[ENBD] Doubled requests
Arne Wiebalck
wiebalck at kip.uni-heidelberg.de
Fri Jan 16 01:55:47 MST 2004
On Thu, 15 Jan 2004, Peter T. Breuer wrote:
> Can you add to the file.c code the following (which I have, and which
> I published yesterday on the group) in the fileit() routine, just above
> the write() to disk:
>
> default:
> case WRITE: // 1
> DEBUG("+[%u@%Lu]", len, self->lastpoint);
>
> + if (1) {
> + // instrumentation
> + static u64 lastpoint = -1LL, point;
> + static int lastlen = -1;
> + point = seek(fd, 0LL, SEEK_CUR);
> + if (!(lastpoint+lastlen <= point || lastpoint >= point+len) ){
> + PERR("two consecutive writes to the same place!\n");
> + PERR("%#Lx-%#Lx and %#Lx-%Lx!\n",
> + lastpoint, lastpoint+lastlen,
> + point, point+len);
> + }
> + lastpoint = point;
> + lastlen = len;
> + }
> +
> res = write(fd, buf, len);
>
>
> and tell me if this makes any noise under your tests.
I added it. It does not trigger. My device however still does. I am sure
I inserted it a the right place and I would have seen it (I checked it
by placing the PERR message before the "if" as a test).
Did you already add your changes to 2.4.32, i.e. shall I download and try
a newer version?
Since it seems to be sensitive to m_r (at least in my setup): what value
do you use for m_r ? maybe it's already sensitive to that and not only to
whether it's switched on or not. I am running with m_r=128 at least.
arne
**********************************************************************
Arne Wiebalck Kirchhoff Institute for Physics
Technical Computer Science
INF 227, Room 3.315
D-69120 Heidelberg
e-mail: wiebalck at kip.uni-heidelberg.de
web : http://www.kip.uni-heidelberg.de Tel.: (+49) 6221/54-9816
**********************************************************************
More information about the ENBD
mailing list