Intel Woodcrest, AMD's Opteron and Sun's UltraSparc T1: Server CPU Shoot-out
by Johan De Gelas on June 7, 2006 12:00 PM EST- Posted in
- IT Computing
MySQL Configuration
We spent weeks on tweaking our MySQL database to the maximum. The results were encouraging: performance was up to 3 times higher on our Opteron machines than out of the box. On the Sun machine, the results were even more impressive, especially when we started using MySQL 5.0. MySQL 5 runs horribly slow on the T1 out of the box, but we got up to 5 times more performance out of our T2000 server after getting some excellent tweaking tips from Peter Zaitsev (MySQL) and Luojia Chen (Sun).
All testing was done with InnoDB as our storage engine in MySQL 5.0.21. We optimized for a server with 4 GB of RAM. Here is our MySQL configuration:
The "query cache" was off, as we wanted to test worst case performance. Our test database is still the same as in previous articles, about 1GB in size. The workload consists of more than 90% selects, thus this is mostly a "read intensive" workload.
MySQL Results
All numbers are expressed in queries per second.
Notice that the T1 needs about 20-30 MySQL threads to run at full speed; this is clearly a result of it's 8 core "4 thread Gatling gun core" architecture. It must also be noted that the out-of-the box MySQL performance is simply horrible, about 4-5 times lower than the well optimized numbers you see above. There is no escaping the face that you must take the time to read Sun's tunings tips well.
Once you do, the 1 GHz T1 is capable of performing like an Opteron 2.2 GHz, which is pretty amazing. Kudos to Luojia Chen and Peter Zaitsev for a job well done. While the old Xeon which consumed 4 times more power than the T1 to give the same performance looked pretty silly, the new Xeon 5160 easily outperforms the T1. The performance/Watt title will probably go to the low power Woodcrest versions, which we haven't tested yet.
Let us see what a single dual-core Woodcrest can do versus a dual-core Opteron and quad-core Sun T1.
As we were testing with only two cores, we brought back the Dual Xeon Irwindale for the test. We did a few extra tests on this platform as we also had the older Nocona platform in the labs. The additional 1MB cache of Irwindale improved our benchmark numbers by 7-8%, which is quite impressive. Our time investment in tweaking our MySQL database also made the caches and memory system more important. Finally, Hyper-Threading still doesn't pay off in MySQL: we noticed a small slowdown of about 7%.
We spent weeks on tweaking our MySQL database to the maximum. The results were encouraging: performance was up to 3 times higher on our Opteron machines than out of the box. On the Sun machine, the results were even more impressive, especially when we started using MySQL 5.0. MySQL 5 runs horribly slow on the T1 out of the box, but we got up to 5 times more performance out of our T2000 server after getting some excellent tweaking tips from Peter Zaitsev (MySQL) and Luojia Chen (Sun).
All testing was done with InnoDB as our storage engine in MySQL 5.0.21. We optimized for a server with 4 GB of RAM. Here is our MySQL configuration:
[mysqld]
port3306
socket= /tmp/mysql.sock
skip-locking
key_buffer = 1G
max_allowed_packet = 1M
table_cache = 1024
sort_buffer_size = 2M
read_buffer_size = 2M
read_rnd_buffer_size = 8M
thread_cache = 125
max_user_connections = 450
max_connections = 450
thread_concurrency = 16
The "query cache" was off, as we wanted to test worst case performance. Our test database is still the same as in previous articles, about 1GB in size. The workload consists of more than 90% selects, thus this is mostly a "read intensive" workload.
MySQL Results
All numbers are expressed in queries per second.
Notice that the T1 needs about 20-30 MySQL threads to run at full speed; this is clearly a result of it's 8 core "4 thread Gatling gun core" architecture. It must also be noted that the out-of-the box MySQL performance is simply horrible, about 4-5 times lower than the well optimized numbers you see above. There is no escaping the face that you must take the time to read Sun's tunings tips well.
