04-21-2010
Installation of MPI in a cluster of SMPs
Hi,
I've installed mpich2 v. 1.2.1p1 on a cluster of dual-processors with the default options (in previous versions I used 'ssm' device, but now I use 'nemesis').
I'd like that every time I execute a job (e.g. with 2 MPI-processes), each job's process be dispatched on a different machine (until to complete the maximum number of machines) and not on a same machine, viz :
Job A with 2 process:
Machine 1:
CPU0 Empty
CPU1 Used
Machine 2:
CPU0 Empty
CPU1 Used
but now it is scheduled as
Machine 1:
CPU0 Used
CPU1 Used
Machine 2:
CPU0 Empty
CPU1 Empty
Regards!
9 More Discussions You Might Find Interesting
1. Red Hat
Linux RedHat Cluster Manager InstallationAdministrationGuide (0 Replies)
Discussion started by: merlin
0 Replies
2. UNIX for Dummies Questions & Answers
hi, may i know how to run mpi after i had install the rock cluster? is there any guidelines or examples? (0 Replies)
Discussion started by: joannetan9984
0 Replies
3. High Performance Computing
Here are steps for installing the Solaris 10 11/06 OS, Solaris Cluster (formerly Sun Cluster) 3.2 software, QFS 4.5, and Oracle 10gR2 RAC. Also provided are instructions on how to configure QFS and Solaris Volume Manager for use with Oracle 10gR2 RAC.
More... (0 Replies)
Discussion started by: Linux Bot
0 Replies
4. High Performance Computing
Gurus,
I have several questions :
1. Does Solaris 10/OpenSolaris has some kind of web based management tools ?
Currently I am using WebMin. It worked fine, however I am very curious to use
the tools provided by Sun Microsystem.
Please advise for package name and how to activate.... (0 Replies)
Discussion started by: Zepiroth
0 Replies
5. High Performance Computing
Hai,
I am trying to install rock4.3 in my Intel core2 quad process, but when i insert kernel cd which is the first step in the installation procedure, it asks for driver disk not found.. insert CD/DVD ROM even after i inserted my CD in my driver.. could anyone help me in solving this problem...... (1 Reply)
Discussion started by: sasirekha
1 Replies
6. Solaris
While performing, solaris 10 U7 interactive initial installation I selected 'End User System Support' software group as below:
Select Software ___________________________________________________________
Select the Solaris software to install on the system.
NOTE: After selecting a software... (0 Replies)
Discussion started by: ramnagaraj
0 Replies
7. High Performance Computing
Hola, he instalado mpich2 vs. 1.2.1p1 en un cluster de biprocesadores con las opciones por defecto (antes usaba ssm pero visto que se quedaba colgado, lo he dejado con nemesis).
El caso es que quisiera que cada vez que lanzo un job (por ejemplo de 2 procesos), cada proceso del trabajo se fuera... (1 Reply)
Discussion started by: Sonia_
1 Replies
8. Solaris
Hello.
I'm trying to install two-node Solaris cluster. All nodes has three NICs (elxl0-elxl2). elxl0 is plumbed, other interfaces - not.
At firstnode I started scinstall, made custom install, wrote hostnames of all two nodes and choose elxl1/elxl2 for cluster interconnection.
After... (1 Reply)
Discussion started by: megabyte2003
1 Replies
9. Solaris
Hi Admins,
I came across an error while installing patch cluster on solaris.
# ./installcluster --s10cluster
ERROR: Another instance of an install script is already running for target
boot
environment '/'.
I did killed the related processes. Now there is no any process running from ps... (1 Reply)
Discussion started by: snchaudhari2
1 Replies
LEARN ABOUT CENTOS
del_timer_sync
DEL_TIMER_SYNC(9) Driver Basics DEL_TIMER_SYNC(9)
NAME
del_timer_sync - deactivate a timer and wait for the handler to finish.
SYNOPSIS
int del_timer_sync(struct timer_list * timer);
ARGUMENTS
timer
the timer to be deactivated
DESCRIPTION
This function only differs from del_timer on SMP: besides deactivating the timer it also makes sure the handler has finished executing on
other CPUs.
SYNCHRONIZATION RULES
Callers must prevent restarting of the timer, otherwise this function is meaningless. It must not be called from interrupt contexts unless
the timer is an irqsafe one. The caller must not hold locks which would prevent completion of the timer's handler. The timer's handler must
not call add_timer_on. Upon exit the timer is not queued and the handler is not running on any CPU.
NOTE
For !irqsafe timers, you must not hold locks that are held in interrupt context while calling this function. Even if the lock has nothing
to do with the timer in question. Here's why:
CPU0 CPU1 ---- ---- <SOFTIRQ> call_timer_fn; base->running_timer = mytimer; spin_lock_irq(somelock); <IRQ> spin_lock(somelock);
del_timer_sync(mytimer); while (base->running_timer == mytimer);
Now del_timer_sync will never return and never release somelock. The interrupt on the other CPU is waiting to grab somelock but it has
interrupted the softirq that CPU0 is waiting to finish.
The function returns whether it has deactivated a pending timer or not.
COPYRIGHT
Kernel Hackers Manual 3.10 June 2014 DEL_TIMER_SYNC(9)