On Mon, 17 Apr 2000, Stephen C. Tweedie wrote:

> Hi,
> 
> On Mon, Apr 17, 2000 at 07:21:31PM +0200, Benno Senoner wrote:
> 
> > > The only way you can get much better is to do non-writeback IO 
> > > asynchronously.  Use O_SYNC for writes, and submit the IOs from multiple
> > > threads, to let the kernel schedule the multiple IOs.  Use large block
> > > sizes for each IO to prevent massive amounts of disk seeking.  O_DIRECT
> > > in this case is not an instant win: it is completely orthogonal to the
> > > IO scheduling issue.
> > 
> > Are you suggesting to fire up multiple threads where each writes a couple of
> > files (in 256kb chunks) with  O_SYNC ?
> 
> That sort of thing, yes.
> 
> > how many threads in you opinion ?
> 
> Good question --- somebody really needs to benchmark it.  At least one per
> file, though.
>  
> > The reading thread: should that still be only one, in order to prevent seeking ?
>

After reading this thread, it occured to me that this tool might
be useful for you guys, specially for iterating thru different
parameters for IO benchmarking. It is called Threaded IO Benchmark and 
You can found it at: http://www.iki.fi/miku/tiobench

I hope it is close what Stephen means by using multiple threads for
writing. 

Feel free to use and abuse it. Its under GPL.
 
-- Mika <[EMAIL PROTECTED]>

Reply via email to