Why does disk I/O slow down a CPU bound task?
davejohansen at gmail.com
Tue Mar 31 15:32:16 UTC 2015
On Mon, Mar 30, 2015 at 10:02 PM, Nico Kadel-Garcia <nkadel at gmail.com>
> On Mon, Mar 30, 2015 at 3:58 PM, Dave Johansen <davejohansen at gmail.com>
> > I noticed on RHEL 6 that when a large amount of disk I/O is happening
> > CPU bound tasks "slow down". I have been able to reproduce it in Fedora
> > as well and here are the instructions of how I can reproduce it with a
> > simple test:
> Writing to disk is not "free". There is overhead in writing the data,
> especially if the files are being re-arranged and the directory
> structure revised, and there's overhead in doing it safely to avoid
> accidental loss of data.
> There are options to improve such performance, such as using the
> 'noatime' option, or using well optimized filesystems. But there are
> certainly limits.
I am not familiar with the low level details of disk I/O but I'm sure that
they are far more complicated than my basic assumptions, but my concern is
how can a disk-bound process steal cycles from a CPU-bound one that is not
access the disk at all. The lwn.net articles that drago01 linked to helped
shed some light on what's going on, but it sounds like there is still some
potential work that could be done to help improve the situation.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the devel