Drew,
Here's where I am: I'm definitely using the 1.3.4 tarball, but after I run
./configure, HAVE_RAW_SUPPORT is not defined in the top-level config.h:
$ cd /tmp
$ gzcat ~/filebench-1.3.4.tar.gz | tar xf -
$ cd filebench-1.3.4
$ ./configure --prefix=/opt > /tmp/config.out 2>&1
$ grep HAVE_RAW_
ndrew Wilson
> Sent: Monday, November 24, 2008 7:25 AM
> To: Demetri S. Mouratis
> Cc: perf-discuss@opensolaris.org
> Subject: Re: [perf-discuss] filebench source hints at raw device
> support
>
> On 11/21/08 15:09, Demetri S. Mouratis wrote:
> > Dear filebench gang,
>
Demetri,
It is defined in "config.h". If you are getting the sources from the
SourceForge source tree, it is very obsolete. The tar package for 1.3.4
is the latest one on SourceForge, and does support the raw devices
(files). Also, you can go to opensolaris.org and download from the
source t
O.k. I downloaded the source version instead of the Solaris packaged version,
followed the instructions in INSTALL, and added some debug log messages to
fileset.c. I don't think HAVE_RAW_SUPPORT is getting defined :-(
I'm having a little trouble finding my way around the configure process. Wh
Oops. Let me check one more thing. I see that fileset.c is checking for block
special, not character-special (as did your example in the posting; sorry!)
Let me try block-special just to see if it recognizes it as a 'raw' device, but
I'd like to be able to use the character-special device so
Hmmm. Still no luck.
For example, I'm trying:
define file name=c3t50060E80047F0B02d3s4, path=/dev/rdsk
define process name=randWriteProcess,instances=$nprocs
{
thread name=randWriteThread1, memsize=16m, instances=$nthreads
{
flowop write name=randWriter1, filename=c3t5006
On 11/21/08 15:09, Demetri S. Mouratis wrote:
> Dear filebench gang,
>
> fileset.c shows some evidence of a way to use filebench against individual
> raw device files instead of the 0001/0001 directory structure implied
> by fileset names. I've been staring at it an hour or more, and I c
