From: Ingo Molnar <mingo@kernel.org>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Alex Shi <alex.shi@linaro.org>, Andi Kleen <andi@firstfloor.org>,
Michel Lespinasse <walken@google.com>,
Davidlohr Bueso <davidlohr.bueso@hp.com>,
Matthew R Wilcox <matthew.r.wilcox@intel.com>,
Dave Hansen <dave.hansen@intel.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Rik van Riel <riel@redhat.com>,
Peter Hurley <peter@hurleysoftware.com>,
linux-kernel@vger.kernel.org, linux-mm <linux-mm@kvack.org>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH v6 6/6] rwsem: do optimistic spinning for writer lock acquisition
Date: Thu, 26 Sep 2013 08:53:35 +0200 [thread overview]
Message-ID: <20130926065335.GC19090@gmail.com> (raw)
In-Reply-To: <1380147051.3467.68.camel@schen9-DESK>
* Tim Chen <tim.c.chen@linux.intel.com> wrote:
> We want to add optimistic spinning to rwsems because
> the writer rwsem does not perform as well as mutexes. Tim noticed that
> for exim (mail server) workloads, when reverting commit 4fc3f1d6 and
> Davidlohr noticed it when converting the i_mmap_mutex to a rwsem in some
> aim7 workloads. We've noticed that the biggest difference
> is when we fail to acquire a mutex in the fastpath, optimistic spinning
> comes in to play and we can avoid a large amount of unnecessary sleeping
> and overhead of moving tasks in and out of wait queue.
>
> Allowing optimistic spinning before putting the writer on the wait queue
> reduces wait queue contention and provided greater chance for the rwsem
> to get acquired. With these changes, rwsem is on par with mutex.
>
> Reviewed-by: Ingo Molnar <mingo@elte.hu>
> Reviewed-by: Peter Zijlstra <peterz@infradead.org>
> Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
> Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
> ---
> include/linux/rwsem.h | 6 +-
> kernel/rwsem.c | 19 +++++-
> lib/rwsem.c | 203 ++++++++++++++++++++++++++++++++++++++++++++-----
> 3 files changed, 207 insertions(+), 21 deletions(-)
>
> diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
> index 0616ffe..ef5a83a 100644
> --- a/include/linux/rwsem.h
> +++ b/include/linux/rwsem.h
> @@ -26,6 +26,8 @@ struct rw_semaphore {
> long count;
> raw_spinlock_t wait_lock;
> struct list_head wait_list;
> + struct task_struct *owner; /* write owner */
> + void *spin_mlock;
> +#define MLOCK(rwsem) ((struct mcs_spin_node **)&((rwsem)->spin_mlock))
> + mcs_spin_lock(MLOCK(sem), &node);
> + mcs_spin_unlock(MLOCK(sem), &node);
> + mcs_spin_unlock(MLOCK(sem), &node);
> + mcs_spin_unlock(MLOCK(sem), &node);
That forced type casting is ugly and fragile.
To avoid having to include mcslock.h into rwsem.h just add a forward
struct declaration, before the struct rw_semaphore definition:
struct mcs_spin_node;
Then define spin_mlock with the right type:
struct mcs_spin_node *spin_mlock;
I'd also suggest renaming 'spin_mlock', to reduce unnecessary variants. If
the lock type name is 'struct mcs_spin_node' then 'mcs_lock' would be a
perfect field name, right?
While at it, renaming mcs_spin_node to mcs_spinlock might be wise as well,
and the include file would be named mcs_spinlock.h.
Thanks,
Ingo
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Ingo Molnar <mingo@kernel.org>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Alex Shi <alex.shi@linaro.org>, Andi Kleen <andi@firstfloor.org>,
Michel Lespinasse <walken@google.com>,
Davidlohr Bueso <davidlohr.bueso@hp.com>,
Matthew R Wilcox <matthew.r.wilcox@intel.com>,
Dave Hansen <dave.hansen@intel.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Rik van Riel <riel@redhat.com>,
Peter Hurley <peter@hurleysoftware.com>,
linux-kernel@vger.kernel.org, linux-mm <linux-mm@kvack.org>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH v6 6/6] rwsem: do optimistic spinning for writer lock acquisition
Date: Thu, 26 Sep 2013 08:53:35 +0200 [thread overview]
Message-ID: <20130926065335.GC19090@gmail.com> (raw)
In-Reply-To: <1380147051.3467.68.camel@schen9-DESK>
* Tim Chen <tim.c.chen@linux.intel.com> wrote:
> We want to add optimistic spinning to rwsems because
> the writer rwsem does not perform as well as mutexes. Tim noticed that
> for exim (mail server) workloads, when reverting commit 4fc3f1d6 and
> Davidlohr noticed it when converting the i_mmap_mutex to a rwsem in some
> aim7 workloads. We've noticed that the biggest difference
> is when we fail to acquire a mutex in the fastpath, optimistic spinning
> comes in to play and we can avoid a large amount of unnecessary sleeping
> and overhead of moving tasks in and out of wait queue.
