Intel's newest Quad Xeon MP versus HP's DL585 Quad Opteron
by Johan De Gelas on November 10, 2006 12:00 PM EST- Posted in
- IT Computing
MySQL Configuration
As our loyal readers know from our previous MySQL adventures, the MySQL database is a highly tweakable but somewhat badly scaling database. Most workloads scale well from one to two cores, but from two to four cores scaling is very mediocre, and in the "SELECT intensive" workload that we benchmark even negative. This has surprised quite a few people, but it is an issue that the InnoDB team is well aware of, and the issue will be resolved in one of the next releases of InnoDB. Until then, we compiled version 5.0.26 with Peter Zaitsev's Mutex patch. This Patch gives much better scaling and performance. Scaling is no longer negative, and we saw a 20% to 40% increase going from two to four cores. However, our workload still doesn't scale beyond four cores, so we tested all CPUs with two CPUs and four cores. That way we have at least an impression on how the different server CPUs compare.
All testing was thus done with InnoDB as our storage engine in MySQL 5.0.26. We optimized for a server with 4GB 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 ~1GB database. The workload consists of more than 90% selects, mostly a "read intensive" workload.
MySQL results
All numbers are expressed in queries per second (Y-axis), and the X-axis shows the number of concurrent accesses.
On average is the Xeon DP 5160 is about 22% faster than the Opteron. That means that the Opteron is clock for clock as fast as the Xeon 5160, which is not bad news for AMD at all, although Woodcrest currently has the raw clock speed advantage. Considering the HP DL585 can only use DDR-333 with the Opteron 880, the picture might even get better with the DL885 which can use DDR-400.
There is little doubt that MySQL is not the favorite application of the Xeon MP: the Opteron 880 beats Xeon MP by 20% to 30%. We have seen this before as the Opteron has always outrun "NetBurst" based CPUs in MySQL. The good news for Intel is that the new Core architecture is no less than 52% faster in MySQL when we compare the 3 GHz Xeon DP with the 3.2 GHz Xeon MP.
We also noted something strange: the Xeon MP performs better with hardware prefetch disabled. Below you can see our findings. All numbers are expressed in queries per second served by the server (Y-axis); and the X-axis shows the number of concurrent accesses.
Hardware prefetch lowers performance by about 1% to 4%, while Hyper-Threading allows the Xeon MP to make better use of its potential and increases performance by 7% to 9% at the higher concurrencies.
As our loyal readers know from our previous MySQL adventures, the MySQL database is a highly tweakable but somewhat badly scaling database. Most workloads scale well from one to two cores, but from two to four cores scaling is very mediocre, and in the "SELECT intensive" workload that we benchmark even negative. This has surprised quite a few people, but it is an issue that the InnoDB team is well aware of, and the issue will be resolved in one of the next releases of InnoDB. Until then, we compiled version 5.0.26 with Peter Zaitsev's Mutex patch. This Patch gives much better scaling and performance. Scaling is no longer negative, and we saw a 20% to 40% increase going from two to four cores. However, our workload still doesn't scale beyond four cores, so we tested all CPUs with two CPUs and four cores. That way we have at least an impression on how the different server CPUs compare.
All testing was thus done with InnoDB as our storage engine in MySQL 5.0.26. We optimized for a server with 4GB of RAM. Here is our MySQL configuration:
| MySQL Configuration | |
| default-storage-engine | InnoDB |
| skip-external-locking | |
| skip-locking | |
| key_buffer | 256M |
| . | |
| table_cache | 64 |
| max_allowed_packet | 1M |
| thread_stack | 128K |
| . | |
| sort_buffer_size | 2M |
| read_buffer_size | 2M |
| innodb_buffer_pool_size | 1G |
| . | |
| thread_concurrency | 16 |
| innodb_thread_concurrency | 16 |
| innodb_additional_mem_pool_size | 8MB |
| read_rnd_buffer_size | 8MB |
| thread_cache | 64 |
| max_heap_table | 256MB |
| tmp_table | 128MB |
| . | |
| innodb_log_file_size | 250MB |
| innodb_table_locks | 0 |
| innodb_flush_log_at_trx_commit | 0 |
| max_user_connections | 2000 |
| max_connections | 2000 |
The "query cache" was off, as we wanted to test worst case performance. Our test database is still the same ~1GB database. The workload consists of more than 90% selects, mostly a "read intensive" workload.
MySQL results
All numbers are expressed in queries per second (Y-axis), and the X-axis shows the number of concurrent accesses.
