Why dmesg showed different "Physical Processor ID" on RedHat Enterprise 6.2 Server ?
I'm running RedHat Enterprise 6.2(Linux version 2.6.32-220.el6.x86_64 (mockbuild@x86-004.build.bos.redhat.com) with Dual Intel Xeon Processor(L5638) configuration.
When I used RedHat 5.x version with this system, "CPU: Physical Processor ID" appeared exact number of cores on the server. For example, this L5638 has 6 cores and if I enabled HyperThread on the BIOS, this "CPU: Physical Processor ID" showed 24 times in the /var/log/dmesg file.
After upgrading(actually installing) from RedHat 5.x to RedHat 6.2, this "CPU: Physical Processor ID" showed only one time and the value of this are not fixed. Followings are case what I got.
Case 1)
Initializing cgroup subsys perf_event
CPU: Physical Processor ID: 1
CPU: Processor Core ID: 0
mce: CPU supports 9 MCE banks
CPU0: Thermal monitoring enabled (TM1)
using mwait in idle threads.
ACPI: Core revision 20090903
ftrace: converting mcount calls to 0f 1f 44 00 00
ftrace: allocating 20776 entries in 82 pages
Setting APIC routing to physical flat
..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1
Case 2)
Initializing cgroup subsys ns
Initializing cgroup subsys cpuacct
Initializing cgroup subsys memory
Initializing cgroup subsys devices
Initializing cgroup subsys freezer
Initializing cgroup subsys net_cls
Initializing cgroup subsys blkio
Initializing cgroup subsys perf_event
CPU: Physical Processor ID: 0
CPU: Processor Core ID: 0
mce: CPU supports 9 MCE banks
CPU0: Thermal monitoring enabled (TM1)
using mwait in idle threads.
ACPI: Core revision 20090903
ftrace: converting mcount calls to 0f 1f 44 00 00
As you saw, the value in "CPU: Physical Processor ID" are not identical even though I didn't change any configuration from hardware and software point of view.
Does anyone have idea when this "CPU: Physical Processor ID" has 0 and when this has 1?
|