All of lore.kernel.org
 help / color / mirror / Atom feed
From: Konstantinos Skarlatos <k.skarlatos@gmail.com>
To: Tobias <tracer@robotech.de>
Cc: linux-btrfs@vger.kernel.org
Subject: Re: Blocked for more than 120 seconds
Date: Sat, 03 Dec 2011 02:35:50 +0200	[thread overview]
Message-ID: <4ED96EE6.2010308@gmail.com> (raw)
In-Reply-To: <4ED92CA6.3030302@gmail.com>

After about 1TB of rsyncs from multiple servers at the same time, plus=20
some heavy filesystem loading, i believe that 3.2rc4 solves the problem=
=20
for me. Now if only we had deduplication and an fsck tool :)
On =CE=A0=CE=B1=CF=81=CE=B1=CF=83=CE=BA=CE=B5=CF=85=CE=AE, 2 =CE=94=CE=B5=
=CE=BA=CE=AD=CE=BC=CE=B2=CF=81=CE=B9=CE=BF=CF=82 2011 9:53:10 =CE=BC=CE=
=BC, Konstantinos Skarlatos=20
wrote:
> I see they got into 3.2rc4, so I am now compiling it. I will report=20
> back in a few hours
>
> On =CE=A0=CE=B1=CF=81=CE=B1=CF=83=CE=BA=CE=B5=CF=85=CE=AE, 2 =CE=94=CE=
=B5=CE=BA=CE=AD=CE=BC=CE=B2=CF=81=CE=B9=CE=BF=CF=82 2011 5:48:31 =CE=BC=
=CE=BC, Tobias wrote:
>> Am 02.12.2011 16:22, schrieb Konstantinos Skarlatos:
>>>>> So, the transaction close is in btrfs_evict_inode, which sounds=20
>>>>> like a
>>>>> deadlock recently fixed by this commit:
>>>>>
>>>>> http://git.kernel.org/?p=3Dlinux/kernel/git/mason/linux-btrfs.git=
;a=3Dcommit;h=3Daa38a711a893accf5b5192f3d705a120deaa81e0=20
>>>>>
>>>>>
>>>>> If you pull the for-linus branch from today, hopefully the proble=
m=20
>>>>> will
>>>>> be gone.
>>>>>
>>>>
>>>> This looks very good. With this Kernel i still have some hangs, bu=
t=20
>>>> only in rsync, only under high load and they don't lock up the=20
>>>> system - so i guess it's ok now.
>>>
>>> I still have hangs and lock ups under the same situation (rsync of=20
>>> many files) under 3.2rc3. rc3 made the hang appear after 200gb of=20
>>> files, while in rc2 i had hangs after only 11gb .
>>
>> Yes, i had them too in 3.2rc3! The problem where solved with patches=
=20
>> from the "btrfs-for-linus" -branch. (see link above).
>>
>> Tobias
>>
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

  reply	other threads:[~2011-12-03  0:35 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-11-28  8:16 Blcoked for more than 120 seconds Tobias
2011-11-28  9:29 ` Chris Samuel
2011-11-30  9:44   ` Blocked " Tobias
2011-11-30 14:10     ` Chris Mason
     [not found]       ` <4ED738E5.3080200@robotech.de>
2011-12-01 18:41         ` Chris Mason
2011-12-02 13:46           ` Tobias
2011-12-02 14:01             ` Chris Mason
2011-12-04 12:11               ` Konstantinos Skarlatos
2011-12-02 15:22             ` Konstantinos Skarlatos
2011-12-02 15:48               ` Tobias
2011-12-02 19:53                 ` Konstantinos Skarlatos
2011-12-03  0:35                   ` Konstantinos Skarlatos [this message]
2011-12-03 14:36                     ` Konstantinos Skarlatos
2011-12-05 13:12                       ` Chris Mason
2011-12-25  1:06                         ` Konstantinos Skarlatos

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=4ED96EE6.2010308@gmail.com \
    --to=k.skarlatos@gmail.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=tracer@robotech.de \
    /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.