Dual CPU Database Server Comparison
by Johan De Gelas on December 2, 2004 12:11 AM EST- Posted in
- IT Computing
Benchmarks IBM DB2 8.1.3: Intel versus AMD
The first question that most people will ask is, of course, how the best AMD Opteron compares to the newest Intel Xeon "Nocona" CPU. Below is a quick table to refresh your memory and to enable you to compare price/performance:
| Intel Xeon CPUs | Core | L2 cache | L3 cache | x86-64 bit | In Test | Price |
| 3.60 GHz w/ 1M cache 800 MHz FSB (90nm) | Nocona = "Prescott server" | 1 MB | No | Yes | Yes | $851 |
| 3.40 GHz w/ 1M cache 800 MHz FSB (90nm) | Nocona = "Prescott server" | 1 MB | No | Yes | No | $690 |
| 3.20D GHz w/ 1M cache 800 MHz FSB (90nm) | Nocona = "Prescott server" | 1 MB | No | Yes | No | $455 |
| 3 GHz w/ 1M cache 800 MHz FSB (90nm) | Nocona = "Prescott server" | 1 MB | No | Yes | No | $316 |
| 3.20C GHz w/ 2M cache 533 MHz FSB (.13) | Galatin = "P4 EE Server" | 0,5 MB | 2 MB | No | Yes | $1,043 |
| 3.20 GHz w/ 1M cache 533 MHz FSB (.13) | Galatin = "P4 EE Server" | 0,5 MB | 1 MB | No | No | $690 |
| 3.06A GHz w/ 1M cache 533 MHz FSB (.13) | Galatin = "P4 EE Server" | 0,5 MB | 1 MB | No | Yes | $455 |
| 3.06 GHz w/ 512k cache 533 MHz FSB (.13) | Prestonia = "Northwood Server" | 0,5 MB | No | No | Yes | $316 |
| AMD Opteron CPU's | Core | L2 cache | L3 cache | x86-64 bit | In Test | Price |
| Model 250 (2.4 GHz) | Sledgehammer | 1 MB | No | Yes | Yes | $851 |
| Model 248 (2.2 GHz) | Sledgehammer | 1 MB | No | Yes | Yes | $690 |
| Model 246 (2.0 GHz) | Sledgehammer | 1 MB | No | Yes | No | $455 |
| Model 244 (1.8 GHz) | Sledgehammer | 1 MB | No | Yes | No | $316 |
We were also very curious about the Xeon Nocona, as the it brings higher clock speeds, a bigger L2-cache, no L3-cache and a pipeline 11 stages longer than the previous Xeon "Prestonia" and Xeon "Gallatin", which maxed out at 3.2 GHz. The first two features mentioned should boost the performance quite well, while the two last are disadvantages.
We should emphasize that, as we tested with SUSE SLES 8 (kernel 2.4.21), the Xeon Nocona was disadvantaged, since we could not test it in 64-bit mode. We assure you that we will update this report with 2.6 kernel. For now, we decided to give you a full report on SLES 8 and kernel 2.4. (All numbers are expressed in queries per second.)
| Concurrency | Xeon 3.6 GHz | Dual Xeon 3.2 L3 (2MB) | Dual Xeon 3.2 | Dual Xeon 3.06 L3 (1MB) | Dual Xeon 3.06 | Opteron 250 DDR400 32 bit | Dual Opteron 250 DDR 400 64 bit | Dual Opteron 248 DDR 400 64 bit |
| 1 | 55 | 46 | 44 | 43 | 42 | 57 | 61 | 57 |
| 2 | 87 | 74 | 61 | 72 | 61 | 105 | 118 | 107 |
| 5 | 128 | 104 | 100 | 98 | 98 | 123 | 137 | 129 |
| 10 | 136 | 112 | 107 | 105 | 102 | 129 | 145 | 132 |
| 20 | 136 | 113 | 106 | 106 | 104 | 131 | 147 | 132 |
| 35 | 138 | 113 | 106 | 104 | 99 | 133 | 150 | 129 |
| 50 | 138 | 110 | 106 | 102 | 100 | 130 | 145 | 128 |
All concurrency tests below 5 are not reliable enough to make any firm conclusion, especially for the Xeon. The margin of error is somewhat higher, but that is not all.
