<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Server Performance Analysis in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437929#M6019</link>
    <description>Hi everybody,&lt;BR /&gt;&lt;BR /&gt;I am having problem in pinpointing the exact reason of slow response of my&lt;BR /&gt;Database Server.&lt;BR /&gt;Below are the output of top and Informix command 'onstat' &lt;BR /&gt;It shows System utilisation 50% and User utilisation as 25%. Does this means&lt;BR /&gt;that my system is using up all my system resources. What is the exact relation between the user usage and system usage ? How can I bring down the System Utilisation ?&lt;BR /&gt;&lt;BR /&gt;System: himalaya                                      Sat Aug 19 11:53:30 2000&lt;BR /&gt;Load averages: 3.49, 2.81, 2.64&lt;BR /&gt;116 processes: 104 sleeping, 12 running&lt;BR /&gt;Cpu states:&lt;BR /&gt;CPU   LOAD   USER   NICE    SYS   IDLE  BLOCK  SWAIT   INTR   SSYS&lt;BR /&gt; 0        6.81  16.8%   0.0%    12.1%  71.1%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt; 1       1.39  28.9%   0.0%     67.3%   3.8%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt; 2       2.61  37.2%   0.0%     59.2%   3.6%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt; 3       3.13  26.1%   0.0%     68.9%   5.0%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt;---   ----  -----  -----  -----  -----  -----  -----  -----  -----&lt;BR /&gt;avg     3.49  27.3%   0.0%     51.9%  20.8%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt;&lt;BR /&gt;Memory: 36564K (32696K) real, 101476K (96472K) virtual, 13620K free  Page# 1/13&lt;BR /&gt;&lt;BR /&gt;CPU TTY   PID USERNAME PRI NI   SIZE    RES STATE    TIME %WCPU  %CPU COMMAND&lt;BR /&gt; 2 rroot  2193 informix 154 20  8060K   780K sleep  216:04 89.61 89.45 oninit&lt;BR /&gt; 1 rroot  2192 informix 180 20  8060K   780K run    203:07 87.82 87.67 oninit&lt;BR /&gt; 3 rroot  2190 informix 180 20  8060K   792K run    215:29 81.15 81.00 oninit&lt;BR /&gt; 0 rroot  2194 informix 154 20  8060K   816K sleep  118:54 29.24 29.19 oninit&lt;BR /&gt; 2 rroot  2046 root      20 20  9544K  8320K sleep   11:21  2.01  2.01 cmcld&lt;BR /&gt; 2 rroot  1184 root     154 20   404K    92K sleep    5:47  1.03  1.03 inetd&lt;BR /&gt; 0 rroot     2 root     128 20     0K     0K sleep    3:27  0.85  0.84 vhand&lt;BR /&gt; 0 rroot    34 root     152 20     0K     0K run      0:41  0.78  0.78 vxfsd&lt;BR /&gt; 0 rroot   357 root     154 20    32K    40K sleep    4:11  0.75  0.74 syncer  &lt;BR /&gt;&lt;BR /&gt;Informix Dynamic Server Version 7.31.FC4    -- On-Line -- Up 11:22:03 -- 3220672&lt;BR /&gt; Kbytes&lt;BR /&gt;&lt;BR /&gt;Segment Summary:&lt;BR /&gt;id                key              addr                   size             ovhd     class blkused blkfree &lt;BR /&gt;97286    1384728577 c0000000001dd000 299040768        5624     R     36495    9   &lt;BR /&gt; &lt;BR /&gt;7        1384728578 c000000011f0d000 1610612736       25208    V     196608   0 &lt;BR /&gt;      &lt;BR /&gt;8        1384728579 c000000071f14000 1073741824       17016    V     129920   1152    &lt;BR /&gt;1033     1384728580 c0000000b1f14000 104857600        2232     V     11637    1163    &lt;BR /&gt;10       1384728581 c0000000b8314000 104857600        2232     V     7760      5040    &lt;BR /&gt;1035     1384728582 c0000000be714000 104857600        2232     V     1360     11440   &lt;BR /&gt;Total:   -          -                3297968128       -        -     383780   18&lt;BR /&gt;804   &lt;BR /&gt;&lt;BR /&gt;   (* segment locked in memory)&lt;BR /&gt;&lt;BR /&gt;Please help..&lt;BR /&gt;Thanks in advance.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Sat, 19 Aug 2000 06:06:26 GMT</pubDate>
    <dc:creator>PROSANJIT MALLICK</dc:creator>
    <dc:date>2000-08-19T06:06:26Z</dc:date>
    <item>
      <title>Server Performance Analysis</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437929#M6019</link>
