discussion G.Skill Phoenix Blade 480GB PCI-E SSD Review

[SKYMTL]

Workstation - ATTO Disk Benchmark

Workstation - ATTO Disk Benchmark

<i>The ATTO disk benchmark tests the drives read and write speeds using gradually larger size files. For these tests, the ATTO program was set to run from its smallest to largest value (.5KB to 8192KB) and the total length was set to 256MB. The test program then spits out an extrapolated performance figure in megabytes per second. </i>

<div align="center"><img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/atto_r.jpg" border="0" alt="" />
<img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/atto_w.jpg" border="0" alt="" /></div>

ATTO has always 'enhanced' the SandForce SF2281's abilities, but even if some of this performance is artificial and unlikely to be encountered in real-world scenarios the G.Skill Phoenix Blade 480GB still posts some very impressive numbers. In fact, the performance of this drive is slightly better than the RevoDrive 350 and it handily beats solutions that cost thousands (yes, thousands) more.

 

[SKYMTL]

Workstation - Crystal DiskMark / AS-SSD

Workstation - Crystal DiskMark

<i>Crystal DiskMark is designed to quickly test the performance of your drives. Currently, the program allows to measure sequential and random read/write speeds; and allows you to set the number of tests iterations to run. We left the number of tests at 5 and size at 100MB. </i>

<div align="center">
<img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/cdm_r.jpg" border="0" alt="" />
<img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/cdm_w.jpg" border="0" alt="" /></div>

Workstation - AS-SSD

<i>AS-SSD is designed to quickly test the performance of your drives. Currently, the program allows to measure sequential and small 4K read/write speeds as well as 4K file speed at a queue depth of 6. While its primary goal is to accurately test Solid State Drives, it does equally well on all storage mediums it just takes longer to run each test as each test reads or writes 1GB of data.</i>
<div align="center">
<img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/asd_r.jpg" border="0" alt="" />

<img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/asd_w.jpg" border="0" alt="" />
</div>

As expected the performance of this older generation PCI-E model varies from very good to good. As with all SandForce based devices the type of data (compressible vs incompressible) will play a keep role in determining how fast performance really is. Of course, newer designs not only outperform the Phoenix Blade but do so without as much CPU over-head and with fewer controllers. They are however significantly more expensive, especially the Intel enterprise drives we are using in this comparison.

 

[SKYMTL]

Workstation - Server Tests; File, Email & Web

IOMETER: Our Standard Test

<i>IOMeter is heavily weighted towards the server end of things, and since we here at HWC are more End User centric we will be setting and judging the results of IOMeter a little bit differently than most. To test each drive we ran 5 test runs per device (1,4,16,64,128 queue depth) each test having 8 parts, each part lasting 10 min w/ an additional 20 second ramp up. The 8 subparts were set to run 100% random, 80% read 20% write; testing 512b, 1k, 2k,4k,8k,16k,32k,64k size chunks of data. When each test is finished IOMeter spits out a report, in that reports each of the 8 subtests are given a score in I/Os per second. We then take these 8 numbers add them together and divide by 8. This gives us an average score for that particular queue depth that is heavily weighted for single user environments and workstation environments.</i>

<div align="center"><img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/iom.jpg" border="0" alt="" />
</div>

IOMETER: File Server Test

<i>To test each drive we ran 6 test runs per device (1,4,16,64,128,256 queue depth) each test having 8 parts, each part lasting 10 min w/ an additional 20 second ramp up. The 6 subparts were set to run 100% random, 75% read 25% write; testing 512b, 4k,8k,16k,32k,64k size chunks of data. When each test is finished IOMeter spits out a report, in that reports each of the 6 subtests are given a score in I/Os per second. We then take these 8 numbers add them together and divide by 6. This gives us an average score for that particular queue depth that is heavily weighted for file server usage.</i>

<div align="center"><img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/iom_f.jpg" border="0" alt="" /></div>

IOMETER: Web Server Test

<i>The goal of our IOMeter Web Server configuration is to help reproduce a typical heavily accessed web server. The majority of the typical web server’s workload consists of dealing with random small file size read requests.

To replicate such an environment we ran 6 test runs per device (1,4,16,64,128,256 queue depth) each test having 8 parts, each part lasting 10 min w/ an additional 20 second ramp up. The 8 subparts were set to run 100% random, 95% read 5% write; testing 512b, 1k, 2k,4k,8k,16k,32k,64k size chunks of data. When each test is finished IOMeter spits out a report, in that reports each of the 8 subtests are given a score in I/Os per second. We then take these 8 numbers add them together and divide by 8. This gives us an average score for that particular queue depth that is heavily weighted for web server environments. </i>

<div align="center"><img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/iom_w.jpg" border="0" alt="" /></div>

IOMETER: Email Server Test

<i>The goal of our IOMeter Email Server configuration is to help reproduce a typical corporate email server. Unlike most servers, the typical email server’s workload is split evenly between random small file size read and write requests.

