Page 1:Seagate's 600 SSD: LAMD And Toshiba, Together Again
Page 2:Test Setup And Benchmarks
Page 3:Results: 128 KB Sequential Performance
Page 4:Results: 4 KB Random Performance
Page 5:Results: Tom's Storage Bench v1.0
Page 6:Results: PCMark 7 And PCMark Vantage
Page 7:Results: Power Consumption
Page 8:Seagate 600: Mediocre Power Numbers, But Solid All-Around
Results: 4 KB Random Performance
Once again, we turn to Iometer as our synthetic metric of choice for testing 4 KB random performance. Technically, "random" translates to a consecutive access that occurs more than one sector away. On a mechanical hard disk, this can lead to significant latencies that hammer performance. Spinning media simply handles sequential accesses much better than random ones, since the heads don't have to be physically repositioned. With SSDs, the random/sequential access distinction is much less relevant. Data can be put wherever the controller wants it, so the idea that the operating system sees one piece of information next to another is mostly just an illusion.
Seagate rates the 240 GB 600 SSD's peak 4 KB read performance at 80,000 IOPS, while writes max out at 70,000 IOPS.
4 KB Random Read
Seagate is fairly conservative with the 600's 4 KB random read potential. Chalk it up to testing methodology or the company's own platforms, but we're getting over 92,000 IOPS at a queue depth of 32 from this 240 GB SSD. That's just short of the supercharged Plextor and Vector drives, both of which fall shy of 100,000 4 KB read I/Os every second. Corsair's Neutron GTX, with its LAMD/Toshiba combination, fares as well as the 600, proving that, at least in this test, they're quite similar.
The 830, SSD 335, and SSD 510 bring up the back of the pack at 75,000, 47,000, and 20,000 IOPS, respectively. Really, that last number is extraordinary. Twenty-thousand IOPS isn't a lot, just a fifth of what the leaders can do. But look at queue depths one through four. The massive performance differences at higher command counts just aren't as pronounced. In fact, all the drives are limited near the 10,000 IOPS level at a queue depth of one. That comes down to the performance of the underlying flash, and not much else matters. How about writes? Well, writes are a different story...
4 KB Random Write
Seagate's 600 isn't quite as fast as the competition when we hit it with fewer outstanding commends (as is the Neutron GTX; the pattern continues unabated). The Vector's speed is unimpeachable to be sure, and it can generate more I/O at lower queue depths, period. Still, the 600 performs admirably, yielding peak numbers just north of 85,000 write IOPS.
Once again, the two Intel-branded drives and Samsung's 830 languish at the bottom. The SSD 510 struggles along, presenting us with a fraction of the performance more elite SSDs manage.
If the sole reason to own a SSD was to benchmark it, this chart would make it pretty clear which drives to avoid. You would keep away from the SSD 510 at all costs. But in reality, recommendations aren't so cut-and-dried. When it comes to actually using these drives, you may only detect subtle differences between them most of the time. And that's why we don't rely on synthetic workload generators for evaluating storage.
- Seagate's 600 SSD: LAMD And Toshiba, Together Again
- Test Setup And Benchmarks
- Results: 128 KB Sequential Performance
- Results: 4 KB Random Performance
- Results: Tom's Storage Bench v1.0
- Results: PCMark 7 And PCMark Vantage
- Results: Power Consumption
- Seagate 600: Mediocre Power Numbers, But Solid All-Around