      <description>Hi everybody,&lt;BR /&gt;&lt;BR /&gt;I am having problem in pinpointing the exact reason of slow response of my&lt;BR /&gt;Database Server.&lt;BR /&gt;Below are the output of top and Informix command 'onstat' &lt;BR /&gt;It shows System utilisation 50% and User utilisation as 25%. Does this means&lt;BR /&gt;that my system is using up all my system resources. What is the exact relation between the user usage and system usage ? How can I bring down the System Utilisation ?&lt;BR /&gt;&lt;BR /&gt;System: himalaya                                      Sat Aug 19 11:53:30 2000&lt;BR /&gt;Load averages: 3.49, 2.81, 2.64&lt;BR /&gt;116 processes: 104 sleeping, 12 running&lt;BR /&gt;Cpu states:&lt;BR /&gt;CPU   LOAD   USER   NICE    SYS   IDLE  BLOCK  SWAIT   INTR   SSYS&lt;BR /&gt; 0        6.81  16.8%   0.0%    12.1%  71.1%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt; 1       1.39  28.9%   0.0%     67.3%   3.8%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt; 2       2.61  37.2%   0.0%     59.2%   3.6%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt; 3       3.13  26.1%   0.0%     68.9%   5.0%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt;---   ----  -----  -----  -----  -----  -----  -----  -----  -----&lt;BR /&gt;avg     3.49  27.3%   0.0%     51.9%  20.8%   0.0%   0.0%   0.0%   0.0%&lt;BR /&gt;&lt;BR /&gt;Memory: 36564K (32696K) real, 101476K (96472K) virtual, 13620K free  Page# 1/13&lt;BR /&gt;&lt;BR /&gt;CPU TTY   PID USERNAME PRI NI   SIZE    RES STATE    TIME %WCPU  %CPU COMMAND&lt;BR /&gt; 2 rroot  2193 informix 154 20  8060K   780K sleep  216:04 89.61 89.45 oninit&lt;BR /&gt; 1 rroot  2192 informix 180 20  8060K   780K run    203:07 87.82 87.67 oninit&lt;BR /&gt; 3 rroot  2190 informix 180 20  8060K   792K run    215:29 81.15 81.00 oninit&lt;BR /&gt; 0 rroot  2194 informix 154 20  8060K   816K sleep  118:54 29.24 29.19 oninit&lt;BR /&gt; 2 rroot  2046 root      20 20  9544K  8320K sleep   11:21  2.01  2.01 cmcld&lt;BR /&gt; 2 rroot  1184 root     154 20   404K    92K sleep    5:47  1.03  1.03 inetd&lt;BR /&gt; 0 rroot     2 root     128 20     0K     0K sleep    3:27  0.85  0.84 vhand&lt;BR /&gt; 0 rroot    34 root     152 20     0K     0K run      0:41  0.78  0.78 vxfsd&lt;BR /&gt; 0 rroot   357 root     154 20    32K    40K sleep    4:11  0.75  0.74 syncer  &lt;BR /&gt;&lt;BR /&gt;Informix Dynamic Server Version 7.31.FC4    -- On-Line -- Up 11:22:03 -- 3220672&lt;BR /&gt; Kbytes&lt;BR /&gt;&lt;BR /&gt;Segment Summary:&lt;BR /&gt;id                key              addr                   size             ovhd     class blkused blkfree &lt;BR /&gt;97286    1384728577 c0000000001dd000 299040768        5624     R     36495    9   &lt;BR /&gt; &lt;BR /&gt;7        1384728578 c000000011f0d000 1610612736       25208    V     196608   0 &lt;BR /&gt;      &lt;BR /&gt;8        1384728579 c000000071f14000 1073741824       17016    V     129920   1152    &lt;BR /&gt;1033     1384728580 c0000000b1f14000 104857600        2232     V     11637    1163    &lt;BR /&gt;10       1384728581 c0000000b8314000 104857600        2232     V     7760      5040    &lt;BR /&gt;1035     1384728582 c0000000be714000 104857600        2232     V     1360     11440   &lt;BR /&gt;Total:   -          -                3297968128       -        -     383780   18&lt;BR /&gt;804   &lt;BR /&gt;&lt;BR /&gt;   (* segment locked in memory)&lt;BR /&gt;&lt;BR /&gt;Please help..&lt;BR /&gt;Thanks in advance.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Sat, 19 Aug 2000 06:06:26 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437929#M6019</guid>
      <dc:creator>PROSANJIT MALLICK</dc:creator>
      <dc:date>2000-08-19T06:06:26Z</dc:date>
    </item>
    <item>
      <title>Re: Server Performance Analysis</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437930#M6020</link>
      <description>That system utilization rate is referring to the percentage of CPU spent on system calls.  These system calls may be in turn triggered by your user process(es).  My suggestion is to first locate what user process(es) are using up the CPU then find out which system call they made.  I've seem a case where a database systems kept looping on the 'select' call for nowait I/Os, and that the server process just loop'ed too frequent hence system utilization rate increased to a high percentage as a result.  So, watch out for your Informix and some tuning on it may be required.&lt;BR /&gt;&lt;BR /&gt;Last time I used glance to find out what the problem was.  If you got glance in your place then just give it a try.&lt;BR /&gt;&lt;BR /&gt;Rgds,&lt;BR /&gt;Philip</description>
