The Seagate 600 & 600 Pro SSD Review
by Anand Lal Shimpi on May 7, 2013 8:00 AM ESTIf you had asked me back in 2008 who I thought would be leading the SSD industry in 2013 I would’ve said Intel, Western Digital and Seagate. Intel because of its commanding early lead in the market, and WD/Seagate because as the leaders in hard drives they couldn’t afford to be absent from the long term transition to SSDs. The days of having to explain why SSDs are better than mechanical drives are thankfully well behind us, now it’s just a question of predicting the inevitable. I figured that the hard drive vendors would see the same future and quickly try to establish a foothold in the SSD market. It turns out I’m really bad at predicting things.
Like most converging markets (in this case, storage + NAND), the SSD industry hasn’t been dominated by players in the market that came before it. Instead, SSDs attracted newcomers to the client/enterprise storage business. Not unlike DRAM, owning a NAND foundry has its benefits when building a profitable SSD business. It’s no surprise that Intel, Micron and Samsung are some of the more frequently discussed SSD vendors - all of them own (either partially or fully) NAND foundries.
Whether or not ownership in a foundry will be a requirement for building a sustainable SSD business is still unclear, but until that question gets answered there’s room for everyone to play in the quickly growing SSD market. This year, Seagate re-enters the SSD market with a serious portfolio. Today it not only announces two 2.5” SATA drives, including its first client-focused SSD, but also a 2.5” SAS product and a PCIe SSD solution.
The products that we’re focusing on today are the two 2.5” SATA drives: Seagate’s 600 and 600 Pro.
Architecture
The 600 and 600 Pro are both based on Link A Media Device’s LM87800 controller. The LAMD controller is the same as the one used in Corsair’s Neutron and Neutron GTX. Previous Seagate SSDs actually used a two-chip solution, with Seagate’s custom silicon controlling the host interface while Link A Media provided a NAND interface chip. The LM87800 is apparently a single chip integration of the earlier Seagate designs. The controller uses the drive chassis for cooling, with a thermal pad acting as an interface layer.
The firmware on the 600/600 Pro is unique to Seagate. It’s unclear whether or not Seagate has access to firmware source, but the solution is definitely custom (as you’ll see from the performance/consistency results). The LM87800 doesn't use any data de-duplication/compression and allegedly uses a DSP-like architecture.
The controller is paired with two DDR2-800 devices, with roughly 1MB of DRAM per GB of NAND storage. The high ratio of DRAM to NAND is common in drives with flat indirection tablets as we’ve come to notice. It’s a more costly (and potentially more power hungry) design decision, but one that can have tangible benefits as far as performance consistency is concerned.
Seagate 600 NAND/DRAM Configuration | |||||||||||
# of NAND Packages | # of Die per Package | Total NAND on-board | DRAM | ||||||||
480GB | 8 | 8 | 512GB | 512MB | |||||||
240GB | 8 | 4 | 256GB | 256MB | |||||||
120GB | 8 | 2 | 128GB | 128MB |
The LM87800 controller is a bit dated by modern standards, especially if we look at what is possible with Crucial’s M500. There’s no hardware encryption support and obviously no eDrive certification. Despite launching in 2013, the 600/600 Pro feature a controller that is distinctly 2012. Admittedly, that seems to be the case with most SSD makers these days. Everyone seems to be waiting for the transition to SATA Express before launching truly new controller designs.
Seagate has deals in place to secure NAND supply from both Samsung and Toshiba, although all of the 600 series will show up with 19nm Toshiba 2-bit-per-cell MLC NAND. The LM87800 controller features 8 NAND channels, and can access even more NAND die in parallel through interleaving.
59 Comments
View All Comments
Kristian Vättö - Tuesday, May 7, 2013 - link
The units we have are all based on the older 24nm NAND. A while back I asked Corsair for review samples of the 128/256GB Neutrons (the original ones are 120/240) but they said they are not sampling them (yet). I can ask if they have changed their mind, although there shouldn't be much difference since 19nm Toshiba NAND has the same page/block/die size as 24nm.FunBunny2 - Tuesday, May 7, 2013 - link
Does "Toshiba" mean toggle-mode NAND, by definition? Or do they sell all types?Kristian Vättö - Wednesday, May 8, 2013 - link
Yes, Toshiba uses Toggle-Mode interface for their NAND. Here's the breakdown of NAND interfaces and manufacturers:Toggle-Mode: Toshiba/SanDisk (joint-venture) & Samsung
ONFI: Intel/Micron (aka IMFT, also a joint-venture) & Hynix
LtGoonRush - Tuesday, May 7, 2013 - link
HardOCP showed pretty significant performance increases, though that could also be due to the new firmware (which is not being back-ported as I understand).romrunning - Tuesday, May 7, 2013 - link
I really wish we had more tests of SSDs in RAID-5 arrays. This is really useful for SMBs who may not want/afford a SAN. I'm very curious to see if the 20% spare area affects SSDs just as much when they're RAIDed together as it does standalone. I also don't care of the SSDs are branded as being "enterprise" drives. It would be nice to see how a 5x256GB Samsung 840 Pro RAID-5 array would peform, or even a 5x400GB Seagate 600 Pro RAID-5 array.FunBunny2 - Tuesday, May 7, 2013 - link
No legitimate RDBMS vendor would allow its database on a RAID-5 machine. Never. Never. Never.romrunning - Wednesday, May 8, 2013 - link
I can't tell if you're just trolling or you're actually serious. Obviously, SMBs use RAID-5 arrays ALL the time, and they use "legitimate" database products like MS-SQL, etc. It doesn't have to be an IBM AIX server running DB2, or anything high-end.daniel_mayes - Wednesday, May 8, 2013 - link
What is FunBunny2 talking about? What Raid would you want to run them on 1,5,6,10, no ssd's?You aren't the only one that want's to see more tests with SSD's in a Raid 5. I would also like to see the destroyer run on ssd's with a higher provision and please add Intel DC S3700 to the destroyer benchmark next.
FunBunny2 - Wednesday, May 8, 2013 - link
"I always have found that based on those requirements RAID 5 requires more spindles to satisfy those requirements than RAID 10 - and this has been found even with a Read/Write of 9:1. "here: http://sqlblog.com/blogs/linchi_shea/archive/2007/...
(no, that's not me)
Fact is, SSD still writes slower than reads, so what kind of RAID one uses matters. Having a 3NF (or higher) schema is a more productive avenue for performance on SSD, anyways, irregardless. Getting rid of all that bloated [un|de]normalized byte pile will allow, in most cases, you to have a much smaller database, and thus not worry about bunches and bunches of discs.
romrunning - Friday, May 10, 2013 - link
That blog is from 2007, and SSDs weren't really in the picture at all. It has been demonstrated how SSDs can trump spinning disks in virtually all I/O-bound operations. The man in the blog even showed a test of RAID-5 beating RAID-10 on the same hardware, so his test was in direct contradiction to the one who later commented about spindles.That being said, I think you're trying to say that getting rid of unnecessary in your database will result in a smaller database & thus lower performance requirements. That might be true at one point, but when you've normalized your data already, then additional data will just make the database grow. After all, if you're writing something like electronic orders to your normalized database, it will grow based upon real data addition. That's why you need to make sure your storage array can handle the increased load.
RAID-5 has been the best for SMBs because it provide the fault-tolerance and the higher utilization of total storage capacity that they want. That's why I would like to see tests of SSDs in RAID-5 arrays - to get Anandtech to test these great SSD performers in something I could use in a database server. Something like their tests of their own website databases would be nice, or even smaller ones using a 10-20GB database.