Re: ext3 performance issue with a Berkeley db application

[Matthias Andree <ma dt e-technik uni-dortmund de>]

Andreas Dilger <adilger clusterfs com> writes:

> On Feb 03, 2003  12:08 +0100, Matthias Andree wrote:
>> Are you aware of a module that applies to recent kernel versions and
>> that traces block numbers of ll_rw_block()? It might turn up some useful
>> information -- then we'd easier know the ext3 "output" to the hard disk;
>> we already know the "input" from the application at the syscall level.
>
> Stephen Tweedie has a loopback driver:
>
> 	 http://people.redhat.com/sct/patches/testdrive/
>
> which allows you to trace all I/O.

lo and behold.

How do I use that one? Load the module and then do a "regular" loopback
mount?

What's the physical unit of "frequency" for fault injection if I am to
use this to test applications for robustness against EIO?

-- 
Matthias Andree