Subject: Storage
Tagged: tlc, ssd, Samsung, pro, mdx, 840

Introduction, Specifications and Packaging

Introduction

Last week, Samsung flew myself and a few of my fellow peers in the storage review community out to Seoul, Korea. The event was the 2012 Samsung SSD Global Summit:

120924-104020-4.28.jpg

At this event, Samsung officially announced their new 840 Pro, which we were able to obtain early under NDA and therefore publish in concert with the announcement. The 840 Pro was largely an incremental inprovement over their 830 Series. Newer, faster flash coupled with a higher clocked controller did well to improve on an already excellent product.

121002-220858-6.35.jpg

As the event closed, we were presented with the second model of the lineup - the 840. This model, sans the 'Pro' moniker, is meant more for general consumer usage. The first mass marketed SSD to use Triple Level Cell (TLC) flash, it sacrifices some write speed and long-term reliability in favor of what should become considerably lower cost/GB as production ramps up to full capacity. TLC flash is the next step beyond MLC, which is in turn a step after SLC. Here's a graphic to demonstrate:

slc-mlc-tlc-glass.jpg

Read on for the full review!

Subject: Storage
Tagged: 840, mdx, pro, Samsung, ssd

Introduction, Specifications and Packaging

Introduction

Samsung has been at this SSD thing for quite some time now. The first SSD I bought was in fact a Samsung unit meant for an ultraportable laptop. Getting it into my desktop was a hack and a half, involving a ZIF to IDE adapter, which then passed through yet another adapter to convert to SATA. The drive was wicked fast at the time, and while it handily slaughtered my RAID-0 pair of 74GB VelociRaptors in random reads, any writes caused serious stuttering of the drive, and therefore the entire OS. I was clearly using the drive outside of its intended use, but hey, I was an early adopter.

Several SSDs later came the Intel X25-M. It was a great drive, but in its earliest form was not without fault. Luckily, these kinks were worked out industry-wide, and everyone quickly accelerated their firmware optimizations as to better handle random writes. Samsung took a few generations to get this under control. The first to truly get over this hump was the 830 Series, which launched earlier this year. It utilized a triple core Arm 9 CPU which was able to effectively brute force heavy random write workloads. It also significantly increased the speed and nimbleness of the 830 across the board, which combined with Samsung's excellent reliability record, quickly made it my most recommended series as of late.

DSC00687.JPG

...and now we have the 840 Series, which launched today. Well, technically it launched yesterday if you're reading from the USA. Here in Korea the launch started at 10 AM and spanned a day of product press briefings leading to the product NDA expiration at 8 PM Korea time. This review will focus on the 512GB capacity of the 840 Pro model. We will follow on with the 840 (non-pro) at a later date:

DSC00688.JPG

Read on for the full review!

Subject: Storage

Introduction and Internals

120711-023332-8.59-.jpg

Introduction:

I'm going to let the cat out of the bag right here and now. Everyone's home RAID is likely an accident waiting to happen. If you're using regular consumer drives in a large array, there are some very simple (and likely) scenarios that can cause it to completely fail. I'm guilty of operating under this same false hope - I have an 8-drive array of 3TB WD Caviar Greens in a RAID-5. For those uninitiated, RAID-5 is where one drive worth of capacity is volunteered for use as parity data, which is distributed amongst all drives in the array. This trick allows for no data loss in the case where a single drive fails. The RAID controller can simply figure out the missing data by running the extra parity through the same formula that created it. This is called redundancy, but I propose that it's not.

Continue on for our full review of the solution to this not-yet-fully-described problem!

