Toshiba offers a refined 12Gb/s product stack with a flavor for every taste. The Toshiba PX02SS offers unmatched endurance in the 12Gb/s segment, while the Toshiba PX02SM provides solid endurance and serves as the mixed-use model for mainstream applications. The PX03SN steps in to provide amazing 12Gb/s performance at a much lower price point. The two heavier-use Toshiba SSDs utilize 24nm eMLC to provide robust endurance, but the PX03SN switches to 19nm consumer-grade MLC to provide a friendlier price point. Pairing the 19nm with the same design and controller as the leading Toshiba SSDs provides blistering performance in a more economical package.
The PX03SM comes in the familiar 2.5-inch form factor, and most notably features a 12Gb/s SAS3 connection. One of the greatest aspects of the PX03SN line is found in the capacity listing. The PX03SN is available in 200, 400, and 800GB capacities in the 7mm form factor, but a whopping 1.6TB version is available in 15mm. This tremendous capacity outstrips all HDDs in the 2.5-inch form factor and provides enhanced density for small servers. Performance density is also important, and the PX03SN brings outstanding performance in a small package.
The PX03SN features 130,000/26,000 random read/write IOPS. Random speed is matched by an impressive 1,100 MiB/s in sequential read, but only 380 MiB/s of sequential write speed. The PX03SN is designed for light-duty storage and read-caching applications that are not overly dependent upon sequential write performance. These read-centric applications tend to rely more upon serving relatively static data repositories at a high rate of speed. The PX03SN also features up to 63,000 IOPS in random workloads with a 70/30 read/write distribution.
Bringing High-Availability features to a read-centric SSD is impressive. The 12Gb/s dual-port SAS provides multipath and failover capabilities, and Toshiba leverages its proprietary Quadruple Swing by Code, a layered ECC system, to provide protection for user data. Another nice inclusion on a value SSD is the power capacitors that flush data to the NAND in the event of host power loss. Toshiba covers the bases for data security compliance with available security models and support for SANITIZE instant secure erase.
For those requiring high endurance, the Toshiba series offers the PX02SM and PX02SS. The PX03SM only offers 1 Drive Write Per Day (DWPD) of endurance. Endurance measurements are measured under worst-case scenarios. The drive is filled to capacity, which significantly reduces endurance, and endurance-killing pure small-block random data is used for testing. With sequential or mixed-workloads, the endurance will likely be incrementally higher, and any spare area increases endurance. Many users manually appropriate extra spare area to boost endurance to accommodate heavier workloads. The lower price associated with MLC provides users a bit more room for endurance optimization.
Read-centric SSDs provide amazing acceleration in read-only caching applications. Server-side caching implementations boost performance of underlying disk storage in SAN/NAS and DAS environments. By only caching read data, lower-endurance SSDs deal with relatively static data sets but deliver big results. The higher capacity versions, such as the 1.6TB PX03SN, allow for plenty of dynamic adjustment of cached data if the dataset changes frequently.
The Toshiba PX03SN offers the standard five-year warranty available with most enterprise SSD products. The read-centric 12Gb/s SSD market is relatively limited as 12Gb/s makes its way into the datacenter. With no other read-centric 12Gb/s SSDs available for testing, we will compare the PX03SN to its higher-endurance brethren.
Toshiba PX02SS Internals and Specifications
Toshiba PX02SS Internals
The 800GB model features a slim 7mm z-height. The case is constructed of a lightweight metal alloy and features the relevant branding. The top of the case also holds a recessed series of indentations that function as heat channels. The rear of the case has a metal recessed area, and we note a square hole, and several round ones, on the bottom of the SSD that allow airflow into interior of the case.
The PCB is secured to the case via four fasteners. The purpose of the heat channels becomes clear when we open the case of the SSD. There are small thermal pads that mate with the NAND and DRAM to wick heat away from these components. The pads are present on both sides of the case. Four small thermal pads mate with the top of the controller, and another four connect to the PCB on the rear of the controller. We usually observe large thick thermal pads that cover entire banks of NAND in many enterprise SSDs. In this type of open-case design, large pads could impede internal airflow.
There is an SK Hynix DRAM module on both sides of the PCB. The large controller dominates the middle of the PCB. There are 16 Toshiba 19nm MLC NAND packages on the PCB.