To replicate such an environment we ran 5 test runs per drive (1,4,16,64,128 queue depth) each test having 3 parts, each part lasting 10 min w/ an additional 20 second ramp up. The 3 subparts were set to run 100% random, 50% read 50% write; testing 2k,4k,8k, size chunks of data. When each test is finished IOMeter spits out a report, in that reports each of the subtests are given a score in I/Os per second. We then take these numbers add them together and divide by 3. This gives us an average score for that particular queue depth that is heavily weighted for email server environments. </i>

<div align="center"><img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/iom_e.jpg" border="0" alt="" /></div>

As you can see the performance curve of this drive does put to bed any ideas of it being able to compete against more modern designs in a server environment. Yes it may be the best performing SandForce based SSD we have tested, but the days of SandForce being classified as a premier controller are now past. Put simply even the now discontinued Intel 910 series outshines it and modern designs simply are in a different league. The only real claim to fame this model can offer is it can provide decent levels of performance here without either breaking the bank, or taking up four SATA ports to do it.

The main concern here is the file server test which can easily replicate a rendering station environment where large amounts of data are being accessed all the time. G.Skill champions the Blade's performance in these situations but it does tend to fall by the wayside and doesn't offer up any more perceptible performance than OCZ's RevoDrive.

 

[SKYMTL]

Workstation - Long Term Steady State Testing

Steady State Testing

While optimum condition performance is important, knowing exactly how a given device will perform after days, weeks and even months of usage is actually more important for most consumers. For home user and enthusiast consumers our Non-Trim performance test is more than good enough. Sadly it is not up to par for enterprise or workstation SSDs and these most demanding of consumers.

Enterprise administrators are more concerned with the realistic long term performance of any device rather than the brand new performance as down time for TCL is simply not an option. Even though an enterprise / workstation device will have many techniques for obfuscating and alleviating a degraded state (eg Idle Time Garbage Collection, multiple controllers, etc) there does come a point where these techniques fail to counteract the negative results of long term usage in an obviously non-TRIM environment. The point at which the performance falls and then plateaus at a lower performance level is known as the “steady state” performance or as “degraded state” in the consumer arena.

To help all consumer gain a better understanding of how much performance degradation there is between “optimal” and “steady state” we have included not only optimal results but have rerun tests after first degrading a drive until it plateaus and reaches its steady state performance level. These tests are labelled as “Steady State” results and can be considered as such.

While the standard for steady state testing is actually 8 hours we feel this is not quiet pessimistic enough and have extended the pre-test run to a full ten hours before testing actually commences. The pre-test or “torture test” consists of our standard “NonTrim performance test” and as such to quickly induce a steady state we ran ten hours of IOMeter set to 100% random, 100% write, 4k size chunks of data at a 64 queue depth across the entire array’s capacity. At the end of this test, the IOMeter file is deleted and the device was then tested using a given test sections’ unique configuration.

IOMETER: Our Standard Steady State Test

​

IOMETER: File Server Steady State Test

​

IOMETER: Web Server Steady State Test

​

IOMETER: Email Server Steady State Test

​

These results simply underscore why the industry has moved away from using SandForce drives in RAID 0 configurations. Put simply, the way in which SandForce handles data makes for a less than optimal long term storage solution. This has always been the weakness of SandForce's SF22xx series and one that cannot be obfuscated by better RAID controllers or firmware. Most workstation users would be better served with multiple SATA based drives that rely upon Marvel, Intel, Indilinx, Samsung or other more modern controllers. Unfortunately, in these situations the Blade's performance drops off a cliff.

 

[SKYMTL]

Workstation - Steady State Application Load Times

Adobe CS5 Steady State Load Time

<i>Photoshop is a notoriously slow loading program under the best of circumstances, and while the latest version is actually pretty decent, when you add in a bunch of extra brushes and the such you get a really great torture test which can bring even the best of the best to their knees. To make things even more difficult we have first placed the devices into a steady state so as to help recreate the absolute worst case scenario possible. </i>

<div align="center"><img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/adobe.jpg" border="0" alt="" /></div>

Firefox Portable Offline Steady State Performance

<i>Firefox is notorious for being slow on loading tabs in offline mode once the number of pages to be opened grows larger than a dozen or so. We can think of fewer worse case scenarios than having 100 tabs set to reload in offline mode upon Firefox startup, but this is exactly what we have done here.