Author:
Manufacturer: ASUS

An overview of Thunderbolt Technology

The promise of Thunderbolt connectivity has been around for a couple of years now. Today, Thunderbolt is finally finding its way to the PC platform in the form of motherboards from ASUS and MSI. First unveiled as "Light Peak" at the Intel Developer Forum in 2009, the technology started out as a way to connect multiple devices to a system over a fiber optic cable (hence the 'light' in the name), though the final products have changed the implementation slightly.

lightpeak-2.JPG

The first prototype implementations actually used a USB-style connection and interface. It further required fiber optic cables. When it was renamed to Thunderbolt and then released in conjunction with a new lineup of Apple MacBook laptops, not only did the physical interface move to a mini-DisplayPort connection but the cable was made to use copper rather than fiber. Without diving too far into the reasons and benefits of either direction, the fact is that the copper cables allow for modest power transfer and are much cheaper than fiber optic variants would be.

slide01.jpg

Thunderbolt's base technology remains the same, however. It is a transfer standard that allows for 10 Gbps of bandwidth for each channel (bi-directional) and concurrently supports both data and display connections. The actual interface for the data path is based on PCI Express and connected devices actually appear to Windows as if they are internally connected to the system which can offer some interesting benefits – and headaches – for hardware developers. The display connection uses the DisplayPort standard and can be used along with the data connection without affecting bandwidth levels or performance.  

slide02.jpg

For current Intel processor implementations, the Thunderbolt connection is supported by a separate controller chip on the motherboard (or a riser card) – and some routing is required for correct usage. The Thunderbolt controller does not actually include a graphics controller, so it must be fed an output from another graphics processor, obviously in this case directly from the Ivy Bridge / Sandy Bridge processors. In theory, these could be from other controllers, but with the ubiquitous nature of integrated processor graphics on IVB and SNB processors, this is going to be the implementation going forward according to motherboard and system designers. 

Continue reading our review of Thunderbolt on Windows and the ASUS P8Z77-V Premium!!

Subject: Storage

ioSafe: Introduction and Internals

Introduction:

Cloud storage is all the talk these days, and our own Tim Verry has been hard at work detailing as much of it as he can keep up with. While all of us at PCPer currently use cloud based solutions for many of the day-to-day goings on, it's not for everyone, and it tends to not be for very large chunks of data, either. Sometimes local storage is just the way to go – especially when you want to be the one in absolute control of the reliability and integrity of your data.

The general rule for proper backups is to have your local copy, a local backup (RAID is *not* a backup), and an additional off-site backup to cover things like theft, fires or floods. So lets say you simply have too much sensitive data for your internet connection to support bulk transferring to an off-side / cloud storage location. Perhaps the cloud storage for that much space is simply cost prohibitive, or your data is sensitive enough that – despite encryption – you don't want it leaving your network and/or premesis? Perhaps you're just stubborn and want only one backup of your data? I think I might have the answer you've been looking for – behold the ioSafe SoloPRO:

120205-095626-8.39.jpg

What is this thing, you may ask? On the inside it's one of the available 1, 2, 3, or even 4TB 3.5" hard drives. On the outside it's a very durable and solid steel enclosure. The hard drive is wrapped in a thermally conductive yet water resistant 'HydroSafe' foil that enables water resistance rated at a 10 ft depth for 3 days with no data loss. The bonus, however, is not the water resistance - that featuer is present primarily to battle the side effects of something much more drastic - the ioSafe is fire-proof. That feature comes from what sits between the steel casing and the shrink wrapped hard drive - something ioSafe calls a DataCast (pictured below):

Internals:

I'm going to break from my normal warranty voiding and show a photo from this past Storage Visions conference at the Consumer Electonics Show, where an ioSafe was already cracked open for our viewing pleasure:

1-int-1.JPG

Read on for the full review!

Author:
Subject: Systems, Storage
Manufacturer: DV Nation

Inside and Out

When you are a little fish in the great big pond of PC builders, you need to do something to stand out from the rest.  The people behind DV Nation apparently were well aware of that when entering the system vendor business and offering up SSDs to every single system configuration.  Through a new system they are offering, provocatively named the "RAMRod PC", DV Nation provides a pre-built system that has some very unique components and configuration settings.

