HGST 8TB Drives – Helium Makes Them Fly

June 9th, 2015

Backblaze uses HGST Helium drives

We recently installed and deployed 45 HGST 8TB hard drives into Backblaze Storage Pod 902 and the drives have recently completed their initial data loading phase. As we have done with Seagate, Western Digital, and Toshiba drives, we tracked the HGST drives during their data loading phase to see how well they performed. Here’s what we know so far.

Helium drives

The HGST 8TB drives are filled with Helium. According to the HGST literature, the helium-filled environment lets the disks spin more easily as helium offers less resistance versus air. This means less power is required to spin the disks and they run cooler. It also means they can have more disks and read/write heads with the HGST 8TB drive having 7 platters in a similar space as other drives.

The amount of Helium in a drive is not published, but it is tracked as SMART attribute 22, with both the raw and normalized values starting at 100. During our period of observation, the value of these attributes did not change.

A 360TB Backblaze Storage Pod

We filled Storage Pod 902 with 45 HGST 8TB drives. That created our very first 360TB Storage Pod. If we built out a rack of 10 Pods we would have 3.6 Petabytes of storage in one full height rack. That would be awesome, but it won’t happen yet – more on that later in this post.

For the moment let’s look at how the HGST 8TB drives in Storage Pod 902 performed versus our current data load test champ, the Toshiba 5TB drives in Storage Pod 909. As always, we tracked the Storage Pods until they were 80% full of data.
Backblaze compares HGST 8TB versus 5TB Toshiba drives
A new data load test champion

A Storage Pod with Toshiba 5TB drives took 26 days to reach 80% capacity and loaded data at an average rate of 5.46 TB per day. The Storage Pod with HGST 8TB drives took 40 days to reach 80% capacity and loaded data at a rate of 5.66 TB per day. Given both Pods are similarly configured and both drives are 7200 rpm drives, perhaps there is something to using helium after all. Regardless, the HGST 8TB drives are our current data load test champion as Storage Pod 902 loaded on average 5.66 Terabytes of data per day.

You might be wondering about the two days in the chart above on the HGST data line where it appears no data was written to the Storage Pod. That was caused by a drive failure. Yes, one of the 45 HGST 8TB drives failed in the middle of our observation period. The drive was replaced a short time after it failed, but no data was loaded for 2 days, why? Let’s walk through the process of when a drive fails.

  1. Our monitoring system reports that a drive has gone offline in Pod 902.
  2. Pod 902 is flipped into maintenance mode. This places the Pod in read only mode, letting any current write operations complete then only allowing read operations.
  3. Once the Pod is in maintenance mode, a Backblaze datacenter technician uses the monitoring system to evaluate the issue looking to determine if it is just a drive failure or something more. Depending on the failure the drive can be restarted, but most often the drive is dead. That was the case in Pod 902. At this point the drive is scheduled for replacement.
  4. Depending on workload and the time-of-day, the failed drive is replaced anywhere from a few minutes to a few hours later. The Pod continues to operate in read-only mode during that time.
  5. To replace the drive, the datacenter technician suspends new read operations then shuts down the Storage Pod.
  6. The technician locates the Storage Pod and slides it out of the rack. They open the Pod, locate the dead drive, confirm it is the failed drive using the serial number, replace the drive, and then close up the Pod. This typically takes 3-5 minutes.
  7. Once the Pod is back in the rack, it is restarted. The replaced drive is then synced into its RAID array. This can take anywhere from a few hours to a couple of days depending on the size of the drive. During this time, the Pod remains in maintenance mode, meaning it is read-only.
  8. Once the new drive sync is complete, the Pod is placed back into full service. This was the case with Pod 902 and it continued loading data after being in maintenance (read only) mode for about 49 hours.

By the way, in a Backblaze Vault when a drive fails it will cause zero downtime for reading or writing even as the datacenter technican goes through the steps outlined above. This is one of the reasons for migrating from individual Storage Pods to the Backblaze Vault architecture.

It should be noted that the 2 days that Storage Pod 902 was not receiving new data is part of the 40 total days it took to reach the 80% full benchmark. If you were to subtract those two days, then the average amount of data loaded per day would be 5.96 Terabytes per days for the 38 days the Pod was able to receive data. Where, oh where should the asterisks be?

More HGST 8TB drives?

There are many things to like about the HGST 8TB drives; the low power requirements, high storage capacity, and 5-year warranty lead the list. Currently the lowest price street price we’ve found is $547.99 on Amazon with some sites asking for as much as $795 for each drive. Using street prices, let’s compare the cost per GB of the HGST to the different drives we currently use most often:

Street Price of Hard Drives Used at Backblaze
Drive Type/Size Street Price Cost/GB
HGST 8TB $547.99 $0.068
Seagate 6TB $239.99 $0.040
Seagate 4TB $152.00 $0.038
HGST 4TB $162.72 $0.041

The cost per terabyte of the HGST 8TB drive is currently about 1.6 times more expensive than the drives we are currently purchasing. While the HGST 8TB drive is an enterprise class drive, the premium we’d have to pay doesn’t make sense for us especially as we move to Backblaze Vaults where individual drive failures have zero effect on downtime. Yes, we’ve built and placed into production a 360TB Storage Pod, but it will be at least a few months before we build the next one while we wait for the cost per terabyte of the 8TB drives to come down. Or maybe we’ll just wait for the newly announced HGST 10TB drives – perhaps HGST will loan us 45 drives for a few years so we can test them…

Andy Klein

Andy Klein

Andy has 20+ years experience in technology marketing. He has shared his expertise in computer security and data backup at the Federal Trade Commission, Rootstech, RSA and over 100 other events. His current passion is to get everyone to back up their data before it's too late.
Andy Klein

