Custom Query (101 matches)
Results (40 - 42 of 101)
Ticket | Resolution | Summary | Owner | Reporter |
---|---|---|---|---|
#64 | fixed | web interface of jobmonarch and joblist | somebody | alexis.michon@… |
Description |
Hello, Is it possible to integrate in the next release the possibility to see the jobs by pack of a configurable number like 25, 50, 100, 200 ? in jobmonarch (we have a lots of jobs archived) and in joblist (we have a lots of jobs running/queued). Something like a tableau and in the first page we can see the first 200 jobs, in the second page 200 to 400 and so on. I'm not sur if i'm clear. Like google do with these results. |
|||
#65 | fixed | Question about ganglia node name vs. PBS node name | ramonb | jsarlo@… |
Description |
We are using ROCKS 5.0 as our cluster framework. For ganglia, the node names are compute-X-Y.local, but for PBS, it uses compute-X-Y. Is there a way to have jobmonarch not think that these are two different nodes? Is there something simple I could add to the jobmond.py to just tack on a .local to the node names that the jobs are running on before it gets sent to gmetad? Thanks. Jeff |
|||
#67 | fixed | small patch to get lsf support working | ramonb | felix@… |
Description |
I had to patch jobmonarch as follows to get it to work with LSF (lava): [root@master52 jobmonarch]# svn diff Index: jobmond/jobmond.py =================================================================== --- jobmond/jobmond.py (revision 556) +++ jobmond/jobmond.py (working copy) @@ -717,7 +717,14 @@ if my_val_str: - my_val_str = my_val_str + ' ' + val_name + '=' + val_value + if type(val_value) != list: + + my_val_str = my_val_str + ' ' + val_name + '=' + val_value + + else: + + my_val_str = my_val_str + ' ' + val_name + '= ' + else: my_val_str = val_name + '=' + val_value @@ -1147,6 +1154,7 @@ if requested_cpus == None or requested_cpus == "": requested_cpus = 1 + display_queue = 1 if QUEUE: for q in QUEUE: if q == queue: I am using ganglia 3.0.7 and Python 2.4.3 |