Seagate births 8TB triplets and a 2TB mobile nipper

Who says spinning rust is finished?


Who says spinning rust is finished? Seagate has rolled out 8TB triplets and a 2TB mobile nipper, using shingled recording on its 8TB Kinetic.

The three 8TB disks use ninth generation perpendicular magnetic recording, and represent a 33.3 per cent capacity uplift on the existing 6TB technology that Seagate uses in its 3.5-inch disk drives. There is an 8TB enterprise capacity drive, one for network-attached storage (NAS), and a Kinetic Ethernet-addressed, key:value store drive.

Seagate_8TB_HDD_table

Overview table of Seagate's 8TB HDD trio. Note on MiBs and MBs below*

We'll note that HGST has an existing 8TB drive, the He8, and also the shingled 10TB He10, each with 7 platters inside their low-friction helium-filled enclosure. Both Toshiba and Western Digital's (WD's) 3.5-inch drive product ranges top out at 6TB. (Actually WD has a 6.3TB Ae archive drive, but what's 0.3TB between friends.)

The 8TB Kinetic drive, a direct-addressed, object-storing drive, comes in 4TB or 8TB versions. It spins at a relatively slow 5,900rpm and the 8TB model uses shingled magnetic recording. Shingling involves overlapping the wider writing tracks but not the narrower read tracks to increase capacity. Blocks of tracks have to be re-written if any data in the block changes, which slows write speed compared to non-shingled drives.

There are 4 x 1TB platters in the 4TB version and 6 x 1.333TB ones with the 8TB drive. The sustained data transfer rate is up to a relatively slow 60MiB/s* at 4TB and 100MiB/s at 8TB. It is fitted with either a 64MB cache (4TB version) or a 128MB one (8TB version) and comes with an 800,000 MTBF (mean time before failure) rating. The workload rating is less than 180TB/year with 24/7 operation – 8,760 power-on hours/year. Regard this as a base spec and we'll move on to the Enterprise NAS and Capacity drives.

Seagate_OneStor_AP_2584

Seagate I+OneStor AP-25844

Seagate is building a Kinetic OneStor 5U enclosure for November availability. It will have 84 drive bays and, filled with 8TB Kinetic drives, will provide 672TB per chassis, 5.3PB per rack. There is a data sheet for the existing OneStor AP-2584 here, which is based on using Seagate's 6TB drives.

The box is described as being a foundation for scale-out architectures, and has single or dual pluggable embedded server modules.

Seagate is encouraging Kinetic drive and system momentum. It says SwiftStack controller software and Scality software support will arrive in the October-November period. The 8TB Kinetic drive will arrive in January 2016 along with Open vStorage software.

This is an open-source VM storage router for virtual machines, a software layer installed on a host or cluster of hosts on which virtual machines are running. A Google cached webpage states, "These VM storage routers (VSRs) operate like a grid leveraging local flash memory or SSDs and any storage back-end (S3 compatible object store, (distributed) filesystem, NAS) to provide an extremely high-performance and reliable storage system as compared to buying expensive SANs or NAS for VM storage."

Envisage Open vStorage as an open source rough equivalent to VMware's VSAN, but with multiple hypervisor support.

NASty drive business

The 8TB NAS spinner rotates faster, at 7,200rpm, and is for mid-range NAS, server and scale-out cloud-storage in 1 – 16-bay enclosures. There are six 1.333TB platters. The capacity points are 2, 3, 4, 5, 6, and 8TB. It has a 6Gbit/s SATA interface, a larger 256MB cache, and the sustained data rate is 216 to 240MB/sec. The drive is also designed for a 24x7 operation/8760 power-on hours/year, but with a 300TB/year workload.

Seagate_NAS_HDD_Positioning

How Seagate positions its NAS disk drives

Enterprise Capacity drive

The Enterprise Capacity drive comes in a single 8TB capacity point with either 12Gbit/s SAS or SATA interfaces. Seagate's previous product topped out at 6TB and used, we understand, 6 x 1TB platters with a 633Gbit/in2 areal density. Its sustained data rate was up to 226MB/sec, whereas the new drive reaches up to 237MB/sec, helped by having a 256MB cache instead of the 128MB used previously.

Seagate says the new drive has a 100 per cent random write performance improvement over the last generation, helped by better caching.

The prior drive featured a 1.4-million-hour MTBF rating. The new one has been uprated to 2 million hours, so it's both fatter and faster and more reliable. The workload rating is 550TB/year with 24x7 operation.

Seagate_8TB_HDD_Trio_650

Mighty mobile mini

Seagate has also revealed 2TB, 2-platter mobile drive technology. Previously it used 500GB platters, but now it has doubled that. The drive is 7mm thick and Seagate says it's 3.17 oz in weight. It is 25 per cent lighter than Seagate's previous generation with Seagate saying it combines "new mechanical firmware architectures, with state-of-the-art heads, media and electronic design."

We can expect this to be used in Seagate small PC and notebook branded drive products. It might, we suppose, bring out a thinner still, 1-platter, 1TB version if there is OEM demand for it. The company says it's evaluating a hybrid flash/disk version of this drive with a NAND cache to provide faster data access speeds.

