Dear Erman,
Need your help in interpreting the below output CPU(s): 16 Thread(s) per core: 2 Core(s) per socket: 4 Socket(s): 2 we would like to know whether 16 is physical or logical? we could understand that we have 4 physical cores,can we find out if those cores are dual or quad? Thanks for the support |
Pls correct me if i am wrong.
1 socket =1 physical CPU 2 socket =2 physical CPU In above output, we have 2 socket means 2 physical CPU? So 32 is logical? |
Administrator
|
what I can say by lookinh at the things you wrote here is;
2 have 2 CPU. Each of them has 4 cores and you have Hyper threading enabled. So you have 8 cores in total. As you have HT enabled, you have 16 vcpus in total. If you have the program dmidecode installed, you can have a good output of your cpu arch.. Here is an example: [root@odavm1 ~]# dmidecode -t 4 | egrep -i "Designation|Intel|core|thread" Socket Designation: P0 -- this is the 1 st cpu Manufacturer: Intel HTT (Hyper-threading technology) Version: Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz Core Count: 12 Core Enabled: 12 Thread Count: 24 --as a result of hyper threading Socket Designation: P1 -- this is the 2 nd cpu Manufacturer: Intel HTT (Hyper-threading technology) Version: Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz Core Count: 12 Core Enabled: 12 Thread Count: 24 --as a result of Hyper Threading |
Dear Erman,
Thanks for providing the info.we ran the below commands in our prod and outputs are as below [root@motoapp01 ~]# dmidecode -t 4 | egrep -i "Designation|Intel|core|thread" Socket Designation: Proc 1 Manufacturer: Intel(R) Corporation HTT (Multi-threading) Version: Intel(R) Xeon(R) CPU E5-2637 v4 @ 3.50GHz Core Count: 4 Core Enabled: 4 Thread Count: 8 Multi-Core Hardware Thread Socket Designation: Proc 2 [root@motoapp01~]# lspu was showing as 1 socket [root@motoapp01 ~]# lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 2 Core(s) per socket: 4 Socket(s): 1 NUMA node(s): 1 Vendor ID: GenuineIntel CPU family: 6 Model: 79 Model name: Intel(R) Xeon(R) CPU E5-2637 v4 @ 3.50GHz Stepping: 1 CPU MHz: 3500.000 BogoMIPS: 6991.57 Virtualization: VT-x L1d cache: 32K L1i cache: 32K L2 cache: 256K L3 cache: 15360K NUMA node0 CPU(s): 0-7 [root@motoapp01~]# We have ran this on our primary node.lscpu showed as 1 socket.could you please take some time on our outputs and update us how many sockets/physical CPU and virtual CPU's we have? |
Administrator
|
please send the output of -> dmidecode -t 4 | egrep -i "Designation|Intel|core|thread"
the whole output! |
Administrator
|
Also the output of -> dmidecode --type 4
|
Thanks for the updates erman
the whole output! [root@motonode1~]# dmidecode -t 4 | egrep -i "Designation|Intel|core|thread" Socket Designation: Proc 1 Manufacturer: Intel(R) Corporation HTT (Multi-threading) Version: Intel(R) Xeon(R) CPU E5-2637 v4 @ 3.50GHz Core Count: 4 Core Enabled: 4 Thread Count: 8 Multi-Core Hardware Thread Socket Designation: Proc 2 [root@motonode1~]# dmidecode --type 4 # dmidecode 3.0 # SMBIOS entry point at 0x788db000 Found SMBIOS entry point in EFI, reading table from /dev/mem. SMBIOS 2.8 present. Handle 0x0003, DMI type 4, 42 bytes Processor Information Socket Designation: Proc 1 Type: Central Processor Family: Xeon Manufacturer: Intel(R) Corporation ID: F1 06 04 00 FF FB EB BF Signature: Type 0, Family 6, Model 79, Stepping 1 Flags: FPU (Floating-point unit on-chip) VME (Virtual mode extension) DE (Debugging extension) PSE (Page size extension) TSC (Time stamp counter) MSR (Model specific registers) PAE (Physical address extension) MCE (Machine check exception) CX8 (CMPXCHG8 instruction supported) APIC (On-chip APIC hardware supported) SEP (Fast system call) MTRR (Memory type range registers) PGE (Page global enable) MCA (Machine check architecture) CMOV (Conditional move instruction supported) PAT (Page attribute table) PSE-36 (36-bit page size extension) CLFSH (CLFLUSH instruction supported) DS (Debug store) ACPI (ACPI supported) MMX (MMX technology supported) FXSR (FXSAVE and FXSTOR instructions supported) SSE (Streaming SIMD extensions) SSE2 (Streaming SIMD extensions 2) SS (Self-snoop) HTT (Multi-threading) TM (Thermal monitor supported) PBE (Pending break enabled) Version: Intel(R) Xeon(R) CPU E5-2637 v4 @ 3.50GHz Voltage: 1.8 V External Clock: 100 MHz Max Speed: 4000 MHz Current Speed: 3500 MHz Status: Populated, Enabled Upgrade: Socket LGA2011-3 L1 Cache Handle: 0x0000 L2 Cache Handle: 0x0001 L3 Cache Handle: 0x0002 Serial Number: Not Specified Asset Tag: UNKNOWN Part Number: Not Specified Core Count: 4 Core Enabled: 4 Thread Count: 8 Characteristics: 64-bit capable Multi-Core Hardware Thread Execute Protection Enhanced Virtualization Power/Performance Control Handle 0x0004, DMI type 4, 42 bytes Processor Information Socket Designation: Proc 2 Type: Central Processor Family: <OUT OF SPEC> Manufacturer: Not Specified ID: 00 00 00 00 00 00 00 00 Version: Not Specified Voltage: Unknown External Clock: Unknown Max Speed: 4000 MHz Current Speed: Unknown Status: Unpopulated Upgrade: Socket LGA2011-3 L1 Cache Handle: Not Provided L2 Cache Handle: Not Provided L3 Cache Handle: Not Provided Serial Number: Not Specified Asset Tag: Not Specified Part Number: Not Specified Characteristics: None [root@motonode1~]# |
Administrator
|
Okay..
You have a 2 socket server . But only 1 of those sockets is occupied with a CPU. The other one is empty. So you have 1 cpu -> Intel(R) Xeon(R) CPU E5-2637 v4 @ 3.50GHz This cpu hase 4 cores and each core has 2 threads. so you have 8 threads. (vpus) |
Thanks erman for making it very simple.Could not stop saying big thanks to you
1)can we know if the cores we are using is dual/quad/octa? 2)can we call 8 threads as 8 processors? |
we have 2 application nodes.
if i run the same query on second node,then i got the similar output. Output above is specific to a node or applies to both the nodes? |
Administrator
|
your cpu is 4 core. "Intel® Xeon® Processor E5-2637 v4" you can read its specs in intel website.
You can ofcourse call 8 threads. You can even call 16 threads, or 32 threads. These Operating Systems are time sharing.. you don't have to have the number of cores equal to your parallel work. However, if you increase parallelism, then you may end up with a high load average. The dmidecode outputs are specific to a node. If you want to see the cpu arch of other nodes, then you will connect them with root and execute dmidecode on that nodes as well.. I m closing this topic. So if you have another question, please create a new thread. |
Free forum by Nabble | Edit this page |