linux-kernel - Re: [PATCH] cpuacct: VIRT_CPU_ACCOUNTING don't prevent percpu cputime count

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 29 Apr 2009 15:08:34 +0900 (JST)
From:	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To:	balbir@...ux.vnet.ibm.com
Cc:	kosaki.motohiro@...fujitsu.com,
	LKML <linux-kernel@...r.kernel.org>,
	Bharata B Rao <bharata@...ux.vnet.ibm.com>,
	Balaji Rao <balajirrao@...il.com>,
	Dhaval Giani <dhaval@...ux.vnet.ibm.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Ingo Molnar <mingo@...e.hu>,
	Martin Schwidefsky <schwidefsky@...ibm.com>,
	seto.hidetoshi@...fujitsu.com
Subject: Re: [PATCH] cpuacct: VIRT_CPU_ACCOUNTING don't prevent percpu cputime count

> > > This will make the end result very off the real value due to large
> > > batch value per cpu. If we are going to go this route, we should
> > > probably consider using __percpu_counter_sum so that the batch value
> > > does not show data that is way off.
> > 
> > No problem.
> > 
> > end-user don't see cputime itself. they see converted time.
> > cpuacct_stats_show() use cputime64_to_clock_t. it mean
> > the value less than 10msec don't display.
> >
> 
> Yes, I know, I reviewed Bharata's patch and suggested converting to
> clock_t for consistency with other metrics.

Oh, sorry.
I didn't know this.


> > --------------------------------------------------------
> > static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
> >                 struct cgroup_map_cb *cb)
> > {
> >         struct cpuacct *ca = cgroup_ca(cgrp);
> >         int i;
> > 
> >         for (i = 0; i < CPUACCT_STAT_NSTATS; i++) {
> >                 s64 val = percpu_counter_read(&ca->cpustat[i]);
> 
> My point is, this should probably be percpu_counter_sum(), but that
> can be expensive and we were willing to tollerate some inaccuracy due
> to batch value, I think your patch adds to the inaccuracy even more,
> even though it fixes a genuine problem.

Not expensive.
cpuacct_stats_show() is only called when reading stat file.
it definitely slow-path.
I think we can use percpu_counter_sum().

However, I doubt its worth.

before my patch:
  VIRT_CPU_ACCOUNTING=y:  accuracy but slow
  VIRT_CPU_ACCOUNTING=n:  inaccuracy few tick but fast

my patch
  VIRT_CPU_ACCOUNTING=y:  inaccuracy few tick but fast
  VIRT_CPU_ACCOUNTING=n:  inaccuracy few tick but fast

if my inaccuracy is wrong, current code is also crap when VIRT_CPU_ACCOUNTING=n.
I only make const accuracy to VIRT_CPU_ACCOUNTING=y and n.

Thought?
Although you still think percpu_counter_sum() is better, I can do it.


> 
> 
> >                 val = cputime64_to_clock_t(val);
> >                 cb->fill(cb, cpuacct_stat_desc[i], val);
> >         }
> >         return 0;
> > }
> > --------------------------------------------------------


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/