lkml.org 
[lkml]   [1998]   [Nov]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] krflushd
Hi!

> > I think that bdflush is much smarter than that: your patch makes
> > kernel sync once every 30 seconds. bdflush is normally more
> > intelligent: it writes smaller ammounts of data more often in order of
> > not generating peaks of heavy disk i/o.
>
> Then, as long as bdflush is doing its smart job, there's no reason to
> expect high i/o peaks.. I've been running the patch in two different
> environments without any problems, so I'm happy with it.

Hugh, I thought your original goal was to kill bdflush?

Anyway, even if bdflush does it job, it looks like

Time: 0 10 20 30 40 50 seconds
Write of 10M into buffers

In case of bdflush, something like
Wr. 2M Wr.2M Wr.2M Wr.2M Wr.2M onto disk
should happen.

In case of bdflush , something like
Wr. 2M Wr.8M may happen in case of your sync awakening
at t=20.
Pavel

--
The best software in life is free (not shareware)! Pavel
GCM d? s-: !g p?:+ au- a--@ w+ v- C++@ UL+++ L++ N++ E++ W--- M- Y- R+

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

\
 
 \ /
  Last update: 2005-03-22 13:45    [from the cache]
©2003-2011 Jasper Spaans