The march to provide more density is never-ending, and over the last 60 years of HDD development, we have witnessed a 500 million-fold increase in areal density. This push for more density has also spawned smaller drives for the performance segment. The datacenter is trending away from legacy 3.5" 15K HDDs, which manufacturers are phasing out, to new 2.5" models. 2.5" models provide more capacity and performance density, and feature a 70% reduction in power consumption compared to their larger 3.5" brethren.
SSDs are encroaching upon the performance HDD segment, but in relative terms, the 10K and 15K segment are still doing well. IDC projects that in 2016 the performance HDD TAM (total available market) will still be double that of enterprise SSDs. Seagate is also expanding their performance segment by incorporating Turbo SSHD models into the Enterprise Performance 15K v5 lineup. These hybrid models provide seamless flash-based workload acceleration without any user configuration or management. We recently took an in-depth look at the Seagate Turbo SSHD here, and the inclusion of a 32GB layer of eMLC NAND cache delivers incredible performance benefits. We tested the inaugural version of the Turbo SSHD, and we will be posting an evaluation of the new 15K v5 SSHD shortly.
The standard Seagate Enterprise Performance 15K v5 brings 146, 300, and 600GB capacities to the slim 2.5" design, and employs a dual-port 12Gb/s SAS interface. The step up to 12Gb/s SAS enables compatibility with the latest HBA and RAID controller designs, and also provides multipath and failover capability. The Enterprise Performance 15K v5 features a 128MB data buffer that supports prefetch (read-ahead) and multi-segmented cache control algorithms. The 15K v5 features an average seek latency of 2.0 ms, and a sustained transfer rate of 180 to 246 MB/s (inner to outer).
15k SAS HDDs are designed for mission critical environments and reliability is a top priority. Seagate's 15K v5 offers a 2 million hour MTBF, a nonrecoverable read-error-per-bits-read rating of 1 per 10^16, and a five-year warranty period. The 15k v5 also employs a humidity sensor and thermal monitoring features. The 600GB model utilizes 3 platters and six heads, and the 300GB model uses 2 platters with 4 heads.
Seagate also offers several security models in the 15k product line. Seagate Secure Drives feature Instant Secure Erase for easy disposal and repurposing, and FIPS models provide the ultimate in data security. There is no significant performance differential between SED and standard models. SED models meet corporate and federal data security mandates through a number of enhanced features that secure data at rest. The drives offer automatic data encryption/decryption, controlled access, a random number generator, and drive locking. 16 independent data bands secure data, and authenticated firmware downloads prevent unauthorized access.
15K HDDs are alive and well, and Seagate's Enterprise Performance offers competitive performance with enhanced density for transactional workloads for blade, rack, or tower servers. Let's take a closer look.
Enterprise Performance 15K HDD v5 Internals and Specifications
Enterprise Performance 15K HDD v5 Internals
Mention 479 areal density, perhaps in intro?
The Enterprise Performance 15K HDD v5 comes in the 2.5" form factor with a 15nmm z-height.
The two main processing components are outfitted with thermal pads to assist in heat dissipation. A foam pad reduces vibration between the PCB and drive housing. There are several accelerometers spaced across the PCB to help detect, and thus counteract, vibration in rack environments.
The Seagate-SMOOTH co-branded controller handles motor operations. A co-branded LSI/Seagate TT50431 controller handles drive operations, and is flanked by a 128MB Samsung multi-segmented DRAM package.
The 12Gb/s SAS connection provides wide compatibility with the latest RAID controllers and HBA's.
Idle power consumption is a pain point in the datacenter. The Seagate Enterprise Performance 15K HDD v5 utilizes PowerChoice Technology, Seagate's proprietary implementation of the T10/T13 Approved Standard. PowerChoice provides 4 enhanced idle modes that place the drive into deeper quasi-sleep cycles to conserve power, and is triggered by the length of drive inactivity. The feature is enabled with a SAS Mode Page or SATA Set Feature command. There is also the option for immediate host-initiated power transitions in a typical implementation. Once enabled, PowerChoice places the drive into successively deeper idle states with SAS/SATA commands, but each consecutive sleep mode requires more time for resumption. We did not test with enhanced PowerChoice states enabled.
The Enterprise Performance 15K HDD v5 provides a 6.4-watt average power draw during the idle power state. It is important to note this measurement is without PowerChoice technology activated; the drive can idle lower when using PowerChoice. The 600GB 15K v5 features more capacity than the 147GB and 300GB competitors do; on an idle Watts-per-GB basis the 15K v5 offers superior idle power consumption metrics.
Enterprise Performance 15K HDD v5 Specifications
The 12Gb/s Seagate Enterprise Performance 15K HDD v5 HDD we are testing today features the 512E format with the ST600MP0035 part number. There are 4KN, 512n, 512E, SED, and FIPS variants available with varying part numbers.