As the Dual Xeon with Hyperthreading spawns 4 logical CPUs, with a concurrency of 2, it is possible that only one physical CPU is doing all the work. Looking at the numbers and the linux tool top, we feel pretty sure that this is exactly what happens most of the time. Compare Row "5" with "2", and "2" with "1" to see what I mean. Note that the results of rows 10 to 50 do not vary a lot; so, we look at these numbers for our conclusions. In the table below, you can see an overview of how the different CPUs compare in percentages.
| 3.6 vs 3.2 | 2 MB L3-cache vs none | 1 MB L3-cache vs none | Xeon 3.2 vs 3.06 | Xeon 3.2 vs 3.06 (both with L3) | Xeon 3.6 vs Opteron 250 | Opteron 64 bit vs 32 bit |
| 20% | 3% | 1% | 7% | 7% | -4% | 6% |
| 17% | 22% | 18% | 3% | 3% | -17% | 12% |
| 24% | 4% | 1% | 5% | 5% | 5% | 12% |
| 21% | 5% | 3% | 6% | 6% | 6% | 13% |
| 21% | 6% | 2% | 6% | 6% | 3% | 12% |
| 22% | 7% | 5% | 8% | 8% | 3% | 12% |
| 26% | 4% | 2% | 8% | 8% | 7% | 12% |
If we had published a similar report back in August, the Opteron would enjoyed a landslide victory. Luckily for Intel, Nocona is very competitive and is about 5% faster than the Opteron 250.
The gigantic - for x86 - L3-cache can not help the Xeon much. We measured only a 2% to 5% performance boost from the 1 MB L2-cache (at 3.06 GHz), and a 4% to 7% performance boost from the 2 MB L3-cache (at 3.2 GHz). The L3-cache seems to boost performance as much as 5% to 6% clock speed increase - nothing to write home about. So a Xeon "Galatin" 3.2 GHz 2 MB L3-cache performs more or less like a Xeon "Galatin" 3.4 GHz, if such a beast should exist.
A comparison between the 3.2 GHz and 3.06 GHz shows that CPU clockscaling - given equal cache sizes - is almost perfect, a testimony to how CPU intensive this benchmark is. Clearly, the generalisation, "databases are all about I/O" is not accurate for a number of database applications. Read-heavy databases seem to be "all about the CPU".
Using a 64 bit database (DB2 8.1.3) on a 64 bit operating system delivers about 12% to 13% better performance. Since we didn't use more than 2 GB, the most likely explanation is the fact that the software can make use of 16 registers instead of 8. We also tested with a twice as large database and 4 GB of RAM, and the results were very similar.
The performance of the Nocona Xeon compared to the older Xeons is also remarkable. The database doesn't mind the longer pipeline and absence of the L3-cache. On the contrary, it performs better than its clock speed indicates, leaving the older 3.2 GHz Xeon (with 2 MB L3 cache!) behind with 21% to 22%, while the Nocona has only a 13% clock speed advantage over the latter. To be honest, we expected Nocona, with its huge branch misprediction penalty, a result of its extremely long pipeline, to scale much worse.
Facebook
Twitter
RSS
46 Comments
View All Comments
JohanAnandtech - Thursday, December 2, 2004 - link
About SLES9 and NUMA: NUMA is also supported by Linux kernel 2.4.21 and it boosts performance only a tiny bit. The reason are the very speedy HT links which keep latency at a minimum.It is still possible that kernel 2.6 NUMA support is far better of course, but I doubt it makes a difference for quad or dual systems as there is only hop in quad systems. With two hops (8 CPUs) from CPU 1 to 8 for example, this will become important.
AtaStrumf - Thursday, December 2, 2004 - link
A TYPO:So for now, the Opteron has an advantage still, but it ***can*** /can't/ knock out the Xeon, as it could have a few months ago, before the Xeon Nocona arrived.
