Home Enterprise Podcast #127 – Backblaze Drive Report

Podcast #127 – Backblaze Drive Report

by Brian Beeler

Brian welcomes Andy Klein to the Podcast this week. Andy is the Principle Storage Cloud Storyteller at Backblaze. In addition to the storyteller role, Andy currently serves as the Technical Marketing Director. Andy has been associated with storage and security technology for most of his career and has been with Backblaze for over 12 years.

Brian welcomes Andy Klein to the Podcast this week. Andy is the Principle Storage Cloud Storyteller at Backblaze. In addition to the storyteller role, Andy currently serves as the Technical Marketing Director. Andy has been associated with storage and security technology for most of his career and has been with Backblaze for over 12 years.

Brian and Andy discuss storage technology and direction and how Backblaze uses and qualifies drives for use in their data centers. This did prove to be a lively discussion around storage products, but not necessarily data center storage products. Backblaze is a service adored by home users.

Andy is one of the techs behind the Backblaze-generated quarterly storage report. The annual report details failure rates for hard drives and, in a limited sense, SSDs in use at Backblaze. Backblaze is one of the best in being open and communicative about drive usage and failures.

We decided to go live with this podcast and invited our Discord to join. Of course, since it was live, ran into a bit of an issue getting started, so there had to be a restart to get back on track.

00:00 Introduction

  • Details from Q1 storage report
  • Backblaze indexes over 300k hard drives
  • High-level overview
  • Drive-farming
  • Drive insights delivered that are unavailable elsewhere

05:00 Operational details

10:00 Procurement Process

  • Testing them all
  • No smart drives
  • Heavy performance penalty
  • Delete and rewrite
    • Encouraging users to delete files
    • Smart drives don’t fit the Backblaze model
    • Catching the drives destined to fail
    • Weeding out the drives that won’t fit the model
      • Discord question
      • Aggregating drive families or even brands
      • Every drive has a different personality
      • Inconsistent model numbers

15:00 Making it easy to track drive changes

  • The report is geared to making it easy to follow trends, changes, failure rates
    • Firmware versions
    • Configuration changes
    • Skew changes
  • Buying the least expensive drives
  • Drives that arrive DOA
  • Let’s go to Costco or Best Buy
  • Oops! Banned from Costco

20:00 Transitioning to Enterprise drives

  • Warranties
  • And then voided warranties
  • You never get a new drive for replacement
  • Learning the drive history!
  • Using Flash
    • Still buying the cheapest
    • Use cases

25:00 Operational considerations

  • Another trip to Costco
  • Burning out drives BEFORE they fail
    • Write, delete, write, delete, use, delete
    • Kinda like a restore server
    • All data goes to hard drives
    • Flash drives are for short stashing
    • Operationally efficient

30:00 Form factors

  • Discord question
    • How do form factors influence purchases
    • Densities can be managed with HDDs
    • Influenced by environment
  • Adding a new tier
    • Dream it, price it
    • Keep it simple
  • HAMR
  • Scheduled
  • Pulled back

35:00 Experimental Tech

  • Watching and Waiting
  • Planned Helium drives
    • Filled a small vault
    • Vault=1200 drives
    • Striping across 20 systems
  • Legacy question from Discord
  • Storage servers are contracted out
  • Supermicro servers

40:00 Protocol for failure

  • Cloning
  • Read-only servicing
  • Recovering data
  • Liquid cooling
  • A data center without AC
  • Nautilus
    • Pulling water from the river
  • Some light banter about pulling water from the Ohio for the Cincy Lab!

45:00 Finding the right chassis

  • Not all Chassis are equal
  • Savings from water-cooled data center
  • Running smart software
    • Servers remember what they were doing in the event of failure
    • Bringing them back online
  • Resiliency
  • Telemetry

50:00 Using Solid Technology

  • Exposure to just about everything
  • Staying in sync
  • Rebuilding on the fly
  • Discord question
    • What’s the network fabric
    • Interconnects
  • Shard integrity checks
  • Rebuilding drives
  • Sustainability
    • Giving away outdated drives
    • Recycling

60:00 What’s exciting for the future?

  • How will larger drives affect business
  • Costs
  • What’s on the bookshelf?

Wrap-Up

Full Video

Engage with StorageReview

Newsletter | YouTube | Podcast iTunes/Spotify | Instagram | Twitter | TikTok | RSS Feed