Linux users want better desktop performance (Screw data. Prioritize code)

Bill Davidsen davidsen at tmr.com
Mon Feb 23 21:39:29 UTC 2009


Mattias Hellström wrote:
> On Tue, Feb 17, 2009 at 8:19 PM, Valent Turkovic
> <valent.turkovic at gmail.com> wrote:
>> http://rudd-o.com/en/linux-and-free-software/tales-from-responsivenessland-why-linux-feels-slow-and-how-to-fix-that
>>
>> What is you comment?
>>
> Do not blame the operating system for badly coded apps. Only the app
> knows if caching is a good idea.
> 
> Exerpt from "man -s 2 open"
> O_DIRECT (Since Linux 2.4.10)
>               Try  to  minimize cache effects of the I/O to and from
> this file.  In general this will degrade perfor-
>               mance, but it is useful in special situations, such as
> when applications do their  own  caching.   File
>               I/O is done directly to/from user space buffers.  The
> I/O is synchronous, that is, at the completion of
>               a read(2) or write(2), data is guaranteed to have been
> transferred.  See NOTES below for  further  dis-
>               cussion.
> 
Just let me add that DIRECT will usually slightly slow the i/o it's doing, but 
greatly reduce the impact on the system. This can really save performance of 
machines doing small transactions such as serving DNS, DHCP, mail, NNTP, of 
database lookups. The transaction per sec of the application can drop by 60% 
writing a large file, if you can pipe it through dd with the direct option it 
will hurt less.

So if the file i/o is non-critical there is a big gain to be had for the 
performance of some applications.

-- 
Bill Davidsen <davidsen at tmr.com>
   "We have more to fear from the bungling of the incompetent than from
the machinations of the wicked."  - from Slashdot




More information about the fedora-list mailing list