by Kevin OBrien

Seagate Enterprise Performance 10K HDD Savvio 10K.6 Review

The Seagate enterprise hard drive portfolio is getting a bit of a branding makeover, in this case the high-speed Savvio 10K drives migrate to the Enterprise Performance 10K category. We still know the drives underneath this umbrella by their proper names though, the Savvio 10K.6 being the subject of this review. In many ways, the 10K.6 represents a progressive step forward when compared to the prior generation 10K.5. The biggest highlight though is performance, the Savvio 10K.6 offers sustained throughput of 204MB/s, where the 10K.5 posted 168MB/s, a better than 20% increase. Such speed bumps are more than a nice to have. For many uses cases, like data centers want both performance and capacity in a high-performance storage tier, being able to move away from large form factor 15K drives and low capacity SFF 15K drives is a tremendous win.

The 10K.6 capacity points remain the same, the drives are offered in 300GB, 450GB, 600GB and 900GB capacities. The 10K.6 now offers all four drives as SED, where before encryption was optional; the 900GB capacity retains the FIPS option for those who need a higher level of security. The 10K.6 also comes with only a SAS 6Gb/s interface, where prior the 10K.5 offered an FC 4Gb/s option. 

Seagate made significant strides on the power efficiency of the Savvio 10K.6 as well. In idle the 10K.6 uses roughly 14% less idle power than 10K.5 and up to 10% less operational power. When compared to large form factor 15K performance hard drives like the Cheetah 15K.7, the value proposition gets even better. The 10K.6 uses around 70% less idle power and up to 55% less operational power. 

Lastly, Seagate includes several software features and enhancements to make the Savvio 10K.6 easier to manage and redeploy. Those include PowerChoice for T10-compliant power management, RAID Rebuild for faster and safer RAID recoveries, Protection Information which protects against inadvertent data change and support for Seagate Instant Secure Erase (ISE), which makes it easy to safely retire or repurpose the drives. 

Seagate Savvio 10K.6 Specifications

  • Capacities
    • 300GB (ST300MM0026)
      • Disks/Heads: 1/2
    • 450GB (ST450MM0026)
      • Disks/Heads: 2/3
    • 600GB (ST600MM0026)
      • Disks/Heads: 2/4
    • 900GB (ST900MM0026), SED FIPS 140-2 Model Number (ST900MM00363)
      • Disks/Heads: 3/6
  • Interface: 6Gb/s SAS
  • Spindle Speed (RPM): 10K
  • Average Latency (ms): 2.9
  • Sustained Transfer Rate Outer to Inner Diameter: 204 to 125MB/s
  • Cache, Multisegmented (MB): 64MB
  • Nonrecoverable Read Errors per Bits Read: 1 per 1016
  • Annualized Failure Rate (AFR): 0.44%
  • Power Management
    • Typical Op (amps) +5V/+12V
      • 900GB: 0.41/0.49
      • 600GB: 0.41/0.44
      • 450GB:0.40/0.43
      • 300GB: 0.41/0.40
    • Power Idle (watts)
      • 900GB: 3.9
      • 600GB: 3.4
      • 450GB: 3.4
      • 300GB: 3.0
  • Temperature, Operating (°C): 5 to 55
  • Temperature, Nonoperating (°C): –40 to 70
  • Shock, Operating: 11ms (Gs): 40
  • Shock, Nonoperating: 2ms (Gs): 400
  • Acoustics Idle (bels—sound power): 3.0
  • Vibration, Operating: <500Hz (Gs): 0.5
  • Vibration, Nonoperating: <500Hz (Gs): 3.0
  • Height: 15mm
  • Weight (kg): 0.212 (900GB)
  • Limited Warranty (years): 5

Design and Build

The Seagate Enterprise Performance 10K HDD (Savvio 10K.6) is a 2.5" SFF drive with a height of 15mm. Its external design is almost identical to the previous 10K.4 and 10K.5 HDDs. Like previous models, it offers a SAS interface, with 6.0Gb/s connection speeds although unlike previous generations, it's not offered in a FC configuration.

Removing the circuit board from the hard drive body, we find multiple thermal pads used to dissipate heat from certain components into the HDD body. This allows the drive to act as one large heatsink, bleeding off excess heat with normal server airflow.

The Seagate Enterprise Performance 10K HDD circuit board includes 64MB of on-board cache from a Samsung DDR2 module, a Marvell controller, and Smooth motor driver. The circuit board layout is such that all components are located on the inward-facing side, protecting them during installation and use.