      <pubDate>Sat, 19 Aug 2000 11:04:15 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437930#M6020</guid>
      <dc:creator>Philip Chan_1</dc:creator>
      <dc:date>2000-08-19T11:04:15Z</dc:date>
    </item>
    <item>
      <title>Re: Server Performance Analysis</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437931#M6021</link>
      <description>You have 20% CPU idle, suggesting that CPU is not your bottleneck.  I noticed that you only have 32MB of memory though.  This seems VERY low in any sort of database environment.</description>
      <pubDate>Sat, 19 Aug 2000 11:35:25 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437931#M6021</guid>
      <dc:creator>Tim Malnati</dc:creator>
      <dc:date>2000-08-19T11:35:25Z</dc:date>
    </item>
    <item>
      <title>Re: Server Performance Analysis</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437932#M6022</link>
      <description>You have a memory bottleneck. With 32MB you don't expect the system to fly. The system is doing a lot of work tying to free and allocate memory to processes thereby 51.9% usage on the report. A good system should report system % as 3/4 of user % (ie 75%user to 25%system )on at a pick period. Try and up grade to 64MB or 128MB.</description>
      <pubDate>Sat, 19 Aug 2000 16:14:05 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437932#M6022</guid>
      <dc:creator>CHRIS_ANORUO</dc:creator>
      <dc:date>2000-08-19T16:14:05Z</dc:date>
    </item>
    <item>
      <title>Re: Server Performance Analysis</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437933#M6023</link>
      <description>Actually, 128 megs would be way too small. This is a 4 processor system. It's going to be very difficult to utilize all the CPU power with such low RAM.&lt;BR /&gt;&lt;BR /&gt;I would suggest 1000 to 2000 megs of RAM for this system. You may need to adjust some Informix and HP-UX kernel parameters to take advantage of the additional RAM.  For 4 processor database servers, most sysadmins run 1000 to 4000 megs on 10.20, 6Gb to 12Gb on 11.0 64 bit systems.</description>
      <pubDate>Sat, 19 Aug 2000 17:33:18 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437933#M6023</guid>
      <dc:creator>Bill Hassell</dc:creator>
      <dc:date>2000-08-19T17:33:18Z</dc:date>
    </item>
    <item>
      <title>Re: Server Performance Analysis</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437934#M6024</link>
      <description>PROSANJIT,&lt;BR /&gt;You appear to have three issues:  tools to use for assessing performance, server performance, and informix performance.  I am not an expert on systems admin...so&lt;BR /&gt;&lt;BR /&gt;Specific to informix, go to the informix user group &lt;A href="http://www.iiug.org." target="_blank"&gt;www.iiug.org.&lt;/A&gt;  Do a search under performance for massive amounts of information.  To monitor performance most folks use the command line (onstat).  However, some use the built in tools and there are a couple 3rd party tools if you search the informix user site.  &lt;BR /&gt;&lt;BR /&gt;Sign up on the iiug.org list serve, ask your performance question and post the following (or you can just email the group:  informix-list@iiug.org with the following):&lt;BR /&gt;- onconfig file&lt;BR /&gt;- h/w specs especially your drive and raid setup&lt;BR /&gt;- onstat -iov, -p, -F -g seg, -g iov&lt;BR /&gt;- is KAIO on or off?&lt;BR /&gt;- have you run update statistics at all? or run it high, low, medium?&lt;BR /&gt;- is it an oltp or dss database, number of users, etc.&lt;BR /&gt;&lt;BR /&gt;From the info you did post I can see your shared mem is probably not high enough. shmvrtsize affects how many shared mem segments you have and you should only have one to two, it appears you have at least 5, which means that informix is dynamically adding memory when it needs it.&lt;BR /&gt;&lt;BR /&gt;hth&lt;BR /&gt;Doug</description>
      <pubDate>Mon, 21 Aug 2000 20:43:02 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/server-performance-analysis/m-p/2437934#M6024</guid>
      <dc:creator>Doug_3</dc:creator>
      <dc:date>2000-08-21T20:43:02Z</dc:date>
    </item>
  </channel>
</rss>

