Must not have been clear. Sorry about that. For every 1 proc or core
of Power you would need 4 or more of x86 (even at their best level). I
have seen the numbers from Intel comparing Newer x86 processors to
Power6 and they are just below the Power 6 (using 2x's the number of
cores). The problem is, You can get Power7 cheaper than Power6, and get
twice the performance. So, the cost might be cheaper per proc on x86,
but the performance isn't half as good. So, you wind up having to buy 4
times the number of processors, which means you pay more in the long run
(requires more servers, LAN ports, Electrical Power, cooling, more
complex management, etc. etc.). The advantages with Power are manifold,
especially with Power7.
There are still some who think that you can use cheap intel hardware and
get the same or better price/performance of a current Power box, but
what you get is unreliable hardware. I've been a Linux guy for a long
time, and for lighter loads (web servers, file servers, app servers and
small to midrange DB servers) Linux is a much cheaper option. However,
for heavy lifting, (large Oracle or DB2 dbs, something like TSM, etc.)
AIX is still the better option. I can run a single TSM instance on
AIX/Power long after Intel boxes have had to complicate their lives with
multiple TSM servers and Library managers, etc.
My challenge to folks is to price it out for yourselves. We have
purchased smaller Power7 Servers for around 12K (gets us 8 cores of
Power7, 6 HBAs or 3 dual port HBAs, 16GB RAM, etc). An equally powered
Intel box (with half the performance) is about 15K.
See Ya'
Howard Coles Jr.
John 3:16!
-----Original Message-----
From: ADSM: Dist Stor Manager [mailto:ADSM-L AT VM.MARIST DOT EDU] On Behalf Of
Shawn Drew
Sent: Friday, October 07, 2011 10:21 AM
To: ADSM-L AT VM.MARIST DOT EDU
Subject: Re: [ADSM-L] Check signals on Power vs. x86...
I think he was looking for Power vs x86 in price/performance.
I.E If you spend 50K on Power systems and 50K on x86 systems. which
could produce more I/O throughput.
(If not, that's what I'd like to hear an update on)
From what I remember from previous discussions, x86/linux would come out
on top for pure price/performance,
but managing many x86 systems vs a single/fewer Power systems certainly
has some value.
I'm sure there are many other intangibles when it comes to value.
Regards,
Shawn
________________________________________________
Shawn Drew
Internet
Howard.Coles AT ARDENTHEALTH DOT COM
Sent by: ADSM-L AT VM.MARIST DOT EDU
10/07/2011 09:44 AM
Please respond to
ADSM-L AT VM.MARIST DOT EDU
To
ADSM-L
cc
Subject
Re: [ADSM-L] Check signals on Power vs. x86...
Yes, it is. There are very few things I would say this about, but this
is
one of 'em.
For a RHEL box to match the performance capabilities it would have to be
installed on Power as well (which it can be). I think the evidence I've
seen both in experience and raw numbers has shown the power boxes can
sustain higher levels of throughput and performance. Because to get an
x86 box to perform at those levels you would have to spend just as much,
buying one really powerful x86 box, or spreading it across multiple
boxes.
All that said, if we didn't have a good AIX guy here, I'd go RHEL on
multiple boxes, or on a really powerful x86 box. I can admin AIX, but
I'm
much more comfortable on Linux. So, as someone else said, it all
depends
on what you're good at.
See Ya'
Howard Coles Jr.
John 3:16!
-----Original Message-----
From: ADSM: Dist Stor Manager [mailto:ADSM-L AT VM.MARIST DOT EDU] On Behalf Of
Allen S. Rout
Sent: Thursday, October 06, 2011 3:46 PM
To: ADSM-L AT VM.MARIST DOT EDU
Subject: [ADSM-L] Check signals on Power vs. x86...
I'm looking around for an update on my expectations that power hardware
and AIX is more performant per memory/CPU/IO than x86 and RHEL.
I know this topic comes up from time to time; I don't think I've seen it
rehashed particularly recently.
I'm an advocate of AIX for this, but I wanted to check signals and
experiences, again.
- Allen S. Rout
DISCLAIMER:
This communication, along with any documents, files or attachments, is
intended only for the use of the addressee and may contain legally
privileged and confidential information. If you are not the intended
recipient, you are hereby notified that any dissemination, distribution
or
copying of any information contained in or attached to this
communication
is strictly prohibited. If you have received this message in error,
please
notify the sender immediately and destroy the original communication and
its attachments without reading, printing or saving in any manner.
Please consider the environment before printing this e-mail.
This message and any attachments (the "message") is intended solely for
the addressees and is confidential. If you receive this message in
error,
please delete it and immediately notify the sender. Any use not in
accord
with its purpose, any dissemination or disclosure, either whole or
partial,
is prohibited except formal approval. The internet can not guarantee the
integrity of this message. BNP PARIBAS (and its subsidiaries) shall
(will)
not therefore be liable for the message if modified. Please note that
certain
functions and services for BNP Paribas may be performed by BNP Paribas
RCC, Inc.
DISCLAIMER:
This communication, along with any documents, files or attachments, is intended
only for the use of the addressee and may contain legally privileged and
confidential information. If you are not the intended recipient, you are hereby
notified that any dissemination, distribution or copying of any information
contained in or attached to this communication is strictly prohibited. If you
have received this message in error, please notify the sender immediately and
destroy the original communication and its attachments without reading,
printing or saving in any manner.
Please consider the environment before printing this e-mail.
|
