The Seagate Enterprise Performance 10K HDD V.6 (formerly branded as the Savvio 10K.6) provides a new enterprise-class SAS 6Gb/s 10K HDD in a svelte 2.5" form factor with a 15mm Z-height. These slim HDD's pack a generous helping of capacity, with models weighing in at 300, 450, 600 and 900GB. The small form factor HDD segment is booming as decreases in size create a high performance tier deployable into dense applications.
High performance tiers of HDD's continue to serve a vital role in the datacenter, with the speedy SSD competition only accounting for 3% of datacenter storage in 2012. While the percentage of SSD's is forecasted to expand to 9.9% by 2016, this still leaves the HDD as the storage backbone of the datacenter with a whopping 90.1% share.
The high capacity HDD market also continues its rapid expansion, with the HDD industry shipping 53% more TB of capacity in 2012 compared to 2011. Creating a fast front-end for these vast arrays of HDD's requires a nimble high-performance tier that can also provide a robust amount of storage capacity.
The SAS Enterprise Performance V.6 delivers enhancements in speed, power consumption and encryption capabilities over the previous 10K.5 generation. The jump from a 168MB/s sustained transfer rate with the 10K.5 to 204MB/s for the Enterprise Performance V.6 equates to a 21% jump in performance. This places the sustained sequential transfer rates for the V.6 on equal footing with 2.5" 15K HDD's.
Another key selling point of the V.6 is its energy efficiency. The V.6 features a 14% decrease in power requirements in comparison to the Savvio 10K.5 HDD's. Even more impressive is the power consumption reduction of up to 71% in comparison to 15K-RPM 3.5" HDD's. The performance and power consumption gains are impressive, but the Seagate Enterprise Performance 10K HDD V.6 also brings other enterprise-class features to the table.
One ongoing concern for large HDD deployments is excessively long RAID rebuilds. The V.6 is the first mission-critical HDD to offer the Seagate RAID Rebuild technology option. The RAID Rebuild feature enables faster recovery from a failed drive in a RAID configuration. RAID Rebuild improves performance by extracting easily readable data from a failing drive by identifying blocks that would take longer to recover from the failed drive than to rebuild from parity data in the RAID array. This minimizes the likelihood of a second drive failure in the array during rebuild and allows host control of error recovery.
The V.6 drives also include self-encryption at no extra cost for all capacity points. For those with more intense requirements for data security, there is a 900GB V.6 that also provides the FIPS Self-Encrypting Drive option. A shocking 50,000 drives leave datacenters daily with terabytes of data intact. According to IBM, more than 90% of drives returned for warranty contain readable data. By providing FIPS 140-2 Level 2 compliance, Seagate gives customers an easy means of protecting data at rest.
Seagate's Instant Secure Erase reduces the time required to overwrite the drive from hours to less than a minute, speeding the process of repurposing or retirement of the drive. Protection Information (PI) technology provides an end-to-end data protection scheme that prevents data corruption from the application level down to the drive. The V.6 is backed up by a five year warranty.
Today we will compare the performance of the 10K V.6 against a leading 15K HDD, and the energy efficiency to a lower RPM 7,200 RPM model.
Enterprise Performance V.6 Specifications
The SAS interface onboard the Enterprise Performance 10K HDD V.6 (Savvio 10K.6) provides enterprise class features along with an enhanced instruction set that eases management of the drive. The drive comes in a 2.5" form factor with a 15mm Z-height.
The V.6 delivers sustained speeds of 204MB/s, an average latency of 2.9ms, and 64MB of segmented cache. The drive provides a prefetch (read look-ahead) and multi-segmented cache control algorithms that in many cases can enhance system performance. When the Prefetch feature is enabled, data in contiguous logical blocks on the disk immediately beyond that which was requested by a Read command are retrieved and stored in the buffer for immediate transfer from the buffer to the host on subsequent read commands that request those logical blocks.
T10-compliant Seagate PowerChoice technology enables users to tailor systems for optimal performance and power usage.
The V.6 implements a temperature warning system that signals the host if the temperature exceeds a value that would threaten the integrity of the drive. The V.6 also saves a S.M.A.R.T. data frame on the drive when it passes the threshold.
The 900 GB drive features three platters with six heads and an areal density of 538Gbit/sq. This is a jump from the 508Gbit/sq density offered from the previous generation 10K.5. The ECC maximum burst correction length is 530 bits, and the logical block sizes are user-configurable at 512, 520, 524, or 528 bytes per logical block.
The V.6 sports an AFR (Annualized Failure Rate) of 0.44%, an MTBF of 2,000,000 hours and a five year warranty. The rated MTBF is based upon a sustained case temperature of 122F (50C), and the maximum allowable drive case temperature is 140F (60C).
