search for it

Showing posts with label SSD. Show all posts
Showing posts with label SSD. Show all posts

Thursday, November 24, 2011

SSD (Solid Storage) Hierarchy Chart

We understand that SSD prices make it difficult to adopt the latest technology. Maybe that's why you aren't too keen on blowing a couple hundred dollars on solid-state storage, especially when you can spend the same amount and buy four 2 TB hard drives or a high-performance processor. That's why it's important to put things into perspective.
Over the past five years, CPU performance has hit new and unforeseen heights, and processors are increasingly spending time waiting on data from hard drives. This is what makes storage today's most glaring bottleneck. Overcoming it requires an SSD.
Zoom
As a point of comparison, a file operation completes 85% faster on a low-end SSD than it does on a high-end hard drive, but there is only an 88% speed difference between a high-end hard drive and a high-end SSD. That why you shouldn't let less aggressive benchmark results at the low-end deter you from making the switch. You don't have to have the best SSD to get great performance relative to a hard drive.
This hierarchy chart relies on information provided in our Storage Bench v1.0, as it ranks performance in a way that reflects average daily use for a consumer workload. This applies to gamers and home office users. The chart has been structured so that each tier represents a 10% difference in performance. Some rankings are educated guesses based on information from testing a model at a different capacity or a drive of similar architecture. As such, it is possible that an SSD may shift one tier once we actually get a chance to test it. Furthermore, SSDs within a tier are listed alphabetically.
There are several drives that we're going to intentionally leave out of our hierarchy list. Enterprise-oriented SLC- and 512 GB MLC-based SSDs are ignored due to the extreme price they command (and the difficult we have getting samples in from vendors). Furthermore, SSDs with a capacity lower than 60 GB are left off because of the budget nature of that price range.

The OCZ Octane Review (512GB)

I have to hand it to OCZ's CEO, Ryan Petersen, I never thought he'd turn the company around in the way that he did. When I first met Ryan around a decade ago, he wanted to know why I wouldn't allow him to advertise OCZ on AnandTech. The company at that time had an extremely bad reputation. It was among the worst I'd ever seen. It was so bad that not only would we not review their products (memory, at the time) but I wouldn't allow OCZ ads to run on the site. Although all advertising on AnandTech is handled through a third party, I still have the ultimate say on what ends up on the site. Back then, OCZ wasn't allowed.

Having just taken over the company, Ryan was eager to know what he had to change to fix OCZ's reputation. I gave him a long list of issues to address. Most of my suggestions were obvious, just to go above and beyond the call of duty in taking care of his customers and our readers. He agreed to do everything on the list, with one exception. I told him that if he really wanted to succeed, he needed to abandon the OCZ name and start fresh. He told me that he didn't believe it was necessary. We agreed to disagree.

I remember leaving that meeting thinking that Ryan didn't stand a chance. Memory companies were a dime a dozen. Differentiation was bordering on impossible. Having to overcome a bad reputation on top of that didn't make things any easier.

Ryan is headstrong. He'll sow a bunch of seed with the hopes of seeing just one blade of grass grow. I consider myself an optimist, but he's a different breed of one. He's had his share of failures over the years. Remember the OCZ brain mouse? The foray into notebook PCs? No one ever succeeded without trying.

Since then OCZ has abandoned memory altogether. It focuses on two product lines: power supplies and SSDs, the latter making up the bulk of its revenue. And earlier this year, OCZ bought one of the first high-performance SSD controller manufacturers - Indilinx.

OCZ's strategy there didn't make sense to me. I knew Ryan wanted to buy SandForce, but SF was too expensive. I asked Ryan why bother with Indilinx if what he really wanted was SandForce? He told me that the best way to drive the price down on SF was to buy Indilinx. It didn't add up until now.

