From: Adhemerval Zanella <adhemerval.zanella@linaro.org>
To: Wangyang Guo <wangyang.guo@intel.com>, libc-alpha@sourceware.org
Subject: Re: [PATCH v2] nptl: Add backoff mechanism to spinlock loop
Date: Wed, 30 Mar 2022 08:53:43 -0300 [thread overview]
Message-ID: <97b1105f-42e8-a347-f82e-c81e548f0c2f@linaro.org> (raw)
In-Reply-To: <20220328084705.468207-1-wangyang.guo@intel.com>
On 28/03/2022 05:47, Wangyang Guo via Libc-alpha wrote:
> When mutiple threads waiting for lock at the same time, once lock owner
> releases the lock, waiters will see lock available and all try to lock,
> which may cause an expensive CAS storm.
>
> Binary exponential backoff with random jitter is introduced. As try-lock
> attempt increases, there is more likely that a larger number threads
> compete for adaptive mutex lock, so increase wait time in exponential.
> A random jitter is also added to avoid synchronous try-lock from other
> threads.
>
> v2: Remove read-check before try-lock for performance.
>
> Signed-off-by: Wangyang Guo <wangyang.guo@intel.com>
> ---
> nptl/pthread_mutex_lock.c | 25 ++++++++++++++++---------
> 1 file changed, 16 insertions(+), 9 deletions(-)
>
> diff --git a/nptl/pthread_mutex_lock.c b/nptl/pthread_mutex_lock.c
> index d2e652d151..7e75ec1cba 100644
> --- a/nptl/pthread_mutex_lock.c
> +++ b/nptl/pthread_mutex_lock.c
> @@ -26,6 +26,7 @@
> #include <futex-internal.h>
> #include <stap-probe.h>
> #include <shlib-compat.h>
> +#include <random-bits.h>
>
> /* Some of the following definitions differ when pthread_mutex_cond_lock.c
> includes this file. */
> @@ -64,11 +65,6 @@ lll_mutex_lock_optimized (pthread_mutex_t *mutex)
> # define PTHREAD_MUTEX_VERSIONS 1
> #endif
>
> -#ifndef LLL_MUTEX_READ_LOCK
> -# define LLL_MUTEX_READ_LOCK(mutex) \
> - atomic_load_relaxed (&(mutex)->__data.__lock)
> -#endif
> -
> static int __pthread_mutex_lock_full (pthread_mutex_t *mutex)
> __attribute_noinline__;
>
> @@ -138,17 +134,28 @@ PTHREAD_MUTEX_LOCK (pthread_mutex_t *mutex)
> int cnt = 0;
> int max_cnt = MIN (max_adaptive_count (),
> mutex->__data.__spins * 2 + 10);
> + int spin_count, exp_backoff = 1;
> + unsigned int jitter = random_bits ();
This will issue a syscall for architectures that do not have clock_gettime
on vDSO, which is a performance regression. You will need to move the
jitter setup to be arch-specific, where the generic interface setting
no random jitter.
> do
> {
> - if (cnt++ >= max_cnt)
> + /* In each loop, spin count is exponential backoff plus
> + random jitter, random range is [0, exp_backoff-1]. */
> + spin_count = exp_backoff + (jitter & (exp_backoff - 1));
> + cnt += spin_count;
> + if (cnt >= max_cnt)
> {
> + /* If cnt exceeds max spin count, just go to wait
> + queue. */
> LLL_MUTEX_LOCK (mutex);
> break;
> }
> - atomic_spin_nop ();
> + do
> + atomic_spin_nop ();
> + while (--spin_count > 0);
> + /* Binary exponential backoff, prepare for next loop. */
> + exp_backoff <<= 1;
> }
> - while (LLL_MUTEX_READ_LOCK (mutex) != 0
> - || LLL_MUTEX_TRYLOCK (mutex) != 0);
> + while (LLL_MUTEX_TRYLOCK (mutex) != 0);
>
> mutex->__data.__spins += (cnt - mutex->__data.__spins) / 8;
> }
next prev parent reply other threads:[~2022-03-30 11:53 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-28 8:47 Wangyang Guo
2022-03-28 16:41 ` Noah Goldstein
2022-03-30 11:44 ` Guo, Wangyang
2022-03-30 19:39 ` Noah Goldstein
2022-03-30 11:53 ` Adhemerval Zanella [this message]
2022-03-30 17:07 ` Noah Goldstein
2022-03-30 17:21 ` Adhemerval Zanella
2022-04-12 11:53 ` Florian Weimer
2022-04-22 13:30 ` Yann Droneaud
2022-04-22 13:32 ` Florian Weimer
2022-04-22 13:35 ` Cristian Rodríguez
2022-04-22 15:25 ` Noah Goldstein
2022-04-26 12:25 ` Florian Weimer
2022-04-26 12:42 ` Yann Droneaud
2022-05-04 2:50 ` [PATCH v3] " Wangyang Guo
2022-05-04 2:58 ` Wangyang Guo
2022-05-04 3:17 ` [PATCH v4] " Wangyang Guo
2022-05-05 1:56 ` H.J. Lu
2022-05-05 2:52 ` Noah Goldstein
2022-05-05 2:59 ` Guo, Wangyang
2022-05-05 22:44 ` H.J. Lu
2022-05-06 1:52 ` Guo, Wangyang
2022-05-06 1:50 ` [PATCH v5] " Wangyang Guo
2022-05-06 3:06 ` H.J. Lu
2022-09-11 20:29 ` Sunil Pandey
2022-09-14 1:26 ` Noah Goldstein
2022-09-29 0:12 ` Noah Goldstein
2022-09-30 13:18 ` FUCKETY FUCK FUCK, PLEASE REMOVE ME FROM THESE EMAILS Darren Tristano
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=97b1105f-42e8-a347-f82e-c81e548f0c2f@linaro.org \
--to=adhemerval.zanella@linaro.org \
--cc=libc-alpha@sourceware.org \
--cc=wangyang.guo@intel.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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).