Subject: Re: Limiting disk I/O?
To: Michael van Elst <mlelstv@serpens.de>
From: Jukka Marin <jmarin@embedtronics.fi>
List: tech-kern
Date: 12/04/2007 22:50:59
On Tue, Dec 04, 2007 at 08:40:28PM +0000, Michael van Elst wrote:
> >> Now guess what happens when you temporarily bypass softdep's ordering.
> >Bad things(TM)
> 
> Why would you want to stop disk writes? The kernel can easily _read_
> data (when it has free buffers) even when it pushes out dirty
> buffers in a tight loop. The problem is that you don't have
> free buffers because all are occupied by data that needs to
> be written. Stopping the writes won't free any buffer.

If extracting pkgsrc.tar.gz takes only 14 s, all the data must fit
into RAM buffers and it's quite unlikely that _all_ buffers were used
up.  However, when ioflush wakes up, the high disk write rate prevents
all read operations for a long time (as I said, loading a small binary
from disk can take at least 120 seconds).

  -jm