From: Mike Kravetz <kravetz@us.ibm.com>
To: Nathan Lynch <ntl@pobox.com>
Cc: Bryan Rosenburg <rosnbrg@us.ibm.com>,
linuxppc-dev@ozlabs.org, Paul Mackerras <paulus@samba.org>,
Arnd Bergmann <arnd@arndb.de>, Christopher Yeoh <cyeoh@samba.org>
Subject: Re: [PATCH 2/3] powerpc: Instrument Hypervisor Calls: add wrappers
Date: Fri, 14 Jul 2006 17:41:56 -0700 [thread overview]
Message-ID: <20060715004156.GJ6824@monkey.ibm.com> (raw)
In-Reply-To: <20060715001545.GK19076@localdomain>
On Fri, Jul 14, 2006 at 07:15:45PM -0500, Nathan Lynch wrote:
> Hmm, isn't it possible that the stats could be corrupted if we process
> an interrupt/softirq which does an hcall while the stats are being
> updated? Maybe it's not a show-stopper, but it seems to me that
> accuracy could suffer under some workloads.
Yes, they can become inaccurate. Is this what you mean by 'corrupted' or
you thinking of something worse?
There is going to be a trade off between accuracy and the overhead of the
data gathering. What really needs to happen is some good benchmarking to
measure the costs of different approaches. I'm pretty sure I can get
someone to provide such data.
In this patch, I have minimized the overhead in data collection at the
cost of accuracy.
--
Mike
next prev parent reply other threads:[~2006-07-15 0:41 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-07-14 23:37 [PATCH 0/3] powerpc: Instrument Hypervisor Calls Mike Kravetz
2006-07-14 23:39 ` [PATCH 1/3] powerpc: Instrument Hypervisor Calls: merge headers Mike Kravetz
2006-07-14 23:40 ` [PATCH 2/3] powerpc: Instrument Hypervisor Calls: add wrappers Mike Kravetz
2006-07-15 0:15 ` Nathan Lynch
2006-07-15 0:41 ` Mike Kravetz [this message]
2006-07-15 8:03 ` Nathan Lynch
2006-07-14 23:41 ` [PATCH 3/3] powerpc: Instrument Hypervisor Calls: add debugfs files Mike Kravetz
2006-07-15 0:00 ` [PATCH 0/3] powerpc: Instrument Hypervisor Calls Arnd Bergmann
2006-07-15 0:06 ` Mike Kravetz
2006-07-15 15:30 ` Anton Blanchard
2006-07-15 16:42 ` Arnd Bergmann
2006-07-15 22:07 ` Anton Blanchard
2006-07-16 23:02 ` Luke Browning
2006-07-17 2:02 ` Luke Browning
2006-07-16 3:53 ` Olof Johansson
2006-07-16 22:53 ` Luke Browning
2006-07-16 23:09 ` Olof Johansson
-- strict thread matches above, loose matches on Subject: below --
2006-07-18 20:47 Mike Kravetz
2006-07-18 20:49 ` [PATCH 2/3] powerpc: Instrument Hypervisor Calls: add wrappers Mike Kravetz
2006-07-18 22:34 ` Olof Johansson
2006-07-18 23:18 ` Mike Kravetz
2006-07-19 3:33 ` Olof Johansson
2006-07-19 3:50 ` Mike Kravetz
2006-06-22 22:56 [PATCH 0/3] powerpc: Instrument Hypervisor Calls Mike Kravetz
2006-06-22 22:58 ` [PATCH 2/3] powerpc: Instrument Hypervisor Calls: add wrappers Mike Kravetz
2006-06-14 3:47 [PATCH 0/3] powerpc: Instrument Hypervisor Calls Mike Kravetz
2006-06-14 3:52 ` [PATCH 2/3] powerpc: Instrument Hypervisor Calls: add wrappers Mike Kravetz
2006-06-14 7:23 ` Arnd Bergmann
2006-06-14 14:42 ` Nathan Lynch
2006-06-14 22:33 ` Paul Mackerras
2006-06-14 22:40 ` Nathan Lynch
2006-06-14 23:52 ` Mike Kravetz
2006-06-15 11:09 ` Arnd Bergmann
2006-06-15 14:58 ` Mike Kravetz
2006-06-15 16:06 ` Arnd Bergmann
2006-06-16 16:11 ` Mike Kravetz
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=20060715004156.GJ6824@monkey.ibm.com \
--to=kravetz@us.ibm.com \
--cc=arnd@arndb.de \
--cc=cyeoh@samba.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=ntl@pobox.com \
--cc=paulus@samba.org \
--cc=rosnbrg@us.ibm.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 NNTP newsgroup(s).