The Intel SSD 510 Review
by Anand Lal Shimpi on March 2, 2011 1:23 AM EST- Posted in
- IT Computing
- Storage
- SSDs
- Intel
- Intel SSD 510
TRIM Performance
As expected, Intel's SSD 510 fully supports the ATA TRIM instruction. To gauge it's implementation I filled the 510 with data then ran a 4KB random write test (QD=32, 100% LBA space) for 20 minutes and measured performance using ATTO. I then TRIMed the entire drive by formatting it in Windows 7 and re-ran the ATTO test. The graphs below show clean, torture and and after TRIM performance.
First clean performance:
Next, after our torture session:
Once tortured the 510's performance drops as far down as 60MB/s for writes. A single TRIM pass restores performance to an almost-new state:
Worst case sequential performance isn't terrible, but worst case random write performance is pretty bad. Remember the ~50MB/s speeds from earlier? Those will drop down to ~5MB/s with an adequately fragmented drive. TRIM will recover performance but write amplification goes through the roof if you have a highly random workload. The 510 is suitable for desktop workloads, but anything more enterprise-like may be out of the question (at least not without significantly increasing the amount of spare area). I'm currently testing the 510 in a Mac to see how performance fares without TRIM over time.
Facebook
Twitter
RSS
128 Comments
View All Comments
aarste - Wednesday, March 2, 2011 - link
Those graphs on the TRIM test look nothing remotely close to ATTO, which I use. I checked HDTach as well and it wasn't that, but close.What app was it?
mino - Wednesday, March 2, 2011 - link
Please, be so king and include a fast HDD (say a WD Velociraptor) in EVERY SSD benchmark.While most readers here understand the difference between SSD and HDD, including a single fast HDD would make the article useful also as a reference/datapoint when talking to not-so-techy people.
strikeback03 - Thursday, March 3, 2011 - link
Then people would complain because the numbers are so small as to be unreadablenerex - Wednesday, March 2, 2011 - link
Maybe I missed it, but i didn't see any discussion of the power usage of the new drives- according the intel press releases, the new drives use 380mW/100mW active/idle and the G2 drives only use 150mW/75mW active/idle.This means the new drives would actually be worse on laptop battery life, correct?
DigitlDrug - Saturday, March 5, 2011 - link
Hi Anand,+1
Power consumption figures would be great for us laptop users!
I find it interesting that a number of these drives report consumption of up to 3watts and others are in the mw range when browsing the Egg.
Some clarity on power consumption would be a great addition.
As always, great review!
ClagMaster - Wednesday, March 2, 2011 - link
The Intel SSD 510 is not a bad drive but it cost more than a Vertex 2 or 3.The Intel Toolbox, and extensive compatablity and reliability testing are major pluses.
The SSD is still an extravagance for desktops though I can see its a no-brainer for laptops because of power conservation. Unless the cost per gigabyte is less than $0.80/gigabyte, the performance gain does not offset the mechanical harddrive.
neotiger - Wednesday, March 2, 2011 - link
I.e., an epic FAIL product priced at a premium to competing products that are far superior.What misguided priorities from Intel. People shell out the big bucks for SSD's for their RANDOM IO performance, NOT sequential IO. So the geniuses at Intel decided to release a "next gen" product that actually has WORSE performance than the last gen product. Really?
I'm speechless. The really sad part about this fiasco is that most people will still buy this piece of crap over far superior competing products just because it's Intel.
Just like NetBurst all over again.
strikeback03 - Thursday, March 3, 2011 - link
Did you actually look at the real-world results? the 510 is almost twice as fast as the G2 160GB in some tests.poohbear - Wednesday, March 2, 2011 - link
nice review, but you're talking & comparing the Vertex 3 and this new drive, but where's the vertex 3 on the market? its not even released, its months away from release if im not mistaken? the C400 will be released before it, so what's the point of comparing tech today with tech months away from release (and in the SSD world months is a very long time!)sor - Wednesday, March 2, 2011 - link
FWIW, we've deployed literally hundreds of X25-E drives, and our failure rate is well over 1%, closer to 2%. Usually they drop link, try to renegotiate at 1.5Gbps, and fail, so it's more likely the controller than a wear-out issue.