Several rows of capacitors provide enough capacitance to flush data to the NAND in the event of host power loss.
The Marvell TC58NC9036GTC controller utilizes custom firmware. The Toshiba/Marvell co-branded controller is utilized on all 12Gb/s SSDs in the Toshiba line.
Toshiba PX02SS Specifications
Power loss protection is built-in with a bank of tantalum capacitors to flush data in-transit down to the NAND in the event of a power failure. The PX03SN features a two-million-hour MTTF. The energy efficiency is 24,400 IOPS-per-Watt for the 800GB model, though this is measured as read IOPS-per-Watt. The PX03SN features 1 DWPD of endurance. There are also self-encrypting versions supporting SANITIZE Instant erase available, with a notable 190 MiB/s decrease in sequential read speed.
Test System and Methodology
Our approach to storage testing targets long-term performance with a high level of granularity. Many testing methods record peak and average measurements during the test period. These average values give a basic understanding of performance, but they fall short in providing the clearest view possible of I/O Quality of Service (QoS).
'Average' results do little to indicate performance variability experienced during actual deployment. The degree of variability is especially pertinent as many applications can hang or lag as they wait for I/O requests to complete. This testing methodology illustrates performance variability, and includes average measurements, during the measurement window.
While under load, all storage solutions deliver variable levels of performance. While this fluctuation is normal, the degree of variability is what separates enterprise storage solutions from typical client-side hardware. Providing ongoing measurements from our workloads with one-second reporting intervals illustrates product differentiation in relation to I/O QoS. Scatter charts give readers a basic understanding of I/O latency distribution without directly observing numerous graphs.
Consistent latency is the goal of every storage solution, and measurements such as Maximum Latency only illuminate the single longest I/O received during testing. This can be misleading as a single 'outlying I/O' can skew the view of an otherwise superb solution. Standard Deviation measurements consider latency distribution, but do not always effectively illustrate I/O distribution with enough granularity to provide a clear picture of system performance. We utilize high-granularity I/O latency charts to illuminate performance during our test runs.
Our testing regimen follows SNIA principles to ensure consistent, repeatable testing. We measure power consumption during precondition runs. This provides measurements in time-based fashion, with results every second, to illuminate the behavior of power consumption in steady state conditions. We also present IOPS-to-Watts measurements to highlight efficiency.
The first page of results will provide the 'key' to understanding and interpreting our test methodology.
4k Random Read/Write
We precondition the 800GB Toshiba PX03SNF080 for 9,000 seconds, or two and a half hours, receiving performance reports every second. We plot this data to illustrate the drive's descent into steady state.
This dual-axis chart consists of 18,000 data points, with the IOPS on the left and the latency on the right. The green dots signify IOPS, and the grey dots are latency measurements during the test. We place latency data in a logarithmic scale to bring it into comparison range. The lines through the data scatter are the average during the test. This type of testing presents standard deviation and maximum/minimum I/O in a visual manner.
Note that the IOPS and latency figures are nearly mirror images of each other. This illustrates that high-granularity testing can give our readers a good feel for latency distribution by viewing IOPS at one-second intervals. This should be in mind when viewing our test results below. This downward slope of performance only occurs during the first few hours of use, and we present precondition results only to confirm steady state convergence.
Each level tested includes 300 data points (five minutes of one second reports) to illustrate performance variability. The line for each OIO depth represents the average speed reported during the five-minute interval. 4k random speed measurements are an important metric when comparing drive performance as the hardest type of file access for any storage solution to master is small-file random. One of the most sought-after performance specifications, 4k random performance is a heavily marketed figure.
The Toshiba PX03SN follows the typical pattern of the other Toshiba 12Gb/s SSDs, and peaks at an outstanding 134,855 IOPS at 32 OIO. At 256 OIO, it delivers 117,073 IOPS. The PX02SS averages 117,289 IOPS at 256 OIO, but its peak is at 32 OIO, where it delivers an outstanding 133,871 IOPS. The Toshiba PX02SM averages an impressive 124,550 IOPS.
All three SSDs reach the optimum performance to latency ratio at 32 OIO.
Garbage collection routines are more pronounced in heavy write workloads, leading to performance variability.