On average is the Xeon DP 5160 is about 22% faster than the Opteron. That means that the Opteron is clock for clock as fast as the Xeon 5160, which is not bad news for AMD at all, although Woodcrest currently has the raw clock speed advantage. Considering the HP DL585 can only use DDR-333 with the Opteron 880, the picture might even get better with the DL885 which can use DDR-400.
There is little doubt that MySQL is not the favorite application of the Xeon MP: the Opteron 880 beats Xeon MP by 20% to 30%. We have seen this before as the Opteron has always outrun "NetBurst" based CPUs in MySQL. The good news for Intel is that the new Core architecture is no less than 52% faster in MySQL when we compare the 3 GHz Xeon DP with the 3.2 GHz Xeon MP.
We also noted something strange: the Xeon MP performs better with hardware prefetch disabled. Below you can see our findings. All numbers are expressed in queries per second served by the server (Y-axis); and the X-axis shows the number of concurrent accesses.
Hardware prefetch lowers performance by about 1% to 4%, while Hyper-Threading allows the Xeon MP to make better use of its potential and increases performance by 7% to 9% at the higher concurrencies.
Facebook
Twitter
RSS
88 Comments
View All Comments
Niv KA - Saturday, November 11, 2006 - link
I belive Clovertown is going to be announced somethime in the next week or two. On thursday I went to the "Microsoft: Ready for a New Day" here in Belgium (where Bill gates made an appearance of about half an hour, although not related!) and at the Intel booth they were showing off 4 servers which where running an "unannounced platform"! One of the technical guys at the booth let me in on a little "secret"! The Supermicro Systems were running "two sockets each box, each socket 4 cores! Eight cores each box! And the best part is its woodcrest arch!". I asked him if it was clovertown and he sayed that he "is just a technical assistant, not alowed to say anything" but he made the answer clear on his face! Clovertown is ready to go, and its FAST! They were running benchmarks all the time! I will post pictures on the fourms if I have enough time, but I have a HUGE project I need to hand in by tuesday so I might forget!
---Niv K Aharonovich
PS: About the "outdated" system comments above, I am fully on Anandtechs side, it is impossible for an online newspaper company to make enough money to BUY everything, esp. in the $15,000 area! The only way is to ask for it from the vendors, and the vendors decide what to provide! Good job anandtech and continue the good work!!!!!!!
Dennis Travis - Saturday, November 11, 2006 - link
Great job as usuall. Keep up the excellent work.AnandThenMan - Friday, November 10, 2006 - link
Another bullshit "comparison" nice job guys. You are comparing an AMD system that has been out for over 2 years. Useless review as usual. Why are you not comparing new with new? Why don't you use a Xeon box that was out 2 years ago?Anandtech's reviews have become more and more worthless.
JohanAnandtech - Saturday, November 11, 2006 - link
1. AMD has confirmed that they feel the HP DL585 with 4x 880 is a worthy competitor for our Tulsa machine.2. This server is 5 months old, not 2 years. As I made clear in the article, this is the 2006 revision.
As we invest a lot of time of effort to convince OEMs and others to send us extremely expensive hardware for review, spend weeks tweaking benchmarks and OS to give you benchmarks, we hope we may expect some useful feedback from our readers.
Just writing "useless" with little or no explanation why you feel it is worthless is not helping anyone.
AnandThenMan - Sunday, November 12, 2006 - link
I was going to post an explanation as to why the "review" is very poorly done. But Scientia over at AMDz did a far better explanation then I could come up with.http://www.amdzone.com/index.php?name=PNphpBB2&...">http://www.amdzone.com/index.php?name=PNphpBB2&...
Either the review is intentionally authored to show Intel in as best light as possible, or the author is incompetent and should not be doing reviews at all. I stand by what I originally posted, the review is bullshit.
primer - Saturday, November 11, 2006 - link
Agreed.goldfish2 - Friday, November 10, 2006 - link
Can I just quickly mention how nice it is to read an article where the author has managed to present all the relevant informatiom in as concise a manner as is possible, good job.JohanAnandtech - Saturday, November 11, 2006 - link
Thanks!Server reviews are extremely time consuming so most publications are not interested in it, so I am glad AT allows me to do this kind of reviews.
AllYourBaseAreBelong2Us - Friday, November 10, 2006 - link
Can you guys get a new DL585 G2 and do benchmarks with this new model instead?Viditor - Friday, November 10, 2006 - link
I thought this too...the G2 has 7 PCIe slots (3 x8, 4 x4), is $800 less expensive, and offers newer SCSI controllers.