Latest posts by Andy Klein (see all)

  • Zac Paul

    I love the work you guys do. I’m a research methodologist currently transitioning into IT. Your testing of drives in such large quantities is my dream job. Considering how much we use storage mediums, it is ironic how few longitudinal studies exist that are using sufficient sample sizes to draw conclusions. Your research is a diamond in the rough. It’s even crazier to think how even fewer studies exist in regards to SSDs…most reviews focus on performance given it would take a lot of time and a lot of money to look at long-term reliability, endurance, and consistency. Many Managers I’ve spoken to have mentioned a preference for HDDs because the work you have done has provided them with a factual foundation for decision-making (and as they may be purchasing several hundred or thousand units of the same product, purchasing a bad model isn’t good for the company’s bottom line or their professional reputation.) If solid-state storage ever overtakes HDDs, there is going to need to be more research, and this research is going to be expensive for whoever bears the burden. The only SSD I know of that has gone through a crazy amount of such testing is the Intel X-25…and given those were the days of SLC & eMLC, where as today we are seeing MLC & TLC enterprise drives, it’s generalizability is limited.

    It seems like HGST’s helium-filled drives could extend the viability of the HDD as energy costs continue to rise. Over the past year and some change, have you found that the price premium is offset by the long term energy savings? My usage thus far has found their 20%+ efficiency claim over standard UltraStars to be true, but the amount of drives I am working with are limited. I would go as far to theorize that the drive’s reduction of energy loss (through heat) could offset the entire premium over a 3-6 year service life, and then some. Applied to the 10k and 15k SAS drives, things could get really interesting at a time when flash storage is being considered for the same role, but often at the consequence of considerable infrastructure modifications. That 20% energy savings could be a game-changer!

    If the He line continues the tradition of the UltraStar line, the reliability and longevity may further justify the premium pricing, and in theory it seems the helium fill could reduce drive wear to an extent where there is financial benefit (of course, in practice, theory doesn’t always hold up so only time will tell here!) HGST’s DRAM media caching is ingenious, but I’m not sure how much that would benefit cloud hosting.

    The one thing I am sure of is that HGST seems to be the company that is constantly coming out with new innovations, making major improvements on existing designs (like addressing the concern of sudden power loss causing loss of pending data writes in the cache), and offering products capable of meeting everything from cold storage to 24-7 writes.

  • Eric Anderson

    Please add power consumed into the cost per gigabyte.

    • Zac Paul

      These things save A LOT of power. My usage has found their claim of 20%+ energy efficiency to be true. I think the long-term energy savings will be so great that it will offset the premium pricing with lower running costs. And as the price of energy continues to climb, this could be an even bigger benefit in the future.

      With 10k & 15k SAS drives, filling them with helium may be even more impressive in the energy savings department.

  • KERR

    Do you have any read/write speed test results for this drive and others? Would be interested to see how they compare with non-helium drives.

  • Chris Moore

    I love the technical info. Please be sure to post the results on the Seagate drive.

  • Keith Schwerin

    I know this is an older post but.. the cost per GB is higher on the 8TB drives, but you need to also power two drives and then also cut your storage capacity in 1/2 to have the lower CpGB. If you want a drive with 80GB (lets just say Raid 0, despite the fact that’s dumb) you need 20 drives to house and power instead of just 10. Eventually the power output and cost to house the extra drives offsets the CpGB.

  • Mark Wroblewski

    Hi Andy, any TCO figures to show whether the price premium for the HGST drives is offset based on lower energy costs?

  • STS,LLC

    Hey Andy, Does your cost per GB include the cost of building another Storage pod to get to the same amount of data? I would think that should weigh in on the calculation.

  • Kyle

    You should try the Seagate Archive 8TB drive. It is about $0.031/GB, which is less than half the cost/GB of the HGST 8TB.

    • ranhalt

      But the Seagate drives use SMR and are not meant for constant usage. They are designed for cold storage. Write data occasionally and remove.

      • Ian Worthington

        Isn’t write and let sit pretty much the BB usage model?

      • Kyle

        We are talking about a company that shucked external drives and put them in their storage pods because they were cheaper than buying internal drives. Backblaze doesn’t care what drives were designed for. Besides, considering Backblaze operates a large backup archive, an archive drive would be perfect for their needs.

        • Chris Moore

          I don’t understand why an external drive would be less expensive than an internal drive.
          I can see how an external drive might be more reliable though.
          Where is the post on this?

          • Kyle

            You may not understand it, but that’s how it is. Here is one of Backblaze’s blog posts talking about how they ripped drives from external boxes because they are cheaper.

            https://www.backblaze.com/blog/crowdsourcing-hard-drives/

          • Franz Resch

            Kudos to Backblaze for coming up with an ingenious idea like that to take advantage of a Black Friday special. Especially if it helps to keep the cost of BB’s service down.

    • Andy Klein

      We have some Seagate SMR drives in house. They are scheduled to be deployed in our engineering test bed to see how they behave in our environment. We are building the testing scenarios now. While the initial data load period is primarily data writes, we do need to be able to locate and restore data quickly when needed. We also need to recover space when for example a trial user decides not to subscribe. We’ll report on our findings over the next few months.

      • JRSahoo

        I have a suggestion, what about changing 4tb restore (I read about it here https://www.backblaze.com/blog/4-tb-usb-restore-drives-are-here-yay/). I’m thinking to start using Backblaze, I’ve two 3tb hdd and one 1tb hdd (plus my desktop internal hdd) which total to something like 7tb. So I think STDT8000100 would be much cheaper in my case as it is $249 for 8TB.

        Another question I’ve, what If I pay for STDT8000100 to Backblaze can you send the backup to me if I lose files?