<?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 Re: sar -d in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445479#M9157</link>
    <description>The 100% BUSY means that the device is busy servicing I/O requests 100% of the interval time you specified. This in itself does not indicate a problem. &lt;BR /&gt;&lt;BR /&gt;Tony</description>
    <pubDate>Thu, 14 Sep 2000 18:39:57 GMT</pubDate>
    <dc:creator>Anthony deRito</dc:creator>
    <dc:date>2000-09-14T18:39:57Z</dc:date>
    <item>
      <title>sar -d</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445478#M9156</link>
      <description>I am running HP-UX 10.20.  When running sar -d I noticed the following:&lt;BR /&gt;&lt;BR /&gt;15:12:12   device   %busy   avque   r+w/s  blks/s  avwait  avserv&lt;BR /&gt;15:12:22   c4t6d0    3.60    0.50       3      33    5.05   31.34&lt;BR /&gt;           c5t2d0  100.00    0.80       2      28    8.86   25.08&lt;BR /&gt;           c1t0d0    0.30    0.50       0       3    6.02   15.49&lt;BR /&gt; &lt;BR /&gt;Disk c5t2d0 is a mirror of c4t6d0&lt;BR /&gt;Why is it showing 100% utilization.  I also have 3 other disk in the same situation.  Glance does not show the disks as active.</description>
      <pubDate>Thu, 14 Sep 2000 18:27:29 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445478#M9156</guid>
      <dc:creator>Stephen Tatrai</dc:creator>
      <dc:date>2000-09-14T18:27:29Z</dc:date>
    </item>
    <item>
      <title>Re: sar -d</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445479#M9157</link>
      <description>The 100% BUSY means that the device is busy servicing I/O requests 100% of the interval time you specified. This in itself does not indicate a problem. &lt;BR /&gt;&lt;BR /&gt;Tony</description>
      <pubDate>Thu, 14 Sep 2000 18:39:57 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445479#M9157</guid>
      <dc:creator>Anthony deRito</dc:creator>
      <dc:date>2000-09-14T18:39:57Z</dc:date>
    </item>
    <item>
      <title>Re: sar -d</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445480#M9158</link>
      <description>Hi:&lt;BR /&gt;&lt;BR /&gt;The 100% means that during the same period the disk was "always" busy servicing an I/O.  More important is the queue depth (avque).  If this is high, you have increasing performance degradation.  I assume that the difference you see with Glance is related to different sample periods.&lt;BR /&gt;&lt;BR /&gt;...JRF...</description>
      <pubDate>Thu, 14 Sep 2000 18:42:57 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445480#M9158</guid>
      <dc:creator>James R. Ferguson</dc:creator>
      <dc:date>2000-09-14T18:42:57Z</dc:date>
    </item>
    <item>
      <title>Re: sar -d</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445481#M9159</link>
      <description>The rest of the sar parameters do not seem to imply any major activity to the disk.&lt;BR /&gt;I have run sar throughtout the day with an interval of 180 seconds and see the same results.  Also the primary disk in the mirror shows little activity and I know the&lt;BR /&gt;disk should not have much activity.</description>
      <pubDate>Thu, 14 Sep 2000 18:51:19 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445481#M9159</guid>
      <dc:creator>Stephen Tatrai</dc:creator>
      <dc:date>2000-09-14T18:51:19Z</dc:date>
    </item>
    <item>
      <title>Re: sar -d</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445482#M9160</link>
      <description>Stephen:&lt;BR /&gt;As has been said, for the sampling period you chose, that was the disk activity...  it is perfectly normal for disks in a mirror to have different disk activity rate.  If you are really worried, you could run sar over diffent sampling rates.&lt;BR /&gt;&lt;BR /&gt;you could also try iostat over various sampling periods.</description>
      <pubDate>Thu, 14 Sep 2000 18:52:57 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445482#M9160</guid>
      <dc:creator>TC ITEMS Unix Admin</dc:creator>
      <dc:date>2000-09-14T18:52:57Z</dc:date>
    </item>
    <item>
      <title>Re: sar -d</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445483#M9161</link>
      <description>There is no way that the disk could be 100% busy doing 2 transfers per second. sar is not always accurate - it is a 'standard' UNIX utility and in your case is not properly interpreting information retrieved from the kernel.&lt;BR /&gt;&lt;BR /&gt;As you have got glance - believe it! It is specifically written to interface with the kernel (using different interfaces from sar).&lt;BR /&gt;&lt;BR /&gt;If you also have measureware then there is no reason to use sar at all.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 14 Sep 2000 20:06:59 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445483#M9161</guid>
      <dc:creator>John Palmer</dc:creator>
      <dc:date>2000-09-14T20:06:59Z</dc:date>
    </item>
    <item>
      <title>Re: sar -d</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445484#M9162</link>
      <description>hi &lt;BR /&gt;the best way is to monitor one days activity to cofirm what is real and fake .&lt;BR /&gt;use the following commnad in cron &lt;BR /&gt;0 * * * * /usr/lbin/sa/sa1 300 12&lt;BR /&gt; which will log all data in /var/adm/sa dir at the end of the day u can view the statistics.&lt;BR /&gt;&lt;BR /&gt;Raj</description>
      <pubDate>Fri, 15 Sep 2000 00:05:38 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/sar-d/m-p/2445484#M9162</guid>
      <dc:creator>rajsri</dc:creator>
      <dc:date>2000-09-15T00:05:38Z</dc:date>
    </item>
  </channel>
</rss>

