From: Tom Zanussi <zanussi@us.ibm.com>
To: Jason Baron <jbaron@redhat.com>
Cc: Tom Zanussi <zanussi@us.ibm.com>,
akpm@osdl.org, linux-kernel@vger.kernel.org, karim@opersys.com,
varap@us.ibm.com, richardj_moore@uk.ibm.com
Subject: Re: Merging relayfs?
Date: Tue, 12 Jul 2005 10:26:33 -0500 [thread overview]
Message-ID: <17107.57641.217499.429075@tut.ibm.com> (raw)
In-Reply-To: <Pine.LNX.4.61.0507121050390.25408@dhcp83-105.boston.redhat.com>
Jason Baron writes:
>
> On Mon, 11 Jul 2005, Tom Zanussi wrote:
>
> >
> > Hi Andrew, can you please merge relayfs? It provides a low-overhead
> > logging and buffering capability, which does not currently exist in
> > the kernel.
> >
>
> One concern I had regarding relayfs, which was raised previously, was
> regarding its use of vmap,
> http://marc.theaimsgroup.com/?l=linux-kernel&m=110755199913216&w=2 On x86,
> the vmap space is at a premium, and this space is reserved over the entire
> lifetime of a 'channel'. Is the use of vmap really critical for
> performance?
Yes, the vmap'ed area is reserved over the lifetime of the channel,
but the typical usage of a channel is transient - allocate it at the
start of say a tracing run, and then vunmap it and free the memory
when done. Unless you're using huge buffers, you wouldn't run into a
problem running out of vmalloc space, and typical applications should
be able to use relatively small buffers.
I don't really know how we would get around using vmap - it seems like
the alternatives, such as managing an array of pages or something like
that, would slow down the logging path too much to make it useful as a
low overhead logging mechanism. I you have any ideas though, please
let me know.
Tom
next prev parent reply other threads:[~2005-07-12 15:29 UTC|newest]
Thread overview: 89+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-07-12 1:10 Tom Zanussi
2005-07-12 1:45 ` Andrew Morton
2005-07-12 2:17 ` Dave Airlie
2005-07-12 2:22 ` Tom Zanussi
2005-07-12 9:12 ` Baruch Even
2005-07-12 2:25 ` Christoph Hellwig
2005-07-12 2:34 ` Andrew Morton
2005-07-12 2:59 ` Karim Yaghmour
2005-07-14 13:26 ` Roman Zippel
2005-07-14 15:01 ` Tom Zanussi
2005-07-17 14:04 ` Roman Zippel
2005-07-17 15:52 ` Tom Zanussi
2005-07-18 5:17 ` Hareesh Nagarajan
2005-07-18 14:31 ` Tom Zanussi
2005-07-18 13:44 ` Steven Rostedt
2005-07-18 14:16 ` Roman Zippel
2005-07-18 14:32 ` Karim Yaghmour
2005-07-18 15:20 ` Roman Zippel
2005-07-18 15:58 ` Tom Zanussi
2005-07-22 20:43 ` Tom Zanussi
2005-07-22 23:19 ` Karim Yaghmour
2005-07-23 2:31 ` Tom Zanussi
2005-07-26 2:35 ` Karim Yaghmour
2005-07-22 20:43 ` Tom Zanussi
2005-07-18 14:36 ` Steven Rostedt
2005-07-18 15:06 ` Roman Zippel
2005-07-18 14:41 ` Tom Zanussi
2005-07-18 8:40 ` Richard J Moore
2005-07-12 13:03 ` Steven Rostedt
2005-07-12 3:05 ` Greg KH
2005-07-12 3:03 ` Karim Yaghmour
