<?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 Kernel Params Pseudo Swap?! in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605610#M35044</link>
    <description>Dear all,&lt;BR /&gt;&lt;BR /&gt;An external application support company has recommended turning off 'pseudo swap' on one of our servers, as they claim it is taking valuable resources, yet not being utilised. Which seems fine.&lt;BR /&gt;My question, I understand the theory of swap but what the h*ll is pseudo swap all about? virtual virtual memory??&lt;BR /&gt;&lt;BR /&gt;Any pointers, explanations, links warmly received!!&lt;BR /&gt;&lt;BR /&gt;Cheers,&lt;BR /&gt;&lt;BR /&gt;-ChaZ-&lt;BR /&gt;</description>
    <pubDate>Thu, 01 Nov 2001 13:27:41 GMT</pubDate>
    <dc:creator>Charles Harris</dc:creator>
    <dc:date>2001-11-01T13:27:41Z</dc:date>
    <item>
      <title>Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605610#M35044</link>
      <description>Dear all,&lt;BR /&gt;&lt;BR /&gt;An external application support company has recommended turning off 'pseudo swap' on one of our servers, as they claim it is taking valuable resources, yet not being utilised. Which seems fine.&lt;BR /&gt;My question, I understand the theory of swap but what the h*ll is pseudo swap all about? virtual virtual memory??&lt;BR /&gt;&lt;BR /&gt;Any pointers, explanations, links warmly received!!&lt;BR /&gt;&lt;BR /&gt;Cheers,&lt;BR /&gt;&lt;BR /&gt;-ChaZ-&lt;BR /&gt;</description>
      <pubDate>Thu, 01 Nov 2001 13:27:41 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605610#M35044</guid>
      <dc:creator>Charles Harris</dc:creator>
      <dc:date>2001-11-01T13:27:41Z</dc:date>
    </item>
    <item>
      <title>Re: Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605611#M35045</link>
      <description>Hi Charles:&lt;BR /&gt;&lt;BR /&gt;Knowledge Base document #KBRC00001129 explains this the best I have heard:&lt;BR /&gt;&lt;BR /&gt;/begin_quote/&lt;BR /&gt;&lt;BR /&gt;Pseudo swap is HP's solution for large memory customers who do not wish to purchase a large amount of swap space. The justification for purchasing large memory systems is to prevent paging and swapping, therefore, the argument&lt;BR /&gt;becomes "Why purchase a lot of swap space if the system is not expected to page or swap?"&lt;BR /&gt;&lt;BR /&gt;Pseudo swap is swap space which the operating systems recognizes, but in reality it does not exist. Pseudo swap is make-believe swap space. It does not exist in memory, it does not exist on disk, it does not exist anywhere.  However, the operating system does recognize it, which means more swap space can be reserved than physically exists.&lt;BR /&gt;&lt;BR /&gt;The purpose of pseudo swap is to allow more processes to run in memory, than could be supported by the swap device(s). Swap devices refer to both device swap or filesystem swap. It allows the operating system(specifically the kernel variable swap_avail) to recognize more swap space, thereby allowing additional&lt;BR /&gt;processes to start when all of the physical swap has been reserved.&lt;BR /&gt;&lt;BR /&gt;By having the operating system recognize more swap space than physically exists, large memory customers can now operate without having to purchase large amounts of swap space which they will most likely never use.&lt;BR /&gt;&lt;BR /&gt;The size of pseudo swap is dependent on the amount of memory in the system. Specifically, the size is 75% of physical memory. This means the swap_avail variable will have an additional amount (75% of physical memory) added to its content. This additional amount allows more processes to start when all of the&lt;BR /&gt;physical swap has been reserved.&lt;BR /&gt;&lt;BR /&gt;Pseudo swap is enabled through the tunable kernel parameter called swapmem_on. If the value for swapmem_on is 1, then psuedo swap is turned on or enabled. The percentage of physical memory that pseudo swap adds to swap_avail is not a tunable kernel parameter and is always 75%. This information is valid for all versions of HP-UX 10.X and 11.0.&lt;BR /&gt;&lt;BR /&gt;/end_quote/&lt;BR /&gt;&lt;BR /&gt;Regards!&lt;BR /&gt;&lt;BR /&gt;...JRF...</description>
