<?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: CPU affinity and subprocess/threads in Operating System - OpenVMS</title>
    <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001441#M79685</link>
    <description>Thomas,&lt;BR /&gt;&lt;BR /&gt;thanks. So this seems to indiciate, that the help text for SET PROC/AFF is not correct.&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
    <pubDate>Thu, 07 Sep 2006 01:05:59 GMT</pubDate>
    <dc:creator>Volker Halle</dc:creator>
    <dc:date>2006-09-07T01:05:59Z</dc:date>
    <item>
      <title>CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001428#M79672</link>
      <description>A collegue ran into the following issue:&lt;BR /&gt;A multi-threaded application runs fine on a single-CPU system but in a multi-user environment, it crashes. It looks like a problem that several thraeds run on diffeernt CPU's and sometimes, the main thread is activated by different thredas on different CPU's causing the application to die.&lt;BR /&gt;As said, it's just on a multi-CPU machine. On a single_CPU system, there is no problem.&lt;BR /&gt;&lt;BR /&gt;We thimnk the problem might be solved in setting the process's affinity to one CPU. If this is a real multi-threaded application, that would solve the problem because all threads would run in that process's context.&lt;BR /&gt;Is this true?&lt;BR /&gt;&lt;BR /&gt;Another - for curiosity: If a process's affinity is set to one (or more) processes, is that setting inherited by subprocesses started by that proces?&lt;BR /&gt;&lt;BR /&gt;Willem</description>
      <pubDate>Wed, 06 Sep 2006 07:17:08 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001428#M79672</guid>
      <dc:creator>Willem Grooters</dc:creator>
      <dc:date>2006-09-06T07:17:08Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001429#M79673</link>
      <description>sounds like a syncronisation problem where the application can't cope multiple threads running concurrently.&lt;BR /&gt;&lt;BR /&gt;A workaround would be to not allow the application to use multiple kernel threads.&lt;BR /&gt;Link it without kernel threads or use (V8.2) command&lt;BR /&gt;SET IMAGE/FLAGS=NOMKTHREADS&lt;BR /&gt;</description>
      <pubDate>Wed, 06 Sep 2006 09:28:34 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001429#M79673</guid>
      <dc:creator>Ian Miller.</dc:creator>
      <dc:date>2006-09-06T09:28:34Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001430#M79674</link>
      <description>On earlier versions of VMS use&lt;BR /&gt;THREADCP/DISABLE=MULTIPLE_KERNEL_THREADS XX.EXE</description>
      <pubDate>Wed, 06 Sep 2006 09:30:56 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001430#M79674</guid>
      <dc:creator>Ian Miller.</dc:creator>
      <dc:date>2006-09-06T09:30:56Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001431#M79675</link>
      <description>Willem,&lt;BR /&gt;&lt;BR /&gt;see HELP SET PROC/AFF&lt;BR /&gt;...&lt;BR /&gt;       As with the other SET PROCESS qualifiers, the bit operations&lt;BR /&gt;       occur on the current process if no /IDENTIFICATION qualifier&lt;BR /&gt;       or explicit process name parameter is specified. Specifying a&lt;BR /&gt;       process name does not imply that all kernel threads associated&lt;BR /&gt;       with the process are affected; the SET PROCESS command affects&lt;BR /&gt;       only the initial kernel thread of a multithreaded process.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;An application with such a behaviour clearly has a synchronization bug, that just does not show up, until you run the application really in parallel on multiple CPUs.&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
      <pubDate>Wed, 06 Sep 2006 11:23:54 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001431#M79675</guid>
      <dc:creator>Volker Halle</dc:creator>
      <dc:date>2006-09-06T11:23:54Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001432#M79676</link>
