pcp
[Top] [All Lists]
<prev [Date] next>
[Advanced]
 <prev [Thread] next>

Re: [pcp] per cpu utilisation from archive - pmval

from [Allan McAleavy] [Permanent Link][Original]
To: Ken McDonell <kenj@xxxxxxxxxxxxxxxx>
Subject: Re: [pcp] per cpu utilisation from archive - pmval
From: Allan McAleavy <allan.mcaleavy@xxxxxxxxx>
Date: Thu, 19 May 2016 13:43:40 +0100
Cc: pcp developers <pcp@xxxxxxxxxxx>
Delivered-to: pcp@xxxxxxxxxxx
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc; bh=o5o6y2MBKzhhk0wzmvzj8sE2GIEqy4Q6Eo47Nejoi44=; b=LqWN4CeikdtZ9Gfec12UguexVACwI2pE4fWIrtoZk2W4JJGQW2/2oun+fPbYHwsN7U 3pW8OZcHfG98SPj3dBJzTQqufSgkjVXi2nX7GAIwDKU8NhF4IKjEzq0fxO780nnYgVZ/ Tk9Ds7LrBymyv3HltaxrpFRKISZJXo8zHLna9VqEJWTJCMofqMGW/mFFUdNIc8EROB/m FCeOcuMl9rlE0NAC/IAl5IthBduolPI1UNisDjEPaQo4N6pvDZYGALFfpyVtwJ7eCeYE xRnJ3StPN1r0hIrWxBLM7hUapmzgZ7v59GerIVQ10lIokK2XxaCmI+iiCZDUhr5CkdYn afog==
In-reply-to: <573DA17D.7040408@xxxxxxxxxxxxxxxx>
References: <CAF6XsOcfikRQ-EJ9cM+iuHhpHEinvKaKDWm3oB27gMPwF2vcOw@xxxxxxxxxxxxxx> <573D0011.5090505@xxxxxxxxxxxxxxxx> <CAF6XsOeRrup35qqzpbB7mKH+cOdKrPHoLJENZDobn5qPWTUzfA@xxxxxxxxxxxxxx> <573DA17D.7040408@xxxxxxxxxxxxxxxx>
Hi Ken

As we have a default of one minute for the pmlogger , I was wanting to gather per cpu %util from the archive on the command line. So following your example where I have one second samples.

Run a five second workload over 12 cores , pmlogger logging at 1 second intervals.

PCP_DERIVED_CONFIG=/var/tmp/user_pct pmval -f3 kernel.pct.cpu.user -s 30 > /var/tmp/pmval.log & Âmpstat -P ALL 1 30 > /var/tmp/mpstat.log & sleep 5 ; stress -c 12 --timeout 5

cat /var/tmp/user_pct
kernel.pct.cpu.user = 100 * kernel.percpu.cpu.user

Take a sample from mpstat where we do some work.
12:36:03   CPU  Â%usr  %nice  Â%sys %iowait  Â%irq  %soft Â%steal Â%guest  %idle
12:36:04   all  71.38  Â0.00  Â0.44  Â0.00  Â0.00  Â0.00  Â0.00  Â0.00  28.19
12:36:04 Â Â Â 0 Â 96.97 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â3.03
12:36:04 Â Â Â 1 Â 73.00 Â Â0.00 Â Â1.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 26.00
12:36:04 Â Â Â 2 Â 90.00 Â Â0.00 Â Â1.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â9.00
12:36:04 Â Â Â 3 Â100.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00
12:36:04 Â Â Â 4 Â 21.00 Â Â0.00 Â Â2.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 77.00
12:36:04 Â Â Â 5 Â100.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00
12:36:04 Â Â Â 6 Â 93.07 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â6.93
12:36:04 Â Â Â 7 Â 74.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 26.00
12:36:04 Â Â Â 8 Â 72.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 28.00
12:36:04 Â Â Â 9 Â 91.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â9.00
12:36:04 Â Â Â10 Â100.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00
12:36:04 Â Â Â11 Â100.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00
12:36:04 Â Â Â12 Â Â1.00 Â Â0.00 Â Â3.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 96.00
12:36:04 Â Â Â13 Â 21.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 79.00
12:36:04 Â Â Â14 Â Â9.90 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 90.10
12:36:04 Â Â Â15 Â100.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00

Take the 6th sample from the pmval file.Â

metric: Â Âkernel.pct.cpu.user
host: Â Â Âxxxxxxxx
semantics: cumulative counter (converting to rate)
units: Â Â millisec (converting to time utilization)
samples: Â 30
interval: Â1.00 sec