01.jpg

Built around the Antec Three Hundred Two chassis, the first glance at the RAMRod doesn't really indicate anything special is going on under the hood.  But let's take a quick look at the specs:

  • Intel Core i7-3820 @ 4.4 GHz
  • 64GB DDR3-1600 Memory from G.Skill
  • Radeon HD 6990 4GB 
  • 2x Seagate Momentus XT 750GB Hybrid HDD in RAID-0
  • OCZ RevoDrive 3 X2 480GB PCIE SSD
  • RAMCache: SuperSpeed Supercache 8GB on PCIE SSD, 8GB on Momentus
  • RAMDisk: 42GB ROMEX Primo rated at 8000 MB/s
  • Cost: $5,400

Obviously there is a LOT of storage work going on in the RAMRod and the purpose of the rig is to be the fastest pre-configured storage available anywhere.  If you are looking for a cheaper version of this system you can get a base model with 16GB of memory, 10GB RAMDisk, 2GB RAMCache, 240GB PCIe SSD, single standard hard drive and even at GTX 680 for $2999.

Let's take a quick walk around the rest of the system before diving into the benchmarks!

Continue reading our review of the DV Nation RAMRod PC!!

Subject: Storage
Manufacturer: Intel SSD 900 Family
Tagged: ssd, pcie, Intel, 910, 800gb

Background and Internals

A little over two weeks back, Intel briefed me on their new SSD 910 Series PCIe SSD. Since that day I've been patiently awaiting its arrival, which happened just a few short hours ago. I've burned the midnight oil for the sake of getting some greater details out there. Before we get into the goods, here's a quick recap of the specs for the 800 (or 400) GB model:

"Performance Mode" is a feature that can be enabled through the Intel Data Center Tool Software. This feature is only possible on the 800GB model, but not for the reason you might think. The 400GB model is *always* in Performance Mode, since it can go full speed without drawing greater than the standard PCIe 25W power specification. The 800GB model has twice the components to drive yet it stays below the 25W limit so long as it is in its Default Mode. Switching the 800GB model to Performance Mode increases that draw to 38W (the initial press briefing stated 28W, which appears to have been a typo). Note that this increased draw is only seen during writes.

Ok, now into the goodies:

120426-193420-5.91.jpg

Click here to read on!

Subject: Storage

Introduction

It's been a long while since we've looked at a hard drive, and how fitting that it be a new model of the Western Digital VelociRaptor! Western Digital appears to be on a somewhat fixed 2-year cycle with these, as out 600GB VelociRaptor Review went up two Aprils ago, and the 300GB two years prior to that. Well then, let's take a look at this new model!

120415-050814-8.19.jpg

(from left) 300GB, 600GB, and finally the 1TB VelociRaptor

 

Here's the old school VelociRaptor logo (from back when they were less than 100GB!) 

 

Continue reading our review of the Western Digital 1TB VelociRaptor hard drive!!

Subject: Storage
Manufacturer: OCZ Technology

Introduction, Specifications, and Packaging

Introduction

OCZ has been in the SSD game for quite some time now. Their first contender was the OCZ Vertex, which we reviewed back in Febuary of 2009. While the original Vertex was powered by an Indilinx BareFoot controller, the Vertex line switched over to SandForce for the second and third generations. The fourth generation brings Indilinx back to the Vertex, this time with the Everest 2. You may recall Everest made its first appearance in the OCZ Octane, which has already proven itself to be a solid contender in the market.

DSC02737.JPG

Before we get into the meat and portatoes, we'll kick this off by saying this will not be a typical Vertex 4 review. We had benches run on 512GB and 256GB Vertex 4 samples, but the numbers we were seeing seemed 'off', so OCZ provided me with an alpha/engineering level firmware late last night. I suspect most other reviews you read today will include results from the 1.30 initial shipping firmware, or perhaps from the 1.31 bugfix firmware (which corrected an issue with secure erasure), but this piece will cover both 1.30 and a newer 1.52 interim build. Sometimes it's necessary to burn the midnight oil in the interest of presenting the full picture (or one as complete as possible) to our readers, and this was one of those pieces. We will revisit the Vertex 4 again very soon in the form of a more final product review, but for now we'll go with what we've got.

Read on for the full review!

