VMWare ESX imposes roughly the same overhead here as z/VM, about 3% of
the processor, and of course, it allocates memory on a virtual basis.
Now, the workstation versions are far more demanding, taking up to 35
or 40% of the processor; as far as I know, there is really no analogy
of this in z/VM.
On Nov 4, 2008, at 2:54 PM, A. Harry Williams wrote:
On Thu, 30 Oct 2008 18:25:17 -0500, Alan Ackerman
<[EMAIL PROTECTED]> wrote:
I got asked:
“Does z/VM impose non-insignificant overhead? Is it similar to
VMware=
, in
which virtual I/O imposes significant overhead, but most processor
and =
memory access runs at close to native physical speed?”
I don’t know anything about VMWARE so I could not answer the
question.=
I
know that CCW Translation in VM costs significant cycles.
I think FCP disks < dedicated DASD < fullpack minidisks < small
minidisk=
s.
I would HOPE that the zSeries, with so much of virtualization built
into=
the hardware, would have lower costs than VMWARE, but I don’t
really k=
now.
Any takers?
I'm hesitant to mention this, since I would have thought it would be
brou=
ght
up by others, but last I knew, VMWare doesn't have anywhere the
performan=
ce
monitoring capabilities that z/VM does. It has some minor SNMP
http://pubs.vmware.com/esx254/admin/wwhelp/wwhimpl/common/html/wwhelp.htm=
?context=admin&file=esx25admin_snmp.8.1.html
but that appears to be the limit of its function.
/ahw
Are there any web sites that give performance comparisons VM versus
VMWA=
RE?
Alan Ackerman =
Alan (dot) Ackerman (at) Bank of America (dot) com
=========================
==========================
=======================