Âcpu0 Âcpu1 Âcpu2 Âcpu3 Âcpu4 Âcpu5 Âcpu6 Âcpu7 Âcpu8 Âcpu9 cpu10 cpu11 cpu12 cpu13 cpu14 cpu15
Â0.000 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000 0.000
Â0.999 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.999 0.000 0.000 0.000 0.000 0.000 0.000
Â0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
Â1.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 1.000 0.000 0.000 0.000 0.000 0.000 0.000
Â1.999 0.000 5.997 7.996 0.000 5.997 0.000 0.000 0.000 0.000 5.997 6.996 0.000 0.000 0.000 5.997
Â99.936 72.953 83.946 99.936 27.982 Â100.935 97.937 80.948 71.954 96.938 Â100.935 99.936 3.997 27.982 15.990 99.936 Â-- sample to match.Â
Â99.933 39.973 47.968 99.933 3.997 59.960 47.968 97.934 0.999 99.933 99.933 99.933 99.933 99.933 99.933 96.935
Â99.935 63.958 48.968 99.935 40.973 82.946 9.993 50.967 0.999 99.935 99.935 99.935 99.935 99.935 99.935 99.935
Â99.935 98.935 47.969 99.935 52.965 74.951 0.000 25.983 0.000 Â100.934 99.935 99.935 99.935 99.935 99.935 99.935
Â91.951 59.968 0.999 91.951 39.979 71.962 22.988 50.973 27.985 90.952 91.951 91.951 91.951 91.951 91.951 91.951
Â0.999 0.999 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.999 0.000 0.000 0.000 0.000 0.000 0.000

ÂWe can see that these roughly match on a 1 second interval from the pmval and mpstat data.Â
Â
cpu0 cpu1 cpu2 cpu3 cpu4 cpu5 cpu6 cpu7 cpu8 cpu9 cpu10 cpu11 cpu12 cpu13 cpu14 cpu15
96.97 73 90 100 21 100 93.07 74 72 91 100 100 1 21 9.9 100 Â Â (MPSTAT DATA )Â
99.936 72.953 83.946 99.936 27.982 100.935 97.937 80.948 71.954 96.938 100.935 99.936 3.997 27.982 15.99 99.936 Â(PMVAL DATA - realtime)

Taking the data from the archive.Â

PCP_DERIVED_CONFIG=/var/tmp/user_pct pmval -w8 -f2 kernel.pct.cpu.user -a /var/log/pcp/pmlogger/udapp40a/20160519.10.50.0Â
       Âcpu0   cpu1   cpu2   cpu3   cpu4   cpu5   cpu6   cpu7   cpu8   cpu9  Âcpu10  Âcpu11  Âcpu12  Âcpu13  Âcpu14  Âcpu15
12:36:04.531 Â 81.30 Â Â69.90 Â Â85.20 Â Â86.10 Â Â10.50 Â Â86.10 Â Â79.40 Â Â61.20 Â Â68.90 Â Â76.60 Â Â86.10 Â Â86.10 Â Â 1.00 Â Â10.50 Â Â 0.00 Â Â85.20
12:36:05.531 Â 98.80 Â Â36.70 Â Â49.90 Â Â99.00 Â Â16.90 Â Â65.40 Â Â51.70 Â Â95.90 Â Â 4.10 Â Â98.50 Â Â99.00 Â Â99.00 Â Â81.60 Â Â95.60 Â Â94.10 Â Â97.00
12:36:06.531 Â100.00 Â Â51.30 Â Â37.40 Â 100.00 Â Â39.00 Â Â89.90 Â Â24.00 Â Â58.70 Â Â 1.00 Â 100.00 Â Â99.00 Â 100.00 Â Â99.50 Â Â99.00 Â 100.00 Â Â98.90
12:36:07.531 Â100.00 Â Â96.30 Â Â60.10 Â 100.00 Â Â40.10 Â Â63.20 Â Â 0.90 Â Â38.70 Â Â 0.00 Â 100.00 Â 100.00 Â 100.00 Â 100.00 Â 100.00 Â 100.00 Â 100.00
12:36:08.531 Â100.00 Â Â69.20 Â Â 3.40 Â 100.00 Â Â57.30 Â Â88.90 Â Â22.10 Â Â40.90 Â Â17.30 Â 100.00 Â 100.00 Â 100.00 Â 100.00 Â 100.00 Â 100.00 Â 100.00
12:36:09.531 Â 13.60 Â Â13.30 Â Â 0.00 Â Â13.60 Â Â 2.20 Â Â 3.50 Â Â 0.90 Â Â11.30 Â Â10.40 Â Â14.60 Â Â14.60 Â Â13.60 Â Â13.60 Â Â14.60 Â Â13.60 Â Â13.60

And looking at one CPUÂ

CPU 7Â
12:36:04.531 61.20
12:36:05.531 95.90
12:36:06.531 58.70
12:36:07.531 38.70
12:36:08.531 40.90
12:36:09.531 11.30

grep " Â Â Â7" mpstat.log.test1
12:36:04 Â Â Â 7 Â 74.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 26.00
12:36:05 Â Â Â 7 Â 98.00 Â Â0.00 Â Â2.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00
12:36:06 Â Â Â 7 Â 52.48 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 47.52
12:36:07 Â Â Â 7 Â 31.31 Â Â0.00 Â Â0.00 Â Â1.01 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 67.68
12:36:08 Â Â Â 7 Â 51.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 49.00

So I am happy with the output as that shows similar from pmlog given sampling.