Subject: Storage
Manufacturer: Samsung
Tagged: ssd, sata, Samsung, 830, 6gbps

Introduction, Specifications, and Packaging

Introduction

Samsung has been in the SSD business for a good long while now. My first "serious" SSD setup consisted of a pair of 32GB G.Skill 'FlashSSD's in a RAID. A few months later I upgraded to an Intel X25-M, starting working for PCPer, and have since seen a slew of different controller types come and go. Of those, Samsung and Intel both come to mind as the most reliable controllers out there. Of those two, Samsung has always been the primary choice of PC OEMs. It may have been because the Samsung controllers have always leaned towards the slow-but-steady approach. Other fire breathing controllers would be quick out of the gate but slow over time as fragmentation effects set in, while Samsung controllers would take the hit on random IOPS, but they maintained that lower level even after repeated and sustained abuse. They were not the fastest, but as a testament to their consistency, I continue to use one of the two aforementioned G.Skill drives in the PCPer Storage Testbed to this day.

120310-091607-4.28.jpg

Read on for the full review!

Subject: Editorial, Storage
Manufacturer: Various
Tagged: ssd, Future, flash, Bleak, 2012

Overcoming Hurdles

A paper, titled “The Bleak Future of NAND Flash Memory” was recently jointly published by the University of California and Microsoft Research. It has been picked up by many media outlets who all seem to be beating the same morbid drum, spinning tales of a seemingly apocalyptic end to the reign of flash-based storage devices. While I agree with some of what these authors have to say, I have reservations about the methods upon which the paper is based.

TLC and beyond?

The paper kicks off by declaring steep increases in latency and drops in lifetime associated with increases in bits-per-cell. While this is true, flash memory manufacturers are not making large pushes to increase bits-per-cell beyond the standard MLC (2 bits per cell) tech. Sure some have dabbled in 3-bit MLC, also called Triple Level Cell (TLC) which is a bit of a misnomer since storing three bits in a cell actually requires eight voltage level bands, not three as the name implies. Moving from SLC to MLC doubles density, but the diminishing returns increase sharply after that – MLC to TLC only increases capacity by a another 1.5x, but sees a 2-4x reduction in performance and endurance. In light of this, there is little demand for TLC flash, and where there is, it’s clear by the usage cases that it is not meant for anything beyond light usage. There's nothing wrong with the paper going down this road, but the reality is that increasing bits per cell is not the envelope being pushed by the flash memory industry.

paper-lifetime.png

Wait a second – where is 25nm MLC?

Looking at the above we see a glaring omission – 25nm MLC flash, which has been around for close to two years now, and constitutes the majority of shipping flash memory parts currently in production. SLC was also omitted, but I can see the reason for this – it’s hard to get your hands on 25nm SLC these days. Why? Because MLC technology has been improved upon to the point where ‘enterprise MLC’ (eMLC) is rapidly replacing SLC even despite the supposed reduction in reliability and endurance over SLC. The reasons for this are simple, and are completely sidestepped or otherwise overlooked by the paper:

  • SSD controllers employ write combination and wear leveling techniques.
  • Some controllers even compress data on-the-fly as to further reduce writes and provisioning.
  • Controller-level Error Correction (ECC) has improved dramatically with each process shrink.
  • SSD controllers can be programmed to compensate for the drift of data stored in a cell (eMLC).

Continue reading our editorial on the not-so-bleak future of NAND Flash Memory!!!

Subject: Storage
Manufacturer: Intel

Introduction, Specifications, and Packaging

 

Introduction

Today we take a look at Intel's newest 6Gb/sec SATA SSD - the 520 Series. This is the second non-Intel controller to appear in one of their products. The first was the Marvell controller, which appeared in the 510 Series last March. This time around, Intel has gone with SandForce. This should leave at least one SATA 6Gb/sec model to be released. Taylorsville is the code name for the next SATA 6Gb/sec native-Intel controller, which has been on their roadmap since mid-2010 but has yet to actually materialize. While Taylorsville development continues, Intel has stop-gapped the 6Gb/sec slot with the 510 and now the 520 Series. Intel seemingly worked wonders with the stock Marvell firmware, and while the Marvell controller was much improved over stock, it still lagged far behind other higher performing SATA 6Gb/sec solutions. The SandForce was one of the much more capable controllers eating the 510's lunch, but how much further could Intel improve upon the SandForce firmware?

outside-2.jpg

I guess a good question to answer up front is - What took them so long?!?! The answer is a bit complicated. Intel has actually been working on getting the 520 out the door for over a year now. They had to start with the same base SandForce firmware but accomplish two things for their version to be successful:

  • Optimize to perform better than other equivalent SandForce models (from competitors).
  • Pass Intel's stringent validation testing.