Ryan took a big risk on Indilinx. They had a promising controller in 2009 and he bought up the bulk of what they could make in exchange for exclusivity rights. OCZ made Indilinx, and Indilinx made OCZ. As Indilinx began courting more vendors, OCZ went after SandForce. As soon as a first generation controller was ready, OCZ began shifting its volume from Indilinx to SandForce. More partners stepped up to fill the gap left by OCZ, but by then no one wanted Indilinx - they wanted SandForce based drives.

Simultaneously (perhaps a result?) Indilinx's execution suffered, the stumble was irrecoverable. The value of Indilinx went down, and Ryan got the company for cheap.

I can only assume the strategy was to rinse and repeat. I had heard rumors of OCZ working on its own controller for the past two years. The Indilinx acquisition sped things up considerably. If the Indilinx solution was good enough, OCZ would shift its volume away from SandForce to its own controller. Starve SandForce and swoop back in later to buy them at a more reasonable price. Competition makes for competitive prices on both sides of the fence it seems.

Things of course didn't work out that way. OCZ took a while to get its own controller design done and it was still very dependent on SandForce. At the same time, SandForce had diversified its portfolio. Since the announcement of the Indilinx acquisition, SandForce brought on a number of new partners to sell its drives. Even Kingston signed up. Finally, LSI agreed to purchase SandForce at a number well in the range of what SF was looking to sell for.

The situation didn't play out exactly how Ryan had hoped, I'm sure. But the result actually isn't all that bad. LSI has no intentions of stopping its supply of SandForce controllers to OCZ (or other partners), and all of the work OCZ put into its own controller finally paid off. Personally, it's hard to believe that I'm writing about the company I once advised to completely abandon their brand. Furthermore, I'm not just writing about them, but I'm writing about their first in-house SSD controller. This is the Indilinx Everest:

There's not much we can tell from looking at the silkscreen on the IC, but it's the first all new SSD controller from Indilinx since 2009. Jetstream was its predecessor, but that part never made it to market.

Everest is Indilinx's first 6Gbps controller and its delivery vehicle is the OCZ Octane SSD. You'll see both 6Gbps and 3Gbps versions of the drive, although what's launching today is the 6Gbps part.


The controller features eight NAND channels, with the ability to interleave multiple requests per channel. The capacities and price breakdown are below:
OCZ Octane Lineup
1TB 512GB 256GB 128GB
NAND Type 25nm Intel Sync MLC 25nm Intel Sync MLC 25nm Intel Sync MLC 25nm Intel Sync MLC
NAND 1TB 512GB 256GB 128GB
User Capacity 953GiB 476GiB 238GiB 119GiB
Random Read Performance Up to 45K IOPS Up to 37K IOPS Up to 37K IOPS Up to 37K IOPS
Random Write Performance Up to 19.5K IOPS Up to 16K IOPS Up to 12K IOPS Up to 7.7K IOPS
Sequential Read Performance Up to 560 MB/s Up to 535 MB/s Up to 535 MB/s Up to 535 MB/s
Sequential Write Performance Up to 400 MB/s Up to 400 MB/s Up to 270 MB/s Up to 170 MB/s
MSRP TBD $879.99 $369.99 $199.99

Thursday, November 10, 2011

Holiday Budget System Buyers' Guide: RAMs, Hard Drives, SSDs, GPUs, PSUs, Cases


RAM
DDR3 prices seem to have bottomed out and are holding steady at around $25 for 2 x 2GB kits and $35 for 2 x 4GB kits. While it might be tempting to spend $10 more on an 8GB kit of DDR3, 4GB is more than ample for basic to moderate multitasking. If the system will be used for extensive multitasking or for applications that benefit from lots of RAM like Photoshop, you might as well spring for an 8GB kit. Both Mushkin and GSkill offer 4GB kits that are usually less than $30 shipped. While these appear to be unremarkable budget memory sticks, my testing indicates both are capable of undervolting to 1.4V (from the default 1.5V) while running at stock speeds, and both kits can be modestly overclocked at the stock 1.5V setting. Additionally, GSkill's budget 8GB kit was capable of modest overclocking (though not undervolting).
Hard drives
As alluded to earlier, prices on hard drives have risen lately in response to flooding in Thailand and other areas of southeast Asia. In my previous buyers' guides, I've recommended 500GB drives that were available at every day prices of $40 shipped. Unfortunately, $40 500GB drives are not currently available from any of the major US internet retailers. How long these elevated prices will persist is anyone's guess, but from what I can gather, the supply disruption will last at least a few more months. It's possible prices will continue to rise, but for now, it's difficult to find 500GB drives for less than $50 shipped (day to day pricing). As much as it pains me to say it, you can save a few dollars by going for smaller capacity drives. For many basic users, 160GB might be enough storage space.

