virtualization (VCPU count according to CPU)

Thread Tools Search this Thread
# 1  
virtualization (VCPU count according to CPU)

We have purchased four intels xeon processors

IntelŽ XeonŽ Processor E7530 (12M Cache, 1.86 GHz, 5.86 GT/s IntelŽ QPI) with SPEC Code(s) SLBRJ

As per the specification each cpu has 6 cores therefore we have 24 cores (considering 4 cpus).
Now how would i calculate the number of vcpus that can be used while visualization?
This will help use to capacity planning.

specification is as below.

IntelŽ XeonŽ Processor E7530
(12M Cache, 1.86 GHz, 5.86 GT/s IntelŽ QPI)
Status Launched
Launch Date Q1'10
Processor Number E7530
# of Cores 6
# of Threads 12
Clock Speed 1.866 GHz
Max Turbo Frequency 2.133 GHz
L3 Cache 12 MB
IntelŽ QPI Speed 5.86 GT/s
Embedded Options Available
Supplemental SKU No
Max TDP 105 W
VID Voltage Range 0.675V-1.35V
Tray 1ku Budgetary Price $1446.00
Package Specifications
Sockets Supported FCLGA1567
Halogen Free Options Available Yes
Advanced Technologies
IntelŽ Turbo Boost Technology
IntelŽ Hyper-Threading Technology
IntelŽ Virtualization Technology (VT-x)
IntelŽ 64
Enhanced Intel SpeedStepŽ Technology
Execute Disable Bit Yes
# 2  
There's no hard rule on this. Some people over commit.. so the sum total of VM resources is greater than actual physical resources. Usually, one place where this is done is with regards to CPUs. BUT... if your VMs REALLY need a whole bunch of CPU resources, it's possible that you'll reach the limits of what you can actually give and have a "good" performing platform. IMHO, it's pretty safe to say that we waste about 50% of CPU resources (in general, the number is usually much, much higher). So you could use that for a very conservative number of total CPUs you can dole out. And don't discount the hyperthreads... they do help out as well...

If your plan is to virtualize large scale servers (e.g. 4 CPUs + 8G+ memory) ... I think that's a BAD plan. Virtualization is most effective when talking about smaller footprint machines. Then the scalability can be VERY large.. and you can really over commit (but again, there is no RULE).

Thread Tools Search this Thread
Search this Thread:
Advanced Search

More UNIX and Linux Forum Topics You Might Find Helpful
Topas - CPU count inconsistent across LPARs
seeing weirdness across some LPARs - they all have 2 vCPUs allocated shared. With prtconf they show 2 CPUs, 'lsdev -c processor' concurs, and 'lsattr -El procX' shows that SMT is enabled and there are 2 SMT threads (power5, sorry). Yet running topas on them shows 2 CPUs on some and 4 on...... AIX
Incorrect vCPU numbering
Hi All, Currently experiencing more-so a visual issue when typing psrinfo, mpstat commands, as the virtual processors start from 8-39, as below: # psrinfo -pv The physical processor has 32 virtual processors (8-39) UltraSPARC-T2 (chipid 0, clock 1165 MHz) Can't seem to find anything to...... Solaris
CPU Count
Hi, I am observing high load average on RHEL5 server and need to check the number of core processors available on the box to give me a bigger picture on whether or not I should be worried. I have always checked the physical count quite simply..... # grep 'physical id' /proc/cpuinfo |...... Red Hat
Red Hat
topas and mpstat disagree on CPU count
I have a number of LPARs on one P520. All LPARs are running 5.3 and I observe the following: On some LPARs the number of CPUs found do not match between topas and mpstat. Server 1: $ mpstat System configuration: lcpu=4 ent=0.2 mode=Uncapped cpu min maj mpc int cs ics rq ...... AIX
CPU count
Is there an easy way in Solaris to count the number of processors?... UNIX for Dummies Questions & Answers
UNIX for Dummies Questions & Answers