[gpfsug-discuss] Wrong behavior of mmperfmon
Dorigo Alvise (PSI)
alvise.dorigo at psi.ch
Fri Nov 16 08:29:46 GMT 2018
Indeed,
I just realized that after last recent update to dssg-2.0a ntpd is crashing very frequently.
Thanks for the hint.
Alvise
________________________________
From: gpfsug-discuss-bounces at spectrumscale.org [gpfsug-discuss-bounces at spectrumscale.org] on behalf of Olaf Weiser [olaf.weiser at de.ibm.com]
Sent: Thursday, November 15, 2018 9:35 PM
To: gpfsug main discussion list
Subject: Re: [gpfsug-discuss] Wrong behavior of mmperfmon
ntp running / time correct ?
From: "Dorigo Alvise (PSI)" <alvise.dorigo at psi.ch>
To: "gpfsug-discuss at spectrumscale.org" <gpfsug-discuss at spectrumscale.org>
Date: 11/15/2018 04:30 PM
Subject: [gpfsug-discuss] Wrong behavior of mmperfmon
Sent by: gpfsug-discuss-bounces at spectrumscale.org
________________________________
Hello,
I'm using mmperfmon to get writing stats on NSD during a write activity on a GPFS filesystem (Lenovo system with dss-g-2.0a).
I use this command:
# mmperfmon query 'sf-dssio-1.psi.ch|GPFSNSDFS|RAW|gpfs_nsdfs_bytes_written' --number-buckets 48 -b 1
to get the stats. What it returns is a list of valid values followed by a longer list of 'null' as shown below:
Legend:
1: sf-dssio-1.psi.ch|GPFSNSDFS|RAW|gpfs_nsdfs_bytes_written
Row Timestamp gpfs_nsdfs_bytes_written
1 2018-11-15-16:15:57 746586112
2 2018-11-15-16:15:58 704643072
3 2018-11-15-16:15:59 805306368
4 2018-11-15-16:16:00 754974720
5 2018-11-15-16:16:01 754974720
6 2018-11-15-16:16:02 763363328
7 2018-11-15-16:16:03 746586112
8 2018-11-15-16:16:04 746848256
9 2018-11-15-16:16:05 780140544
10 2018-11-15-16:16:06 679923712
11 2018-11-15-16:16:07 746618880
12 2018-11-15-16:16:08 780140544
13 2018-11-15-16:16:09 746586112
14 2018-11-15-16:16:10 763363328
15 2018-11-15-16:16:11 780173312
16 2018-11-15-16:16:12 721420288
17 2018-11-15-16:16:13 796917760
18 2018-11-15-16:16:14 763363328
19 2018-11-15-16:16:15 738197504
20 2018-11-15-16:16:16 738197504
21 2018-11-15-16:16:17 null
22 2018-11-15-16:16:18 null
23 2018-11-15-16:16:19 null
24 2018-11-15-16:16:20 null
25 2018-11-15-16:16:21 null
26 2018-11-15-16:16:22 null
27 2018-11-15-16:16:23 null
28 2018-11-15-16:16:24 null
29 2018-11-15-16:16:25 null
30 2018-11-15-16:16:26 null
31 2018-11-15-16:16:27 null
32 2018-11-15-16:16:28 null
33 2018-11-15-16:16:29 null
34 2018-11-15-16:16:30 null
35 2018-11-15-16:16:31 null
36 2018-11-15-16:16:32 null
37 2018-11-15-16:16:33 null
38 2018-11-15-16:16:34 null
39 2018-11-15-16:16:35 null
40 2018-11-15-16:16:36 null
41 2018-11-15-16:16:37 null
42 2018-11-15-16:16:38 null
43 2018-11-15-16:16:39 null
44 2018-11-15-16:16:40 null
45 2018-11-15-16:16:41 null
46 2018-11-15-16:16:42 null
47 2018-11-15-16:16:43 null
48 2018-11-15-16:16:44 null
If I run again and again I still get the same pattern: valid data (even 0 in case of not write activity) followed by more null data.
Is that normal ? If not, is there a way to get only non-null data by fine-tuning pmcollector's configuration file ?
The corresponding ZiMon sensor (GPFSNSDFS) have period=1.
The ZiMon version is 4.2.3-7.
Thanks,
Alvise
_______________________________________________
gpfsug-discuss mailing list
gpfsug-discuss at spectrumscale.org
http://gpfsug.org/mailman/listinfo/gpfsug-discuss
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://gpfsug.org/pipermail/gpfsug-discuss_gpfsug.org/attachments/20181116/80b95fe3/attachment-0002.htm>
More information about the gpfsug-discuss
mailing list