      <description>Volker,&lt;BR /&gt;That implies that SET PROCESS/AFFINITY=CPUxx won't help. &lt;BR /&gt;&lt;BR /&gt;Ian,&lt;BR /&gt;I'm not certain on the VMS version but I'm quite certain it's 7.3-something. So 8.2 commands are not applicable.&lt;BR /&gt;&lt;BR /&gt;I fully agree it might be a synchronisation issue. Not really a surprise ;-). To solve the problem it will be needed to redo this part, I guess. &lt;BR /&gt;</description>
      <pubDate>Wed, 06 Sep 2006 11:41:48 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001432#M79676</guid>
      <dc:creator>Willem Grooters</dc:creator>
      <dc:date>2006-09-06T11:41:48Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001433#M79677</link>
      <description>Willem,&lt;BR /&gt;I'm not sure how badly the following will affect other applications/processes on the system, but couldn't you just simply disable the creation of kernel threads altogether (setting the system parameter MULTITHREAD to 0 (zero)). We once solved a problem by doing so. The app (actually one process of the app) was also multithreaded, and very CPU hungry. If we allowed kernel threads, all CPUs (four of them) were busy serving that single process. By preventing kernel threads to be created, we could keep 1 CPU busy with that process, while the other 3 could service the rest.&lt;BR /&gt;Hope this helps,&lt;BR /&gt;Kris (aka Qkcl)</description>
      <pubDate>Wed, 06 Sep 2006 13:33:37 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001433#M79677</guid>
      <dc:creator>Kris Clippeleyr</dc:creator>
      <dc:date>2006-09-06T13:33:37Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001434#M79678</link>
      <description>SET IMAGE/FLAGS=NOMKTHREADS only works on Itanium images so THREADCP would be the correct command (its been around for serveral versions).&lt;BR /&gt;&lt;BR /&gt;As Kris said you can disable kernel threads completely but it would be better to fix the application.</description>
      <pubDate>Wed, 06 Sep 2006 15:15:09 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001434#M79678</guid>
      <dc:creator>Ian Miller.</dc:creator>
      <dc:date>2006-09-06T15:15:09Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001435#M79679</link>
      <description>Willem, we locked a number of processes to a single CPU in our 4 node 4 CPU 7.3-2 environment. The developers got ambitious with their multithreading and we suffered numerious bugchecks. After the processes were assigned to a single CPU no more problem ! I am sure there are problems with VMS in this area of multi-threading. In spite of conceptual brilliance of some these applications developed, when assigned to a single CPU, did not measurably affect the applications throughput. I all for keeping things simple.</description>
      <pubDate>Wed, 06 Sep 2006 20:02:03 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001435#M79679</guid>
      <dc:creator>Thomas Ritter</dc:creator>
      <dc:date>2006-09-06T20:02:03Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001436#M79680</link>
      <description>Thomas,&lt;BR /&gt;&lt;BR /&gt;how did you 'lock a number of processes to a single CPU' ? That's the question.&lt;BR /&gt;&lt;BR /&gt;SET PROC/AFF ?&lt;BR /&gt;THREADCP/DISABLE=MULTIPLE_KERNEL_THREADS ?&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
      <pubDate>Thu, 07 Sep 2006 00:24:38 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001436#M79680</guid>
      <dc:creator>Volker Halle</dc:creator>
      <dc:date>2006-09-07T00:24:38Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001437#M79681</link>
      <description>Try this&lt;BR /&gt;&lt;BR /&gt;$ set proc "''process_name'"/AFFINITY/SET=1/permanent</description>
      <pubDate>Thu, 07 Sep 2006 00:29:26 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001437#M79681</guid>
      <dc:creator>Thomas Ritter</dc:creator>
      <dc:date>2006-09-07T00:29:26Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001438#M79682</link>