After opening up the new 900GB Seagate Enterprise Performance 10K HDD, we find the 3-platter, 6-head configuration with very little space that's not utilized.

High-Quality Version

Moving in at a lower angle, we see the elegantly design head parking structure, which keeps the heads off the rotating assembly when the drive is not in use. While not a new technology, it does prevent platter damage in the event the drive is dropped or impacted, by minimalizing the chance of a head striking the platter surface.

Testing Background and Comparables

10,000RPM Enterprise HDD comparables for this review:

  • Seagate Savvio 10K.4 600GB
  • Seagate Savvio 10K.5 600GB
  • Seagate Savvio 10K.6 900GB
  • Toshiba MBF2600RC 600GB

All enterprise HDDs are benchmarked on our enterprise testing platform based on a Lenovo ThinkServer RD240. The ThinkServer RD240 is configured with:

  • 2 x Intel Xeon X5650 (2.66GHz, 12MB Cache)
  • Windows Server 2008 Standard Edition R2 SP1 64-Bit and CentOS 6.2 64-Bit
  • Intel 5500+ ICH10R Chipset
  • Memory - 8GB (2 x 4GB) 1333Mhz DDR3 Registered RDIMMs
  • LSI 9211 SAS/SATA 6.0Gb/s HBA

Enterprise Synthetic Workload Analysis

Our enterprise hard drive benchmark process preconditions each drive into steady-state with the same workload the device will be tested with under a heavy load of 16 threads with an outstanding queue of 16 per thread, and then tested in set intervals in multiple thread/queue depth profiles to show performance under light and heavy usage. Since hard drives reach their rated performance level very quickly, we only graph out the main sections of each test.

Preconditioning and Primary Steady-State Tests:

  • Throughput (Read+Write IOPS Aggregate)
  • Average Latency (Read+Write Latency Averaged Together)
  • Max Latency (Peak Read or Write Latency)
  • Latency Standard Deviation (Read+Write Standard Deviation Averaged Together)

Our Enterprise Synthetic Workload Analysis includes four profiles based on real-world tasks. These profiles have been developed to make it easier to compare to our past benchmarks as well as widely-published values such as max 4K read and write speed and 8K 70/30, which is commonly used for enterprise drives. We also included two legacy mixed workloads, the traditional File Server and Webserver, each offering a wide mix of transfer sizes.

  • 4K
    • 100% Read or 100% Write
    • 100% 4K
  • 8K 70/30
    • 70% Read, 30% Write
    • 100% 8K
  • File Server
    • 80% Read, 20% Write
    • 10% 512b, 5% 1k, 5% 2k, 60% 4k, 2% 8k, 4% 16k, 4% 32k, 10% 64k
  • Webserver
    • 100% Read
    • 22% 512b, 15% 1k, 8% 2k, 23% 4k, 15% 8k, 2% 16k, 6% 32k, 7% 64k, 1% 128k, 1% 512k

In our first workload with a 100% random 4K transfers, we measured 448 IOPS read and 369 IOPS write from the Seagate Enterprise Performance 10K HDD, showing remarkable performance enhancements through the generations.

With a heavy 16T/16Q workload with 100% 4K random transfers, we measured an average read latency of 570.34ms and a write latency of 692.73ms from the Enterprise Performance 10K; the lowest in its class.

Switching our focus to maximum response times, we measured peak read latency of 2,370ms and write latency of 1,125ms, also the lowest in the 10K category.

In our latency standard deviation section for 4K transfers, the Seagate Savvio 10K.6 slipped in its read consistency, but offered the best write consistency.

Compared to the fixed 16 thread, 16 queue max workload we performed in the 100% 4K write test, our mixed workload profiles scale the performance across a wide range of thread/queue combinations. In these tests we span workload intensity from 2 threads and 2 queue up to 16 threads and 16 queue. In the expanded 8K 70/30 test, the Seagate Enterprise Performance 10K offered the highest 8K 70/30 performance in its class, with a solid improvement over previous-generation Savvio models.

In our scaled 8K 70/30 workload, we measured average latency as low as 18.18ms at 2T/2Q and increased to a peak of 634.68 at 16T/16Q. Across the board it offered measurably lower response times than other models in this category.

In our 8K 70/30 test, the Seagate Enterprise Performance 10K offered some of the lowest peak response times across the board at various thread/queue levels.