The company isn't saying anything about spin speeds. We reckon 7,200rpm is a certainty but 10,000rpm a little less so.

The company thinks that helium-filled drives cost more to make than air-filled drives and it won't suffer profit and revenue-wise through not having them in its portfolio this year. We think that its engineers are working on Seagate's own helium-filling technology though, as this enables high capacity through adding a platter and the disk drive future is a capacity-focused one.

It must be a racing certainty that WD will use HGST's helium-drive technology once China's MOFCOM gives the go-ahead to its operational merger with HGST. ®

* 1MB is based on 1KB = 1,000 bytes while 1MiB is based on 1KiB = 1024 bytes.

Similar topics


Other stories you might like

  • New audio server Pipewire coming to next version of Ubuntu
    What does that mean? Better latency and a replacement for PulseAudio

    The next release of Ubuntu, version 22.10 and codenamed Kinetic Kudu, will switch audio servers to the relatively new PipeWire.

    Don't panic. As J M Barrie said: "All of this has happened before, and it will all happen again." Fedora switched to PipeWire in version 34, over a year ago now. Users who aren't pro-level creators or editors of sound and music on Ubuntu may not notice the planned change.

    Currently, most editions of Ubuntu use the PulseAudio server, which it adopted in version 8.04 Hardy Heron, the company's second LTS release. (The Ubuntu Studio edition uses JACK instead.) Fedora 8 also switched to PulseAudio. Before PulseAudio became the standard, many distros used ESD, the Enlightened Sound Daemon, which came out of the Enlightenment project, best known for its desktop.

    Continue reading
  • VMware claims 'bare-metal' performance on virtualized GPUs
    Is... is that why Broadcom wants to buy it?

    The future of high-performance computing will be virtualized, VMware's Uday Kurkure has told The Register.

    Kurkure, the lead engineer for VMware's performance engineering team, has spent the past five years working on ways to virtualize machine-learning workloads running on accelerators. Earlier this month his team reported "near or better than bare-metal performance" for Bidirectional Encoder Representations from Transformers (BERT) and Mask R-CNN — two popular machine-learning workloads — running on virtualized GPUs (vGPU) connected using Nvidia's NVLink interconnect.

    NVLink enables compute and memory resources to be shared across up to four GPUs over a high-bandwidth mesh fabric operating at 6.25GB/s per lane compared to PCIe 4.0's 2.5GB/s. The interconnect enabled Kurkure's team to pool 160GB of GPU memory from the Dell PowerEdge system's four 40GB Nvidia A100 SXM GPUs.

    Continue reading
  • Nvidia promises annual updates across CPU, GPU, and DPU lines
    Arm one year, x86 the next, and always faster than a certain chip shop that still can't ship even one standalone GPU

    Computex Nvidia's push deeper into enterprise computing will see its practice of introducing a new GPU architecture every two years brought to its CPUs and data processing units (DPUs, aka SmartNICs).

    Speaking on the company's pre-recorded keynote released to coincide with the Computex exhibition in Taiwan this week, senior vice president for hardware engineering Brian Kelleher spoke of the company's "reputation for unmatched execution on silicon." That's language that needs to be considered in the context of Intel, an Nvidia rival, again delaying a planned entry to the discrete GPU market.

    "We will extend our execution excellence and give each of our chip architectures a two-year rhythm," Kelleher added.

    Continue reading
  • Amazon puts 'creepy' AI cameras in UK delivery vans
    Big Bezos is watching you

    Amazon is reportedly installing AI-powered cameras in delivery vans to keep tabs on its drivers in the UK.

    The technology was first deployed, with numerous errors that reportedly denied drivers' bonuses after malfunctions, in the US. Last year, the internet giant produced a corporate video detailing how the cameras monitor drivers' driving behavior for safety reasons. The same system is now apparently being rolled out to vehicles in the UK. 

    Multiple camera lenses are placed under the front mirror. One is directed at the person behind the wheel, one is facing the road, and two are located on either side to provide a wider view. The cameras are monitored by software built by Netradyne, a computer-vision startup focused on driver safety. This code uses machine-learning algorithms to figure out what's going on in and around the vehicle.

    Continue reading
  • AWS puts latest homebrew ‘Graviton 3’ Arm CPU in production
    Just one instance type for now, but cheaper than third-gen Xeons or EPYCs

    Amazon Web Services has made its latest homebrew CPU, the Graviton3, available to rent in its Elastic Compute Cloud (EC2) infrastructure-as-a-service offering.

    The cloud colossus launched Graviton3 at its late 2021 re:Invent conference, revealing that the 55-billion-transistor device includes 64 cores, runs at 2.6GHz clock speed, can address DDR5 RAM and 300GB/sec max memory bandwidth, and employs 256-bit Scalable Vector Extensions.

    The chips were offered as a tech preview to select customers. And on Monday, AWS made them available to all comers in a single instance type named C7g.

    Continue reading

Biting the hand that feeds IT © 1998–2022