Changes between Version 10 and Version 11 of Public/Energy

Timestamp:

Dec 17, 2020, 2:36:24 PM (3 years ago)

Author:

Michael Ott

Comment:

—

Public/Energy

@@ -3 +3 @@
 For the CM and ESB modules there is fine-grained energy measurement in place using Megware's energy meters, attached to the respective compute nodes. In addition, the DCDB monitoring framework is deployed on the entire DEEP-EST prototype, providing a variety of sensor measurements in addition to energy consumption. There are different ways to get information about energy consumption for your jobs (and the nodes). Preferred methods are: 
 
-=== SLURM sacctl command
+=== SLURM sacct command
 
 This is probably the easiest way to get energy consumption for your interactive and batch jobs. Once your job has finished, you can use the
@@ -40 +40 @@
 
 {{{
-dcdbconfig sensor listpublic
+dcdbconfig sensor list
 }}}
 
@@ -75 +75 @@
 }}}
 
-Instead of a single sensor, a list of space-separated sensor names can be supplied as well; these will be queried sequentially. Instead of using relative time-stamps, absolute time-stamps (in nanoseconds) can also be used:
-
-{{{
-Example: dcdbquery /deepest/cn/s01/power 159654356469315800 1596543788812750000
+Instead of a single sensor, a list of space-separated sensor names can be supplied as well; these will be queried sequentially. Instead of using relative time-stamps, absolute UNIX time-stamps (in s, ms, ns) as well as time/date strings can also be used:
+
+{{{
+Example: dcdbquery /deepest/cn/s01/power 1596543564693158000 1596543788812750000
+         dcdbquery /deepest/cn/s01/power "2020-08-04 14:19:24" "2020-08-04 14:23:08"
 }}}
 
@@ -150 +151 @@
 
 {{{
-dcdbconfig sensor listpublic | grep beegfs
+dcdbconfig sensor list | grep beegfs
 }}}