The PX03SN brings along a nice surprise with a very clearly defined consistent performance envelope in 4k write testing, averaging 28,443 IOPS at 256 OIO. The PX02SS provides 45,786 IOPS at 256 OIO, and the PX02SM offers 28,602 IOPS.
The improved latency performance from the PX03SN is clear at 256 OIO, where it surprisingly offers better consistency than its eMLC PX02SM counterpart.
Our write percentage testing illustrates the varying performance of each solution with mixed workloads. The 100% column to the right is a pure write workload of the 4k file size, and 0% represents a pure 4k read workload. Mixed workload testing reveals strengths, and weaknesses, that remain hidden during typical tests. In reality, much of the real-world data is going to feature mixed data.
We get a clearer picture of the consistency improvement as the workload begins to add more write activity. The improved consistency is encouraging considering the move from 24nm eMLC with the Px02SM to the 19nm MLC on the PX03SN.
We record the power consumption measurements during our precondition run. We calculate the stated average results during the last five minutes of the test, after the device has settled into steady state.
The PX03SN averages 5.28 watts.
IOPS-to-Watts measurements are generated from data recorded during our precondition run, and the stated average is from the last five minutes of the test.
The Toshiba PX03SN averages 5,184 IOPS-per-Watt. It is important to note the IOPS-per-Watt set forth in the specifications of both drives is with read activity. We measure IOPS-per-Watt with write activity.
8k Random Read/Write
Server workloads rely heavily upon 8k performance, and we include this as a standard with each evaluation. Many of our server workloads also test 8k performance with various mixed read/write workloads.
The average 8k random read speed of the Toshiba PX03SN averages 99,802 IOPS; the PX02SS measures an outstanding 100,277 IOPS at 256 OIO, while the Toshiba PX02SM takes the low road with 88,549 IOPS. Once again, we note improved performance with the 19nm MLC NAND.
All three SSDs exhibit a tight latency range during the 8k random read test.
The PX03SN averages 14,968 IOPS, and the PX02SS averages 29,714 IOPS at 256 OIO. The PX02SM averages 16,391 IOPS at 256 OIO.
The PX03SN and the PX02SM experience performance variability at 256 OIO.
The PX03SN bests the eMLC PX02SM with read activity, but matches it as we add in more write activity.
Power consumption for the PX03SN averages 5.55 watts during the measurement window, lower than the high endurance models.
The PX03SN trails during the efficiency test with an average of 2,660 IOPS-per-Watt. The MLC doesn't seem to be nearly as efficient during heavy write workloads.
128k Sequential Read/Write
128k sequential speed reflects the maximum sequential throughput of the SSD.
The Toshiba PX03SN averages 890 MB/s; the PX02SS averages 1,040 MB/s, and the PX02SM averages 812 MB/s.
Latency measurements indicate solid latency during sequential read activity for all three SSDs.
The PX03SN averages 392 MB/s, and the Toshiba PX02SS and PX02SM score slightly over their rated speed at 417 MB/s.
The Toshiba PX03SN and PX02SM suffer variability during heavy mixed sequential workloads. The Toshiba SSDs aren't geared for high sequential write activity, so these results are within expectations.
The PX03SN averages 5.71 watts, well below the eMLC SSDs.
The PX03SN averages 68 MB/s-per-Watt.
Database/OLTP and File Server
This test emulates Database and On-Line Transaction Processing (OLTP) workloads. OLTP is the processing of transactions such as credit cards and high frequency trading in the financial sector. Databases are the bread and butter of many enterprise deployments. These demanding 8k random workloads with a 66% read and 33% write distribution bring even the best solutions down to earth.
The Toshiba PX03SN averages 43,118 IOPS; the PX02SS averages 60,240 IOPS at 256 OIO, and the PX02SM averages 43,127 IOPS. The PX03SN makes great strides in performance consistency over the PX02SM.
The scale of the consistency improvement is obvious at 256 OIO. The PX03SN has no commands above 14ms.
The PX03SN averages 6 watts.
The PX03SN averages 7,050 IOPS-per-Watt.
The File Server profile represents typical file server workloads. This profile tests a wide variety of different file sizes simultaneously, with an 80% read and 20% write distribution.
The PX03SN averages 40,412 IOPS; the PX02SS averages 55,288 IOPS, and the PX02SM delivers 42,653 IOPS at 256 OIO.
