From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Avi Kivity <avi@redhat.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
Ingo Molnar <mingo@elte.hu>,
Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Subject: Re: [PATCH v1 5/5] KVM: Expose a version 1 architectural PMU to guests
Date: Fri, 03 Jun 2011 16:41:51 +0200 [thread overview]
Message-ID: <1307112111.2353.3390.camel@twins> (raw)
In-Reply-To: <1305129333-7456-6-git-send-email-avi@redhat.com>
On Wed, 2011-05-11 at 11:55 -0400, Avi Kivity wrote:
> - counters that have PMI (interrupt) enabled stop counting after the
> interrupt is signalled. This is because we need one-shot samples
> that keep counting, which perf doesn't support yet
You'll have to reprogram the thing anyway, since not all hardware has
the same counter width:
[ 0.046996] Performance Events: AMD PMU driver.
[ 0.048998] ... bit width: 48
vs
[ 0.026998] Performance Events: PEBS fmt0+, Core2 events, Intel PMU driver.
[ 0.026998] ... bit width: 40
simply letting the thing run will not behave in a consistent fashion.
Or are you going to assume all software will properly read the cpuid
leaf and not assume bit width?
Also, I can't seem to locate where you fill that cpuid-leaf,
kvm_pmu_cpuid_update() seems to read the entry, not write it.
next prev parent reply other threads:[~2011-06-03 14:42 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-05-11 15:55 [PATCH v1 0/5] KVM in-guest performance monitoring Avi Kivity
2011-05-11 15:55 ` [PATCH v1 1/5] perf: add context parameter to perf_event overflow handler Avi Kivity
2011-06-03 14:41 ` Peter Zijlstra
2011-06-05 8:07 ` Avi Kivity
2011-05-11 15:55 ` [PATCH v1 2/5] x86, perf: add constraints for architectural PMU v1 Avi Kivity
2011-05-11 15:55 ` [PATCH v1 3/5] perf: export perf_event_refresh() to modules Avi Kivity
2011-05-11 15:55 ` [PATCH v1 4/5] KVM: Expose kvm_lapic_local_deliver() Avi Kivity
2011-05-11 15:55 ` [PATCH v1 5/5] KVM: Expose a version 1 architectural PMU to guests Avi Kivity
2011-05-17 19:41 ` Ingo Molnar
2011-05-18 9:03 ` Avi Kivity
2011-05-18 11:07 ` Ingo Molnar
2011-05-18 11:29 ` Peter Zijlstra
2011-05-18 11:57 ` Ingo Molnar
2011-05-18 11:32 ` Peter Zijlstra
2011-05-18 11:37 ` Avi Kivity
2011-05-18 12:35 ` Peter Zijlstra
2011-05-18 12:49 ` Avi Kivity
2011-06-03 14:41 ` Peter Zijlstra [this message]
2011-06-05 8:12 ` Avi Kivity
2011-06-03 14:41 ` Peter Zijlstra
2011-06-05 8:12 ` Avi Kivity
2011-05-12 9:33 ` [PATCH v1 0/5] KVM in-guest performance monitoring Joerg Roedel
2011-05-12 9:47 ` Jan Kiszka
2011-05-12 9:53 ` Avi Kivity
2011-05-12 13:11 ` Joerg Roedel
2011-05-12 13:23 ` Jan Kiszka
2011-05-12 13:43 ` Joerg Roedel
2011-05-12 13:31 ` Avi Kivity
2011-05-12 14:24 ` Joerg Roedel
2011-05-12 14:37 ` Avi Kivity
2011-05-12 14:45 ` Avi Kivity
2011-05-13 12:34 ` Joerg Roedel
2011-05-12 9:51 ` Avi Kivity
2011-05-12 13:06 ` Joerg Roedel
2011-05-12 13:38 ` Avi Kivity
2011-05-12 14:29 ` Joerg Roedel
2011-05-17 9:52 ` Avi Kivity
2011-06-01 9:45 ` Avi Kivity
2011-06-01 10:26 ` Peter Zijlstra
2011-06-01 11:26 ` Avi Kivity
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=1307112111.2353.3390.camel@twins \
--to=a.p.zijlstra@chello.nl \
--cc=acme@ghostprotocols.net \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--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;
as well as URLs for NNTP newsgroup(s).