mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Trond Myklebust <trond.myklebust@fys.uio.no>
To: busterbcook@yahoo.com
Cc: Andrew Morton <akpm@osdl.org>, linux-kernel@vger.kernel.org
Subject: Re: pdflush eating a lot of CPU on heavy NFS I/O
Date: Thu, 29 Apr 2004 00:21:55 -0400	[thread overview]
Message-ID: <1083212515.2856.247.camel@lade.trondhjem.org> (raw)
In-Reply-To: <Pine.LNX.4.58.0404282254290.13673@ozma.hauschen>

On Wed, 2004-04-28 at 23:55, Brent Cook wrote:

> ozma:/home /home nfs rw,v3,rsize=8192,wsize=8192,hard,udp,lock,addr=ozma 0 0

OK, then it's not the case that it is doing synchronous I/O.

I see that we're failing to set wbc->encountered_congestion in the case
where a nonblocking writeback is forced to exit due to congestion. Could
that be causing pdflush to loop Andrew?

If so, does the following patch help?

--- linux-2.6.6-rc3/fs/nfs/write.c.orig	2004-04-28 22:25:46.000000000 -0400
+++ linux-2.6.6-rc3/fs/nfs/write.c	2004-04-29 00:06:25.000000000 -0400
@@ -347,8 +347,10 @@ int nfs_writepages(struct address_space 
 	if (err)
 		return err;
 	while (test_and_set_bit(BDI_write_congested, &bdi->state) != 0) {
-		if (wbc->nonblocking)
+		if (wbc->nonblocking) {
+			wbc->encountered_congestion = 1;
 			return 0;
+		}
 		nfs_wait_on_write_congestion(mapping, 0);
 	}
 	err = nfs_flush_inode(inode, 0, 0, wb_priority(wbc));


  reply	other threads:[~2004-04-29  4:22 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-04-28  5:18 Brent Cook
2004-04-28  6:02 ` Andrew Morton
2004-04-28  7:29   ` Phy Prabab
2004-04-28 10:18   ` Sven Geggus
2004-04-28 13:50   ` Brent Cook
2004-04-28 19:48     ` Andrew Morton
2004-04-28 20:12       ` Brent Cook
2004-04-28 20:39       ` Brent Cook
2004-04-28 21:19         ` Trond Myklebust
2004-04-29  3:55           ` Brent Cook
2004-04-29  4:21             ` Trond Myklebust [this message]
2004-04-29  4:42               ` Andrew Morton
2004-04-29  1:24         ` Andrew Morton
2004-04-29  3:53           ` Brent Cook
2004-04-29  4:02             ` Andrew Morton
2004-04-29  4:03               ` Andrew Morton
2004-04-29  4:37               ` Brent Cook
2004-04-29  4:47                 ` Andrew Morton
2004-04-29  5:29                   ` Andrew Morton
2004-04-29 13:19                   ` Brent Cook
2004-04-29  3:54         ` Andrew Morton
2004-04-28  6:06 ` Brett E.

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=1083212515.2856.247.camel@lade.trondhjem.org \
    --to=trond.myklebust@fys.uio.no \
    --cc=akpm@osdl.org \
    --cc=busterbcook@yahoo.com \
    --cc=linux-kernel@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®