      <pubDate>Thu, 01 Nov 2001 13:39:30 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605611#M35045</guid>
      <dc:creator>James R. Ferguson</dc:creator>
      <dc:date>2001-11-01T13:39:30Z</dc:date>
    </item>
    <item>
      <title>Re: Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605612#M35046</link>
      <description>&lt;BR /&gt;   Regular swap exists on Disk, as per the&lt;BR /&gt;way it is configured.  For eg, /dev/vg00/lvol2&lt;BR /&gt;by default is primary swap and is part&lt;BR /&gt;of the VG00 disks.   Similarly you can&lt;BR /&gt;add more deviceswaps (or filesystem swaps)&lt;BR /&gt;in addition to the primary swap. But, the&lt;BR /&gt;point is, all of them exist on Disk.&lt;BR /&gt;&lt;BR /&gt;  Whereas, Pseudo swap exists in Memory.&lt;BR /&gt;When pseudo-swap is enabled through a &lt;BR /&gt;setting in the kernel configuration parameter&lt;BR /&gt;called pseudo_swap,  it makes the system&lt;BR /&gt;use  75% of memory for swapping purpose,&lt;BR /&gt;as on demand.  The advantage of this is,&lt;BR /&gt;you get a faster swap area, since it is&lt;BR /&gt;within memory.   Another advantage is&lt;BR /&gt;on High-memory systems, where much&lt;BR /&gt;of the memory may lie unused, pseudo-swap&lt;BR /&gt;is a way to make the best use of it.&lt;BR /&gt;The flip side is , it lessens the availability&lt;BR /&gt;of memory to be used for "memory"!.&lt;BR /&gt;&lt;BR /&gt;  With this background, enabling or disabling&lt;BR /&gt;pseudoswap depends on the system- the&lt;BR /&gt;applications running on it, how much&lt;BR /&gt;load is on the memory, how much of swapping&lt;BR /&gt;is being done etc.  &lt;BR /&gt;&lt;BR /&gt; To check your current Swap usage: do&lt;BR /&gt; swapinfo -mt&lt;BR /&gt;   -&amp;gt; and look for the row corresponding&lt;BR /&gt;      to memory.  Also look at overall&lt;BR /&gt;      swap usage&lt;BR /&gt;  &lt;BR /&gt; If there is a heavy load on memory, then&lt;BR /&gt; you may be better of disabling the pseudo-swap.  At the same time, make sure you&lt;BR /&gt; add device swap (lvcreate ..; swapon )to&lt;BR /&gt;make up for the pseudo-swap loss.&lt;BR /&gt;&lt;BR /&gt;  Have a look at glance and see how the&lt;BR /&gt;memory usage is.  Monitor it for a few&lt;BR /&gt;days, before making a decision.&lt;BR /&gt;Also have a look at   the VHAND and&lt;BR /&gt;SWAPPER processes amd see how active they&lt;BR /&gt;are. If VHAND is very active, then it&lt;BR /&gt;means there is a load on memory.&lt;BR /&gt;&lt;BR /&gt;  If you have more questions, pls post&lt;BR /&gt;the physical memory of your system and&lt;BR /&gt;the swapinfo -mt output.&lt;BR /&gt;&lt;BR /&gt;HTH&lt;BR /&gt;raj&lt;BR /&gt;</description>
      <pubDate>Thu, 01 Nov 2001 13:41:03 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605612#M35046</guid>
      <dc:creator>Roger Baptiste</dc:creator>
      <dc:date>2001-11-01T13:41:03Z</dc:date>
    </item>
    <item>
      <title>Re: Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605613#M35047</link>
      <description>Hi (again) Charles:&lt;BR /&gt;&lt;BR /&gt;ALSO, see this link.&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://forums.itrc.hp.com/cm/QuestionAnswer/1,,0x9e7487dc4d7dd5118ff00090279cd0f9,00.html" target="_blank"&gt;http://forums.itrc.hp.com/cm/QuestionAnswer/1,,0x9e7487dc4d7dd5118ff00090279cd0f9,00.html&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;Follow the discussion and note particularly Carsten Krege's comments.  He unearthed some very interesting information regarding performance when pseudo-swap is enabled.&lt;BR /&gt;&lt;BR /&gt;Regards!&lt;BR /&gt;&lt;BR /&gt;...JRF...</description>
      <pubDate>Thu, 01 Nov 2001 13:43:33 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605613#M35047</guid>
      <dc:creator>James R. Ferguson</dc:creator>
      <dc:date>2001-11-01T13:43:33Z</dc:date>
    </item>
    <item>
      <title>Re: Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605614#M35048</link>
      <description>Once again, I astounded by the great advice / links fellow members share with this forum!!! - Exactly what I was looking for !!&lt;BR /&gt;&lt;BR /&gt;Thanks!&lt;BR /&gt;&lt;BR /&gt;-ChaZ-&lt;BR /&gt;</description>
