XCP-ng
    • Categories
    • Recent
    • Tags
    • Popular
    • Users
    • Groups
    • Register
    • Login

    Alert: Control Domain Memory Usage

    Scheduled Pinned Locked Moved Solved Compute
    194 Posts 21 Posters 200.7k Views 16 Watching
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • O Offline
      OlivierD
      last edited by

      Hello,
      I can confirm we encountered this issue on several hosts in the past few months.

      Config :

      • Server is Dell PowerEdge M630
      • local storage on SSD + remote SR on ISCSI
      • kernel used: kernel-4.19.19-6.0.11.1.xcpng8.1.x86_64
      • we use ixgbe (intel-ixgbe-5.5.2-2.xcpng8.1.x86_64) and network cards are Intel 82599 10 Gigabit dual Port (with bonding on XCP NG).
      • firmwares up to date (less than 6 months, when we updated to XCP-NG 8.1+).

      Additional informations :

      • we don't have any VM with memory ballooning
      • shutting down VMs does not free memory
      • we don't do many operations each day (less than 5 reboots/stop/start).
      • size of pools does not matter (bug happened with two hosts and on another pool with 10 hosts).

      According to some messages, it seems kernel-alt fixes the issue ... We'll try to switch kernel when we encounter the issue again.

      1 Reply Last reply Reply Quote 2
      • olivierlambertO Online
        olivierlambert Vates 🪐 Co-Founder CEO
        last edited by olivierlambert

        Yes, please, keep us posted 🙂

        Thank for your feedback!

        1 Reply Last reply Reply Quote 0
        • F Offline
          fasterfourier
          last edited by

          One more observation here. This issue does not occur on a different pool of ours that's also running CH8.2LTSR. That pool has lower loading overall, 2 hosts instead of 7, and does not contain any NICs using the ixgbe driver. Other aspects of the pool are identical.

          1 Reply Last reply Reply Quote 1
          • stormiS Offline
            stormi Vates 🪐 XCP-ng Team @stormi
            last edited by

            @stormi said in Alert: Control Domain Memory Usage:

            Before I realized that not every affected host was using the ixgbe driver, contrarily to what I initially thought, I built an alternate driver from the latest sources from Intel.

            So, even if there's little hope that it will fix anything, here's how to install it (on XCP-ng 8.1 or 8.2):

            yum install intel-ixgbe-alt --enablerepo=xcp-ng-testing
            reboot
            

            Has anyone tested the updated ixgbe driver?

            daveD 1 Reply Last reply Reply Quote 2
            • daveD Offline
              dave @stormi
              last edited by

              @stormi

              I upgraded a pool which was affected from 8.1 to 8.2 this weekend and installed the driver on one of the Hosts. Its a little early, but as you can see, there seems to be a difference in the memory usage:

              Stock Driver

              c53f2add-8bbe-4203-bba8-97e94b466c56-image.png

              Stromis Driver:

              57bf6a63-eff5-47ca-a155-b918c12b95b2-image.png

              One can allready see a constanty, slowly growing mem-usage in "small steps" on the Server with the stock driver, wheras the server with stormis driver seems to be stable.

              1 Reply Last reply Reply Quote 1
              • olivierlambertO Online
                olivierlambert Vates 🪐 Co-Founder CEO
                last edited by

                Indeed, sounds better in any case! Thanks a lot @dave for the feedback.

                For everyone else with the issue: please try the same and report. Maybe we found the culprit!

                1 Reply Last reply Reply Quote 0
                • olivierlambertO Online
                  olivierlambert Vates 🪐 Co-Founder CEO
                  last edited by

                  That's really likely the problem all along.

                  See https://sourceforge.net/p/e1000/bugs/633/#af80/154d

                  So our alt driver is indeed fixing it 🙂

                  1 Reply Last reply Reply Quote 2
                  • M Offline
                    MrMike
                    last edited by

                    Good job guys!

                    1 Reply Last reply Reply Quote 0
                    • olivierlambertO Online
                      olivierlambert Vates 🪐 Co-Founder CEO
                      last edited by

                      A big thanks for the link that @andyhhp provided to confirm the problem 🙂

                      delafD D 2 Replies Last reply Reply Quote 1
                      • delafD Offline
                        delaf @olivierlambert
                        last edited by

                        I have installed intel-ixgbe-alt-5.9.4-1.xcpng8.1.x86_64 on my server (268).
                        I'll check in some days if I still have the problem or not.

