The OCZ Octane Review (512GB)
by Anand Lal Shimpi on November 23, 2011 12:00 PM ESTPerformance Over Time & TRIM
Testing TRIM functionality is important because it gives us insight into the drive's garbage collection algorithms. OCZ insists the Octane has idle time garbage collection, a remnant of the original Indilinx drives, however in my testing I could not get the idle GC to do anything once I put the drive into a highly fragmented state. Let's start at the beginning though. The easiest way to ensure real time garbage collection is working is to fill the drive with data and then write sequentially across the drive. All LBAs will have data in them and any additional writes will force the controller to allocate from the drive's pool of spare area. This path shouldn't have any bottlenecks in it; the process should be seamless. As we've already seen from our Iometer numbers, sequential write performance at low queue depths is around 280MB/s. A quick HD Tach pass of a completely full drive gives us the same result:
The Octane works as expected here, but now what happens if we subject the drive to a ton of 4KB random writes? Unfortunately this is where the Octane falls short. If we just throw a few minutes of random writes, constrained to a small LBA range, at the Octane its performance hardly varies:
However once the Octane passes a threshold of fragmentation, the performance drop is considerable. Our standard test involves a 20 minute, 4KB random write across all LBAs at a queue depth of 32. A sequential write pass across the drive afterwards took place at between 2 and 7MB/s. Since our test drive was a 512GB model, there simply wasn't enough time to conduct a full pass in the course of preparing this review. Instead I did a shorter test with HD Tach to give you some indication of what happens to the Octane under a highy random load without TRIM:
Performance drops considerably. A single TRIM pass restores performance to new. I did have one TRIM test where only the latter half of the drive seemed to TRIM but I couldn't get the same result more than once. Now the question is, what does all of this mean?
If you have TRIM enabled on a desktop platform with a client (read: non-server) workload, none of this should matter to you. TRIM works and there doesn't appear to be any weird lag or bottlenecks in the GC path. If you don't have TRIM enabled (read: OS X) with a client workload, this could warrant a pass. The only reason I'm hesitant to recommend the Octane for use with a TRIM-less OS X installation is because I'm not entirely sure the drive will recover from this ultra low performance state without TRIM. Sequential writing alone may not be enough to adequately restore the Octane's performance. Normally idle GC would be enough, but it seems as if things get slow enough the drive's idle GC can't do much. I suspect all of this is stuff that OCZ can tweak via firmware, but I need more time with the drive to really be certain.
Finally if you're deploying a server with lots of random writes, the Octane isn't for you. OCZ will eventually release an Everest based drive for the enterprise, but the Octane is not that drive.
Facebook
Twitter
RSS
75 Comments
View All Comments
Flashfir - Wednesday, November 23, 2011 - link
A little correction to your claim that OCZ is becoming jack of all trades, practically failure at all of them.Almost ALL of OCZ new lines of PSUs have been garnering really great reviews over reputable review sites like Jonnyguru and Hardwaresecrets. Personally I'm running an OCZ StealthXStream II 600w and I did my review searching, seemed good, it's running my rig excellently. 80+ Cert which actually meets bronze level!
Newest lines: ZX, Z, ZT, ZS series. I recall seeing ZS reviews, ZX reviews and ZT reviews all glowing, >9/10 ratings on Jonnyguru!
PSUs doing well, their SSD lines are suffering granted. The particular Vertex Plus line got crippled by data corruption issues when used with SATA I, instead of Sata II or III aka, lower than Sata 3GB/S standard.
They didn't loudly warn people about it nor did they loudly advertise the fix which was included in the 3.55 firmware update. I helped my roommate get one and it works great but I had to research and double check to see if all the 50%+ negative reviews on NewEgg were because of a controllable issue. It was true! And now his netbook is lightning fast.
Beenthere - Wednesday, November 23, 2011 - link
Just because of late OCZ's PSUs have improved, doesn't mean that they have resolved their QC/design issues any more than fixing one SandForce BSOD issues means SSDs are now free of reliability and compatibility issues. I just call it like it is and OCZ has and continues to have a very checkered history on product quality.Corsair has also had issues with their PSUs, SSDs and closed loop coolers. This is what happens when companies rush crap out the door for quick profits without doing proper qualification of the goods. As long as "enthusiasts" buy this half-baked crap and make these companies huge profits, that's what they will continue to deliver - crap.
Flashfir - Wednesday, November 23, 2011 - link
True. Everything you say is true. You know how emphasizing the bad without talking about anything good tends to give people the wrong ideas about how things really are.If OCZ's PSUs continue to be good from here on out, then their past is still checkered but they've spent enough effort to show they're good. Which we're seeing if they will do.
It's not about being right or wrong but whether or not if people who don't know much who read in can really get the same sense of "it as it really is". I wanted to correct you a little bit to clarify that PSU lines can possibly be improving.
Beenthere - Wednesday, November 23, 2011 - link
To be perfectly fair OCZ would not be at the top of my list for any product at the moment. Maybe five years down the road they will be selling reliable, trouble-free products, but right now I wouldn't touch their stuff. Same goes for Corsair other than their RAM. You couldn't pay me to use a half-baked Asus mobo either. All of this stuff is rushed out the door for profit before it's ready for prime time, IME.Unfortunately the PC industry is rifle with crap products - because people are naive enough to buy them.
jleach1 - Sunday, November 27, 2011 - link
Oh yeah? My stealthxstream blew in a spectacular manner 6 months after I purchased it and it filled my whole house with that burnt electronics smell that you can never seem to get out of your nose.That combined with the nonexistent support I received for a set of DDR3 dims that required lowering the speed and upping the voltages every few months has me avoiding OCZ for the 12 months Anand spoke of at all costs.
I didn't even attempt to rma my power supply.
How many people have decided just to junk their hardware after being nickeled out of a manufacturers rebate or hounded on by ocz support for months with useless questions, I don't know. And we'll probably never know.
jimbowdang - Wednesday, November 23, 2011 - link
Great review Anand, reading your comments on passing up on this drive for use on OS X makes me wonder if those hacks that supposedly allow non-Apple SSDs to use Trim actually work. I've been using an Intel G2 160 GB SSD in my 2010 13" MBP for over a year now and I've done the hack but I've never seen any testing to confirm that it actually works. I would love to see some testing on this as real Trim support would open up a lot of SSD options for OS X.NCM - Thursday, November 24, 2011 - link
Surely you'd notice if your enabling OS X TRIM on a (non-Sandforce) SSD wasn't working, at least unless you had a quite large amount of spare capacity to start with. Even then you'd eventually start reusing storage and would see a slowdown.I think it's worth making clear that although OS X only turns on TRIM by default for Apple supplied SSDs, it's trivial to enable it for third party units. It also seems reasonable to suppose that anyone motivated to install their own SSD on a Mac would also know to do that.
We're currently running four of our Macs with SSDs, two laptops and an Xserve that I ordered that way, plus a Mac Pro that I retrofitted.
Peroxyde - Wednesday, November 23, 2011 - link
Did the new CEO also setup un-honored Mail In Rebate as a business? If so it is quite successful.geddarkstorm - Wednesday, November 30, 2011 - link
Had that happen to me with two different kingston products. Don't trust mail-in-rebate to begin with, no matter who is peddling it.krazyderek - Wednesday, November 23, 2011 - link
Would have really liked to see a throughput vs transfer size for this drive :( some of us move around large compressed movies for editing and i'd like to know how the octane fairs against the m4 in such cases.also, where is the avg access time, and max latency?? could also be good points to have about a new controller!