The SSD Relapse: Understanding and Choosing the Best SSD
by Anand Lal Shimpi on August 30, 2009 12:00 AM EST- Posted in
- Storage
What's Wrong with Samsung?
The largest SSD maker in the world is Samsung. Samsung makes the drives offered by Apple in its entire MacBook/MacBook Pro lineup. Samsung makes the drives you get if you order a Lenovo X300. In fact, if you're buying any major OEM system with an SSD in it, Samsung makes that drive.
It's just too bad that those drives aren’t very good.
This is the 4KB random write performance of Samsung's latest SSD, based on the RBB controller:
4.4MB/s. That's 3x the speed of a VelociRaptor, but 1/3 the speed of a cheaper Indilinx drive.
Speedy, but not earth shattering. Now let's look at performance once every LBA has been written to. This is the worst case scenario performance we've been testing for the past year:
...and now we're down to mechanical hard drive speeds
Holycrapwtfbbq? Terrible.
Now to be fair to Samsung, this isn’t JMicron-terrible performance. It’s just not worth the money performance.
The Samsung RBB based SSDs are rebranded by at least two manufacturers: OCZ and Corsair.
The OCZ Summit and the Corsair P256 both use the Samsung RBB platform.
The Corsair and OCZ Samsung RBB drives.
The drive most OEMs are now shipping is an even older, lower performing Samsung SSD based on an older controller.
I talked to some of the vendors who ship Samsung RBB based SSDs and got some sales data. They simply can’t give these drives away. The Indilinx based drives outsell those based on the Samsung RBB controller by over 40:1. If end users are smart enough to choose Indilinx and Intel, why aren't companies like Apple and Lenovo?
Don't ever opt for the SSD upgrade from any of these OEMs if you've got the option of buying your own Indilinx or Intel drive and swapping it in there. If you don't know how, post in our forums; someone will help you out.
Samsung realized it had an issue with its used-state performance and was actually the first to introduce background garbage collection; official TRIM support will be coming later. Great right? Not exactly.
There’s currently no way for an end user to flash the firmware on any of these Samsung drives. To make matters worse, there’s no way for companies like OCZ or Corsair to upgrade the firmware on these drives either. If you want a new firmware on the drive, it has to go back to Samsung. I can’t even begin to point out how ridiculous this is.
If you’re lucky enough to get one of the Samsung drives with background garbage collection, then the performance drop I talked about above doesn’t really matter. How can you tell? Open up Device Manager, go to your SSD properties, then details, then select Hardware Ids from the dropdown. Your firmware version will be listed at the end of your hardware id string:
Version 1801Q doesn’t support BGC. Version 18C1Q (or later) does.
How can you ensure you get a model with the right firmware revision? Pick a religion and start praying, because that’s the best you can do.
Now the good news. When brand new, the Samsung drives actually boast competitive sequential write, sequential read and random write speeds.
These drives are also highly compatible and very well tested. For all of the major OEMs to use them they have to be. It’s their random write performance that’s most disappointing. TRIM support is coming later this year and it will help keep the drives performing fresh, but even then they are still slower than the Indilinx alternatives.
There’s no wiper tool and there’s currently no method to deploy end-user flashable firmware updates. Even with TRIM coming down the road, the Samsung drives just don’t make sense.
Facebook
Twitter
RSS
295 Comments
View All Comments
zodiacfml - Wednesday, September 2, 2009 - link
Very informative, answered more than anything in my mind. Hope to see this again in the future with these drive capacities around $100.mgrmgr - Wednesday, September 2, 2009 - link
Any idea if the (mid-Sept release?) OCZ Colossus's internal RAID setup will handle the problem of RAID controllers not being able to pass Windows 7's TRIM command to the SSD array. I'm intent on getting a new Photoshop machine with two SSDs in Raid-0 as soon as Win7 releases, but the word here and elsewhere so far is that RAID will block the TRIM function.kunedog - Wednesday, September 2, 2009 - link
All the Gen2 X-25M 80GB drives are apparently gone from Newegg . . . so they've marked up the Gen1 drives to $360 (from $230):http://www.newegg.com/Product/Product.aspx?Item=N8...">http://www.newegg.com/Product/Product.aspx?Item=N8...
Unbelievable.
gfody - Wednesday, September 2, 2009 - link
What happened to the gen2 160gb on Newegg? For a month the ETA was 9/2 (today) and now it's as if they never had it in the first place. The product page has been removed.It's like Newegg are holding the gen2 drives hostage until we buy out their remaining stock of gen1 drives.
iwodo - Tuesday, September 1, 2009 - link
I think it acts as a good summary. However someone wrote last time about Intel drive handling Random Read / Write extremely poorly during Sequential Read / Write.Has Aanand investigate yet?
I am hoping next Gen Intel SSD coming in Q2 10 will bring some substantial improvement.
statik213 - Tuesday, September 1, 2009 - link
Does the RAID controller propagate TRIM commands to the SSD? Or will having RAID negate TRIM?justaviking - Tuesday, September 1, 2009 - link
Another great article, Anand! Thanks, and keep them coming.If this has already been discussed, I apologize. I'm still exhausted from reading the wonderful article, and have not read all 17 pages of comments.
On PAGE 3, it talks about the trade-off of larger vs. smaller pages.
I wonder if it would be feasible to make a hybrid drive, with a portion of the drive using small pages for faster performance when writing small files, and the majority of it being larger pages to keep the management of the drive reasonable.
Any file could be written anywhere, but the controller would bias small writes to the small pages, and large writes to large files.
Externally it would appear as a single drive, of course, but deep down in the internals, it would essentially be two drives. Each of the two portions would be tuned for maximum performance in different areas, but able to serve as backup or overflow if the other portion became full or ever got written to too many times.
Interesting concept? Or a hair brained idea buy an ignorant amateur?
CList - Tuesday, September 1, 2009 - link
Great article, wonderful to see insightful, in depth analysis.I'd be curious to hear anyone's thoughts on the implications are of running virtual hard disk files on SSD's. I do a lot of work these days on virtual machines, and I'd love to get them feeling more snappy - especially on my laptop which is limited to 4GB of ram.
For example;
What would the constant updates of those vmdk (or "vhd") files do to the disk's lifespan?
If the OS hosting the VM is windows 7, but the virtual machine is WinServer2003 will the TRIM command be used properly?
Cheers,
CList
pcfxer - Tuesday, September 1, 2009 - link
Great article!"It seems that building Pidgin is more CPU than IO bound.."
Obviously, Mr. Anand doesnt' understand how compilers work ;). Compilers will always be CPU and memory bound, reduce your memory in the computer to say 256MB (or lower) and you'll see what I mean. The levels of recursion necessary to follow the production (grammars that define the language) use up memory but would rarely use the drive unless the OS had terrible resource management. :0.
CMGuy - Wednesday, September 2, 2009 - link
While I can't comment on the specifics of software compilers I know that faster disk IO makes a big difference when your performing a full build (compilation and packaging) of software.IDEs these days spend a lot their time reading/writing small files (thats a lot of small, random, disk IO) and a good SSD can make a huge difference to this.