The PX03SN experiences some variability during this test.
The PX03SN requires 5.67 watts during the file server workload.
The Toshiba PX03SN delivers 6,636 IOPS-per-Watt.
Email Server & Web Server
The email server profile is a demanding 8k test with a 50% read and 50% write distribution. This application is indicative of the performance in heavy write workloads.
The PX03SN averages 28,962 IOPS; the PX02SS averages 51,119 IOPS at 256 OIO, and the PX02SM averages 30,572 IOPS.
The PX03SN averages 5.86 watts in steady state.
The PX03SN provides 4,929 IOPS-per-Watt.
The Web Server profile is a read-only test with a wide range of file sizes. Web servers are responsible for generating content users view over the Internet, much like the very page you are reading. The speed of the underlying storage system has a massive impact on the speed and responsiveness of the server hosting the website.
The PX03SN averages a monster 43,050 IOPS at 256 OIO; the PX02SS averages 41,886 IOPS, and the PX02SM takes the backseat with an average of 31,517 IOPS.
The PX03SN averages 5.46 watts.
The PX03SN averages 1,414 IOPS-per-Watt.
The PX03SN engages a rapidly growing customer base in the datacenter. Caching and tiering applications are by far the most common SSD use-case in the datacenter. Explosive acceleration of existing infrastructure is always an attractive option, leading to better CPU utilization and enhanced application performance. Server-side caching and tiering models provide the best of both world's. The high performance from SSDs boost application performance, and the tremendous capacity of HDDs provide enough room for the ever-growing amount of data.
Read-intensive applications and read-caching/tiering models do not always require bulletproof endurance, especially if they are dealing with relatively static datasets. This allows the use of value-based alternatives, but in many cases, those alternatives can skimp in areas that leave administrators open to catastrophic events. Installing consumer-grade SSDs without power loss protection features opens the door for data loss in mission-critical environments. Lower-tier SATA SSDs also lack enhanced High-Availability features provided by the dual-port 12Gb/s SAS connection on the PX03SN.
The enhanced random-read performance from 12Gb/s SSDs can also boost existing 6Gb/s SAS infrastructure. There isn't a 6Gb/s SAS SSD that can push the tremendous random read performance of the PX03SN. The integration of 12Gb/s SAS into server motherboards isn't entirely complete, but the transition has already started. The PX03SN can be connected directly to 12Gb/s-capable motherboards for an easy performance boost without populating another PCIe slot with an HBA or RAID controller.
The wisdom of integrating 19nm MLC into the existing Toshiba 12Gb/s platform was clear during testing. The same controller utilized with higher-endurance 24nm eMLC models wrung impressive performance from 19nm MLC. Delivering 134,000 4k random read IOPS is fantastic on any platform, and the terrific random read speed from the PX03SN is a definite bright spot. In our 8k read testing, the PX03SN blew past the PX02SM. In our web server workload, the PX03SN even provided more performance than the top-of-the-pyramid PX02SS. This highlights the advantages of Toshiba's tuning for read-centric workloads.
In our testing, we also noted improved consistency in mixed random workloads over the PX02SM, and much tighter performance in heavy-write workloads. The PX03SN supplied incrementally lower sequential write performance than the high-endurance SSDs, but sequential read speed was surprisingly robust, even outperforming the PX02SM by a healthy margin. The PX03SN suffered a notable reduction in IOPS-to-Watts performance, but it is important to specify these measurements were taken with write activity. The PX03SN is designed specifically for read-intensive workloads, where it is ranked at 24,400 IOPS-per-Watt, matching the PX02SS and above the PX02SM.
The PX03SN delivers tremendous performance in an economic package. The marriage of mission-critical features, such as High-Availability and power loss protection, with a lower price point provides significant value. The endurance trade-off does not show in performance, and the PX03SN blew away our expectations for a value-based SSD, winning the TweakTown Best Value Award for the 12Gb/s segment.
PRICING: You can find products similar to this one for sale below.
United States: Find other tech and computer products like this over at Amazon.com
United Kingdom: Find other tech and computer products like this over at Amazon.co.uk
Australia: Find other tech and computer products like this over at Amazon.com.au
Canada: Find other tech and computer products like this over at Amazon.ca
Deutschland: Finde andere Technik- und Computerprodukte wie dieses auf Amazon.de