Re: Excessive stall times on ext4 in 3.9-rc2

[Mel Gorman]

On Tue, Apr 02, 2013 at 07:16:13PM -0400, Theodore Ts'o wrote:
> I've tried doing some quick timing, and if it is a performance
> regression, it's not a recent one --- or I haven't been able to
> reproduce what Mel is seeing.  I tried the following commands while
> booted into 3.2, 3.8, and 3.9-rc3 kernels:
> 
> time git clone ...
> rm .git/index ; time git reset
> 

FWIW, I had run a number if git checkout based tests over time and none
of them revealed anything useful. Granted it was on other machines but I
don't think it's git on its own. It's a combination that leads to this
problem. Maybe it's really an IO scheduler problem and I need to figure
out what combination triggers it.

> <SNIP>
>
> Mel, how bad is various git commands that you are trying?  Have you
> tried using time to get estimates of how long a git clone or other git
> operation is taking?
> 

Unfortunately, the milage varies considerably and it's not always
possible to time the operation. It may be that one occasion that opening
a mail takes an abnormal length time with git operations occasionally
making it far worse.

-- 
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/