The SSD Relapse: Understanding and Choosing the Best SSD
by Anand Lal Shimpi on August 30, 2009 12:00 AM EST- Posted in
- Storage
Random Read/Write Speed
This test writes 4KB in a completely random pattern over an 8GB space of the drive to simulate the sort of random writes that you'd see on an OS drive (even this is more stressful than a normal desktop user would see). I perform three concurrent IOs and run the test for 3 minutes. The results reported are in average MB/s over the entire time:
As we established in previous articles, the disk operations that feel the slowest are the random small file reads and writes. Both of which are easily handled by an SSD. A good friend of mine and former AnandTech Editor, Matthew Witheiler, asked me if he'd notice the performance improvement. I showed him the chart above.
He asked again if he'd notice. I said, emphatically, yes.
Now this is super interesting. Intel's X25-M G1 drops from 40.8MB/s when new down to 26.3MB/s in a well used state. Unfortunately for the G1, it will never get TRIM and will spend more time in the lower performance state over the life of the drive. But look at what happens with the X25-M G2: it drops from 36.1MB/s to 35.8MB/s - virtually no performance is lost. In fact, the G2 is so fast here that it outperforms the super expensive X25-E. Granted you don't get the lifespan of the X25-E and the SLC drive should perform better on more strenuous random write tests, but this is a major improvement.
The explanation? It actually boils down to the amount of memory on the drive. The X25-M G1 had 16MB of 166MHz SDRAM on-board, the G2 upped it to 32MB of slower 133MHz DRAM. Remember that Intel doesn't keep any user data in DRAM, it's only used for the remapping, defragmenting and tracking of all of the data being written to the drive. More DRAM means that the drive can now track more data, which means that even in the heaviest of random-write workloads you could toss at it on a normal desktop you will not actually lose any performance with the drive in a used state. And this is the drive Intel has decided to grant TRIM to.
The G2 is good.
The Indilinx drives do lose performance here. They drop from roughly 13MB/s down to 7MB/s. We're still talking ~5x the speed of a VelociRaptor, so there's no cause for alarm. But it's clear that even Indilinx's SLC drive can't match Intel's random write performance. And from what I hear, Intel's performance is only going to get better.
This is what the X25-M price premium gets you.
Bahahaha, look at the hard drive scores here: 0.7MB/s and 0.3MB/s? That's freakin' terrible! And that's why your system feels so slow when you start it up, there are a ton of concurrent random reads and writes happening all over the place which your hard drive crunches through at roughly 0.5MB/s. Even the Samsung based OCZ Summit manages a significant performance advantage here.
The Indilinx drives all cluster around the 30 - 40MB/s mark for random read performance, nothing to be ashamed of. The Intel drives kick it up a notch and give you roughly 60MB/s of random read performance. It's a noticeable improvement. As our application launch tests will show however, loading a single app on either an Indilinx or Intel drive will take about the same amount of time. It's only in the heavy multitasking and "seat of the pants" feel that you'll have a chance at feeling a difference.
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.