Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
Shawn
Shawn,
----- Original Message -----
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
You have to remember, or at least as I understand it, that a load of 1 is full for a single CPU/core. Since you have 24, a full load would be 24.
Linux gets even weirder with more cores. I have one system that has 64 cores... and it has a lot of threads/process running just to support those.
Another thing that uses quite a bit of CPU is ksm. If you don't have a number of similar VMs then I don't think it is very helpful... and it seems to eat up quite a bit of CPU resources trying to be helpful.
Ok, now the uber-CentOS geeks can tell me how stupid I am. Mmmm... go.
TYL,
About the only thing you can do is not run Windows, or at least that version, XP does the same thing, continuouslys spins the CPU when there aren't any user processes using time. I've heard this is resolved in Windows-7 but haven't tried it personally.
-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_- Eskimo North Linux Friendly Internet Access, Shell Accounts, and Hosting. Knowledgeable human assistance, not telephone trees or script readers. See our web site: http://www.eskimo.com/ (206) 812-0051 or (800) 246-6874.
On Fri, 7 Dec 2012, Shawn Everett wrote:
Date: Fri, 7 Dec 2012 12:02:14 -0800 From: Shawn Everett shawn@tandac.com Reply-To: Discussion about the virtualization on CentOS
To: centos-virt@centos.org Subject: [CentOS-virt] (no subject)
Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
Shawn
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
I've also heard that older versions of Windows don't put the CPU to "idle mode" even when there is nothing to do. It is a known problem with older Windows kernels.
Anyway, try to install the latest virtio drivers for Windows if you don't already have.
On 12/7/2012 9:18 PM, Robert Dinse wrote:
About the only thing you can do is not run Windows, or at least thatversion, XP does the same thing, continuouslys spins the CPU when there aren't any user processes using time. I've heard this is resolved in Windows-7 but haven't tried it personally.
-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_- Eskimo North Linux Friendly Internet Access, Shell Accounts, and Hosting. Knowledgeable human assistance, not telephone trees or script readers. See our web site: http://www.eskimo.com/ (206) 812-0051 or (800) 246-6874.
On Fri, 7 Dec 2012, Shawn Everett wrote:
Date: Fri, 7 Dec 2012 12:02:14 -0800 From: Shawn Everett shawn@tandac.com Reply-To: Discussion about the virtualization on CentOS
<centos-virt@centos.org>To: centos-virt@centos.org Subject: [CentOS-virt] (no subject)
Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
Shawn
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
On Sat, 2012-12-08 at 06:48 +0100, Zoltan Frombach wrote:
I've also heard that older versions of Windows don't put the CPU to "idle mode" even when there is nothing to do. It is a known problem with older Windows kernels.
Windows is installed without ACPI, this way the CPU does not get IDLE instructions and Windows uses all vCPU time it can get. I don't know why ACPI is deactivated by default - some say performance without ACPI is higher, some say because of compatibility - anyway you have to choose between high load of host machine's CPU at ALL time or the best performance of Windows virtual machine when under load.
My choice is to enable ACPI on windows virtual machines and the problem is solved.
#virsh edit WinXP .... <features> <acpi/> <apic/> <pae/> </features> ....
You should have <acpi/> in <features>. If you don't - add it.
Another way to add it is to open virtual machine manager (virt-manager), open virtual machine there, go to 'details' (button with blue 'i' on it), look in 'overview' screen, open 'Machine Settings', mark 'enable ACPI' there.
Best regards, Dmitry Mikhailov.
Anyway, try to install the latest virtio drivers for Windows if you don't already have.
On 12/7/2012 9:18 PM, Robert Dinse wrote:
About the only thing you can do is not run Windows, or at least thatversion, XP does the same thing, continuouslys spins the CPU when there aren't any user processes using time. I've heard this is resolved in Windows-7 but haven't tried it personally.
-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_- Eskimo North Linux Friendly Internet Access, Shell Accounts, and Hosting. Knowledgeable human assistance, not telephone trees or script readers. See our web site: http://www.eskimo.com/ (206) 812-0051 or (800) 246-6874.
On Fri, 7 Dec 2012, Shawn Everett wrote:
Date: Fri, 7 Dec 2012 12:02:14 -0800 From: Shawn Everett shawn@tandac.com Reply-To: Discussion about the virtualization on CentOS
<centos-virt@centos.org>To: centos-virt@centos.org Subject: [CentOS-virt] (no subject)
Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
Shawn
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
On Sat, Dec 8, 2012 at 12:48 AM, Zoltan Frombach zoltan@frombach.comwrote:
I've also heard that older versions of Windows don't put the CPU to "idle mode" even when there is nothing to do. It is a known problem with older Windows kernels.
Windows 98 and the like don't idle. It requires software to help idle the CPU usage. So I've read - I believe a table on the libvirt site says Win98 is no longer possible.
Anyway, try to install the latest virtio drivers for Windows if you don't already have.
I have a WinXP Pro 32bit VM with virtio drivers and it runs just fine. I don't watch the load on it, so I don't know if its CPU goes idle. I'll have to take a peek at it next week.
Is the OP absolutely certain that there is no process running that would consume that small amount of CPU? I'd be more concerned if the usage was 10% or greater when the system _should_ be idle.
On 12/7/2012 9:18 PM, Robert Dinse wrote:
About the only thing you can do is not run Windows, or at leastthat
version, XP does the same thing, continuouslys spins the CPU when there
aren't
any user processes using time. I've heard this is resolved in Windows-7
but
haven't tried it personally.
