linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jeff Moyer <jmoyer@redhat.com>
To: Fengguang Wu <fengguang.wu@intel.com>
Cc: Wanpeng Li <liwp.linux@gmail.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	Gavin Shan <shangw@linux.vnet.ibm.com>
Subject: Re: [PATCH V2] writeback: fix hung_task alarm when sync block
Date: Tue, 19 Jun 2012 16:14:16 -0400	[thread overview]
Message-ID: <x491ulbjbzb.fsf@segfault.boston.devel.redhat.com> (raw)
In-Reply-To: <20120614133600.GB14883@localhost> (Fengguang Wu's message of "Thu, 14 Jun 2012 21:36:00 +0800")

Fengguang Wu <fengguang.wu@intel.com> writes:

> Good idea! Yes we can do some estimation and adaptively extend the
> hang timeout for the current writeback_inodes_sb_nr()/sync_inodes_sb()
> call.
>
> Note that it's not going to reliably get rid of false warnings due to
> estimation errors, which could be pretty large and unavoidable on
> change of workload. But still, it would be a net improvement and
> perhaps enough to get rid of most false warnings, while still being
> able to catch livelock or other kind of task hang.

Hi, Fengguang,

I didn't see a patch from you for this, so I went ahead and threw
something together.  Let me know what you think of it.  I wasn't sure
how to estimate the total I/O that will be issued for syncing out an
entire superblock, though, so I didn't do that part.

Cheers,
Jeff

Signed-off-by: Jeff Moyer <jmoyer@redhat.com>

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8d2fb8c..346f3de 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1291,6 +1291,37 @@ static void wait_sb_inodes(struct super_block *sb)
 }
 
 /**
+ * wb_wait_for_completion_nohang -	wait for the given work item to
+ * complete, attempting to not falsely trigger the hangcheck timer.
+ * @work: the wb_writeback_work we're waiting on
+ *
+ * Wait for the completion of the given work item.  If the hang check
+ * timer is activated, then estimate the amount of time we should spend
+ * waiting for I/O, and wake up often enough to not trigger the timer.
+ * Once we've exceeded the estimated I/O time, wait without a timeout so
+ * that the hangcheck timer will then fire.
+ */
+void wb_wait_for_completion_nohang(struct wb_writeback_work *work)
+{
+	unsigned long hang_check = sysctl_hung_task_timeout_secs;
+	bool completed = false;
+
+	if (hang_check) {
+		/* loop until the time remaining is less than the timer */
+		unsigned long est_io_time_s = work->nr_pages /
+					work->sb->s_bdi->avg_write_bandwidth;
+		while (!completed && est_io_time_s > hang_check) {
+			completed = !!wait_for_completion_timeout(work->done,
+							hang_check * (HZ/2));
+			est_io_time_s -= hang_check / 2;
+		}
+	}
+
+	if (!completed)
+		wait_for_completion(work->done);
+}
+
+/**
  * writeback_inodes_sb_nr -	writeback dirty inodes from given super_block
  * @sb: the superblock
  * @nr: the number of pages to write
@@ -1316,7 +1347,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
 
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 	bdi_queue_work(sb->s_bdi, &work);
-	wait_for_completion(&done);
+	wb_wait_for_completion_nohang(&work);
 }
 EXPORT_SYMBOL(writeback_inodes_sb_nr);
 

  reply	other threads:[~2012-06-19 20:14 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-13  4:42 [PATCH V2] writeback: fix hung_task alarm when sync block Wanpeng Li
2012-06-13 14:27 ` Jeff Moyer
2012-06-13 14:48   ` Fengguang Wu
2012-06-13 14:55     ` Fengguang Wu
2012-06-13 15:34     ` Jeff Moyer
2012-06-14 13:36       ` Fengguang Wu
2012-06-19 20:14         ` Jeff Moyer [this message]
2012-06-19 21:02           ` Dave Chinner
2012-06-19 21:09             ` Jeff Moyer
2012-06-19 21:56               ` Dave Chinner
2012-06-14  1:35     ` Wanpeng Li
2012-06-14 13:26       ` Fengguang Wu
2012-06-15 22:43     ` Dave Chinner
2012-06-14 10:52 ` Wanpeng Li
2012-06-15 22:38 ` Dave Chinner

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=x491ulbjbzb.fsf@segfault.boston.devel.redhat.com \
    --to=jmoyer@redhat.com \
    --cc=fengguang.wu@intel.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=liwp.linux@gmail.com \
    --cc=shangw@linux.vnet.ibm.com \
    --cc=viro@zeniv.linux.org.uk \
    /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).