Compared to other 10K SFF enterprise HDDs, the Seagate Enterprise Performance 10K had the best latency consistency at effective queue depths equal to or less than 32, and then played leapfrog with previous generation Savvio models.

The next workload we used is our File Server profile, putting the drives through a varying workload, where we scaled the thread and queue count from 2T/2Q up to 16T/16Q. In this profile, the Seagate Enterprise Performance 10K offered a modest lead across the board over previous-generation Savvio models as well as the Toshiba 10K comparable. Measured performance scaled from 212 IOPS at 2T/2Q up to 410 IOPS at 16T/16Q.

Average latency measured in our File Server workload varied between 18.8ms at 2T/2Q and 622.87ms at 16T/16Q.

Comparing peak response times in our File Server workload, the new Seagate Enterprise Performance 10K HDD offered the lowest times in the group with the wide-spread of transfer sizes in this profile.

While the Seagate Enterprise Performance 10K HDD had the lowest peak times, it only held the lead in latency standard deviation in loads at or below QD32. Above that rate, latency consistency increased above that of previous-generation Savvio models, but still remained better than the Toshiba comparable.

Our final test measures the performance of each 10K enterprise HDD in a traditional Web Server profile with 100% read activity. In this test the Seagate Enterprise Performance 10K continued to show its strong lead, with a strong lead in front of older Savvio models as well as the 10K Toshiba comparable.

In the 100% read Web Server profile, the Seagate Enterprise Performance 10K HDD scaled in average latency from 19.88ms at 2T/2Q and increased to 587.95ms at 16T/16Q. In this test the next closest drive was the Toshiba MBF2600RC, which came out ahead of the previous-generation Savvio models.

Comparing peak response times between enterprise HDDs, the Savvio 10K.6 offered some of the lowest max latency, although trading places occasionally with other drives in the category.

Comparing latency standard deviation between each drive in our Web Server test, the Seagate Enterprise Performance 10K HDD offered the most consistent performance at queue depths up to and equal to 64, before swapping places with the previous-generation Savvios.


The Seagate Savvio 10K.6 refreshes Seagate's popular 2.5" 10,000 RPM enterprise hard drive line. Collectively the line is now referred to as Enterprise Performance 10K, but the drives within still retain their sequential versioning names. When we compare the 10K.6 to the 10K.5 predecessor, the headline is the 20% improved throughput. When looking at 4K read and write IOPS performance, we saw a 24% increase in read speeds and a tremendous jump in writes, though to be fair the 10K.5 took a step back compared to the 10K.4 in that category. Compared to the 10K.4, the 10K.6 is up about 23%.

4K performance metrics are certainly not the be all and end all, as we dive into other performance areas we see the 10K.6 making nice strides across the board. The fact that the 10K.6 performs as well as it does as a 10K drive is definitely important as enterprises contemplate which drives to use in a high speed HDD tier. Looking more closely at the Seagate enterprise hard drive line, the Savvio 10K.6 is faster in raw throughput than the current 2.5" 15K options, while offering a better capacity per square inch footprint metric than the 3.5" 15K drives. That's not to say 15K is dead, perhaps far from it, it's more a statement of how much Seagate has been able to progress their enterprise performance 10K platform at large.

Seagate also continues to push the security of their drives, the Savvio 10K.6 comes with SED standard and Seagate offers FIPS security as an option for those who need it in the 900GB capacity. There are also several softer features that enterprise users may find various levels of interest in, like instant secure erase, RAID Rebuild and PowerChoice.

There's very little to complain about with the Savvio 10K.6; if we have to get nitpicky, since its release another vendor has launched a 1.2TB 2.5" 10K offering, which puts Seagate a single capacity step behind. Another area that could be seen as a minor tradeoff is it appears the firmware has been tuned for improved low queue depth latency; we see max latency climb higher than previous-generation Savvios' at effective queue depths greater than 32. Even that is fairly minor, as total throughput and average latency in those areas were still better on the 10K.6. 


  • Excellent performance across all mixed workloads
  • Solid jump from prior gen 10K Savvio models
  • SED included, FIPS optional on 900GB


  • Loses a bit of traction with higher peak latency >QD32

Bottom Line

The Seagate Savvio 10K.6 beats out prior gen Seagate 10K offerings across the board, posting better than the listed 20% throughput performance gain in our testing. Couple in the inclusion of SED standard and some of the other Seagate features like instant secure erase and enterprises will find quite a bit to like about the new Savvio 10K.6. 

Savvio 10K.6 Product Page

Discuss This Review