...
Page Properties | ||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
Introduction:
This tool is meant to replace the 'pbs_diag' script which is currently the means to capture data from PBS for diagnostics.
...
The first version of the tool will also come with the ability to anonymize/obfuscate PBS data to enable users with sensitive data to obfuscate and share snapshots for bug reporting and debugging.
Shape and Form of a 'snapshot':
A 'snapshot', which will be the output produced by the pbs_snapshot tool, will be in the form of a directory containing the following files/sub-directories:
- server (qstat -Bf output): equivalent to the qmgr_Bf.out file generated by pbs_diag
- queues (qstat -Qf output): equivalent to the qmgr_Qf.out file generated by pbs_diag
nodes (pbsnodes -va output): equivalent to the pbsnodes_va.out file generated by pbs_diag
- jobs (qstat -f output): equivalent to the qstat_f.out file generated by pbs_diag
- sched (derived from qmgr print sched): equivalent to the qmgr_psched.out generated by pbs_diag
- pbs.conf: a copy of the pbs.conf file for the PBS system
- sched_priv sub-directory: a copy of the 'sched_priv' directory inside PBS_HOME with all the files.
- server_priv sub-directory: a copy of the 'server_priv' directory inside PBS_HOME, may or may not include accounting logs (see the -L option under "Interface Documentation")
- sched_logs sub-directory(optional): contains scheduler logs from the PBS_HOME/sched_logs directory for the number of days specified by -L option
- server_logs sub-directory(optional): contains server logs from the PBS_HOME/server_logs directory for the number of days specified by -L option
rscs (derived from the resourcedef file): Will list out built-in as well as custom resources in the following format:
Name: <resource name>
type = <resource type attribute>
flag = <resource flag attribute>Name: <resource name>
type = <resource type attribute>
flag = <resource flag attribute>...
...- resvs (pbs_rstat -f output): equivalent to the pbs_rstat_f.out file generated by pbs_diag
- ctime: this will log the time (since epoch) when the snapshot was taken.
Interface Documentation:
The interface for pbs_snapshot will be as follows:
...
- Synopsis: Option to display the version of pbs_snapshot being used
- Details:
- This will just display the version and exit
- The versions would display the version of PBSPro
Sample Usage:
- sudo pbs_snapshot: Will capture snapshot of the system without any logs, and will store the output inside /tmp/snapshot_<timestamp>
- sudo pbs_snapshot -L 10 -o mysnapshot: Will capture a snapshot at $PWD/mysnapshot along with 11 days of logs going back from the present day (including the present day's logs)
- sudo pbs_snapshot -L 10 -o mysnapshot --obfuscate --map=mapfile.txt: Will capture a snapshot at $PWD/mysnapshot along with 11 days of logs, will obfuscate the data and store data mapping in the map file named 'mapfile.txt'.
...