Conversations with the hackers, leaders, and innovators of the software world. Hosts Adam Stacoviak and Jerod Santo face their imposter syndrome so you don’t have to. Expect in-depth interviews with the best and brightest in software engineering, open source, and leadership. This is a polyglot podcast. All programming languages, platforms, and communities are welcome. Open source moves fast. Keep up.
Hard drive reliability at scale
This week Adam talks with Andy Klein from Backblaze about hard drive reliability at scale.
Changelog++ members get a bonus 15 minutes at the end of this episode and zero ads. Join today!
Sponsors:
- DevCycle – Build better software with DevCycle. Feature flags, without the tech debt. DevCycle is a Feature Flag Management platform designed to help you build maintainable code at scale.
- Sentry – See the untested code causing errors - or whether it’s partially or fully covered - directly in your stack trace, so you can avoid similar errors from happening in the future. Use the code
CHANGELOGand get the team plan free for three months. - Postman – Build APIs together — More than 20 million developers use Postman for building and using APIs. Postman simplifies each step of the API lifecycle and streamlines collaboration so you can create better APIs—faster.
- Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You iterlly can’t get any faster!
Featuring:
- Andy Klein – Twitter, LinkedIn, Website
- Adam Stacoviak – Mastodon, Twitter, GitHub, LinkedIn, Website
Show Notes:
- Backblaze Drive Stats for 2022
- 10 Stories From 10 Years of Drive Stats Data
- Hard Drive Life Expectancy
- The SSD Edition: 2022 Drive Stats Review
- SSD 101: How Reliable are SSDs?
- Hard Drive Cost Per Gigabyte
- A Behind the Scenes Look at Our US East Data Center
- Sean Has a New Friend. His Name Is Guido.
- The Storage Pod Story: Innovation to Commodity
We love 45Drives. If you need an intro to them, let us know.
Something missing or broken? PRs welcome!
Timestamps:
(00:00) - This week on The Changelog
(01:45) - Sponsor: DevCycle
(04:32) - Start the show!
(07:01) - 10 stories from 10 years
(14:39) - Software at the storage layer
(17:18) - S.M.A.R.T. predictive analysis
(20:49) - Digging into S.M.A.R.T. stats
(24:08) - Causes of High Fly Writes
(25:00) - Collecting and storing S.M.A.R.T. data
(29:10) - Sponsor: Sentry
(33:19) - Many DCs around the world
(37:24) - Burn-in testing
(40:45) - Dollars per failure and leveraged buying
(43:35) - The Backblaze Storage Pod
(51:13) - Storage servers are HEAVY!
(57:11) - 52Us, 12 high @ 150lbs each
(59:34) - Sponsor: Postman
(1:03:12) - How does backblaze buy drives?
(1:09:12) - Determining the size of the drive
(1:12:08) - What is your capacity/usage limit?
(1:14:39) - How should homelabers buy drives?
(1:25:43) - SSDs as boot drives
(1:30:41) - HDD vs SSD cost
(1:33:26) - How Adam buys drives
(1:36:20) - Closing out the show
(1:38:26) - Outro