                        Thank you guys!

                        1 Reply Last reply Reply Quote 0
                        • D Offline
                          daKju @olivierlambert
                          last edited by

                          @olivierlambert is there a plan to deploy the alt-driver over the xcp-ng update or should we installed by the xcp-ng-testing repo?
                          THX for the good job guys 👍 😊

                          1 Reply Last reply Reply Quote 0
                          • stormiS Offline
                            stormi Vates 🪐 XCP-ng Team
                            last edited by

                            I'm going to build a driver package that only has the patch that is thought to fix the memory issue and let everyone here test it. If the results are good, then it will become an official update.

                            delafD 1 Reply Last reply Reply Quote 0
                            • delafD Offline
                              delaf @stormi
                              last edited by delaf

                              @stormi
                              Screenshot 2021-03-04 at 21.21.16.png
                              The 2 servers have been reinstalled with an up to date 8.2. They host each 2 VMs that are doing the same thing (~100Mb/s of netdata stream).

                              The right one has the 5.9.4-1.xcpng8.2, the left one has 5.5.2-2.xcpng8.2.

                              The patch seem to be OK for me.

                              J 1 Reply Last reply Reply Quote 1
                              • stormiS Offline
                                stormi Vates 🪐 XCP-ng Team
                                last edited by

                                Announcement

                                Here's an updated ixgbe driver package that is meant as an update candidate without updating to a higher version. If need all feedback we can get on this one, because this is the candidate for the official fix as would be delivered to everyone. Of course the intel-igb-alt will remain available for those who need a more recent driver, and I even moved it to the updates repository so that one doesn't need to add --enablerepo=xcp-ng-testing to install it anymore.

                                To test the official update candidate on XCP-ng 8.1 or 8.2.

                                • If you had previously installed intel-ixgbe-alt:
                                  • yum remove intel-ixgbe-alt -y
                                  • Check that the /lib/modules/4.19.0+1/override/ixgbe.ko file was properly deleted. I've seen, once, a situation where a .ko file from an -alt package wasn't deleted, so I'm being cautious here and ask you to report you see that it is still present. In theory, this is impossible, but as I've seen it once I don't know anymore 🙂
                                  • Run depmod -a
                                • Update the intel-ixgbe package from the testing repo: yum update intel-ixgbe --enablerepo=xcp-ng-testing
                                • Reboot

                                Note: I'm not 100% sure that I picked the right patch, nor that this patch alone is sufficient.

                                delafD 1 Reply Last reply Reply Quote 0
                                • delafD Offline
                                  delaf @stormi
                                  last edited by

                                  @stormi I have installed intel-ixgbe 5.5.2-2.1.xcpng8.2 on my server s0267. Let's wait a some days to check if the memleak is solved by this patch.

                                  delafD 1 Reply Last reply Reply Quote 1
                                  • delafD Offline
                                    delaf @delaf
                                    last edited by

                                    @stormi
                                    It seems to be good here!

                                    Screenshot 2021-03-09 at 08.36.50.png

                                    1 Reply Last reply Reply Quote 2
                                    • olivierlambertO Online
                                      olivierlambert Vates 🪐 Co-Founder CEO
                                      last edited by

                                      So we found the good patch 🙂 That was a really tricky issue to find!

                                      1 Reply Last reply Reply Quote 0
                                      • stormiS Offline
                                        stormi Vates 🪐 XCP-ng Team
                                        last edited by stormi

                                        Once again, an issue that was present in vendor drivers but not in the mainline kernel. It's becoming harder and harder to trust vendor drivers. But that's what they require for support...

                                        1 Reply Last reply Reply Quote 2
                                        • F Offline
                                          fasterfourier
                                          last edited by olivierlambert

                                          Our Citrix ticket has been worked and they concluded that the NIC driver is to blame here as well. They had us collect debug info using:

                                          /opt/xensource/libexec/xen-cmdline --set-dom0 page_owner=on
                                          

                                          They then confirmed the memory leak was from the NIC driver. They are intending to release a public hotfix for this issue.

                                          1 Reply Last reply Reply Quote 3
                                          • olivierlambertO Online
                                            olivierlambert Vates 🪐 Co-Founder CEO
                                            last edited by olivierlambert

                                            Nice to see Citrix are also getting to the same conclusions 🙂

                                            edit: thanks @fasterfourier for your feedback!

                                            F 1 Reply Last reply Reply Quote 1
                                            • First post
                                              Last post