Having a strange issue where snmp polling a vm for the ssCpuRawIdle
stats (and all the other raw cpu stats) shows up as double:
snmpwalk -v 2c -c ''XXXX'' nathanxen1 1.3.6.1.4.1.2021.11.53
&& sleep 60
&& snmpwalk -v 2c -c ''XXXXXXX'' nathanxen1
1.3.6.1.4.1.2021.11.53
UCD-SNMP-MIB::ssCpuRawIdle.0 = Counter32: 47631385
UCD-SNMP-MIB::ssCpuRawIdle.0 = Counter32: 47643353
(47643353 - 47631385) / 6000 * 100 = 199%
Except that this VM has a single cpu. Polling regular machines works
fine with this logic and returns the expected numbers.
nathanxen1 ~ # cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 44
model name : Intel(R) Xeon(R) CPU L5640 @ 2.27GHz
stepping : 2
cpu MHz : 2266.806
cache size : 12288 KB
fpu : yes
fpu_exception : yes
cpuid level : 11
wp : yes
flags : fpu de tsc msr pae cx8 sep cmov pat clflush mmx fxsr
sse sse2 ss ht syscall nx lm constant_tsc up rep_good aperfmperf pni
ssse3 cx16 sse4_1 sse4_2 popcnt hypervisor lahf_lm ida arat
bogomips : 4533.61
clflush size : 64
cache_alignment : 64
address sizes : 40 bits physical, 48 bits virtual
power management:
nathanxen1 ~ #
Xm info:
xen1 ~ # xm info
host : xen1
release : 2.6.31.13
version : #11 SMP Mon Aug 23 16:12:21 PDT 2010
machine : x86_64
nr_cpus : 12
nr_nodes : 2
cores_per_socket : 6
threads_per_core : 1
cpu_mhz : 2266
hw_caps :
bfebfbff:2c100800:00000000:00001f40:009ee3fd:00000000:00000001:00000000
virt_caps : hvm hvm_directio
total_memory : 24566
free_memory : 10939
node_to_cpu : node0:0-5
node1:6-11
node_to_memory : node0:10939
node1:0
node_to_dma32_mem : node0:2996
node1:0
max_node_id : 1
xen_major : 4
xen_minor : 0
xen_extra : .1-rc6-pre
xen_caps : xen-3.0-x86_64 xen-3.0-x86_32p hvm-3.0-x86_32
hvm-3.0-x86_32p hvm-3.0-x86_64
xen_scheduler : credit
xen_pagesize : 4096
platform_params : virt_start=0xffff800000000000
xen_changeset : unavailable
xen_commandline : console=com1,com2,vga com1=115200,8n1
com2=115200,8n1 dom0_mem=1024M dom0_max_vcpus=1 dom0_vcpus_pin=true
cc_compiler : gcc version 4.3.4 (Gentoo 4.3.4 p1.1, pie-10.1.5)
cc_compile_by : root
cc_compile_domain :
cc_compile_date : Mon Aug 23 10:52:16 PDT 2010
xend_config_format : 4
Anyone have any thoughts on this?
Thanks,
Nathan
_______________________________________________
Xen-users mailing list
Xen-users@lists.xensource.com
http://lists.xensource.com/xen-users
On Wed, Oct 6, 2010 at 6:54 AM, Nathan March <nathan@gossamer-threads.com>wrote:> Having a strange issue where snmp polling a vm for the ssCpuRawIdle stats > (and all the other raw cpu stats) shows up as double: > > snmpwalk -v 2c -c ''XXXX'' nathanxen1 1.3.6.1.4.1.2021.11.53 && sleep 60 && > snmpwalk -v 2c -c ''XXXXXXX'' nathanxen1 1.3.6.1.4.1.2021.11.53 > > UCD-SNMP-MIB::ssCpuRawIdle.0 = Counter32: 47631385 > UCD-SNMP-MIB::ssCpuRawIdle.0 = Counter32: 47643353 > > (47643353 - 47631385) / 6000 * 100 = 199% > > Except that this VM has a single cpu. Polling regular machines works fine > with this logic and returns the expected numbers. > >My guess is that it''s kernel issue. Are you running newer pv_ops kernel? If yes, you should ask to xen-devel. I''ve checked RHEL''s kernel-xen and newer xenlinux kernel, both return the correct values. -- Fajar _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Tried updating the VM to 2.6.32.24 and still happens. When I get a chance to update to the latest xen-unstable I''ll test more. - Nathan On 10/5/2010 6:33 PM, Fajar A. Nugraha wrote:> On Wed, Oct 6, 2010 at 6:54 AM, Nathan March > <nathan@gossamer-threads.com <mailto:nathan@gossamer-threads.com>> wrote: > > Having a strange issue where snmp polling a vm for the > ssCpuRawIdle stats (and all the other raw cpu stats) shows up as > double: > > snmpwalk -v 2c -c ''XXXX'' nathanxen1 1.3.6.1.4.1.2021.11.53 && > sleep 60 && snmpwalk -v 2c -c ''XXXXXXX'' nathanxen1 > 1.3.6.1.4.1.2021.11.53 > > UCD-SNMP-MIB::ssCpuRawIdle.0 = Counter32: 47631385 > UCD-SNMP-MIB::ssCpuRawIdle.0 = Counter32: 47643353 > > (47643353 - 47631385) / 6000 * 100 = 199% > > Except that this VM has a single cpu. Polling regular machines > works fine with this logic and returns the expected numbers. > > > > My guess is that it''s kernel issue. Are you running newer pv_ops > kernel? If yes, you should ask to xen-devel. I''ve checked RHEL''s > kernel-xen and newer xenlinux kernel, both return the correct values. > > -- > Fajar_______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users