<?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: ps -elf SZ column in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250354#M175259</link>
    <description>4096 bytes (4k) is the default block size unless you have chosen to change the kernel. &lt;BR /&gt;&lt;BR /&gt;SZ is a UNIX95 standard part of ps.&lt;BR /&gt;                    &lt;BR /&gt;The size in physical pages of the core image of the process, including text, data, and stack space. &lt;BR /&gt;&lt;BR /&gt;No you cannot summ all these blocks mainly because these do not account for shared memory, memory mapped files etc. &lt;BR /&gt;&lt;BR /&gt;Again if you could be more specific what you want to achieve it would be easier to suggest an approach for you.&lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Mon, 19 Apr 2004 11:21:54 GMT</pubDate>
    <dc:creator>Navin Bhat_2</dc:creator>
    <dc:date>2004-04-19T11:21:54Z</dc:date>
    <item>
      <title>ps -elf SZ column</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250352#M175257</link>
      <description>HPUX 11.11&lt;BR /&gt;ps -elf list a SZ value that is described as "The size of blocks of the core image of the process." &lt;BR /&gt;&lt;BR /&gt;How big is a block in bytes? &lt;BR /&gt;If I know the answer, can I summ all the process blocks plus the free pages from vmstat and get my total 2GB of memory or something close for that instant in time?</description>
      <pubDate>Fri, 16 Apr 2004 08:09:44 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250352#M175257</guid>
      <dc:creator>james p. boyle</dc:creator>
      <dc:date>2004-04-16T08:09:44Z</dc:date>
    </item>
    <item>
      <title>Re: ps -elf SZ column</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250353#M175258</link>
      <description>Hi James,&lt;BR /&gt;&lt;BR /&gt;4KB is the block size&lt;BR /&gt;&lt;BR /&gt;Rgds,&lt;BR /&gt;Jeff</description>
      <pubDate>Fri, 16 Apr 2004 08:11:27 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250353#M175258</guid>
      <dc:creator>Jeff Schussele</dc:creator>
      <dc:date>2004-04-16T08:11:27Z</dc:date>
    </item>
    <item>
      <title>Re: ps -elf SZ column</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250354#M175259</link>
      <description>4096 bytes (4k) is the default block size unless you have chosen to change the kernel. &lt;BR /&gt;&lt;BR /&gt;SZ is a UNIX95 standard part of ps.&lt;BR /&gt;                    &lt;BR /&gt;The size in physical pages of the core image of the process, including text, data, and stack space. &lt;BR /&gt;&lt;BR /&gt;No you cannot summ all these blocks mainly because these do not account for shared memory, memory mapped files etc. &lt;BR /&gt;&lt;BR /&gt;Again if you could be more specific what you want to achieve it would be easier to suggest an approach for you.&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Mon, 19 Apr 2004 11:21:54 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250354#M175259</guid>
      <dc:creator>Navin Bhat_2</dc:creator>
      <dc:date>2004-04-19T11:21:54Z</dc:date>
    </item>
    <item>
      <title>Re: ps -elf SZ column</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250355#M175260</link>
      <description>You would be better advised to assert the XPG4 ps behavior by setting the UNIX95 env. variable.&lt;BR /&gt;&lt;BR /&gt;e.g.&lt;BR /&gt;UNIX95= ps -e -o vsz,pid,comm&lt;BR /&gt;&lt;BR /&gt;vsz will always be in KB.&lt;BR /&gt;&lt;BR /&gt;Memory calculations are extremely difficult because shared library code might be used by many processes. The same is true of shared memory segments.&lt;BR /&gt;</description>
      <pubDate>Mon, 19 Apr 2004 11:32:25 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250355#M175260</guid>
      <dc:creator>A. Clay Stephenson</dc:creator>
      <dc:date>2004-04-19T11:32:25Z</dc:date>
    </item>
    <item>
      <title>Re: ps -elf SZ column</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250356#M175261</link>
      <description>Couple of clarifications there 1st I presume that you meant page size not block size. Either way the default pages are 4k in size. &lt;BR /&gt;&lt;BR /&gt;You can use sz,vsz after setting the UNIX95 variable to the open portability standard.&lt;BR /&gt;&lt;BR /&gt;export UNIX95=XPG4   &lt;BR /&gt;&lt;BR /&gt;Again "sz" is the real and "vsz" is the virtual size of the core image (data,text and stack) this does not include memory mapped or shared memory regions and cannot be used to sum physical memory totals with vmstat free pages. &lt;BR /&gt;&lt;BR /&gt;Use top/glance as a good starting tool to get per process memory layout information.&lt;BR /&gt;</description>
      <pubDate>Mon, 19 Apr 2004 13:28:12 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ps-elf-sz-column/m-p/3250356#M175261</guid>
      <dc:creator>Navin Bhat_2</dc:creator>
      <dc:date>2004-04-19T13:28:12Z</dc:date>
    </item>
  </channel>
</rss>