2005-07-12 3:24 ` Greg KH
2005-07-12 3:52 ` Karim Yaghmour
2005-07-12 4:30 ` Greg KH
2005-07-12 4:40 ` Karim Yaghmour
2005-07-12 5:23 ` Greg KH
2005-07-12 14:36 ` Steve Rotolo
2005-07-12 3:55 ` Tom Zanussi
2005-07-12 4:27 ` Greg KH
2005-07-12 14:01 ` Tomasz Kłoczko
2005-07-12 14:21 ` Baruch Even
2005-07-12 15:30 ` Tomasz Kłoczko
2005-07-12 15:16 ` Tom Zanussi
2005-07-12 15:44 ` Tomasz Kłoczko
2005-07-12 16:27 ` Tom Zanussi
2005-07-12 17:01 ` Tomasz Kłoczko
2005-07-12 17:23 ` Tom Zanussi
[not found] ` <Pine.BSO.4.62.0507121935500.6919@rudy.mif.pg.gda.pl>
[not found] ` <17108.1906.628755.613285@tut.ibm.com>
[not found] ` <Pine.BSO.4.62.0507122026520.6919@rudy.mif.pg.gda.pl>
[not found] ` <17108.5721.202275.377020@tut.ibm.com>
2005-07-12 19:29 ` Tomasz Kłoczko
2005-07-12 20:44 ` Vara Prasad
2005-07-12 21:02 ` Vara Prasad
2005-07-13 12:40 ` Tomasz Kłoczko
2005-07-13 15:04 ` Vara Prasad
2005-07-13 16:22 ` Tomasz Kłoczko
2005-07-13 4:29 ` Vara Prasad
2005-07-13 13:47 ` Tomasz Kłoczko
2005-07-13 15:55 ` Karim Yaghmour
2005-07-13 15:56 ` Vara Prasad
2005-07-13 16:50 ` Tomasz Kłoczko
2005-07-12 14:58 ` Jason Baron
2005-07-12 15:26 ` Tom Zanussi [this message]
2005-07-12 16:00 ` Steven Rostedt
2005-07-12 15:53 ` Steven Rostedt
2005-07-12 16:08 ` Tom Zanussi
2005-07-12 16:23 ` Steven Rostedt
2005-07-12 16:36 ` Tom Zanussi
2005-07-12 16:49 ` Steven Rostedt
2005-07-12 17:01 ` Tom Zanussi
2005-07-12 21:38 ` Tom Zanussi
2005-07-12 23:40 ` Steven Rostedt
2005-07-12 23:55 ` Andrew Morton
2005-07-13 0:08 ` Steven Rostedt
2005-07-16 21:07 ` relayfs documentation sucks? bert hubert
2005-07-16 23:13 ` Tom Zanussi
2005-07-17 9:01 ` [PATCH] " bert hubert
2005-07-17 15:43 ` Tom Zanussi
2005-07-17 19:45 ` bert hubert
2005-07-17 20:47 ` Tom Zanussi
2005-07-18 13:27 ` Steven Rostedt
2005-07-20 21:27 ` Paul Jackson
2005-07-20 21:45 ` bert hubert
2005-07-21 0:31 ` Paul Jackson
2005-07-22 20:01 ` Paul Jackson
2005-07-22 20:33 ` relayfs as infrastructure, ltt, systemtap, diskstat bert hubert
2005-07-23 18:53 ` Christoph Hellwig
2005-07-23 18:53 ` [PATCH] Re: relayfs documentation sucks? Christoph Hellwig
2005-07-25 23:47 ` Karim Yaghmour
2005-07-26 5:15 ` bert hubert
[not found] <17107.6290.734560.231978@tut.ibm.com.suse.lists.linux.kernel>
[not found] ` <20050712022537.GA26128@infradead.org.suse.lists.linux.kernel>
[not found] ` <20050711193409.043ecb14.akpm@osdl.org.suse.lists.linux.kernel>
2005-07-12 4:36 ` Merging relayfs? Andi Kleen
2005-07-13 8:13 Spirakis, Charles
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=17107.57641.217499.429075@tut.ibm.com \
--to=zanussi@us.ibm.com \
--cc=akpm@osdl.org \
--cc=jbaron@redhat.com \
--cc=karim@opersys.com \
--cc=linux-kernel@vger.kernel.org \
--cc=richardj_moore@uk.ibm.com \
--cc=varap@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
Powered by JetHome