      <description>And with a $show cpu/all extract&lt;BR /&gt;&lt;BR /&gt;CPU 1    State: RUN                CPUDB: 81921880     Handle: 00000E90&lt;BR /&gt;         Owner: 00000640         Current: 00000640     Partition 0 (WIZ22)&lt;BR /&gt;        ChgCnt:        0           State: Present, In-Console, Reassignable&lt;BR /&gt;       Process: * None *&lt;BR /&gt;  Capabilities:&lt;BR /&gt;        System: QUORUM RUN RAD0 &lt;BR /&gt;  Slot Context: C94A0400&lt;BR /&gt;     CPU     -  State..........: RC, PA, PP, CV, PV, PMV, PL&lt;BR /&gt;                Type...........: EV68 (21264/EV68CB 21264C),  Minor = 5&lt;BR /&gt;                Speed..........: 1000 Mhz&lt;BR /&gt;                Variation......: VAX FP, IEEE FP, Primary Eligible&lt;BR /&gt;                Serial Number..: AY20408008&lt;BR /&gt;                Revision.......: &lt;BR /&gt;                Halt Request...: 0&lt;BR /&gt;                Software Comp..: 8.4&lt;BR /&gt;     PALCODE -  Revision Code..: 1.98-01&lt;BR /&gt;                Compatibility..: 43&lt;BR /&gt;                Max Shared CPUs: 4&lt;BR /&gt;                Memory  Space..: Physical = 00000000.00000000  Length = 0&lt;BR /&gt;                Scratch Space..: Physical = 00000000.00000000  Length = 0&lt;BR /&gt;  Bindings:&lt;BR /&gt;     WIR_CGI_FOXPRD   PID = 2C80190C  Reason: Affinitized to this CPU             &lt;BR /&gt;     WIR_CGI_FOXPRD   PID = 2C80110C  Reason: Affinitized to this CPU             &lt;BR /&gt;     WIR_CGI_FOXPRD   PID = 2C80090C  Reason: Affinitized to this CPU             &lt;BR /&gt;  Fastpath:&lt;BR /&gt;</description>
      <pubDate>Thu, 07 Sep 2006 00:32:20 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001438#M79682</guid>
      <dc:creator>Thomas Ritter</dc:creator>
      <dc:date>2006-09-07T00:32:20Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001439#M79683</link>
      <description>Thomas,&lt;BR /&gt;&lt;BR /&gt;thanks.&lt;BR /&gt;&lt;BR /&gt;It looks like actually the process and all its threads are bound to that CPU. This seems to contradict the help text of SET PROC/AFF.&lt;BR /&gt;&lt;BR /&gt;Does $ SHOW SYS/MULTI/FULL show 3 kernel threads for process WIR_CGI_FOXPRD ?&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
      <pubDate>Thu, 07 Sep 2006 00:44:07 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001439#M79683</guid>
      <dc:creator>Volker Halle</dc:creator>
      <dc:date>2006-09-07T00:44:07Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001440#M79684</link>
      <description>OpenVMS V7.3-2  on node WIZ22   7/09/06 15:49:20.88  Uptime  2 13:43:57&lt;BR /&gt;        AlphaServer ES45 Model 2B&lt;BR /&gt;  Pid    Process Name    State  Pri      I/O       CPU       Page flts  Pages&lt;BR /&gt;2C800818 ACME_SERVER     HIB      8      111   0 00:00:00.53       384    538 M &lt;BR /&gt;2C801018                 HIB      8&lt;BR /&gt;2C801818                 HIB     10&lt;BR /&gt;         [SYSTEM]                                                        4304Kb&lt;BR /&gt;2C80090C WIR_CGI_FOXPRD  HIB      4    79389   0 00:01:19.19      1483   1891 M &lt;BR /&gt;2C80110C                 HIB      4&lt;BR /&gt;2C80190C                 HIB      6&lt;BR /&gt;         [WIZARD_100,ADDR_FOXPRD]                                       15128Kb&lt;BR /&gt;</description>
      <pubDate>Thu, 07 Sep 2006 00:50:32 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001440#M79684</guid>
      <dc:creator>Thomas Ritter</dc:creator>
      <dc:date>2006-09-07T00:50:32Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001441#M79685</link>
      <description>Thomas,&lt;BR /&gt;&lt;BR /&gt;thanks. So this seems to indiciate, that the help text for SET PROC/AFF is not correct.&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
      <pubDate>Thu, 07 Sep 2006 01:05:59 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001441#M79685</guid>
      <dc:creator>Volker Halle</dc:creator>
      <dc:date>2006-09-07T01:05:59Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001442#M79686</link>
      <description>&amp;gt;multi-threaded application runs fine on a &lt;BR /&gt;&amp;gt;single-CPU system but in a multi-user &lt;BR /&gt;&amp;gt;environment, it crashes&lt;BR /&gt;&lt;BR /&gt;Can you provide some more details on&lt;BR /&gt;how it crashes? System crash? process crash?&lt;BR /&gt;ACCVIO?&lt;BR /&gt;&lt;BR /&gt;Guy</description>
      <pubDate>Thu, 07 Sep 2006 01:45:44 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001442#M79686</guid>
      <dc:creator>Guy Peleg</dc:creator>
      <dc:date>2006-09-07T01:45:44Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001443#M79687</link>
      <description>Just a process crash - data attached.</description>
      <pubDate>Thu, 07 Sep 2006 04:15:01 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001443#M79687</guid>
      <dc:creator>Willem Grooters</dc:creator>
      <dc:date>2006-09-07T04:15:01Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001444#M79688</link>
      <description>Willem,&lt;BR /&gt;&lt;BR /&gt;what does SDA&amp;gt; EXA/INS 808F8290 return ? What module is the exception PC in.&lt;BR /&gt;&lt;BR /&gt;Although this 'may be' an underlying application problem, the exception PC and the most recent call frames on the traceback stack are from OpenVMS/PTHREAD/JAVA i.e. HP code !&lt;BR /&gt;&lt;BR /&gt;Could you create a process dump for this situation (SET PROC/DUMP in LOGIN.COM or SET PROC/DUMP/PID=xxx) ?&lt;BR /&gt;&lt;BR /&gt;Make sure you're up-to-date on PTRHEAD patches.&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
      <pubDate>Thu, 07 Sep 2006 05:27:00 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001444#M79688</guid>
      <dc:creator>Volker Halle</dc:creator>
      <dc:date>2006-09-07T05:27:00Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001445#M79689</link>
      <description>Willem,&lt;BR /&gt;&lt;BR /&gt;while you're in SDA, please also check&lt;BR /&gt;&lt;BR /&gt;SDA&amp;gt; EXA/INS 8083D830&lt;BR /&gt;&lt;BR /&gt;This is more likely the real exception PC. The values in the vms condition printout from PHTREADs may be misleading.&lt;BR /&gt;&lt;BR /&gt;The code most likely at fault here is in PTHREAD$RTL or JAVA$HPI_SHR, which are the most recent callers.&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
      <pubDate>Thu, 07 Sep 2006 05:56:24 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001445#M79689</guid>
      <dc:creator>Volker Halle</dc:creator>
      <dc:date>2006-09-07T05:56:24Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001446#M79690</link>
      <description>Willem,&lt;BR /&gt;&lt;BR /&gt;&lt;QUOTE&gt;&lt;BR /&gt;Another - for curiosity: If a process's affinity is set to one (or more) processes, is that setting inherited by subprocesses started by that proces?&lt;BR /&gt;&lt;/QUOTE&gt;&lt;BR /&gt;&lt;BR /&gt;You can easily test this for yourself:&lt;BR /&gt;&lt;BR /&gt;$ set proc/aff/set=0/perm&lt;BR /&gt;$ SHOW PROC&lt;BR /&gt;...&lt;BR /&gt;Soft CPU Affinity: off&lt;BR /&gt;Hard CPU Affinity Mask: 00000001&lt;BR /&gt;$ SPAWN&lt;BR /&gt;$ SHOW PROC&lt;BR /&gt;...&lt;BR /&gt;Soft CPU Affinity: off&lt;BR /&gt;$&lt;BR /&gt;&lt;BR /&gt;The Hard CPU affinity is not inherited by the spawned subprocess.&lt;BR /&gt;&lt;BR /&gt;Volker.</description>
      <pubDate>Thu, 07 Sep 2006 06:14:14 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001446#M79690</guid>
      <dc:creator>Volker Halle</dc:creator>
      <dc:date>2006-09-07T06:14:14Z</dc:date>
    </item>
    <item>
      <title>Re: CPU affinity and subprocess/threads</title>
      <link>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001447#M79691</link>
      <description>Willem, what's  the progress ?  Did you try to set lock the process(s) to a single CPU ? &lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 21 Sep 2006 19:00:01 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-openvms/cpu-affinity-and-subprocess-threads/m-p/5001447#M79691</guid>
      <dc:creator>Thomas Ritter</dc:creator>
      <dc:date>2006-09-21T19:00:01Z</dc:date>
    </item>
  </channel>
</rss>