>
> Allowing optimistic spinning before putting the writer on the wait queue
> reduces wait queue contention and provided greater chance for the rwsem
> to get acquired. With these changes, rwsem is on par with mutex.
>
> Reviewed-by: Ingo Molnar <mingo@elte.hu>
> Reviewed-by: Peter Zijlstra <peterz@infradead.org>
> Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
> Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
> ---
> include/linux/rwsem.h | 6 +-
> kernel/rwsem.c | 19 +++++-
> lib/rwsem.c | 203 ++++++++++++++++++++++++++++++++++++++++++++-----
> 3 files changed, 207 insertions(+), 21 deletions(-)
>
> diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
> index 0616ffe..ef5a83a 100644
> --- a/include/linux/rwsem.h
> +++ b/include/linux/rwsem.h
> @@ -26,6 +26,8 @@ struct rw_semaphore {
> long count;
> raw_spinlock_t wait_lock;
> struct list_head wait_list;
> + struct task_struct *owner; /* write owner */
> + void *spin_mlock;
> +#define MLOCK(rwsem) ((struct mcs_spin_node **)&((rwsem)->spin_mlock))
> + mcs_spin_lock(MLOCK(sem), &node);
> + mcs_spin_unlock(MLOCK(sem), &node);
> + mcs_spin_unlock(MLOCK(sem), &node);
> + mcs_spin_unlock(MLOCK(sem), &node);
That forced type casting is ugly and fragile.
To avoid having to include mcslock.h into rwsem.h just add a forward
struct declaration, before the struct rw_semaphore definition:
struct mcs_spin_node;
Then define spin_mlock with the right type:
struct mcs_spin_node *spin_mlock;
I'd also suggest renaming 'spin_mlock', to reduce unnecessary variants. If
the lock type name is 'struct mcs_spin_node' then 'mcs_lock' would be a
perfect field name, right?
While at it, renaming mcs_spin_node to mcs_spinlock might be wise as well,
and the include file would be named mcs_spinlock.h.
Thanks,
Ingo
next prev parent reply other threads:[~2013-09-26 6:53 UTC|newest]
Thread overview: 129+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <cover.1380144003.git.tim.c.chen@linux.intel.com>
2013-09-25 22:10 ` [PATCH v6 0/6] rwsem: performance optimizations Tim Chen
2013-09-25 22:10 ` Tim Chen
2013-09-25 22:10 ` [PATCH v6 1/6] rwsem: check the lock before cpmxchg in down_write_trylock Tim Chen
2013-09-25 22:10 ` Tim Chen
2013-09-25 22:10 ` [PATCH v6 2/6] rwsem: remove 'out' label in do_wake Tim Chen
2013-09-25 22:10 ` Tim Chen
2013-09-25 22:10 ` [PATCH v6 3/6] rwsem: remove try_reader_grant label do_wake Tim Chen
2013-09-25 22:10 ` Tim Chen
2013-09-25 22:10 ` [PATCH v6 4/6] rwsem/wake: check lock before do atomic update Tim Chen
2013-09-25 22:10 ` Tim Chen
2013-09-25 22:10 ` [PATCH v6 5/6] MCS Lock: Restructure the MCS lock defines and locking code into its own file Tim Chen
2013-09-25 22:10 ` Tim Chen
2013-09-26 6:46 ` Ingo Molnar
2013-09-26 6:46 ` Ingo Molnar
2013-09-26 8:40 ` Peter Zijlstra
2013-09-26 8:40 ` Peter Zijlstra
2013-09-26 9:37 ` Ingo Molnar
2013-09-26 9:37 ` Ingo Molnar
2013-09-26 18:18 ` Tim Chen
2013-09-26 18:18 ` Tim Chen
2013-09-26 19:27 ` Jason Low
2013-09-26 19:27 ` Jason Low
2013-09-26 20:06 ` Davidlohr Bueso
2013-09-26 20:06 ` Davidlohr Bueso
2013-09-26 20:23 ` Jason Low
2013-09-26 20:23 ` Jason Low
2013-09-26 20:40 ` Davidlohr Bueso
2013-09-26 20:40 ` Davidlohr Bueso
2013-09-26 21:09 ` Jason Low
2013-09-26 21:09 ` Jason Low
2013-09-26 21:41 ` Tim Chen
2013-09-26 21:41 ` Tim Chen
2013-09-26 22:42 ` Jason Low
2013-09-26 22:42 ` Jason Low
2013-09-26 22:57 ` Tim Chen
2013-09-26 22:57 ` Tim Chen
2013-09-27 6:02 ` Ingo Molnar
2013-09-27 6:02 ` Ingo Molnar
2013-09-27 6:26 ` Jason Low
2013-09-27 6:26 ` Jason Low
2013-09-27 11:23 ` Peter Zijlstra