By having 100 pages open in Firefox portable, setting Firefox to reload the last session upon next session start and then setting it to offline mode, we are able to easily recreate a worse case scenario. Since we are using Firefox portable all files are easily positioned in one location, making it simple to repeat the test as necessary. In order to ensure repetition, before touching the Firefox portable files, we have backed them up into a .rar file and only extracted a copy of it to the test device.

As with the Adobe test, we have first placed the devices into a steady state.</i>

<div align="center"><img src="http://images.hardwarecanucks.com/image/akg/Storage/Phoenix Blade/ff.jpg" border="0" alt="" />
</div>

In non-workstation orientated tasks there is no denying the power of this drive. Unfortunately, the CPU overhead and cost of this drive will place it outside the reach of most home consumers. Workstation users on the other hand will appreciate its capabilities in this respect but there are still some lingering questions about long term data access performance as we saw in the previous pages.

 

[SKYMTL]

Workstation - Real World Data Transfers

Real World Data Transfers

No matter how good a synthetic benchmark like IOMeter or PCMark is, it can not really tell you how the device will perform in “real world” situations. All of us here at Hardware Canucks strive to give you the best, most complete picture of a review item’s true capabilities and to this end we will be running timed data transfers to give you a general idea of how its performance relates to real life use. To help replicate worse case scenarios we will transfer a 10.00GB contiguous file and a folder containing 400 subfolders with a total 12,000 files varying in length from 200mb to 100kb (10.00 GB total).

Testing will include transfer to and transferring from the devices, using MS RichCopy and logging the performance of the drive.

Here is what we found.

Once again, this drive would make a very decent game or time sensitive storage device and even in a workstation environment it seems to offer up decent file transfer capabilities.

 

[SKYMTL]

Conclusion

Conclusion

G.Skill’s Phoenix Blade represents a big step forward for a company that decided to temporarily exit the SSD market altogether. It is obscenely fast and extremely expensive but its value quotient is surprisingly high when the competition is factored into the equation. However, while G.Skill is trying to market the Blade with a dual home use and workstation environment slant but it is really only well suited for enthusiasts.

What G.Skill has accomplished on the performance front is quite incredible. The Phoenix Blade 480GB is able to beat the OCZ RevoDrive 350 in every benchmark and sometimes by a pretty wide margin as well. That goes for home and workstation tasks alike. In comparison to other options it delivers staggering numbers while providing an excellent value quotient against both multiple SSDs in RAID and PCI-E based alternatives like the Revo.

What will appeal to workstation users is the Phoenix Blade’s impressive 1.68 petabytes of NAND endurance which more than triples what’s offered on OCZ’s comparable RevoDrive 350 480GB. Naturally it can’t touch Intel’s higher end workstation drives in this department but it isn’t meant to. As an blazingly fast PCI-E SSD which bridges the gap between high end desktop SSDs and their professional counterparts, it does a good job.

Despite very good longevity numbers, the Blade falls flat in the workstation space since its long term performance nosedives off a cliff as time goes on. Our Stable State testing showed it barely able to keep up with the RevoDrive in this respect. While most workstation SSDs are designed from the ground up for bandwidth stability over time, G.Skill has obviously engineered their PCI-E model with an eye towards home users even though it is marketed towards rendering stations as well. Truth be told, the Phoenix Blade may initially be a good choice for this segment but over time it would quickly lose its ability to keep up with the competition in prolonged, heavy I/O situations.

There are also a number of concerns regarding some other elements of G.Skill’s design. Compatibility will be a major challenge for the Phoenix Blade since in requires eight PCI-E lanes, something that is only available on higher end PLX-equipped Z97 boards (or you’ll need to install it into the secondary PCI-E 3.0 slot which will reduce available GPU bus bandwidth by half), their X99-series siblings, upper echelon workstation boards or AMD’s 990FX.

Another area of concern is how the Blade will stand up over the next few months. Many of its direct competitors were launched in the first quarter of 2014 while G.Skill waited until November to launch their flagship and it was only available in early December. Given how quickly native PCI-E storage solutions like SATA Express and NVMe will be rolled out in the coming year, the Phoenix Blade’s relatively late release date may cause it to be quickly surpassed by faster, less expensive alternatives that use more adaptable form factors.

The G.Skill Phoenix Blade is currently one of the fastest drives available in the home use market despite beating much of the competition’s price points. While we wouldn’t recommend it for long term workstation use, its endurance specifications make it an appealing choice for enthusiasts who are looking for awesome performance coupled with peace of mind.