Wednesday, November 9, 2011

OWC Mercury Aura Pro Express 6G Review: A Fast MacBook Air SSD Upgrade

I've written previously about the SSD lottery you play when you buy a new MacBook Air. As with many commodity components, Apple sources its SSDs from two sources. For now, that appears to be Toshiba and Samsung. Apple tends to pick suppliers that can deliver a reliable product in the quantities it's interested in. In the storage space at least, Apple doesn't seem to be overly concerned with performance but rather making sure the solution works.
A year ago, the Toshiba and Samsung controllers offered fairly similar performance. These days the same isn't true. While Samsung has updated its controllers, Toshiba's solution still offers the fairly abysmal random write performance it did a year ago. With the recent release of the Samsung SSD 830, I expect the trend of Samsung drives increasing in performance will continue next year as well.
Unlike the rest of Apple's notebook lineup however, it's not so easy to just swap in a higher performing (or larger capacity) SSD in your MacBook Air. The very first MBAs used a PATA LIF connector, a rarity on most drives. Apple eventually transitioned to a SATA LIF connector, and then with the release of the 2010 MacBook Air we encountered a new thin form factor SSD with a custom interface connector. In all of those cases, the market for third party MacBook Air SSDs popped up at some point post-launch. The 2010/2011 MacBook Air has been no different.
If you've followed the aftermarket Mac support business then OWC should be no stranger to you. If you haven't heard of OWC from their Mac efforts, there's always the fact that second to only OCZ, no one has been quicker at releasing SSDs based on brand new SandForce controllers.
OWC put out an aftermarket drive for owners of 2010 MacBook Airs based on the 3Gbps SF-1200 controller. For 2011 MBA owners there's a 6Gbps SF-2281 option: the OWC Mercury Aura Pro Express 6G.
The drive is available in 120GB and 240GB capacities, for $280 and $550 respectively. Both drives come with pentalobe and torx drivers to aid in opening your MBA and replacing your old drive.
For another $35 OWC will sell you an external USB 2.0/3.0 enclosure that can house your old MBA SSD either to help you transfer your data or give you a sweet, high performance external drive once you're done.
OWC sent me a 240GB Aura Pro, which I installed into an 11-inch MacBook Air. The installation process was a cinch. The only hiccup was that I couldn't just clone my 256GB Toshiba SSD using Disk Utility since the Aura Pro was technically smaller. Instead I used Lion's internet recovery to download and install a fresh copy of OS X, before restoring my data and installing benchmarks.
If you've followed our SSD reviews you'll know what to expect next. SandForce's SF-2281 controller is the fastest option on the market today, while the Toshiba controller Apple uses is pretty much on the opposite end of the spectrum. I ran our standard four-corners Iometer test to put into perspective just how much faster the OWC upgrade is:
2011 MacBook Air SSD Performance Comparison
  4KB Random Write (8GB LBA Space, QD3) 4KB Random Read (QD3) 128KB Sequential Write 128KB Sequential Read
OWC Mercury Aura Pro Express 6G 88.4 MB/s 30.4 MB/s 495.1 MB/s 451.4 MB/s
13-inch MacBook Air (Mid 2011) - Toshiba SSD 1.65 MB/s 18.0 MB/s 204.2 MB/s 189.5 MB/s
11-inch MacBook Air (Mid 2011) - Samsung SSD 27.2 MB/s 44.6 MB/s 258.0 MB/s 234.4 MB/s
11-inch MacBook Air (Late 2010) - Toshiba SSD 2.49 MB/s 31.1 MB/s 147.0 MB/s 113.0 MB/s