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 fall short in providing the clearest view possible of I/O QoS (Quality of Service).
While under load, all storage solutions deliver variable levels of performance. '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. 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. This testing methodology illustrates performance variability, and includes average measurements, during the measurement window.
IOPS data that ignores latency is useless. 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 Latency v IOPS testing also reveals performance at varying latency thresholds.
We conduct our tests over the full LBA range to allow each HDD to highlight its average performance. All three HDDs spin at 15,000 RPM and feature varying capacity points. Capacity should be taken into consideration when analyzing performance and power metrics. The first page of results will provide the 'key' to understanding and interpreting our test methodology.
Benchmarks - 4k Random Read/Write
4k Random Read/Write
Each level tested includes 300 data points (five minutes of one second reports) to illustrate performance variability. The line for each queue 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 Enterprise Performance 15K v5 starts out with an impressive average of 509 IOPS at QD256. The Savvio 15K.3 leads with 540 IOPS, and the Toshiba MK1401GRRB averages 507 IOPS.
Our Latency vs IOPS charts compare the amount of performance attained from each solution at specific latency measurements. Many applications have specific latency requirements. These charts present relevant metrics in an easy to read manner for readers who are familiar with their application requirements. The HDDs that are lowest and furthest to the right exhibit the most desirable latency characteristics.
The Seagate 15K v5 trails the other contenders in this test.
The Enterprise Performance 15K v5 averages 497 IOPS at QD256. The Savvio 15K.3 averages 428 IOPS, and the Toshiba delivers 444 IOPS. The Seagate 15K v5 exhibits excellent performance in random write workloads.
The Enterprise Performance 15K v5 takes an impressive lead in write latency.
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 15K v5 trails slightly in random read performance, but wins the majority of the test by displaying excellent mixed write workload performance.
We record power consumption measurements during our test run at QD256. It is important to consider Watts-per-GB in the overall analysis due to the varying capacities in the test pool.
The Enterprise Performance 15K v5 draws 7.4 watts during the test. The incremental increase in power consumption is more than offset by the much larger addressable capacity of the drive.
We generate IOPS-to-watts measurements from data recorded during the test period. The 15K v5 averages 66 IOPS-per-watt during the write workload and 59 IOPS-per-watt during read activity.
Benchmarks - 8k Random Read/Write
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 Enterprise Performance 15K v5 averages 501 IOPS at QD256 and the Savvio 15K.3 leads with 535 IOPS. The Toshiba 15K scores 522 IOPS at QD256.
The Enterprise Performance 15K v5 falls behind the competing drives, in similar fashion to the 4k results, with random read activity.
The Enterprise Performance 15K v5 displays its strength with 8k random write activity with an average of 492 IOPS at QD256, and the Savvio 15K.3 provides 430 IOPS. The Toshiba also averages 479 IOPS at QD256, but falls behind with lower queue depths.
The 15K v5 provides an excellent performance to latency ratio in this test.
The Enterprise Performance 15K v5 takes a comfortable lead as we mix in more write activity, winning the majority of the write mixtures.
Power consumption for the 15K v5 averages 8.38 watts.
The 15K v5 provides 58 IOPS-per-watt with 8k write activity and 59 IOPS-per-watt during read activity.
Benchmarks - 128k Sequential Read/Write
128k Sequential Read/Write
We write to every LBA to highlight performance degradation from the outer to inner tracks of the drive. The drives begin with much higher speed on the outer tracks and lose speed as it works inward. The small platter sizes allow the drives to write the entire platter of the drive very quickly. The varying capacity points in the test pool are evident, as the high-capacity Enterprise Performance 15K v5 requires the most time to complete a full pass across the platter. The superior sequential speed is evident in this test as the Seagate Enterprise Performance 15K v5 manages to top 250MB/s on the outer edge of the platter.
128k sequential speed reflects the maximum sequential throughput of the HDD and is indicative of performance in OLAP, batch processing, streaming, content delivery applications, and backup scenarios. Today's HDDs are increasingly used for sequential workloads as SSDs encroach upon the application space.
The Enterprise Performance 15K v5 drive averages an impressive 252 MB/s during the sequential read workload at QD256, taking an easy lead in this test. The Savvio 15K.3 averages 187 MB/s, and the Toshiba offers 198 MB/s.
The 15K v5 exhibits excellent latency characteristics with sequential read activity, separating itself from the other competitors.
Sequential write performance is important in tasks such as caching, replication, HPC, and database logging. The Enterprise Performance 15K v5 stretches its legs and averages an impressive 251 MB/s, the previous-gen Savvio 15K.3 averages 187 MB/s, and the Toshiba weighs in with 196 MB/s.
The 15K v5 demonstrates continued dominance in sequential workloads.