-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-
Eskimo North Linux Friendly Internet Access, Shell Accounts, and
Hosting.
Knowledgeable human assistance, not telephone trees or scriptreaders.
See our web site: http://www.eskimo.com/ (206) 812-0051 or (800)
246-6874.
On Fri, 7 Dec 2012, Shawn Everett wrote:
Date: Fri, 7 Dec 2012 12:02:14 -0800 From: Shawn Everett shawn@tandac.com Reply-To: Discussion about the virtualization on CentOS
<centos-virt@centos.org>To: centos-virt@centos.org Subject: [CentOS-virt] (no subject)
Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall
nx
pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est
tm2
ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx
lahf_lm
ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0
to
1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty
light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
Shawn
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
On Sat, 8 Dec 2012, SilverTip257 wrote:
I have a WinXP Pro 32bit VM with virtio drivers and it runs just fine. I don't watch the load on it, so I don't know if its CPU goes idle. I'll have to take a peek at it next week.
I have XP, 2003 and Win7 with virtio drivers, and the CPU does go idle on all of them when Windows is doing nothing. However, Windows is often not doing nothing; make sure that you have volume indexing, for example, turned off.
Steve
On Sat, 2012-12-08 at 14:17 -0500, Steve Thompson wrote:
On Sat, 8 Dec 2012, SilverTip257 wrote:
I have a WinXP Pro 32bit VM with virtio drivers and it runs just fine. I don't watch the load on it, so I don't know if its CPU goes idle. I'll have to take a peek at it next week.
I have XP, 2003 and Win7 with virtio drivers, and the CPU does go idle on all of them when Windows is doing nothing.
Are we talking about virtual machine's CPU that goes idle or host cpu that goes idle (i.e. host OS load decreasing) when virtual machine does nothing?
However, Windows is often not doing nothing; make sure that you have volume indexing, for example, turned off.
Steve _______________________________________________ CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
I was running XP installed directly onto the CentOS 6.3 guest, and two problems occurred: 1) the guest ran like a dog, and 2) the host ran as many cores at 100% as I had cores in the guest.
Both problems were fixed by loading the virtio drivers for disk and network.
Yours,
Clint Redwood
Screwtape Limited, Registered 06663232, Babington House, 26 College Road, Chilwell, Nottingham NG9 4AS
On 8 Dec 2012, at 17:20, SilverTip257 silvertip257@gmail.com wrote:
On Sat, Dec 8, 2012 at 12:48 AM, Zoltan Frombach zoltan@frombach.com wrote:
I've also heard that older versions of Windows don't put the CPU to "idle mode" even when there is nothing to do. It is a known problem with older Windows kernels.
Windows 98 and the like don't idle. It requires software to help idle the CPU usage. So I've read - I believe a table on the libvirt site says Win98 is no longer possible.
Anyway, try to install the latest virtio drivers for Windows if you don't already have.
I have a WinXP Pro 32bit VM with virtio drivers and it runs just fine. I don't watch the load on it, so I don't know if its CPU goes idle. I'll have to take a peek at it next week.
Is the OP absolutely certain that there is no process running that would consume that small amount of CPU? I'd be more concerned if the usage was 10% or greater when the system _should_ be idle.
On 12/7/2012 9:18 PM, Robert Dinse wrote:
About the only thing you can do is not run Windows, or at least thatversion, XP does the same thing, continuouslys spins the CPU when there aren't any user processes using time. I've heard this is resolved in Windows-7 but haven't tried it personally.
-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_- Eskimo North Linux Friendly Internet Access, Shell Accounts, and Hosting. Knowledgeable human assistance, not telephone trees or script readers. See our web site: http://www.eskimo.com/ (206) 812-0051 or (800) 246-6874.
On Fri, 7 Dec 2012, Shawn Everett wrote:
Date: Fri, 7 Dec 2012 12:02:14 -0800 From: Shawn Everett shawn@tandac.com Reply-To: Discussion about the virtualization on CentOS
<centos-virt@centos.org>To: centos-virt@centos.org Subject: [CentOS-virt] (no subject)
Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
Shawn
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
CentOS-virt mailing list CentOS-virt@centos.org http://lists.centos.org/mailman/listinfo/centos-virt
Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
Shawn
On 12/07/2012 10:04 PM, Shawn Everett wrote:
Hi All,
I have recently installed CentOS 6.3 with QEMU+KVM for Virtualization.
I have successfully created a Windows 2003 VM with 4GB of RAM. The host server is an HP ML350 G8 with 24GB RAM and 24 cores. Details of one of the cores is shown below:
processor : 23 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 1200.000 cache size : 15360 KB physical id : 1 siblings : 12 core id : 5 cpu cores : 6 apicid : 43 initial apicid : 43 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 3989.86 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
On an otherwise completely idle system I've noticed the load to be 1.0 to 1.5 range. Running "top" shows the culprit to be: qemu-kvm.
Is this normal behavior? I would have expected the load to be pretty light.
Stopping the VM restores the load to normal once again.
Is there anything I can do to reduce the load?
You probably have 12 cores and thanks to hyper-threading that gives you 24 threads (big difference). Have you installed the virtio drivers in the VM? That might reduce the load a bit. Also was does running "vmstat 3" for about 20 seconds show?
Regards, Dennis
-
Clint Redwood -
Dennis Jacobfeuerborn -
Dmitry E. Mikhailov -
Robert Dinse -
Scott Dowdle -
Shawn Everett -
SilverTip257 -
Steve Thompson -
Zoltan Frombach