On Thu, 18 Dec 2008 13:59:06 -0600
"Rahul Nabar" wrote:
> For a while I've been seeing errors of this sort in my /var/log/messages
>
> kernel: nfsd: too many open TCP sockets, consider increasing the number of
> nfsd threads
>
> I googled a bunch and think the solution might be to boost RPCNFSD
On Thu, Dec 18, 2008 at 2:46 PM, John Hearns wrote:
> This depends on your distribution.
> On SuSE Linux, look in /etc/sysconfig/nfs
Found it. Its the same file on Fedora, my distro.
>
> I used to set the number of NFS kernel threads to the number of clients when
> building a cluster. This is v
On Thu, Dec 18, 2008 at 3:02 PM, Alex Chekholko wrote:
>
> Up it to 32, see if you keep getting the message? :)
Okie! Thanks Alex! I'm going to try 32 now.
>
> Also check that you're actually running just 8:
> ps auxf|grep nfs
Just checked that. Yes. It is truely 8.
--
Rahul
_
- "Gus Correa" wrote:
> GPU programming lacks a common standard API,
Hopefully OpenCL will help address this!
--
Christopher Samuel - (03) 9925 4751 - Systems Manager
The Victorian Partnership for Advanced Computing
P.O. Box 201, Carlton South, VIC 3053, Australia
VPAC is a not-for-prof
- "Rahul Nabar" wrote:
> For a while I've been seeing errors of this sort in my
> /var/log/messages
Are you using ext3 for that filesystem by some chance ?
We long ago switched from RHEL to to Debian for our NFS
servers so we could use XFS rather than ext3 as ext3 just
couldn't keep up wit
2008/12/18 Rahul Nabar
> For a while I've been seeing errors of this sort in my /var/log/messages
>
>
>
> Question: This seems a suspicious place to change it. Isn't there a nfs
> config file somewhere else?
>
This depends on your distribution.
On SuSE Linux, look in /etc/sysconfig/nfs
I used
For a while I've been seeing errors of this sort in my /var/log/messages
kernel: nfsd: too many open TCP sockets, consider increasing the number of
nfsd threads
I googled a bunch and think the solution might be to boost RPCNFSDCOUNT in
the line "[ -z "$RPCNFSDCOUNT" ] && RPCNFSDCOUNT=8" in the f
Prentice Bisbal wrote:
Micha Feigin wrote:
I'm trying to learn cluster/parallel programing properly. I've got some
information on MPI, although I'm not sure if it's the best books. I was
wondering if you have some book recommendations regarding the more specialized
things, especially the cpu
Micha Feigin wrote:
> I'm trying to learn cluster/parallel programing properly. I've got some
> information on MPI, although I'm not sure if it's the best books. I was
> wondering if you have some book recommendations regarding the more specialized
> things, especially the cpu vs gpu paralelization
I'm trying to learn cluster/parallel programing properly. I've got some
information on MPI, although I'm not sure if it's the best books. I was
wondering if you have some book recommendations regarding the more specialized
things, especially the cpu vs gpu paralelization issue (or as far as I
under
Lux, James P wrote:
I can't find the Intel P/E cycle, but the Ridata units are 2x10^6 (2E+6).
Is that the underlying device wearout life, or is it the apparent life at
the "integrated unit"'s external interface. For instance, if they had a
The latter I believe, as consumers (the mass marke
Heh Chris,
Thanks for dropping a line. Heh, on your own department i happen to
see that in systems support
you've got a collegue Andrew Underwood. Would you mind asking him
whether he's family from Paul Underwood,
with 3 persons (Tony Reix, Paul and me says the fool) we're searching
for Wag
>>
>> If they are cherry picked, then it's not really a turning point
>> in SSDs. It also bothers me that a normal production run can
>> have parts with rewrites at 100K and 1M. Sounds like there
>> are some variabilities that can't be controlled.
>
> Similar things happen with RAM.
And in CPUs
Jeff Layton wrote:
Nifty Tom Mitchell wrote:
On Fri, Dec 12, 2008 at 04:35:26PM +0100, Peter Jakobi wrote:
Sun and Micron recently reported a million plus cycles for a single
level flash
product. Current shipping product is on the order of 10 cycles.
From what I understand these w
Nifty Tom Mitchell wrote:
On Fri, Dec 12, 2008 at 04:35:26PM +0100, Peter Jakobi wrote:
Sun and Micron recently reported a million plus cycles for a single level flash
product. Current shipping product is on the order of 10 cycles.
From what I understand these were cherry picked pa
2008/12/16 Vincent Diepeveen
>
> That's what we did do (not in cuda, simply at the pc).
> A single core P4 can render a second or 10 of animations of an entire scene
> within a few minutes.
> That's a 3d engine in C/C++ code, not even using SSE2 assembler.
>
>
Where do you get these figures from?
16 matches
Mail list logo