The mixed-workload sequential testing is one of our most demanding tests. Many drives will fare very well on the high-end, but fall short with mixed sequential activity. The Enterprise Performance 15K v5 wins in every write mixture during the test period.
The 15K v5 averages 9.88 watts during the measurement window.
The Enterprise Performance 15K v5 averages 25 MB/s-per-watt for both read and write activity.
Benchmarks - Database/OLTP
This test consists of 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 percent read and 33 percent write distribution bring even the best solutions down to earth.
The 15K v5 comes in a very close second with 524 IOPS at QD256 during the OLTP workload. The Savvio 15K.3 averages 469 IOPS, and the Toshiba provides 532 IOPS.
The Enterprise Performance 15K v5 trails the much smaller 147GB Toshiba offering slightly in this test.
The 15K v5 requires an average of 7.87 watts during the transactional workload.
The Enterprise Performance provides 66 IOPS-per-watt during the measurement window.
Benchmarks - Email Server
The email server workload 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 Enterprise Performance 15K v5 leads the test by a large margin with an average of 532 IOPS at QD256. The Toshiba comes in a close second with 510 IOPS and the Savvio 15K.3 delivers 466 IOPS. The superior random write speed from the 15K v5 is very apparent in this workload.
The Enterprise Performance 15K v5 beats the other contenders during our latency v IOPS test.
The 15K v5 averages 7.7 watts during the email server workload.
The 15K v5 provides 68 IOPS-per-watt during the measurement window.
3.5" 15K models are being phased out of production, and thus in the datacenter as well, which turns attention to nimble 2.5" 15K offerings. Flash is increasingly leveraged for high-performance tiers, but the need for performance hard disk drives remains. Flash is an attractive solution for many workloads, but the economics are not the right fit for every deployment. Many environments prioritize high-availability features over bleeding-edge flash performance, and the performance HDD segment (10K, 15K) employs the venerable SAS connection. The majority of value-centric SSDs are SATA, and thus lack high availability features. SAS SSDs can step in and offer high availability features, along with tremendous performance, but they continue to command a premium in comparison to the performance HDD segment. Value-centric SSDs, in both SAS and SATA flavors, often do not meet endurance requirements for write-heavy applications. These applications require durable SSDs to address endurance concerns, but these fall into a higher price bracket as well.
Truth be told, not every workload requires the ultimate in performance. The key is to address performance challenges with cost-effective solutions right-sized for the application at hand. 15K HDDs serve a valuable position as a fast front-end for large working datasets, and provide plenty of performance for the majority of workloads. Complimentary technologies, such as caching algorithms and tiered storage hierarchies, can address more demanding performance challenges.
The chasm between HDDs and flash storage has left many in an either/or position. Seagate's inclusion of SSHD models into the 15K segment offers an intermediary product between flash and typical rotating media, and SSHDs are not as limited by endurance concerns. The intelligent caching algorithms work independently to provide seamless acceleration that requires no management or optimization. This eases deployment by reducing complexity associated with caching/tiering software and speeding qualification cycles.
The Seagate Enterprise Performance 15K HDD v5 performed well in many of the key testing attributes for a performance HDD. The 15K v5 displayed a propensity for 4k and 8k random write workloads, which suits it well for deployment into transactional workloads. The small mixed random read testing results trailed the other drives slightly, but analysis of our mixed workload testing revealed excellent performance as we mixed in more write activity, and the 15K v5 took the win in the majority of mixed workloads. Our Latency v IOPS tests also revealed excellent latency performance in mixed workloads.
A surprisingly impressive aspect of the Enterprise Performance 15K v5 came in sequential workloads. We expect blistering performance in random workloads from 15k drives, but the Enterprise Performance 15K v5 blew away the competition in both sequential read and write workloads by a large margin. This enhanced performance bodes well for numerous workloads that lean heavily on sequential performance. As we turned to mixed sequential workloads, Seagate also chalked up another big win with leading performance during every category of the test.
We noted a rough increase of 1W in power consumption, but considering the large boost in capacity (3X the Savvio 15K.3) the small increase is more than acceptable. On a watt-per-GB basis in the 15K segment the Enterprise Performance 15K v5 leads the pack. Seagate infused a slew of refined and mature Seagate proprietary technologies into their latest high-performance offering. With enhanced density and a big jump in performance, the Seagate Enterprise Performance 15K v5 wins the TweakTown Best Performance Award.
|Performance (including Overclocking w/a)||96%|
|Quality, Design, Build and Warranty||94%|
|Power Consumption and Efficiency||93%|
The Bottom Line: Seagate's Enterprise Performance 15K v5 adds in more performance for random workloads, along with a huge boost in every aspect of sequential performance. The 15K v5 also makes big gains in Watts-per-GB metrics, and features a mature and robust feature set.
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