tag:support.primatelabs.com,2011-01-31:/discussions/geekbench/396-centos-55-results-on-ec2Primate Labs: Discussion 2012-07-20T12:23:49Ztag:support.primatelabs.com,2011-01-31:Comment/74120822011-05-24T02:55:46Z2011-05-24T02:55:46ZCentOS 5.5 Results on EC2<div><p>Hi Jason,</p>
<p>Thanks for your message. I looked at your Geekbench results and
it looks like while EC2 is reporting that 2, 4, or 8 cores are
available, EC2 is only providing 2 cores to your instances. If you
examine the multi-threaded workloads (which are the workloads that
take advantage of multiple cores), you'll see that in the best case
they're only 2x faster than the single-threaded workloads. This
generally indicates that only two cores are available.</p>
<p>Let me know if you have any other questions and I'd be happy to
answer them!</p>
<p>Best,<br>
John</p></div>Johntag:support.primatelabs.com,2011-01-31:Comment/74120822011-05-24T04:42:51Z2011-05-24T04:42:51ZCentOS 5.5 Results on EC2<div><p>John,</p>
<p>Could it be a problem with how the OS is working with Geekbench,
because using a non-RHEL AMI such as Ubuntu, I'm able to get about
triple the score on the same m2.4xlarge instance size.</p>
<p>Jason</p></div>Jason Readtag:support.primatelabs.com,2011-01-31:Comment/74120822011-05-24T07:06:43Z2011-05-24T07:07:03ZCentOS 5.5 Results on EC2<div><p>Here are tests we ran about a year ago on the same instance
sizes, but with a slightly older CentOS AMI:</p>
<p>m2.xlarge (2 X5550 cores): 5877<br>
<a href=
"http://browse.geekbench.ca/geekbench2/view?id=241462">http://browse.geekbench.ca/geekbench2/view?id=241462</a></p>
<p>m2.2xlarge (4 X5550 cores): 5163<br>
<a href=
"http://browse.geekbench.ca/geekbench2/view?id=241409">http://browse.geekbench.ca/geekbench2/view?id=241409</a></p>
<p>m2.4xlarge (8 X5550 cores): 4049<br>
<a href=
"http://browse.geekbench.ca/geekbench2/view?id=241403">http://browse.geekbench.ca/geekbench2/view?id=241403</a></p>
<p>Our Unixbench parallel results do show a linear increase in CPU
performance with the different m2 instance sizes on the same
instances where Geekbench shows flat results, so it seems like the
CPU resources are available, but Geekbench is not incorporating
them into the results for some reason.</p></div>Jason Readtag:support.primatelabs.com,2011-01-31:Comment/74120822011-05-24T17:31:33Z2011-09-13T23:10:55ZCentOS 5.5 Results on EC2<div><p>Here are our Unixbench results running on the same instances
where we are seeing the flat Geekbench results:</p>
<p>m2.xlarge (2 X5550 cores): 929<br>
<a href=
"http://benchmarks.cloudharmony.com/unixbench/0311-ec2-use-ec2-us-east.linux.m2.xlarge.txt">
http://benchmarks.cloudharmony.com/unixbench/0311-ec2-use-ec2-us-ea...</a></p>
<p>m2.2xlarge (4 X5550 cores): 1559<br>
<a href=
"http://benchmarks.cloudharmony.com/unixbench/0311-ec2-use-ec2-us-east.linux.m2.2xlarge.txt">
http://benchmarks.cloudharmony.com/unixbench/0311-ec2-use-ec2-us-ea...</a></p>
<p>m2.4xlarge (8 X5550 cores): 2396<br>
<a href=
"http://benchmarks.cloudharmony.com/unixbench/0211-sc-ec2-us-east.linux.m2.4xlarge.txt">
http://benchmarks.cloudharmony.com/unixbench/0211-sc-ec2-us-east.li...</a></p>
<p>So, Unixbench is clearly getting access to and utilizing the
additional cores on these instances. Any idea why this would not be
the case for Geekbench?</p></div>Jason Readtag:support.primatelabs.com,2011-01-31:Comment/74120822011-06-04T00:42:53Z2011-06-04T00:42:53ZCentOS 5.5 Results on EC2<div><p>Hi Jason,</p>
<p>Interesting! Thanks for the links. We'll dig into it and see if
there's a problem with Geekbench that needs to be addressed.</p>
<p>Thanks,<br>
John</p></div>John