They didn't say so directly, but I can only imagine Intel's process was plagued by multiple 'back to the drawing board' moments. Trying to one-up competition like OCZ can't be easy as they've been tweaking SandForce firmware since the very beginning. There's also those nasty bugs that would cause random BSOD's or even permanently brick the drive. Such failures have no place in an Intel SSD. Intel's upper limit for each SSD line is a 0.75% annual failure rate, and we've seen SandForce SSD's failing at a higher rate than that this past year.

With each tweak made, Intel would have to once again pass their drives through another round of full validation testing. This is no small task for Intel. As an example: It took Intel just a couple of weeks to recreate and correct the long-term performance issue I discovered back in 2009, but despite mountingpressure, they could not release the updated firmware until it had successfully passed their validation a full three months later. Intel takes this testing very seriously, and that's what leads people to trust their reliability.

Read on for the full review!

 

Subject: Storage
Manufacturer: Corsair

Introduction, Specifications, and Packaging

 Introduction

A couple of days ago we looked at a pair of SSD's from Patriot. Next up is a pair of SSD's from Corsair. These are another two SandForce controlled units, but this time it's Async IMFT flash vs. Sync IMFT flash:

120131-220915-5.63_resize.jpg

We'll carry the Patriot Pyro (IMFT Async) into the results for comparison, and keeping the other benchmark OCZ and Intel models in with the mix of results. The OCZ Vertex 3 and Agility 3 will again share the same SandForce controller, but OCZ has been known to add many performance tweaks to their firmware. Let's see if Corsair was able to use 'tweaked' firmware or instead went with the stock one provided by SandForce.

Specifications

The Corsair Force 3 and Force GT are both available in the following capacities:

  • 60GB
  • 90GB
  • 120GB
  • 180GB
  • 240GB
  • 480GB

The added capacity points are a bonus of how IMFT can stack their dies in 'odd' multiples (i.e. 3 per package, making a 24GB TSOP). Varying slightly from low to high capacities (and across the two models), specs range from 490 to 525 MB/sec writes and 550 to 555 MB/sec reads. 60GB models get 80,000 4K IOPS and the rest get a rating of 85,000 4K IOPS. Corsairs specs indicate IOMeter 2008 was used for this test, and it's important to note that 2008's writes were a repeating pattern that is easily and fully compressible by the SandForce controller, meaning those specs were derived using fully compressible data.

Subject: Storage
Manufacturer: Patriot Memory

Introduction, Specifications, and Packaging

Introduction

Today we're going to take a look at a pair of SSD models from Patriot. While they both share the same SandForce controller, that's where the differences end. This won't be your typical review - because this time we're pitting an Async IMFT flash unit against a Toshiba Toggle-mode flash unit:

icon.jpg

We're also tossing a few OCZ and Intel models into the mix. The OCZ Vertex 3 and Agility 3 will again share the same SandForce controller, but OCZ has been known to add many performance tweaks to their firmware. This will give us a chance to see the 'baseline' SandForce firmware in action.

Specifications

Patriot has their drive specs spread out over several pages. Here's a consolidated list for these two models. We will be reviewing a 120GB sample from each of the two product lines.

  • Wildfire 120GB:

-Sequential Read & Write Transfer: 555MB/s read | 520MB/s Write
-Max Random Write IOPS: Up to 85,000 (4K aligned)

  • Wildfire 240GB:

-Sequential Read & Write Transfer: 555MB/s read | 520MB/s Write
-Max Random Write IOPS: Up to 85,000 (4K aligned)

  • Wildfire 480GB:

-Sequential Read & Write Transfer: 540MB/S Read | 450MB/S Write*
-Max Random Write IOPS: Max 4K Random IOPS: 40K*

  • Pyro 60GB:

- Sequential Read & Write Transfer: 520MB/s read | 490MB/s Write.
- Max Random Write IOPS: Up to 80,000 (4K aligned).