2013-09-27 11:23 ` Peter Zijlstra
2013-09-27 13:44 ` Joe Perches
2013-09-27 13:44 ` Joe Perches
2013-09-27 13:48 ` Peter Zijlstra
2013-09-27 13:48 ` Peter Zijlstra
2013-09-27 14:05 ` Joe Perches
2013-09-27 14:05 ` Joe Perches
2013-09-27 14:18 ` Peter Zijlstra
2013-09-27 14:18 ` Peter Zijlstra
2013-09-27 14:14 ` [PATCH] checkpatch: Make the memory barrier test noisier Joe Perches
2013-09-27 14:14 ` Joe Perches
2013-09-27 14:26 ` Peter Zijlstra
2013-09-27 14:26 ` Peter Zijlstra
2013-09-27 14:34 ` Joe Perches
2013-09-27 14:34 ` Joe Perches
2013-09-27 14:50 ` Peter Zijlstra
2013-09-27 14:50 ` Peter Zijlstra
2013-09-27 15:17 ` Paul E. McKenney
2013-09-27 15:17 ` Paul E. McKenney
2013-09-27 15:34 ` Peter Zijlstra
2013-09-27 15:34 ` Peter Zijlstra
2013-09-27 16:04 ` Paul E. McKenney
2013-09-27 16:04 ` Paul E. McKenney
2013-09-27 16:04 ` Paul E. McKenney
2013-09-27 23:40 ` Oliver Neukum
2013-09-27 23:40 ` Oliver Neukum
2013-09-28 7:54 ` Peter Zijlstra
2013-09-28 7:54 ` Peter Zijlstra
2013-09-27 16:12 ` [PATCH v6 5/6] MCS Lock: Restructure the MCS lock defines and locking code into its own file Jason Low
2013-09-27 16:12 ` Jason Low
2013-09-27 16:19 ` Tim Chen
2013-09-27 16:19 ` Tim Chen
2013-10-02 19:19 ` Waiman Long
2013-10-02 19:19 ` Waiman Long
2013-10-02 19:30 ` Jason Low
2013-10-02 19:30 ` Jason Low
2013-10-02 19:37 ` Waiman Long
2013-10-02 19:37 ` Waiman Long
2013-09-26 22:22 ` Davidlohr Bueso
2013-09-26 22:22 ` Davidlohr Bueso
2013-09-27 15:29 ` Paul E. McKenney
2013-09-27 15:29 ` Paul E. McKenney
2013-09-27 18:09 ` Tim Chen
2013-09-27 18:09 ` Tim Chen
2013-09-28 2:58 ` Waiman Long
2013-09-28 2:58 ` Waiman Long
2013-09-27 19:38 ` Tim Chen
2013-09-27 19:38 ` Tim Chen
2013-09-27 20:16 ` Jason Low
2013-09-27 20:16 ` Jason Low
2013-09-27 20:38 ` Paul E. McKenney
2013-09-27 20:38 ` Paul E. McKenney
2013-09-27 22:46 ` Tim Chen
2013-09-27 22:46 ` Tim Chen
2013-09-27 23:01 ` Paul E. McKenney
2013-09-27 23:01 ` Paul E. McKenney
2013-09-27 23:54 ` Jason Low
2013-09-27 23:54 ` Jason Low
2013-09-28 0:02 ` Davidlohr Bueso
2013-09-28 0:02 ` Davidlohr Bueso
2013-09-28 2:19 ` Paul E. McKenney
2013-09-28 2:19 ` Paul E. McKenney
2013-09-28 4:34 ` Jason Low
2013-09-28 4:34 ` Jason Low
2013-09-30 15:51 ` Waiman Long
2013-09-30 15:51 ` Waiman Long
2013-09-30 16:10 ` Jason Low
2013-09-30 16:10 ` Jason Low
2013-09-30 16:36 ` Waiman Long
2013-09-30 16:36 ` Waiman Long
2013-10-01 16:48 ` Tim Chen
2013-10-01 16:48 ` Tim Chen
2013-10-01 20:01 ` Waiman Long
2013-10-01 20:01 ` Waiman Long
2013-10-01 21:16 ` Tim Chen
2013-10-01 21:16 ` Tim Chen
2013-10-02 1:25 ` Waiman Long
2013-10-02 1:25 ` Waiman Long
2013-10-02 18:43 ` Tim Chen
2013-10-02 18:43 ` Tim Chen
2013-10-02 19:32 ` Waiman Long
2013-10-02 19:32 ` Waiman Long
2013-09-30 16:28 ` Tim Chen
2013-09-30 16:28 ` Tim Chen
2013-09-25 22:10 ` [PATCH v6 6/6] rwsem: do optimistic spinning for writer lock acquisition Tim Chen
2013-09-25 22:10 ` Tim Chen
2013-09-26 6:53 ` Ingo Molnar [this message]
2013-09-26 6:53 ` Ingo Molnar
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=20130926065335.GC19090@gmail.com \
--to=mingo@kernel.org \
--cc=a.p.zijlstra@chello.nl \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=alex.shi@linaro.org \
--cc=andi@firstfloor.org \
--cc=dave.hansen@intel.com \
--cc=davidlohr.bueso@hp.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=matthew.r.wilcox@intel.com \
--cc=mingo@elte.hu \
--cc=peter@hurleysoftware.com \
--cc=riel@redhat.com \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
--cc=walken@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.