }
+ dump_stack();
+ current->state = TASK_RUNNING;
+ goto out;
}
expire = timeout + jiffies;
@@ -1478,32 +1464,7 @@ signed long __sched schedule_timeout(signed long timeout)
out:
return timeout < 0 ? 0 : timeout;
}
-EXPORT_SYMBOL(schedule_timeout);
-
-/*
- * We can use __set_current_state() here because schedule_timeout() calls
- * schedule() unconditionally.
- */
-signed long __sched schedule_timeout_interruptible(signed long timeout)
-{
- __set_current_state(TASK_INTERRUPTIBLE);
- return schedule_timeout(timeout);
-}
-EXPORT_SYMBOL(schedule_timeout_interruptible);
-
-signed long __sched schedule_timeout_killable(signed long timeout)
-{
- __set_current_state(TASK_KILLABLE);
- return schedule_timeout(timeout);
-}
-EXPORT_SYMBOL(schedule_timeout_killable);
-
-signed long __sched schedule_timeout_uninterruptible(signed long timeout)
-{
- __set_current_state(TASK_UNINTERRUPTIBLE);
- return schedule_timeout(timeout);
-}
-EXPORT_SYMBOL(schedule_timeout_uninterruptible);
+EXPORT_SYMBOL(__schedule_timeout);
static int __cpuinit init_timers_cpu(int cpu)
{
next prev parent reply other threads:[~2013-08-21 12:49 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-16 15:42 [PATCH RESEND 0/4] nohz: Fix racy sleeptime stats Frederic Weisbecker
2013-08-16 15:42 ` [PATCH 1/4] nohz: Only update sleeptime stats locally Frederic Weisbecker
2013-08-18 16:49 ` Oleg Nesterov
2013-08-18 21:38 ` Frederic Weisbecker
2013-08-18 17:04 ` Oleg Nesterov
2013-08-19 18:05 ` Stratos Karafotis
2013-08-16 15:42 ` [PATCH 2/4] nohz: Synchronize sleep time stats with seqlock Frederic Weisbecker
2013-08-16 16:02 ` Oleg Nesterov
2013-08-16 16:20 ` Frederic Weisbecker
2013-08-16 16:26 ` Oleg Nesterov
2013-08-16 16:46 ` Frederic Weisbecker
2013-08-16 16:49 ` Oleg Nesterov
2013-08-16 17:12 ` Frederic Weisbecker
2013-08-18 16:36 ` Oleg Nesterov
2013-08-18 21:25 ` Frederic Weisbecker
2013-08-19 10:58 ` Peter Zijlstra
2013-08-19 15:44 ` Arjan van de Ven
2013-08-19 15:47 ` Arjan van de Ven
2013-08-19 11:10 ` Peter Zijlstra
2013-08-19 11:15 ` Peter Zijlstra
2013-08-20 6:59 ` Fernando Luis Vázquez Cao
2013-08-20 8:44 ` Peter Zijlstra
2013-08-20 15:29 ` Frederic Weisbecker
2013-08-20 15:33 ` Arjan van de Ven
2013-08-20 15:35 ` Frederic Weisbecker
2013-08-20 15:41 ` Arjan van de Ven
2013-08-20 15:31 ` Arjan van de Ven
2013-08-20 16:01 ` Peter Zijlstra
2013-08-20 16:33 ` Oleg Nesterov
2013-08-20 17:54 ` Peter Zijlstra
2013-08-20 18:25 ` Oleg Nesterov
2013-08-21 8:31 ` Peter Zijlstra
2013-08-21 11:35 ` Oleg Nesterov
2013-08-21 12:33 ` Peter Zijlstra
2013-08-21 14:23 ` Peter Zijlstra
2013-08-21 16:41 ` Oleg Nesterov
2013-10-01 14:05 ` Frederic Weisbecker
2013-10-01 14:26 ` Frederic Weisbecker
2013-10-01 14:27 ` Frederic Weisbecker
2013-10-01 14:49 ` Frederic Weisbecker
2013-10-01 15:00 ` Peter Zijlstra
2013-10-01 15:21 ` Frederic Weisbecker
2013-10-01 15:56 ` Peter Zijlstra
2013-10-01 16:47 ` Frederic Weisbecker
2013-10-01 16:59 ` Peter Zijlstra
2013-10-02 12:45 ` Frederic Weisbecker
2013-10-02 12:50 ` Peter Zijlstra
2013-10-02 14:35 ` Arjan van de Ven
2013-10-02 16:01 ` Frederic Weisbecker
2013-08-21 12:48 ` Peter Zijlstra [this message]
2013-08-21 17:09 ` Oleg Nesterov
2013-08-21 18:31 ` Peter Zijlstra
2013-08-21 18:32 ` Oleg Nesterov
2013-08-20 22:18 ` Frederic Weisbecker
2013-08-21 11:49 ` Oleg Nesterov
2013-08-20 6:21 ` Fernando Luis Vázquez Cao
2013-08-20 21:55 ` Frederic Weisbecker
2013-08-16 16:32 ` Frederic Weisbecker
2013-08-16 16:33 ` Oleg Nesterov
2013-08-16 16:49 ` Frederic Weisbecker
2013-08-16 16:37 ` Frederic Weisbecker
2013-08-18 16:54 ` Oleg Nesterov
2013-08-18 21:40 ` Frederic Weisbecker
2013-08-16 15:42 ` [PATCH 3/4] nohz: Consolidate sleep time stats read code Frederic Weisbecker
2013-08-18 17:00 ` Oleg Nesterov
2013-08-18 21:47 ` Frederic Weisbecker
2013-08-16 15:42 ` [PATCH 4/4] nohz: Convert a few places to use local per cpu accesses Frederic Weisbecker
2013-08-16 16:00 ` Peter Zijlstra
2013-08-16 16:12 ` Frederic Weisbecker
2013-08-16 16:19 ` Oleg Nesterov
2013-08-16 16:34 ` Frederic Weisbecker
2013-08-20 18:15 ` [PATCH RESEND 0/4] nohz: Fix racy sleeptime stats Oleg Nesterov
2013-08-21 8:28 ` Peter Zijlstra
2013-08-21 11:42 ` Oleg Nesterov
-- strict thread matches above, loose matches on Subject: below --
2014-05-07 13:41 [PATCH 1/4] nohz: Only update sleeptime stats locally Denys Vlasenko
2014-05-07 13:41 ` [PATCH 2/4] nohz: Synchronize sleep time stats with seqlock Denys Vlasenko
2014-04-24 18:45 [PATCH 1/4] nohz: Only update sleeptime stats locally Denys Vlasenko
2014-04-24 18:45 ` [PATCH 2/4] nohz: Synchronize sleep time stats with seqlock Denys Vlasenko
2013-08-09 0:54 [PATCH 0/4] nohz: Fix racy sleeptime stats Frederic Weisbecker
2013-08-09 0:54 ` [PATCH 2/4] nohz: Synchronize sleep time stats with seqlock Frederic Weisbecker
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=20130821124849.GB31370@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=arjan@linux.intel.com \
--cc=fernando_b1@lab.ntt.co.jp \
--cc=fweisbec@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=penguin-kernel@I-love.SAKURA.ne.jp \
--cc=tglx@linutronix.de \
/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
all inboxes | Powered by JetHome®