  • Pyro 120GB:

- Sequential Read & Write Transfer: 550MB/s read | 515MB/s Write.
- Max Random Write IOPS: Up to 85,000 (4K aligned).

  • Pyro 240GB:

- Sequential Read & Write Transfer: 550MB/s read | 515MB/s Write.
- Max Random Write IOPS: Up to 85,000 (4K aligned).

I've highlighted a few outlier specs in the above list. While the Pyro sees the now expected dip in performance when transitioning from 120GB down to 60GB - due to a reduction in the communication channels to the (fewer) flash chips, the Wildfire sees a seemingly opposite and more drastic effect. This is not due to a change in the number of data paths - it's a limit inherent in the SandForce controller itself, and is not limited to Toggle-mode flash. The difference caused by the Toggle-mode flash is the missing 60GB model - caused by the intermix of capacity points and configuration needed for this different type of flash memory.

Read on for our full review!

Subject: Storage
Manufacturer: Various

Introduction

Back in 2006, storage tech talk was intermittently buzzy with a few different innovations. One was wrapped around the pending release of Windows Vista, particularly two bullets on its feature list: ReadyBoost and ReadyDrive. In parallel with all of the Ready_____ talk, many tech pundits asked why it would be necessary to have the flash talk to Windows through special drivers. Why couldn't the flash memory just act like a larger RAM cache already present on?

samsung.jpg

A prototype ReadyBoost-enabled HDD by Samsung.

The answer, which nobody was aware of at that time, was that management of flash memory was a tricky thing to do successfully. It would not be until several years later that SSD's would (mostly) beat the issues of Long Term Performance and other issues that crop up when attempting to store randomly written data onto a device that can only be erased in relatively large blocks.

ReadyDrive required a special 'Hybrid' disk drive to be connected to and recognized by Windows Vista, containing both spinning platters and flash memory. Vista would then place frequently used small files on the flash. Since flash memory has negligible access times when compared to seek times of a HDD, the drive overall would boot significantly faster. Other tasks using those cached system files also saw a benefit. While ReadyDrive looked great on paper, there were very few devices ever released that could take advantage of it. Seagate was the earliest to release such a drive, and their Momentus 5400 PSD laptop drive did not see the light of day until Vista was nearly a full year old.

Continue reading our roundup of the best hybrid storage solutions on the market today!!

Subject: Storage
Manufacturer: OCZ

Introduction, Specifications, and Packaging

Introduction

A few months back, OCZ acquired Indilinx. Ever since, we've been wondering if the next generation Indilinx offering could stand up to the competition, who has made leaps and bounds since the first generation SSD controllers were released.

111121-224609-11.jpg

 

Specifications

  • 128GB Max Performance
Max Read: up to 535MB/s
Max Write: up to 170MB/s
Random Write 4KB: 7,700 IOPS
Random Read 4KB: 37,000 IOPS
  • 256GB Max Performance
Max Read: up to 535MB/s
Max Write: up to 270MB/s
Random Write 4KB: 12,000 IOPS
Random Read 4KB: 37,000 IOPS
  • 512GB Max Performance
Max Read: up to 535MB/s
Max Write: up to 400MB/s
Random Write 4KB: 16,000 IOPS
Random Read 4KB: 37,000 IOPS
  • 1TB Max Performance
Max Read: up to 560MB/s
Max Write: up to 400MB/s
Random Write 4KB: 19,500 IOPS
Random Read 4KB: 45,000 IOPS
 
Yes, you read that right. 1TB - in a 2.5" form factor SSD! HDD's hit this mark not too long ago, and while a 1TB Octane will most certainly cost a pretty penny, there's something to be said for SSD's so rapidly catching up to HDD's for a given form factor.

 

block diagram pic.png

Here's a basic block diagram of the new Everest controller from Indilinx. All of the usual bits are present, of particular note being the ability to drive 8 channels, with each channel rated at 4-way. This should mean an Everest could theoretically drive 32 flash chips.

