From: Oleg Nesterov <oleg@tv-sign.ru>
To: Ravikiran G Thirumalai <kiran@scalex86.org>
Cc: Christoph Lameter <clameter@engr.sgi.com>,
Shai Fultheim <shai@scalex86.org>,
Nippun Goel <nippung@calsoftinc.com>,
linux-kernel@vger.kernel.org, Andrew Morton <akpm@osdl.org>
Subject: Re: [rfc][patch] Avoid taking global tasklist_lock for single threadedprocess at getrusage()
Date: Fri, 30 Dec 2005 20:57:41 +0300 [thread overview]
Message-ID: <43B57515.967F53E3@tv-sign.ru> (raw)
In-Reply-To: 20051228225752.GB3755@localhost.localdomain
> Ravikiran G Thirumalai wrote:
>
> Following patch avoids taking the global tasklist_lock when possible,
> if a process is single threaded during getrusage(). Any avoidance of
> tasklist_lock is good for NUMA boxes (and possibly for large SMPs).
> --- arch/mips/kernel/irixsig.c.orig 2005-12-27 14:49:57.000000000 -0800
> +++ arch/mips/kernel/irixsig.c 2005-12-27 14:52:47.000000000 -0800
> @@ -540,7 +540,7 @@ out:
> #define IRIX_P_PGID 2
> #define IRIX_P_ALL 7
>
> -extern int getrusage(struct task_struct *, int, struct rusage __user *);
> +extern int getrusage_both(struct task_struct *, struct rusage __user *);
I think it's better sense to move this declaration to include/.
> -static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
> +int getrusage_children(struct rusage __user *ru)
> {
> - struct task_struct *t;
> unsigned long flags;
> + int lockflag = 0;
> cputime_t utime, stime;
> + struct task_struct *p = current;
> + struct rusage r;
> + memset((char *) &r, 0, sizeof (r));
>
> - memset((char *) r, 0, sizeof *r);
> + if (!thread_group_empty(p)) {
> + read_lock(&tasklist_lock);
> + if (unlikely(!p->signal)) {
> + read_unlock(&tasklist_lock);
> + goto ret;
Is this possible? 'current' always has valid signal/sighand.
Or better say, process can't call getrusage after exit_signal().
> + }
> + spin_lock_irqsave(&p->sighand->siglock, flags);
> + lockflag = 1;
> + }
What if another thread just exited? I think you need 'else smp_rmb()'.
here. Otherwise cpu can read signal->c* out of order.
> +int getrusage_self(struct rusage __user *ru)
Same comments.
> +int getrusage_both(struct task_struct *p, struct rusage __user *ru)
> {
> + unsigned long flags;
> + cputime_t utime, stime;
> struct rusage r;
> + struct task_struct *t;
> + memset((char *) &r, 0, sizeof (r));
> +
> read_lock(&tasklist_lock);
> - k_getrusage(p, who, &r);
> + if (unlikely(!p->signal)) {
> + read_unlock(&tasklist_lock);
> + goto ret;
> + }
> +
> + spin_lock_irqsave(&p->sighand->siglock, flags);
> + utime = p->signal->cutime;
> + stime = p->signal->cstime;
> + r.ru_nvcsw = p->signal->cnvcsw;
> + r.ru_nivcsw = p->signal->cnivcsw;
> + r.ru_minflt = p->signal->cmin_flt;
> + r.ru_majflt = p->signal->cmaj_flt;
> + spin_unlock_irqrestore(&p->sighand->siglock, flags);
> +
> + utime = cputime_add(utime, p->signal->utime);
> + stime = cputime_add(stime, p->signal->stime);
> + r.ru_nvcsw += p->signal->nvcsw;
> + r.ru_nivcsw += p->signal->nivcsw;
> + r.ru_minflt += p->signal->min_flt;
> + r.ru_majflt += p->signal->maj_flt;
> +
> + t = p;
> + do {
> + utime = cputime_add(utime, t->utime);
> + stime = cputime_add(stime, t->stime);
> + r.ru_nvcsw += t->nvcsw;
> + r.ru_nivcsw += t->nivcsw;
> + r.ru_minflt += t->min_flt;
> + r.ru_majflt += t->maj_flt;
> + t = next_thread(t);
> + } while (t != p);
> +
> read_unlock(&tasklist_lock);
> + cputime_to_timeval(utime, &r.ru_utime);
> + cputime_to_timeval(stime, &r.ru_stime);
> +
> +ret:
> return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
> }
Looks we can factor out some code.
Actually I dont't understand why can't we move the locking into
k_getrusage,
k_getrusage()
lock_flag = (p == current && thread_group_empty(p));
if (lockflag) {
read_lock(&tasklist_lock);
spin_lock_irqsave(&p->sighand->siglock, flags);
}
and remove ->sighand locking under 'switch' statement.
Isn't this enough to solve perfomance problems?
Oleg.
next prev parent reply other threads:[~2005-12-30 16:42 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-24 17:52 [rfc][patch] Avoid taking global tasklist_lock for single threaded process at getrusage() Oleg Nesterov
2005-12-27 20:21 ` Christoph Lameter
2005-12-28 12:38 ` [rfc][patch] Avoid taking global tasklist_lock for single threadedprocess " Oleg Nesterov
2005-12-28 18:33 ` Ravikiran G Thirumalai
2005-12-28 22:57 ` Ravikiran G Thirumalai
2005-12-30 17:57 ` Oleg Nesterov [this message]
2006-01-04 23:16 ` Ravikiran G Thirumalai
2006-01-05 19:17 ` Oleg Nesterov
2006-01-06 9:46 ` Ravikiran G Thirumalai
2006-01-06 17:23 ` Christoph Lameter
2006-01-06 19:46 ` Ravikiran G Thirumalai
2006-03-20 18:04 ` Oleg Nesterov
2006-03-22 22:18 ` Ravikiran G Thirumalai
2006-03-23 18:18 ` Oleg Nesterov
2006-01-06 23:52 ` Andrew Morton
2006-01-08 11:49 ` Oleg Nesterov
2006-01-08 19:58 ` Ravikiran G Thirumalai
2006-01-09 18:55 ` Oleg Nesterov
2006-01-09 20:54 ` Ravikiran G Thirumalai
2006-01-10 19:03 ` Oleg Nesterov
2006-01-16 20:56 ` Ravikiran G Thirumalai
2006-01-17 19:59 ` Oleg Nesterov
2006-01-17 19:52 ` Ravikiran G Thirumalai
2006-01-18 9:17 ` Oleg Nesterov
2006-01-03 18:18 ` Christoph Lameter
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=43B57515.967F53E3@tv-sign.ru \
--to=oleg@tv-sign.ru \
--cc=akpm@osdl.org \
--cc=clameter@engr.sgi.com \
--cc=kiran@scalex86.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nippung@calsoftinc.com \
--cc=shai@scalex86.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
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 NNTP newsgroup(s).