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

    how to identifi that server is not overloaded by VMs?

    Scheduled Pinned Locked Moved Hardware
    9 Posts 3 Posters 399 Views 2 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.
    • gudge25G Offline
      gudge25
      last edited by

      fc18fd80-3b6a-4439-945f-2c39bc983fb8-image.png

      860d73ad-3cae-4f6a-9e5c-36b11db697e3-image.png

      4614e7e2-b53c-426c-a2d5-2f00f40bd855-image.png

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

        Hi,

        If you want constructive feedback from the community, you should try to explain a bit more what do you need and why 🙂 This way, we could try to provide the best approach/solution for your use case. Thanks!

        gudge25G 1 Reply Last reply Reply Quote 0
        • gudge25G Offline
          gudge25 @olivierlambert
          last edited by gudge25

          @olivierlambert my bad sorry
          i have a server with 3 VMs on it
          from a prev week without any reason CPU utilization doubles
          and I noticed even on reboot VM Grub loads with a delay

          so I'm wondering is there a way to check maybe one or all VMs started overload server

          need advice how I can identify that
          Regards

          D 1 Reply Last reply Reply Quote 0
          • D Offline
            DustinB @gudge25
            last edited by

            @gudge25 Why are you using TOP instead of Xen Orchestra to check the status of your pool?

            gudge25G 1 Reply Last reply Reply Quote 0
            • gudge25G Offline
              gudge25 @DustinB
              last edited by

              @DustinB
              Storage
              f379251f-4748-4104-8542-7ef2a4d3c807-image.png

              Server itself
              e2f7c230-3f24-4c4f-9c2d-76b3f96e9117-image.png

              gudge25G 1 Reply Last reply Reply Quote 0
              • gudge25G Offline
                gudge25 @gudge25
                last edited by

                @gudge25 POOL
                6a06f189-85ae-43fa-b292-09c9df1a1c6c-image.png

                gudge25G 1 Reply Last reply Reply Quote 0
                • gudge25G Offline
                  gudge25 @gudge25
                  last edited by

                  @gudge25 Strange is that

                  Host + 3 VMS started to use more CPU on exactly the same day (time)

                  Host:
                  ec8f4f20-9588-4611-ae43-cae6ac3b0b2b-image.png

                  VM1
                  6658e73e-9191-4f4b-b5a0-9f2aadafb419-image.png

                  VM2
                  ae430ff0-758e-4add-9beb-4ee9979a063f-image.png

                  VM3
                  8f8c8e16-3703-498f-b417-136bdf452529-image.png

                  gudge25G 1 Reply Last reply Reply Quote 0
                  • gudge25G Offline
                    gudge25 @gudge25
                    last edited by

                    @gudge25 i disabled TCP Offload checksum errors

                    ethtool -K eth0 tx off rx off

                    but no luck

                    gudge25G 1 Reply Last reply Reply Quote 0
                    • gudge25G Offline
                      gudge25 @gudge25
                      last edited by gudge25

                      please advice is there a way to check
                      that RAID1 read speed can be a bottleneck ?
                      like 3 VMs are more than NVME Raid can give
                      and that's why VMs are slow in responce

                      1 Reply Last reply Reply Quote 0
                      • First post
                        Last post