Enterprise Performance V.6 Internals
The Seagate Enterprise 10K HDD Performance V.6 comes in a standard 2.5" SFF with a 15mm Z-height. The components face into the body of the drive to facilitate heat transfer into the case, which acts as a large heatsink.
Removing the PCB reveals the drive controller and drive motor controller components with a thermal pad covering. We can observe the two metal squares on the bottom of the HDD case that transfer the heat from the thermal pads into the case of the HDD.
The Samsung chip is a 64MB DDR2 component for caching, a Smooth chip to control the drive motor, and a Marvell drive controller.
The Marvell I 1062-B0 213ACTE controller is responsible for managing the HDD.
The SAS 6Gb/s connection allows for a robust instruction set, dual port and failover technologies.
Test System and Methodology
We utilize a new approach to HDD and SSD storage testing for our Enterprise Test Bench, designed specifically to target 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 fall short in providing the clearest view possible of I/O QoS (Quality of Service).
'Average' results do little to indicate the 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 use histograms to illuminate the latency of every single I/O issued during our test runs.
We measure power consumption during test runs. This provides measurements in time-based fashion, with results every second, to illuminate the behavior of power consumption in steady state conditions. Power consumption can cost more over the life of the device than the initial acquisition price of the hardware itself. This significantly affects the TCO of the storage solution. We also present IOPS-to-Watts measurements to highlight the efficiency of the storage solution.
Our test pool features HDDs of varying speed and capacity, so it is important to bear this in mind when viewing results. We conduct our tests over the full LBA range to allow each HDD to highlight its top performance. In some cases, this approach can give slower speed, and higher capacity, HDDs a slight advantage in test results due to a longer 'dwell' time on outer tracks. Typically, this is not a concern when testing HDDs of similar speeds and capacities. However, today's product evaluation centers on exploration of HDD performance and scaling among varying HDD RPM performance. The first page of results will provide the 'key' to understanding and interpreting our new test methodology.
4K Random Read/Write
Each QD for every parameter tested includes 300 data points (five minutes of one second reports) to illustrate the degree of performance variability. The line for each QD 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 Seagate Enterprise Performance V.6 averages 414 IOPS at QD256, falling into the gap between the 15,000 RPM Toshiba and 7,200 RPM, as expected.
The 15,000 RPM Toshiba leads with random writing, though the Seagate V.6 falls within expectations at 368 IOPS at QD256.
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.
The Seagate V.6 follows a predictable curve as we mix in write activity, but does not lose much performance compared to the pure read workload.
The Seagate Enterprise Performance V.6 provides 81,584 I/O's (74.82%) at 80-100ms, 19,842 I/O's (18.18%) in the 60-80ms range, and 7,604 I/O's (6.97%) at 100-200ms.
We record the power consumption measurements during our test run at QD256. The Seagate V.6 matches the much higher RPM Toshiba 15K in power consumption at 6.16 Watts.
IOPS to Watts measurements are generated from data recorded during our test. The Seagate V.6 delivers an average of 59 IOPS per watt for 4K random writes, and 62 IOPS per Watt for 4K random read.
8K Random Read/Write
8K random read and write speed is a metric that is not tested for consumer use, but for enterprise environments this is an important aspect of performance. With several different workloads relying heavily upon 8K performance, we include this as a standard with each evaluation. Many of our Server Emulations below will also test 8K performance with various mixed read/write workloads.
The Seagate Enterprise Performance V.6 delivers an average of 426 IOPS at QD256, which is surprisingly close to the Toshiba MK01GRRB/R 15K. The MG03SDCA300 chugs along at a respectable 250 IOPS.
The average 8K random write speed of the Seagate V.6 is 363 IOPS at QD256.
The Seagate V.6 exhibits a traditional curve with slightly slower random write speed than random read speed.
The Seagate V.6 delivers 76.67% of I/O's (83,425) at 80-100ms, 18,163 I/O's (16.69%) at 60-80ms, and 7,218 I/O's (6.63%) at 60-80ms, 11.9% at 100-200ms.
Power consumption for the Seagate V.6 again matches the higher RPM Toshiba 15K at 6.56 Watts during the measurement window.
Though both HDDs pull the same power, the 15K HDD proves more efficient in the test. The Seagate V.6 still delivers solid performance with an average of 55 IOPS per Watt in 8K random write, and 62 IOPS for 8K random read.
128K Sequential Read/Write
The 128K sequential speeds reflect the maximum sequential throughput of the SSD using a realistic file size encountered in an enterprise scenario.
The Seagate Enterprise Performance V.6 averages 190 MB/s at sequential read, nearly matching the smaller capacity 15K Toshiba. The Toshiba MK01GRRB/R exhibits an apparently strange pattern to its I/O distribution, this results from working its way from the inner to the outer tracks during the measurement windows.
The Seagate V.6 averages the same impressive 190 MB/s in sequential write speed, very impressive when we note that it is nearly matching the 15K in read and write speed.