Test2 - Default setting 1 min.


mpstat dataÂ
13:26:55   CPU  Â%usr  %nice  Â%sys %iowait  Â%irq  %soft Â%steal Â%guest  %idle
13:26:56   all  67.56  Â0.00  Â0.31  Â0.00  Â0.00  Â0.00  Â0.00  Â0.00  32.12
13:26:56 Â Â Â 0 Â 98.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â2.00
13:26:56 Â Â Â 1 Â 88.89 Â Â0.00 Â Â2.02 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â9.09
13:26:56 Â Â Â 2 Â 97.03 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â2.97
13:26:56 Â Â Â 3 Â 99.01 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.99
13:26:56 Â Â Â 4 Â 97.98 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â2.02
13:26:56 Â Â Â 5 Â 96.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â4.00
13:26:56 Â Â Â 6 Â 98.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â2.00
13:26:56 Â Â Â 7 Â 74.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 26.00
13:26:56 Â Â Â 8 Â 46.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 54.00
13:26:56 Â Â Â 9 Â 92.93 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â7.07
13:26:56 Â Â Â10 Â Â0.00 Â Â0.00 Â Â2.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 98.00
13:26:56 Â Â Â11 Â100.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00
13:26:56 Â Â Â12 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â100.00
13:26:56 Â Â Â13 Â 94.95 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â5.05
13:26:56 Â Â Â14 Â Â0.00 Â Â0.00 Â Â1.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â 99.00
13:26:56 Â Â Â15 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â Â0.00 Â100.00

Âcpu0 Âcpu1 Âcpu2 Âcpu3 Âcpu4 Âcpu5 Âcpu6 Âcpu7 Âcpu8 Âcpu9 cpu10 cpu11 cpu12 cpu13 cpu14 cpu15
Â0.998 1.996 0.998 0.998 0.000 0.000 0.000 0.000 0.000 0.000 1.996 2.994 0.000 0.998 0.000 0.000
Â0.999 0.999 0.000 0.999 0.000 0.000 0.000 0.000 0.999 0.999 2.998 1.999 0.000 0.000 0.000 0.000
Â0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.999 0.000 0.000 0.000 0.000 0.000 0.000
Â0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
Â0.000 0.000 0.000 1.999 0.000 0.000 0.000 0.000 0.000 0.999 0.000 2.998 0.000 0.000 0.000 0.000
Â100.319 90.387 Â100.319 Â100.319 99.326 98.333 Â100.319 76.481 48.670 94.360 0.000 99.326 0.000 96.346 0.000 0.000 -- our data ( 1st sample )
Â99.923 97.925 99.923 99.923 99.923 99.923 99.923 99.923 99.923 99.923 0.000 99.923 3.997 99.923 2.998 0.999
Â81.944 97.933 99.932 63.956 99.932 99.932 99.932 99.932 99.932 99.932 0.999 99.932 17.988 99.932 0.999 34.976
Â5.996 98.931 54.962 40.971 48.966 99.930 10.992 99.930 99.930 59.958 88.938 Â100.930 99.930 99.930 89.937 99.930
Â1.999 96.938 41.973 74.952 52.966 96.938 0.000 95.939 95.939 20.987 96.938 95.939 95.939 96.938 96.938 96.938
Â0.999 0.999 0.000 1.999 0.000 0.000 0.000 0.000 0.999 0.000 0.999 0.999 0.999 0.000 0.000 0.000

Â98 Â 88.89 97.03 Â99.01 Â97.98 96 Â 98 Â 74 Â46 92.93Â 0 Â ÂÂ100ÂÂ Â0 94.95Â 0 0 Â Â(MPSTAT DATA )Â
Â100.319 90.387 Â100.319 Â100.319 99.326 98.333 Â 100.319 76.481 48.670 94.360 Â0.000 99.326 0.000 96.346 0.000 0.000 Â(PMVAL DATA - realtime)

So we match ok as sampling at 1 second.
Â
PCP_DERIVED_CONFIG=/var/tmp/user_pct pmval -w8 -f2 kernel.pct.cpu.user -a 20160519.13.26.0

