From: Peter Zijlstra <peterz@infradead.org>
To: Stephane Eranian <eranian@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
"mingo@elte.hu" <mingo@elte.hu>,
"ak@linux.intel.com" <ak@linux.intel.com>,
Jiri Olsa <jolsa@redhat.com>, "Liang, Kan" <kan.liang@intel.com>,
Borislav Petkov <bp@alien8.de>,
Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Subject: Re: [PATCH v2 0/12] perf/x86: implement HT leak workaround for SNB/IVB/HSW
Date: Wed, 22 Oct 2014 11:12:39 +0200 [thread overview]
Message-ID: <20141022091239.GG12706@worktop.programming.kicks-ass.net> (raw)
In-Reply-To: <CABPqkBQuf_W1X_VbVzLhKbv6AZwKE3YyHGpT=cRFNBEak5wz_Q@mail.gmail.com>
On Tue, Oct 21, 2014 at 03:08:32PM +0200, Stephane Eranian wrote:
> On Tue, Oct 21, 2014 at 3:03 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> > On Tue, Oct 21, 2014 at 02:28:06PM +0200, Stephane Eranian wrote:
> >> Peter,
> >>
> >> On Tue, Oct 21, 2014 at 1:25 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> >> >
> >> >
> >> > lkml.kernel.org/r/CABPqkBRbst4sgpgE5O_VXt-CSC0VD=aP2KWA0e3Uy64tw7df3A@mail.gmail.com
> >> >
> >> > I missed that 3 lines if they were in here.
> >> >
> >> I did not put them in there because there is another problem.
> >> If you partition the generic counters 2 and 2, then some CPUs will not
> >> be able to measure some events.
> >> Unfortunately, there is no way to partition the 4 counters such that
> >> all the events can be measured by
> >> each CPU. Some events or precise sampling requires counter 2 for
> >> instance (like prec_dist).
> >> That's why I did not put this fix in.
> >
> > Ah, I wasn't thinking about a hard partition, just a limit on the number
> > of exclusive counters any one CPU can claim such as to not starve. Or is
> > that what you were talking about? I feel not being able to starve
> > another CPU is more important than a better utilization bound for
> > counter scheduling.
>
> So you're saying, just limit number of used counters to 2 regardless
> of which one they are.
used as in marked exclusive and forced empty on the other side.
> So sometimes, this will avoid the problem aforementioned and sometimes
> not. We can try that.
How will this sometimes not avoid the starvation issue?
next prev parent reply other threads:[~2014-10-22 9:12 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-09 16:34 [PATCH v2 0/12] perf/x86: implement HT leak workaround for SNB/IVB/HSW Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 01/12] perf,x86: rename er_flags to flags Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 02/12] perf/x86: vectorize cpuc->kfree_on_online Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 03/12] perf/x86: add 3 new scheduling callbacks Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 04/12] perf/x86: add index param to get_event_constraint() callback Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 05/12] perf/x86: add cross-HT counter exclusion infrastructure Stephane Eranian
2014-10-21 11:17 ` Peter Zijlstra
2014-10-21 11:18 ` Peter Zijlstra
2014-10-22 15:07 ` Jiri Olsa
2014-10-22 17:25 ` Stephane Eranian
2014-10-23 7:14 ` Jiri Olsa
2014-10-09 16:34 ` [PATCH v2 06/12] perf/x86: implement cross-HT corruption bug workaround Stephane Eranian
2014-10-22 12:31 ` Jiri Olsa
2014-10-23 7:19 ` Jiri Olsa
2014-10-23 8:01 ` Stephane Eranian
2014-10-23 8:13 ` Jiri Olsa
2014-10-09 16:34 ` [PATCH v2 07/12] perf/x86: enforce HT bug workaround for SNB/IVB/HSW Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 08/12] perf/x86: enforce HT bug workaround with PEBS " Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 09/12] perf/x86: fix intel_get_event_constraints() for dynamic constraints Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 10/12] watchdog: add watchdog enable/disable all functions Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 11/12] perf/x86: make HT bug workaround conditioned on HT enabled Stephane Eranian
2014-10-22 13:27 ` Jiri Olsa
2014-10-22 14:36 ` Stephane Eranian
2014-10-22 14:58 ` Jiri Olsa
2014-10-22 16:42 ` Stephane Eranian
2014-10-09 16:34 ` [PATCH v2 12/12] perf/x86: add syfs entry to disable HT bug workaround Stephane Eranian
2014-10-21 11:25 ` [PATCH v2 0/12] perf/x86: implement HT leak workaround for SNB/IVB/HSW Peter Zijlstra
2014-10-21 12:28 ` Stephane Eranian
2014-10-21 13:03 ` Peter Zijlstra
2014-10-21 13:08 ` Stephane Eranian
2014-10-22 9:12 ` Peter Zijlstra [this message]
2014-10-22 21:04 ` Stephane Eranian
2014-10-23 8:53 ` Peter Zijlstra
2014-10-23 8:57 ` Stephane Eranian
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=20141022091239.GG12706@worktop.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=ak@linux.intel.com \
--cc=bp@alien8.de \
--cc=eranian@google.com \
--cc=jolsa@redhat.com \
--cc=kan.liang@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=maria.n.dimakopoulou@gmail.com \
--cc=mingo@elte.hu \
/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