2 Replies Latest reply: Jan 18, 2013 12:45 PM by user12273962 RSS

    OVM 3.1.1 on HP Proliant DL585G7 256GB RAM, 4CPUx16cores


      I have problem with OVM 3.1.1, on our new server HP Proliant 585 G7 with 256GB RAM, 4CPU with 16cores

      After successfull installation, system reboots and then

      ++------------[ cut here ]------------++
      ++WARNING: at arch/x86/xen/enlighten.c:823 xen_apic_write+0x1a/0x20()++
      ++Hardware name: ProLiant DL585 G7++
      ++Modules linked in:++
      ++Pid: 0, comm: swapper Tainted: G W 2.6.39-200.1.1.el5uek #1++
      ++Call Trace:++
      ++<IRQ> [<ffffffff810037da>] ? xen_apic_write+0x1a/0x20++
      ++[<ffffffff8106ce10>] warn_slowpath_common+0x90/0xc0++
      ++[<ffffffff8106ce5a>] warn_slowpath_null+0x1a/0x20++
      ++[<ffffffff810037da>] xen_apic_write+0x1a/0x20++
      ++[<ffffffff810236a7>] perf_events_lapic_init+0x37/0x40++
      ++[<ffffffff81027273>] x86_pmu_enable+0xe3/0x220++
      ++[<ffffffff811021d4>] perf_pmu_enable+0x24/0x30++
      ++[<ffffffff81026fe4>] x86_pmu_commit_txn+0xa4/0xb0++
      ++[<ffffffff8103ef91>] ? pvclock_get_nsec_offset+0x11/0x50++
      ++[<ffffffff8103eff9>] ? pvclock_clocksource_read+0x29/0x80++
      ++[<ffffffff8103ef91>] ? pvclock_get_nsec_offset+0x11/0x50++
      ++[<ffffffff8103eff9>] ? pvclock_clocksource_read+0x29/0x80++
      ++[<ffffffff81106db4>] group_sched_in+0x144/0x160++
      ++[<ffffffff8110873e>] __perf_event_enable+0x15e/0x170++
      ++[<ffffffff81104cb3>] remote_function+0x43/0x50++
      ++[<ffffffff810a6c91>] generic_smp_call_function_single_interrupt+0xa1/0xf0++
      ++[<ffffffff81011a33>] xen_call_function_single_interrupt+0x13/0x30++
      ++[<ffffffff810d4a1d>] handle_irq_event_percpu+0x5d/0x1b0++
      ++[<ffffffff810d7198>] handle_percpu_irq+0x48/0x70++
      ++[<ffffffff812f4fdf>] __xen_evtchn_do_upcall+0x16f/0x270++
      ++[<ffffffff812f5a9f>] xen_evtchn_do_upcall+0x2f/0x50++
      ++[<ffffffff8150a0ce>] xen_do_hypervisor_callback+0x1e/0x30++
      ++<EOI> [<ffffffff810013aa>] ? hypercall_page+0x3aa/0x1000++
      ++[<ffffffff810013aa>] ? hypercall_page+0x3aa/0x1000++
      ++[<ffffffff81009dc0>] ? xen_safe_halt+0x10/0x20++
      ++[<ffffffff8101cceb>] ? default_idle+0x5b/0x170++
      ++[<ffffffff810137b6>] ? cpu_idle+0xc6/0xf0++
      ++[<ffffffff8100a5d9>] ? xen_irq_enable_direct_reloc+0x4/0x4++
      ++[<ffffffff814f057e>] ? cpu_bringup_and_idle+0xe/0x10++
      ++---[ end trace a7919e7f17c0a74b ]---++

      Occasionally system boot sucessfully.

      I found that similar problem was on Dell servers related to advanced power managments, but on HP servers that doesn't help.

      Did someone had such problem?

      Thank you in advance
        • 1. Re: OVM 3.1.1 on HP Proliant DL585G7 256GB RAM, 4CPUx16cores
          that I find also in dmesg

          Jan 18 15:56:48 bilbo-ovm kernel: Performance Events: Broken BIOS detected, complain to your hardware vendor.
          Jan 18 15:56:48 bilbo-ovm kernel: [Firmware Bug]: the BIOS has corrupted hw-PMU resources (MSR c0010200 is 430076)
          Jan 18 15:56:48 bilbo-ovm kernel: AMD Family 15h PMU driver.
          Jan 18 15:56:48 bilbo-ovm kernel: ------------[ cut here ]------------

          • 2. Re: OVM 3.1.1 on HP Proliant DL585G7 256GB RAM, 4CPUx16cores

            7.2.1. Server BIOS Settings
            The following server BIOS settings may be required to use Oracle VM Server:
            • AHCI mode may be necessary to recognize the CDROM device to perform an installation from CDROM.
            • Disable I/O MMU Virtualization Settings; for Intel-based servers this is VT-d; for AMD based servers this
            is AMD-Vi or IOMMU. I/O MMU is not supported in this release.