Performance is just staggering. The comparison is borderline unfair because both the Samsung and Toshiba controllers Apple uses in its MacBook Air are really a generation old at this point, while the Mercury Aura Pro Express is the absolute latest and greatest 6Gbps solution SandForce offers. The performance advantage is noticeable. The upgrade does make everything feel snappier, particularly compared to a MBA equipped with a Toshiba SSD. Large file transfers complete quicker and heavy multitasking workloads see an improvement as well.
SandForce achieves this performance advantage by using real time compression and data deduplication algorithms to reduce the amount of data actually written to the NAND. Since much of what we write to our drives in the course of normal use is easily compressible data, SandForce's technology is quite effective. Where the controller falls short however is if you're moving incompressible data, for example already highly compressed videos or encrypted data. While highly compressed content like H.264 movies will really only impact sequential read/write speed, enabling full disk encryption under OS X impacts all of your data. Truly random data is impossible to compress/dedupe, so I enabled FileVault under Lion and re-ran our performance tests on the Aura Pro:
(Encryp
2011 MacBook Air SSD Performance Comparison
  4KB Random Write (8GB LBA Space, QD3) 4KB Random Read (QD3) 128KB Sequential Write 128KB Sequential Read
OWC Mercury Aura Pro Express 6G 88.4 MB/s 30.4 MB/s 495.1 MB/s 451.4 MB/s
OWC Mercury Aura Pro Express 6G (Encrypted) 80.8 MB/s 28.8 MB/s 184.8 MB/s 431.9 MB/s
Apple Toshiba SSD (Encrypted) 1.13 MB/s 19.4 MB/s 178.7 MB/s 195.8 MB/s
Sequential write performance takes a pretty significant hit, but the rest of the metrics look ok. In fact, I'd say even if you're running with your drive encrypted you'll have a better experience on the OWC drive than with either of the Apple SSDs.
With the OWC Mercury Aura Pro Express 6G you get much better performance than the stock Apple SSDs regardless of usage. Is there any downside to going with the aftermarket drive? Unfortunately there appears to be one:
Power Consumption Comparison
  Idle Load (Sequential Write)
OWC Mercury Aura Pro Express 6G 6.2W 19.0W
OWC Mercury Aura Pro Express 6G (Encrypted) 6.2W 18.0W
Apple Toshiba SSD 5.5W 16.4W
It's natural for the OWC solution to draw more power under load, you're getting over twice the performance so the increase in power draw is actually not an issue (better power efficiency since you'll be at idle quicker than with a stock SSD). The bigger concern is what happens at idle. My 11-inch MacBook Air typically idles at 5.5W, swapping in the OWC drive increased that idle power consumption to 6.2W. Now this is measured at the wall, so it takes into account AC adapter inefficiency. The actual impact at idle should be somewhere in the 300mW - 400mW range. For a mostly idle workload you'd probably see a 30 minute reduction in battery life.

Final Words

The OWC Mercury Aura Pro Express 6G is a well executed SSD upgrade for 2011 MacBook Air owners. You get an absolutely huge performance increase and an option for users who want the entry level 2011 MBAs but with a larger capacity SSD. If your MacBook Air is your primary workhorse, perhaps even your desktop replacement, and you got stuck with a Toshiba SSD the OWC option makes a lot of sense. OWC thankfully provides everything you need in the box to get into your MacBook Air and swap drives.
The downside is power consumption. At idle the SandForce controller simply draws more power than the Toshiba controller in the MBA we tested. The overall impact on battery life won't be tremendous (perhaps 5% on a mostly idle workload), but if you're already on the edge of usability with the battery life from your stock MacBook Air you may want to remain stock.