Continue reading our review of OCZ's new Octane Indilinx Everest 512GB SSD!

Subject: Storage
Manufacturer: OCZ Technology
Tagged: z-drive, ssd, r4, pcie, pci-e, ocz

Introduction

Introduction:

Back in June of last year, OCZ released the RevoDrive, followed up rather quickly by the RevoDrive x2. A further jump was made with the introduction of VCA 2.0 architecture with the RevoDrive 3 and 3 x2. Each iteration pushed the envelope further as better implementations of VCA were introduced, using faster and greater numbers of PCIe channels, linked to faster and greater numbers of SandForce controllers.

While the line of RevoDrives was tailored more towards power users and mild server use, OCZ has taken their VCA 2.0 solution to the next level entirely, putting their sights on full blown enterprise purposing. With that, we introduce the OCZ Z-Drive R4:

110911-140440-5.5.jpg

Continue to the full review for all the details!

Subject: Storage
Manufacturer: OCZ Technology
Tagged: ssd, PCIe SSD, pcie, ocz

Introduction

Introduction:

Back in June of last year, OCZ released the RevoDrive, followed up rather quickly by the RevoDrive x2. Both models represented a new way of economically bundling multiple SSD controllers behind an integrated RAID solution. This broke the mold for storage, as the vast majority of end users were stuck with the common 2.5" form factor SATA SSD (as well as trying to figure out where to put one inside their desktop case full of 3.5" drive bays). Since all desktops had PCIe slots, the Revo concept just seemed to make sense.

Now on the 1-year mark since the original Revo, we have the RevoDrive 3. OCZ has opted to skip the staggering of releases and is also releasing the 4-channel version, the RevoDrive 3 x2. Today we will be looking at the latter, in 480GB form factor. Here's a look at the new silicon:

110628-053039-7.31.jpg

110628-053023-15.24.jpg

Continue to the full review for all the details!

Subject: Storage
Manufacturer: OCZ Technology
Tagged: ssd, sata, sandforce, ocz, 6Gb

Introduction, Specifications, and Packaging

Introduction

Just over a month ago, OCZ released the Vertex 3, an immediate follow-up to the Vertex 3 Pro. At the time they promised an even cheaper solution at some point down the line. We've now seen that come to pass. Following the same convention as with the last series, the lower cost solution will be called the Agility 3. This is meant to be a mid-grade performance drive, as there is to also be a 'Solid 3' model on the horizon, but for today we'll focus on the new Agility.

Specifications

60GB Max Performance*

  • Max Read: up to 525MB/s
  • Max Write: up to 475MB/s
  • Random Write 4KB: 50,000 IOPS
  • Maximum 4K Random Write: 80,000 IOPS

120GB Max Performance*

  • Max Read: up to 525MB/s
  • Max Write: up to 500MB/s
  • Random Write 4KB: 50,000 IOPS
  • Maximum 4K Random Write: 85,000 IOPS

240GB Max Performance*

  • Max Read: up to 525MB/s
  • Max Write: up to 500MB/s
  • Random Write 4KB: 45,000 IOPS
  • Maximum 4K Random Write: 85,000 IOPS

    *Max performance achieved using Native SATA 6Gbps chipset. Please refer to product sheet for additional performance metrics.

Their * note is very important. You won't be able to hit the best possible performance marks without using these newest SATA 6Gb/sec drives in conjunction with native SATA 6Gb/sec storage controllers. There are just too many bottlenecks and other irregularities seen with the aftermarket / add-on solutions at this time, and they just can't stack up against a good native chipset implementation.

Subject: Storage
Manufacturer: Intel

Introduction

For the past few months, we've seen rumors upon rumors of a hybrid combination of the H67 and P67 chipsets into a 'Z' series. As the storage editor, I don't normally focus on a chipset update unless there is a corresponding increase in SATA bus speeds and/or ports available on the newer product.

This time things were different. While the Z series had the same SATA bandwidth specs as its older brothers, there was an extra feature that was rather huge in the storage world: Smart Response Technology.

Z68-blockdiagram.gif