From: Con Kolivas <kernel@kolivas.org>
To: "Jörn Engel" <joern@wohnheim.fh-wedel.de>,
"David S. Miller" <davem@redhat.com>
Cc: linux-mtd@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: jmorris@intercode.com.au
Subject: Re: [PATCH RFC] 1/2 central workspace for zlib
Date: Sat, 31 May 2003 18:22:21 +1000 [thread overview]
Message-ID: <200305311822.21823.kernel@kolivas.org> (raw)
In-Reply-To: <20030531075615.GA25089@wohnheim.fh-wedel.de>
On Sat, 31 May 2003 17:56, Jörn Engel wrote:
> CC List pruned a little.
>
> On Fri, 30 May 2003 23:55:05 -0700, David S. Miller wrote:
> > From: Jörn Engel <joern@wohnheim.fh-wedel.de>
> >
> > How about preemption? zlib operations take their time, so at least on
> > up, it makes sense to preempt them, when not in softirq context. Can
> > this still be done lockless?
> >
> > You'll need to disable preemption.
>
> My gut feeling claims that this would hurt interactivity. Con, would
> contest on a jffs2 (zlib compressed) filesystem be able to show
> interactivity problems wrt zlib?
The only way I could think of was perhaps using a load on another disk
(io_other which is in contest) that is using jffs2 when the contest baseline
is running on a normal filesystem - this has shown very little differences
between filesystems normally. Otherwise if everything in contest is run on
jffs2 it would affect every layer and hard to be sure you had a control to
compare with.
Con
WARNING: multiple messages have this Message-ID (diff)
From: Con Kolivas <kernel@kolivas.org>
To: "Jörn Engel" <joern@wohnheim.fh-wedel.de>,
"David S. Miller" <davem@redhat.com>
Cc: jmorris@intercode.com.au, linux-mtd@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH RFC] 1/2 central workspace for zlib
Date: Sat, 31 May 2003 18:22:21 +1000 [thread overview]
Message-ID: <200305311822.21823.kernel@kolivas.org> (raw)
In-Reply-To: <20030531075615.GA25089@wohnheim.fh-wedel.de>
On Sat, 31 May 2003 17:56, Jörn Engel wrote:
> CC List pruned a little.
>
> On Fri, 30 May 2003 23:55:05 -0700, David S. Miller wrote:
> > From: Jörn Engel <joern@wohnheim.fh-wedel.de>
> >
> > How about preemption? zlib operations take their time, so at least on
> > up, it makes sense to preempt them, when not in softirq context. Can
> > this still be done lockless?
> >
> > You'll need to disable preemption.
>
> My gut feeling claims that this would hurt interactivity. Con, would
> contest on a jffs2 (zlib compressed) filesystem be able to show
> interactivity problems wrt zlib?
The only way I could think of was perhaps using a load on another disk
(io_other which is in contest) that is using jffs2 when the contest baseline
is running on a normal filesystem - this has shown very little differences
between filesystems normally. Otherwise if everything in contest is run on
jffs2 it would affect every layer and hard to be sure you had a control to
compare with.
Con
next prev parent reply other threads:[~2003-05-31 8:20 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-05-30 14:49 [PATCH RFC] 1/2 central workspace for zlib Jörn Engel
2003-05-30 14:49 ` Jörn Engel
2003-05-30 15:29 ` James Morris
2003-05-30 15:29 ` James Morris
2003-05-30 17:43 ` Jörn Engel
2003-05-30 17:43 ` Jörn Engel
2003-05-31 0:14 ` David S. Miller
2003-05-31 0:14 ` David S. Miller
2003-05-31 6:48 ` Jörn Engel
2003-05-31 6:48 ` Jörn Engel
2003-05-31 6:55 ` David S. Miller
2003-05-31 6:55 ` David S. Miller
2003-05-31 7:56 ` Jörn Engel
2003-05-31 7:56 ` Jörn Engel
2003-05-31 7:59 ` David S. Miller
2003-05-31 7:59 ` David S. Miller
2003-05-31 8:11 ` Jörn Engel
2003-05-31 8:11 ` Jörn Engel
2003-05-31 8:12 ` David S. Miller
2003-05-31 8:12 ` David S. Miller
2003-05-31 8:22 ` Con Kolivas [this message]
2003-05-31 8:22 ` Con Kolivas
2003-06-01 1:25 ` Matt Mackall
2003-06-01 1:25 ` Matt Mackall
2003-06-02 12:19 ` Jörn Engel
2003-06-02 12:19 ` Jörn Engel
2003-05-31 9:09 ` Arjan van de Ven
2003-05-31 9:09 ` Arjan van de Ven
2003-05-31 6:20 ` David S. Miller
2003-05-31 6:20 ` David S. Miller
2003-05-31 10:51 ` James Morris
2003-05-31 10:51 ` James Morris
2003-05-31 11:07 ` Jörn Engel
2003-05-31 11:07 ` Jörn Engel
2003-05-31 15:44 ` Joakim Tjernlund
2003-06-02 12:26 ` Jörn Engel
2003-06-02 13:03 ` Joakim Tjernlund
2003-06-02 13:32 ` Jörn Engel
2003-06-02 15:15 ` matsunaga
2003-06-02 15:15 ` matsunaga
2003-06-02 15:36 ` Jörn Engel
2003-06-02 15:36 ` Jörn Engel
2003-06-02 15:40 ` David Woodhouse
2003-06-02 15:40 ` David Woodhouse
2003-06-02 15:53 ` Jörn Engel
2003-06-02 15:53 ` Jörn Engel
2003-06-02 15:59 ` David Woodhouse
2003-06-02 15:59 ` David Woodhouse
2003-06-02 16:37 ` Jörn Engel
2003-06-02 16:37 ` Jörn Engel
2003-06-02 19:36 ` David Woodhouse
2003-06-02 19:36 ` David Woodhouse
2003-06-02 20:54 ` Jörn Engel
2003-06-02 20:54 ` Jörn Engel
2003-06-02 16:07 ` matsunaga
2003-06-02 16:07 ` matsunaga
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=200305311822.21823.kernel@kolivas.org \
--to=kernel@kolivas.org \
--cc=davem@redhat.com \
--cc=joern@wohnheim.fh-wedel.de \
--cc=linux-mtd@lists.infradead.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.