      <pubDate>Thu, 01 Nov 2001 14:22:22 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605614#M35048</guid>
      <dc:creator>Charles Harris</dc:creator>
      <dc:date>2001-11-01T14:22:22Z</dc:date>
    </item>
    <item>
      <title>Re: Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605615#M35049</link>
      <description>Just to keep the facts straight, I have to contradict RajMan's "The flip side is , it lessens the availability of memory to be used for "memory"!." comment and other similar comments. swapmen_on set to 1 does NOT have an impact on the availability/use of memory. Quite the contrary, with swapmem_on set to 0, the system will be unable to use available memory if the disk swap space is too small.&lt;BR /&gt;&lt;BR /&gt;As James' pointer indicates, see Carsten Krege's comments in the referenced thread, especially his "Pseudo swap has no negative performance impact." and "For the vast majority of systems it makes sense to enable pseudo swap." comments.&lt;BR /&gt;&lt;BR /&gt;To be complete: There *is* a possible performance impact, but that is normally *not* applicable to the majority of applications, i.e. the 'business' ones. This performance impact is *only* applicable to highly *compute bound* processes, i.e. *not* your typical business application (my/HP reference &lt;TAGQRTSBC3MTQJ50N6ABOBHRQKJ1JJANAC&gt;).&lt;BR /&gt;&lt;BR /&gt;So bottom line:&lt;BR /&gt;&lt;BR /&gt;Unless you have compute bound performance problems, swapmem_on should be set to 1.&lt;/TAGQRTSBC3MTQJ50N6ABOBHRQKJ1JJANAC&gt;</description>
      <pubDate>Thu, 01 Nov 2001 14:25:12 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605615#M35049</guid>
      <dc:creator>Frank Slootweg</dc:creator>
      <dc:date>2001-11-01T14:25:12Z</dc:date>
    </item>
    <item>
      <title>Re: Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605616#M35050</link>
      <description>Thanks for the additional explanation, the almost text book definition was what I am really interested in, although I must admit, I'm not tempted to turn off the pseudo swap as the server in question has 6 gig of memory, which would prove a little excessive ( especially in cost per MB ) in EMC disk space ( mirrored 4 ways!!!! )&lt;BR /&gt;&lt;BR /&gt;Thanks again!&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;-ChaZ-&lt;BR /&gt;</description>
      <pubDate>Thu, 01 Nov 2001 14:30:54 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605616#M35050</guid>
      <dc:creator>Charles Harris</dc:creator>
      <dc:date>2001-11-01T14:30:54Z</dc:date>
    </item>
    <item>
      <title>Re: Kernel Params Pseudo Swap?!</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605617#M35051</link>
      <description>&amp;lt;&lt;I have="" to="" contradict="" rajman=""&gt;&amp;gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt; My observation was based on one instance,where  on a 2Gb K Database server, i had to remove pseudo-swap, since the load on the&lt;BR /&gt;memory was  constantly high causing memory&lt;BR /&gt;bottlenecks. The memory issue eased considerably after that. &lt;BR /&gt; &lt;BR /&gt;  But the thumb rule of having pseudo swap&lt;BR /&gt;enabled remains. &lt;BR /&gt;&lt;BR /&gt;Also, in one of the threads James posted,&lt;BR /&gt;there was a reference to  Primary swap&lt;BR /&gt;getting higher priority over Pseudoswap,&lt;BR /&gt;since it's priority is one.  But, i have&lt;BR /&gt;noticed pseudo-swap getting used first.&lt;BR /&gt;(in swapinfo -mt output or glance-&amp;gt; systems&lt;BR /&gt;with pseudo swap have a xx usage against&lt;BR /&gt;them, whereas the primary swap has less or&lt;BR /&gt;no usage.).&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;Keeping the Swap-pot boiling ;-)&lt;BR /&gt;-raj&lt;/I&gt;</description>
      <pubDate>Fri, 02 Nov 2001 05:21:39 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/kernel-params-pseudo-swap/m-p/2605617#M35051</guid>
      <dc:creator>Roger Baptiste</dc:creator>
      <dc:date>2001-11-02T05:21:39Z</dc:date>
    </item>
  </channel>
</rss>