From the archive. ( started test at 13:26:51 - 13:27:20)Â
            ÂÂÂcpu0   cpu1   cpu2   cpu3   cpu4   cpu5   cpu6   cpu7   cpu8   cpu9   cpu10  cpu11   cpu12  cpu13   cpu14  cpu15
13:26:51.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.40 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 8.00 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:26:52.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:26:53.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.80 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.40 Â Â 8.80 Â Â 3.60 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:26:54.759 Â Â5.10 Â Â 8.40 Â Â 6.80 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:26:55.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.40 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:26:56.759 Â Â5.00 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 8.00 Â Â 7.40 Â Â 6.60 Â Â 3.40 Â Â 8.70 Â Â 3.60 Â Â 8.30 Â Â 3.10 Â Â 4.00
13:26:57.759 Â Â5.10 Â Â 8.50 Â Â 6.80 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:26:58.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.40 Â Â 6.80 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.20 Â Â 3.20 Â Â 3.90
13:26:59.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.60 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:27:00.759 Â Â5.10 Â Â 8.40 Â Â 6.80 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.40 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:01.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 8.00 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:02.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.60 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:27:03.759 Â Â5.00 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.80 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.40 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.10 Â Â 3.90
13:27:04.759 Â Â5.10 Â Â 8.40 Â Â 6.80 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.70 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:05.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.40 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:27:06.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 8.00 Â Â 7.50 Â Â 6.50 Â Â 3.40 Â Â 8.80 Â Â 3.60 Â Â 8.20 Â Â 3.20 Â Â 3.90
13:27:07.759 Â Â5.10 Â Â 8.40 Â Â 6.80 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:08.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.80 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:27:09.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.30 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.40 Â Â 8.80 Â Â 3.60 Â Â 8.30 Â Â 3.10 Â Â 3.90
13:27:10.759 Â Â5.00 Â Â 8.40 Â Â 6.80 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:11.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 8.00 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:27:12.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.40 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.40 Â Â 8.70 Â Â 3.60 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:13.759 Â Â5.10 Â Â 8.40 Â Â 6.80 Â Â 6.50 Â Â 6.80 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.20 Â Â 3.20 Â Â 4.00
13:27:14.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:15.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.60 Â Â 3.40 Â Â 8.80 Â Â 3.60 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:16.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 8.00 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.10 Â Â 4.00
13:27:17.759 Â Â5.00 Â Â 8.40 Â Â 6.80 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:18.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.80 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.40 Â Â 8.80 Â Â 3.60 Â Â 8.30 Â Â 3.20 Â Â 3.90
13:27:19.759 Â Â5.10 Â Â 8.40 Â Â 6.90 Â Â 6.50 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.50 Â Â 6.50 Â Â 3.50 Â Â 8.70 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 4.00
13:27:20.759 Â Â5.10 Â Â 8.40 Â Â 6.80 Â Â 6.40 Â Â 6.70 Â Â 8.30 Â Â 5.20 Â Â 7.90 Â Â 7.40 Â Â 6.60 Â Â 3.50 Â Â 8.80 Â Â 3.70 Â Â 8.30 Â Â 3.20 Â Â 3.90


So from above is where I was having the issue converting this to a per CPU utilisation.

Thanks
Al



On Thu, May 19, 2016 at 12:20 PM, Ken McDonell <kenj@xxxxxxxxxxxxxxxx> wrote:
On 19/05/16 21:04, Allan McAleavy wrote:
Hi All

Ok so I have this now working, my pmlogger was running as follows, so
the data was in 1 min samples.

pmlogger -P -r -T24h10m -c config.default -m pmlogger_check 20160519.10.50

Changing to -t 1 gives the appropriate result. What is the best practice
for this? or should I have still been able to get similar results with
the default option? version running is pcp-3.10.9-6.el6.x86_64

Thanks for everyone's help on this.

Not sure I'm following all of this.

Adding -t 1 to the pmlogger command line would change the logging interval from 1 minute to 1 second for any metrics named in config.default with a "default" logging interval.

Depending on the contents of config.default this could mean something between no change and 60 times more data being logged.

The choice if -t for the replay tools is largely independent of the choice of the logging intervals in the archive ... most of the tools use interpolate mode where we effectively do straight line interpolation between the logged data to synthesize the values at the times the reporting tools are asking for it.

[More with this subject...]
<Prev in Thread] Current Thread [Next in Thread>
Previous by Date:  Re: [pcp] Oracle connection debugging (was Re: Handling Oracle PMDA Latencies), Ken McDonell
Next by Date:  Re: [pcp] Oracle connection debugging (was Re: Handling Oracle PMDA Latencies), Marko Myllynen
Previous by Thread:  Re: [pcp] per cpu utilisation from archive - pmval, Ken McDonell
Next by Thread:  [Bug 1336808] New: RFE: Provide uncached per-process memory metrics, bugzilla
Indexes:  [Date] [Thread] [Top] [All Lists]