[Top] [All Lists]

Re: High latencies writing to a memory mapped file

To: Stan Hoeppner <stan@xxxxxxxxxxxxxxxxx>
Subject: Re: High latencies writing to a memory mapped file
From: Matthias Schniedermeyer <ms@xxxxxxx>
Date: Tue, 27 Jul 2010 16:49:14 +0200
Cc: xfs@xxxxxxxxxxx
In-reply-to: <4C4EDEFD.7000401@xxxxxxxxxxxxxxxxx>
References: <20100722144706.GA2840@xxxxxxxxxxxxxxxxxxxxxxxxx> <20100727092452.GA23307@xxxxxxx> <4C4EDEFD.7000401@xxxxxxxxxxxxxxxxx>
User-agent: Mutt/1.5.19 (2009-01-05)
On 27.07.2010 08:28, Stan Hoeppner wrote:
> Matthias Schniedermeyer put forth on 7/27/2010 4:24 AM:
> > We have a linux-computer with samba to act as a fileserver for a few 
> > Windows-Clients and ever since kernel 2.6.26 (Never happend with 2.6.25) 
> > the server randomly "hangs" for a few seconds (Which is more of a 
> > problem that drives people crazy).
> Can you supply any kinda of empirical data or logging that would suggest the
> problem lies with XFS?  You've not given us much to go on except anecdote.
> Google "linux server hangs" and you'll find thousands of causes and solutions.

The "best" further anecdote i have is:
I cloned(*) the server, on identical hardware (ignoring HDDs), for 
someone else with 2 major differences.
- no loop-aes, as they didn't need encryption.
- ext4 instead of xfs

That machine has currently an uptime of 180 days and i don't have a 
single report of a "hang". (Which technically doesn't mean that the 
machine doesn't have that same bug. Only that no one ever complained to 

For empirical data: I don't know how or where to start.

In the best sense of the word.
As the first step i 'rsync'ed the "system"-HDD of our server to a new 
HDD. ...

Bis denn

Real Programmers consider "what you see is what you get" to be just as 
bad a concept in Text Editors as it is in women. No, the Real Programmer
wants a "you asked for it, you got it" text editor -- complicated, 
cryptic, powerful, unforgiving, dangerous.

<Prev in Thread] Current Thread [Next in Thread>