Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Invalid "jsrun" failure #71

Open
cponder opened this issue Jan 18, 2021 · 1 comment
Open

Invalid "jsrun" failure #71

cponder opened this issue Jan 18, 2021 · 1 comment

Comments

@cponder
Copy link

cponder commented Jan 18, 2021

When I run commands like this

bin/shocdriver -p 0 -n 1 -d 0,1 -s 3 -cuda
bin/shocdriver -p 0 -n 1 -d 0,1 -s 3 -opencl

all of the tests fail, and some of the corresponding Log/* files say this

sh: 1: jsrun: not found

I don't get why this is happening, since this is the only reference I can find in the source

783        # check if we're on summit
784        if (index($host, "summit.olcf")) {
785            # summit uses jsrun
786            $command .= "jsrun -n $numTasks -a 1 -c 1 -g $numDevices ";

and the hostname is clearly set differently from "summit.olcf":

Hostname: luna-0063

The problem doesn't show up with single-GPU tests, likely because the launcher is not invoked.

@cponder
Copy link
Author

cponder commented Jan 18, 2021

I'm told that

 This is a mistake in their script, index() returns 0 if the names match and -1 otherwise so it should be if ( index() >= 0 ).

and I can see that this change to libexec/driver.pl fixes the problem:

 784c784
 <        if (index($host, "summit.olcf")) {
 ---
 >        if (index($host, "summit.olcf") >= 0) {

Can you please integrate the change?

@cponder cponder changed the title Inappropriate "jsrun" failure Invalid "jsrun" failure Jan 18, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant