Do the DirectMap?? entries in /proc/meminfo account for huge page compaction?











up vote
0
down vote

favorite
1












I've been tracking down some Transparent Huge Pages performance issues--nothing unusual there--in x86_64 CentOS 6.7, and I've noticed something odd. The values in /proc/meminfo for DirectMap?? are supposed to keep track of the number of pages mapped for each of the three page sizes. But once DirectMap1G has dropped to 0, it appears that DirectMap2M will only decrease. No amount of huge page compaction ever seems to increase the value back up.



When I look at the relevant kernel source in arch/x86/mm/pageattr.c, it's pretty clear that the DirectMap?? counters get set at initialization via update_page_count() and updated when pages are split via split_page_count(). But there's nothing in the kernel that does the reverse split adjustment to the counters when pages are compacted.



I've looked at kernel source from 2.6 up to 4.18.20, and it seems that this behavior hasn't changed.



So, am I missing something, or is this a bug?






linux-kernel memory-management huge-pages







share|improve this question







New contributor




Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
























    up vote
    0
    down vote

    favorite
    1












    I've been tracking down some Transparent Huge Pages performance issues--nothing unusual there--in x86_64 CentOS 6.7, and I've noticed something odd. The values in /proc/meminfo for DirectMap?? are supposed to keep track of the number of pages mapped for each of the three page sizes. But once DirectMap1G has dropped to 0, it appears that DirectMap2M will only decrease. No amount of huge page compaction ever seems to increase the value back up.



    When I look at the relevant kernel source in arch/x86/mm/pageattr.c, it's pretty clear that the DirectMap?? counters get set at initialization via update_page_count() and updated when pages are split via split_page_count(). But there's nothing in the kernel that does the reverse split adjustment to the counters when pages are compacted.



    I've looked at kernel source from 2.6 up to 4.18.20, and it seems that this behavior hasn't changed.



    So, am I missing something, or is this a bug?






    linux-kernel memory-management huge-pages







    share|improve this question







    New contributor




    Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.






















      up vote
      0
      down vote

      favorite
      1









      up vote
      0
      down vote

      favorite
      1






      1





      I've been tracking down some Transparent Huge Pages performance issues--nothing unusual there--in x86_64 CentOS 6.7, and I've noticed something odd. The values in /proc/meminfo for DirectMap?? are supposed to keep track of the number of pages mapped for each of the three page sizes. But once DirectMap1G has dropped to 0, it appears that DirectMap2M will only decrease. No amount of huge page compaction ever seems to increase the value back up.



      When I look at the relevant kernel source in arch/x86/mm/pageattr.c, it's pretty clear that the DirectMap?? counters get set at initialization via update_page_count() and updated when pages are split via split_page_count(). But there's nothing in the kernel that does the reverse split adjustment to the counters when pages are compacted.



      I've looked at kernel source from 2.6 up to 4.18.20, and it seems that this behavior hasn't changed.



      So, am I missing something, or is this a bug?






      linux-kernel memory-management huge-pages







      share|improve this question







      New contributor




      Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      I've been tracking down some Transparent Huge Pages performance issues--nothing unusual there--in x86_64 CentOS 6.7, and I've noticed something odd. The values in /proc/meminfo for DirectMap?? are supposed to keep track of the number of pages mapped for each of the three page sizes. But once DirectMap1G has dropped to 0, it appears that DirectMap2M will only decrease. No amount of huge page compaction ever seems to increase the value back up.



      When I look at the relevant kernel source in arch/x86/mm/pageattr.c, it's pretty clear that the DirectMap?? counters get set at initialization via update_page_count() and updated when pages are split via split_page_count(). But there's nothing in the kernel that does the reverse split adjustment to the counters when pages are compacted.



      I've looked at kernel source from 2.6 up to 4.18.20, and it seems that this behavior hasn't changed.



      So, am I missing something, or is this a bug?






      linux-kernel memory-management huge-pages




      linux-kernel memory-management huge-pages






      share|improve this question







      New contributor




      Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question







      New contributor




      Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question






      New contributor




      Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked Dec 6 at 1:02









      Harold Zable

      11




      11




      New contributor




      Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      Harold Zable is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.



























          active

          oldest

          votes











          Your Answer








          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "106"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });






          Harold Zable is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2funix.stackexchange.com%2fquestions%2f486265%2fdo-the-directmap-entries-in-proc-meminfo-account-for-huge-page-compaction%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown






























          active

          oldest

          votes













          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          Harold Zable is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          Harold Zable is a new contributor. Be nice, and check out our Code of Conduct.













          Harold Zable is a new contributor. Be nice, and check out our Code of Conduct.












          Harold Zable is a new contributor. Be nice, and check out our Code of Conduct.
















          Thanks for contributing an answer to Unix & Linux Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid …



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          To learn more, see our tips on writing great answers.





          Some of your past answers have not been well-received, and you're in danger of being blocked from answering.


          Please pay close attention to the following guidance:


          • Please be sure to answer the question. Provide details and share your research!

          But avoid …



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2funix.stackexchange.com%2fquestions%2f486265%2fdo-the-directmap-entries-in-proc-meminfo-account-for-huge-page-compaction%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          -

          Popular posts from this blog

          Accessing regular linux commands in Huawei's Dopra Linux

          Image
          4 Backstory: I have a Huawei HG8245 router in my house and I want to change the default username/password. I've tried following this guide but the config file always gets reset. My ISP isn't helping either so I'm looking for other ways to accomplish this. The router has telnet access so this seems like a way to change the credentials. The first shell I gain access to looks like this: WAP> Pressing "?" gives me a list of available commands which I've pasted here, the two interesting ones are "su" and "shell". I can't seem to get su access, even after logging in as root (challenge password prompt, and then nothing happens), but shell gives me a proper linux shell. WAP>shell BusyBox v1.18.4 (2017-12-26 17:06:34 CST) built-in shell (ash) Enter 'hel...
          Read more

          Can't connect RFCOMM socket: Host is down

          Image
          up vote 3 down vote favorite I have bluez 5.4.3 and I am attempting to communicate with a ble device through minicom. These two deceives (my computer and a bluno nano) are alreadt paired and this has been my method so far. #bluetoothctl # pair xx:xx:xx:xx:xx:xx # exit Everything is working well so far then... #sudo rfcomm connect /dev/rfcomm0 xx:xx:xx:xx:xx:xx 1 & [1] 3665 Can't connect RFCOMM socket: Host is down Does anyone know how to resolve this issue? Any help would be very much appreciated. bluetooth bluez share | improve this question asked Feb 9 '17 at 18:46 Brandon Knape 46 2 ...
          Read more

          Kernel panic - not syncing: Fatal Exception in Interrupt

          Image
          0 Every day this error occured on my pc, kernel panic error on interrupt, what will be the problem? linux-mint share asked 6 mins ago Vinod Selvin Vinod Selvin 1 1 New contributor Vinod Selvin is a new contributor to this site. Take care in asking for clarification, commenting, and answering. Check out our Code of Conduct. add a comment ...
          Read more