From: Greg KH <greg@kroah.com>
To: Benjamin LaHaise <bcrl@kvack.org>
Cc: James Bottomley <James.Bottomley@SteelEye.com>,
Satyam Sharma <satyam.sharma@gmail.com>,
Matthew Wilcox <matthew@wil.cx>, Simon Arlott <simon@fire.lp0.eu>,
Dave Jones <davej@redhat.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
linux-scsi@vger.kernel.org, kernel-packagers@vger.kernel.org,
"Robert P. J. Day" <rpjday@mindspring.com>
Subject: Re: sysfs makes scaling suck Re: Asynchronous scsi scanning
Date: Sat, 19 May 2007 09:30:53 -0700 [thread overview]
Message-ID: <20070519163052.GA4793@kroah.com> (raw)
In-Reply-To: <20070517174952.GB30571@kvack.org>
On Thu, May 17, 2007 at 01:49:52PM -0400, Benjamin LaHaise wrote:
> On Thu, May 17, 2007 at 01:45:24PM -0400, James Bottomley wrote:
> > But also, the sysfs with over 4,000 (and higher) devices was
> > specifically checked by OSDL (actually as part of the CGL testing) some
> > of the Manoj changes (for unpinning entries etc) were needed to get it
> > to function, but as of now, I believe an enterprise scaling test works
> > reasonably well for it ... there certainly wasn't any evidence of it
> > dying horribly in the tests.
>
> i386 exhausts lowmem very quickly. SCSI is in a bit better shape than
> network devices as the multiplier is only around 4 compared to 16 for network
> devices.
And sysfs pushes nodes out of memory when we start to exhaust memory, so
there should not be a problem at all. If there is, please let the sysfs
developers know about it and we will work to fix this.
thanks,
greg k-h
next prev parent reply other threads:[~2007-05-19 18:50 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <Pine.LNX.4.64.0705131106160.3197@localhost.localdomain>
2007-05-13 16:06 ` why does x86 "make defconfig" build a single, lonely module? Dave Jones
2007-05-13 16:10 ` James Bottomley
2007-05-13 16:18 ` James Bottomley
2007-05-13 16:30 ` Dave Jones
2007-05-14 9:35 ` Satyam Sharma
2007-05-14 9:45 ` Satyam Sharma
2007-05-14 12:00 ` Satyam Sharma
2007-05-14 12:23 ` Satyam Sharma
2007-05-14 14:31 ` James Bottomley
2007-05-15 0:41 ` Satyam Sharma
2007-05-15 11:26 ` Simon Arlott
2007-05-15 12:02 ` Asynchronous scsi scanning Matthew Wilcox
2007-05-15 16:30 ` Simon Arlott
2007-05-15 17:29 ` Matthew Wilcox
2007-05-15 21:56 ` [PATCH] SCSI: Let users disable SCSI_WAIT_SCAN to be built Stefan Richter
2007-05-16 14:43 ` Stefan Richter
2007-05-17 14:00 ` James Bottomley
2007-05-17 17:02 ` Satyam Sharma
2007-05-15 23:27 ` Asynchronous scsi scanning Satyam Sharma
2007-05-15 23:28 ` Arjan van de Ven
2007-05-15 23:49 ` Satyam Sharma
2007-05-16 2:51 ` Matthew Wilcox
2007-05-16 2:59 ` Roland Dreier
2007-05-17 17:13 ` Satyam Sharma
2007-05-17 17:20 ` Matthew Wilcox
2007-05-17 17:41 ` Satyam Sharma
2007-05-17 18:24 ` Christoph Hellwig
2007-05-17 18:47 ` Satyam Sharma
2007-05-17 18:51 ` Christoph Hellwig
2007-05-17 19:04 ` Satyam Sharma
2007-05-17 19:39 ` Matthew Wilcox
2007-05-17 19:43 ` Benjamin LaHaise
2007-05-17 21:30 ` Matthew Wilcox
2007-05-17 21:42 ` Dave Jones
2007-05-17 22:00 ` Peter Jones
2007-05-18 14:00 ` Stefan Richter
2007-05-18 5:28 ` Satyam Sharma
2007-05-18 11:24 ` Matthew Wilcox
2007-05-18 13:14 ` Satyam Sharma
2007-05-18 3:41 ` Satyam Sharma
2007-05-17 17:32 ` sysfs makes scaling suck " Benjamin LaHaise
2007-05-17 17:45 ` James Bottomley
2007-05-17 17:49 ` Benjamin LaHaise
2007-05-19 16:30 ` Greg KH [this message]
2007-05-17 22:24 ` Peter Jones
2007-05-13 16:20 ` why does x86 "make defconfig" build a single, lonely module? Robert P. J. Day
2007-05-13 16:27 ` James Bottomley
2007-05-13 16:37 ` Robert P. J. Day
2007-05-13 17:42 ` Simon Arlott
2007-05-13 17:48 ` James Bottomley
2007-05-13 18:26 ` Simon Arlott
2007-05-13 18:45 ` Dave Jones
2007-05-13 18:45 ` James Bottomley
2007-05-14 17:29 ` Jan Engelhardt
2007-05-14 18:46 ` Alan Cox
2007-05-14 20:06 ` Jan Engelhardt
2007-05-13 16:28 ` Dave Jones
2007-05-13 20:38 ` Simon Arlott
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=20070519163052.GA4793@kroah.com \
--to=greg@kroah.com \
--cc=James.Bottomley@SteelEye.com \
--cc=bcrl@kvack.org \
--cc=davej@redhat.com \
--cc=kernel-packagers@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=matthew@wil.cx \
--cc=rpjday@mindspring.com \
--cc=satyam.sharma@gmail.com \
--cc=simon@fire.lp0.eu \
/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).