CODEWITHSUNDEEP
scheduleraltairsungridengine
Yash Chauhan
Yash Chauhan

Reputation: 366

Grid Engine - How to detect cluster node status?

I'm currently working with Altair Grid Engine and I need to find a way to determine the status of each node in Altair Grid Engine (i.e., whether it is running or stopped). I have already tried a couple of commands, but they don't provide the information I need.

Here's what I have attempted so far:

qconf -sel: This command helped me obtain a list of registered nodes in the cluster. However, it doesn't provide any specific information about the state or status of each node.

qconf -se <cluster-node-name>: This command gives me cluster information for a specific node. Unfortunately, the information returned doesn't include any details about the node's state or status.

I tried with qhost -F, it does show the cluster information but, not the current status of that node.

I would greatly appreciate it if someone could guide me on how to detect the status of each cluster node accurately. Is there any other command or method that I should try?

Thank you in advance for your assistance!

Upvotes: 1

Views: 949

Answers (2)

Carlos Madrid
Carlos Madrid

Reputation: 26

qstat -u -f <queue_name>

The -f option causes summary information on all queues to be displayed along with the queued job list.

Example:

qstat -f -q 12cores.q

queuename        qtype resv/used/tot. load_avg arch          states
---------------------------------------------------------------------------
[email protected]   BIP   0/0/12         -NA-     lx-amd64     au
---------------------------------------------------------------------------
[email protected]   BIP   0/12/12        12.00    lx-amd64      
---------------------------------------------------------------------------
[email protected]   BIP   0/12/12        11.97    lx-amd64      
---------------------------------------------------------------------------
[email protected]   BIP   0/12/12        12.02    lx-amd64      
---------------------------------------------------------------------------
[email protected]   BIP   0/12/12        12.03    lx-amd64      
---------------------------------------------------------------------------

Upvotes: 1

William Hay
William Hay

Reputation: 2308

Depends what you mean by the status of a node. In gridengine the status shows up on the queue instances. You could try either qhost -q or use qselect -qs u ;qselect -qs E ;qselect -qs a to get a list of queue instances on uncontactable hosts, queue instances in an error state or alarmed queue instances.

Upvotes: 0

Related Questions