The Seagate V.6 dips lower in the mixed read/write testing than the 15K, and even lower than the 7,200 RPM Toshiba Mg03SDCA300 with a 10-20% write mixture, but performs well in the heavier write workloads.
The Seagate V.6 offers up 99.84% of requests in the 20-40ms range.
The V.6 averages 5.61 Watts during sequential write testing.
The Seagate V.6 provides 33 MB/s per Watt for 128AK sequential write and 33 MB/s for sequential read.
Database/OLTP and Webserver
This test emulates Database and On-Line Transaction Processing (OLTP) workloads. OLTP is in essence the processing of transactions such as credit cards and high frequency trading in the financial sector. Enterprise SSDs are uniquely well suited for the financial sector with their low latency and high random workload performance. Databases are the bread and butter of many enterprise deployments. These are demanding 8K random workloads with a 66% read and 33% write distribution that can bring even the highest performing solutions down to earth.
The Seagate V.6 averages 402 IOPS at QD256.
The Seagate V.6 offers up a wide range of access time, much like the other HDDs.
The Seagate V.6 again roughly matches the Toshiba 15K at our power measurements with 6.28 Watts.
The V.6 averages 63 IOPS per Watt.
The Webserver profile is a read-only test with a wide range of file sizes. Web servers are responsible for generating content for users to 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 that is hosting the website, and thus the end-user experience.
The Seagate Enterprise Performance V.6 averages 60 MB/s at QD256.
The V.6 nearly matches the Toshiba 15K in latency distribution during the test period.
The V.6 averages 6.38 Watts.
The Seagate V.6 averages 60 IOPS per Watt.
Fileserver and Emailserver
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 Seagate V.6 averages 406 IOPS at QD256.
The Seagate V.6 again runs neck and neck with latency performance in comparison to the 15K Toshiba.
The V.6 averages 6.56 Watts.
The V.6 averages 61 IOPS per Watt.
The Emailserver profile is a very demanding 8K test with a 50% read and 50% write distribution. This application is indicative of the performance of the solution in heavy write workloads.
The Seagate V.6 averages 387 IOPS at QD256.
The Seagate Enterprise Performance V.6 offers a wide spread of latency, but falls to the 15K Toshiba in this test.
The Seagate V.6 averages 6.1 Watts.
The V.6 averages 61 IOPS per Watt.
In 2012, Seagate was the second largest storage company in the world, second only to EMC. This places Seagate at the top of the market for HDD manufacturers. With the tremendous manufacturing output of more than half a million drives per day, it is easy to understand how they have risen to the top of the market. Seagate manufactures eight HDDs per second, 24 hours a day, seven days a week. This equals 28,519 HDD's an hour, and 684,462 HDD's per day.
The Seagate Enterprise Performance V.6 (formerly known as the Savvio 10K.6) is a solid performer from Seagate that leverages enhanced technology to deliver great performance. In our sequential tests, the V.6 nearly matched a 2.5" 15,000-RPM competitor. This is a great level of performance from the V.6 and a testament to the continuing innovation from Seagate.
Keeping up with the data explosion by increasing capacity has become the norm, the average capacity per drive shipped for enterprise applications has increased by 31% between 2011 and 2012, while areal density only rose by 15%. This equates to the majority of density increases coming from more platters and heads, adding speed, but also in many ways adding complexity.
Seagate chose to stay at the 900GB max capacity, instead relying upon other improvements to speed up the performance of the Enterprise Performance V.6. Increasing the performance of a 10K HDD is no small task when keeping the same amount of platters like the V.6 and only adding 5% more areal density.
A 21 percent sequential performance improvement over the previous generation models places the V.6 within striking distance of 3.5" 15K RPM HDDs, shows the fruits of Seagate's labors. Impressive power consumption figures allow the V.6 to deliver a 55% decrease in operational power when compared to 3.5" 15K HDDs.
The Seagate V.6 also offers a SAS connection for enterprise-class connectivity and a host of features that increase the functionality of the HDD over the previous generation. The Enterprise Performance V.6 is the first HDD to offer the Seagate RAID Rebuild feature, which significantly increases RAID rebuild rates.
Security is an ongoing concern for customers, and the V.6 offers Seagate Instant Secure Erase for drive erasures in less than a minute. The inclusion of encryption as a standard for all capacity points, and the option for FIPS for the 900 GB versions, rounds out the security options. Protection Information (PI) technology provides an end-to-end data protection scheme that prevents data corruption from the application level down to the drive, and the T-10 compliant Power Choice technology allows users to tailor systems for optimal performance and power usage.
Finally, the V.6 is covered by a five year warranty. The Seagate Enterprise Performance V.6 performed well in our tests, and excelled in sequential workloads, earning it the TweakTown Best Performance Award.