Re: udevd is killing file write performance.

["Jeff V. Merkey" <jmerkey@wolfmountaingroup.com>]

Andrew Morton wrote:

> Robin Holt <holt@sgi.com> wrote:
>  
>
> > Let me reiterate, I know _VERY_ little about filesystems.  Can the
> > dentry->d_lock be changed to a read/write lock?
> >    
>
> Well, it could, but I suspect that won't help - the hold times in there
> will be very short so the problem is more likely acquisition frequency.
>
> However it's a bit strange that this function is the bottleneck.  If their
> workload is doing large numbers of reads or writes from large numbers of
> processes against the same file then they should be hitting heavy
> contention on other locks, such as i_sem and/or tree_lock and/or lru_lock
> and others.
>
> Can you tell us more about the kernel-visible behaviour of this app?
>  

I have also seen this problem, and it's hard to reproduce. What you will 
see is udev getting spawned
multiple times as reported by top. I have found its related to 
intermittent failures of the hard drive and
the hotpluger for some reason invoking udev multiple times in response 
to this. I saw it on a Compaq
laptop right before my hard drive croaked, and it seems BIOS specific as 
well, since I have never seen
it or been able to reproduce it reliably.

Jeff

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

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