Once you do, the 1 GHz T1 is capable of performing like an Opteron 2.2 GHz, which is pretty amazing. Kudos to Luojia Chen and Peter Zaitsev for a job well done. While the old Xeon which consumed 4 times more power than the T1 to give the same performance looked pretty silly, the new Xeon 5160 easily outperforms the T1. The performance/Watt title will probably go to the low power Woodcrest versions, which we haven't tested yet.
Let us see what a single dual-core Woodcrest can do versus a dual-core Opteron and quad-core Sun T1.
As we were testing with only two cores, we brought back the Dual Xeon Irwindale for the test. We did a few extra tests on this platform as we also had the older Nocona platform in the labs. The additional 1MB cache of Irwindale improved our benchmark numbers by 7-8%, which is quite impressive. Our time investment in tweaking our MySQL database also made the caches and memory system more important. Finally, Hyper-Threading still doesn't pay off in MySQL: we noticed a small slowdown of about 7%.
Facebook
Twitter
RSS
91 Comments
View All Comments
zsdersw - Thursday, June 8, 2006 - link
I'm not saying the board is particularly stellar.. I'm saying that it's referred to by MSI as a "server" product.ashyanbhog - Thursday, June 8, 2006 - link
Irespective of what MSI says,fact is there were better mainstream boards for Anandtech to choose from if a honest, independent review was their intention
zsdersw - Thursday, June 8, 2006 - link
I.E., your comment belongs under someone else's.. not mine.zsdersw - Thursday, June 8, 2006 - link
And that's completely irrelevant to what I was saying.ashyanbhog - Thursday, June 8, 2006 - link
all I was saying is, its nice to see Intel finally making a comebackbut Anandtech seems have conducted a skewed benchmark that favours Intel, that unfairly increases the performance gap between Opteron and Woodcrest
In the final summary of the review he says
"In one word: Woodcrest rocks!"
There are quite a few holes in the review, the motherboard is just on of them,
I quoted MySQL number errors in my posts above,
just search for "ashyanbhog" in the page and read my earlier comments if you are interested.
AnandThenMan - Thursday, June 8, 2006 - link
What you're saying in general is irrelevant. Intel calls their integrated graphics "high performance" but that doesn't make it so.
MSI calling that a server board is just marketing, it does not represent what a true, high performance server class mobo is all about. Not that it's a bad piece of hardware, it is good for the price to be sure. But it is NOT a server class product.
zsdersw - Thursday, June 8, 2006 - link
At a certain price point, it could certainly be a nice entry-level server board.Performance alone isn't what makes a server-class motherboard a server-class motherboard.
ashyanbhog - Thursday, June 8, 2006 - link
One of the motherboards used in this review is a cheap piece that trades performance to keep price low.
Why was that motherboard selected over mainstream server/workstation boards that are proven to offer slightly better performance? Why pick a 250$ MSI board for opteron over $500 boards from Tyan, Iwill, Supermicro or others. The Intel Xeon "Inderwale" gets a $500 board, so price could not have been the issue.
So what's the point in using a Single Channel board for this benchmark, when price was not a limitation?
Single memory channel boards like the one from MSI, are known to offer lower performance than dual / dedicated memory channel boards when used in 2P Opteron configurations. Dual Channel boards are the mainstream boards for 2P Opteron systems. There are plently Server boards available in Dual / dedicated memory lane configuration. There are enough reviews on the net to show the performance diff b/w single memory channel boards and dual memory channel boards
The issue is not about the MSI or its class, the issue is why did Anandtech pick a Single memeory channel board instead of a more mainstream dual memory channel board.
Hope that clears up "zsdersw"'s query
zsdersw - Thursday, June 8, 2006 - link
I'm not making excuses for the choices that were made regarding this comparison test. I'm talking about what constitutes a "server-class" motherboard.ashyanbhog - Thursday, June 8, 2006 - link
Game PC review link for the above commenthttp://www.gamepc.com/labs/view_content.asp?id=tig...">http://www.gamepc.com/labs/view_content.asp?id=tig...