HardwareD00d - Thursday, December 2, 2004 - link
There have been enough benchmarks on the web for a long time which show that Opteron generally wipes Xeon's a$$ hands down, and scales far better in multi processor configurations. The latest Xeon is nothing special compared to prior versions and will no doubt preform better mostly due to its increased clock speed. Xeon will never be better than Opteron no matter how much cache and tweaks Intel adds.Maybe Intel's next server architecture will be something to woo, but that's a ways off.
jshaped - Thursday, December 2, 2004 - link
as a long-time reader of aceshardware, i'll be the first to welcome Johan here, great first article. keep them coming!!!!HardwareD00d - Thursday, December 2, 2004 - link
I don't think there are enough variations of the way requests are handled to make a realistic conclusion for either chip. I'm sure you could create a situation where Intel bests AMD in My Sql, and vice versa. This article really needs more benchmarks and more in-depth analysis. Still, it provides enough information to conclude that both Xeon and Opteron have their strengths and weaknesses.mczak - Thursday, December 2, 2004 - link
Nice read. I really think though you should have used SLES 9. Not only does it use kernel 2.6, but it's also NUMA-aware (and DB2 should specifically support it, though it might not have been released yet). SLES 9 also ought to be faster especially on x86_64 due to newer compiler (not that it would matter much with precompiled databases, but every bit counts...). Though for 2-cpu boxes, NUMA might not be that important - but it's safe to predict a landslide victory for a 4-cpu opteron with NUMA support vs. a 4-cpu xeon box. Xeons simply don't scale to 4 cpus, intel might sell them but they are useless (especially since the Xeon MPs are still limited to 400 (or was that 533?) Mhz FSB.A pity though the quad opterons don't support ddr-400. I guess manufacturers decided it's more important to have a boatload of ram slots than fewer slots (with shorter traces) with higher speeds...
And btw, where are the 90nm Opterons? AMD's latest roadmap shows them as available in 2004, which doesn't leave too much time...
bthomas - Thursday, December 2, 2004 - link
Bogus conclusions about IBM tests IMO. From the
article:
> If we had published a similar report back in
> August, the Opteron would enjoyed a landslide
> victory. Luckily for Intel, Nocona is very
> competitive and is about 5% faster than the Opteron 250.
and later in the "conclusion":
> Nevertheless, AMD cannot sit on its laurels.
> Intel made a very good comeback with Nocona, as > this 3.6 GHz CPU is just a tiny bit faster in >
DB2.
It has not.
You fail to specify that this is comparing the _32 bit_ mode for the Opteron. IF you compare the Nocoma performance to the Opteron 64 bit capability...it sweeps the the Nocona in all tests.
The true conclusion is that based on the results in the article, for neither of the databases tested do *any* of the Intel processors compete with the Opteron.
fitten - Thursday, December 2, 2004 - link
Randomized benchmarks are hard to verify as well. You could get a "good" distribution that really takes advantage of cache locality while another randomization may be very cache unfriendly. I agree with #5 to a degree. A database that fits entirely inside of RAM isn't very interesting, ultimately.Still, I am happy that AnandTech is going down these paths of benchmarking instead of just being about Doom3, HL2, and FarCry like most other sites. I eagerly await further database benchmark articles.
PrinceXizor - Thursday, December 2, 2004 - link
#5 - Since when do top tier e-commerce cites compare to mid-level company database users as the beginning of the article mentioned?My company is an engineering firm that does custom electronics. Our database server handles all the transactions for our Inventory/MRP system which is mostly reads. These benchmarks are very appropriate. I wish I could have convinced my boss to go Opteron. Its funny, they had Athlon MP's before and then switched to Xeons when Opteron was out. Go figure.
Anyway, great article. I'm not IT guy by any stretch, but I enjoyed the article.
P-X
Jason Clark - Thursday, December 2, 2004 - link
#6, done ages ago..http://www.anandtech.com/IT/showdoc.aspx?i=2205
http://www.anandtech.com/IT/showdoc.aspx?i=1982