Velocity 2011: Artur Bergman, "Artur on SSD's"
O'Reilly1 HN recommender · recommended in 1 month, 2011–2021
talk · intermediate · 2011–2021 on HN
A four-minute Velocity 2011 talk in which Artur Bergman, then at Wikia, argues bluntly and with profanity that SSDs should replace spinning disks in servers.
Cited as the memorable case for moving to SSDs and as an example of how swearing can make a talk stick.
Up next
9 mo on HNHarder Drive: Hard drives we didn't want or need
suckerpinch
12 HN recommender · 2022–2025
4 mo on HNHow does Computer Memory Work? 💻🛠
Branch Education
5 HN recommender · 2022–2023
3 mo on HNVintage Electronics - The Tefifon
Techmoan
3 HN recommender · 2016–2018
4 mo on HNShouting in the Datacenter
Bryan Cantrill
4 HN recommender · 2011–2026
3 mo on HNSamsung SSD Awesomeness
ssdawesome
3 HN recommender · 2009–2011
2 mo on HNDEF CON 23 - Zoz - And That's How I Lost My Other Eye...Explorations in Data Destruction (Fixed)
DEFCONConference
2 HN recommender · 2016–2022
2 mo on HNHetzner shows Special AM5 Board with 90° Rotated Socket
der8auer EN
1 HN recommend · 2023–2025
2 mo on HNGet Perpendicular
teraera08
2 HN recommender · 2011–2026
1 mo on HNWhy Your Webcam Still SUCKS!
Techquickie
1 HN recommend · 2020–2020
1 mo on HNLinear Book Scanner
Google TechTalks
1 HN recommend · 2015–2021
1 mo on HNScanRobot 2.0 MDS: Scanning very thick books up to 15 cm (6 inch)
bookscanner
1 HN recommend · 2021–2023
1 mo on HNAll of our data is GONE!
Linus Tech Tips
1 HN recommend · 2019–2021
4 comments from Hacker News
Look. :) Yeah, the build machine churns a lot. But that work should be primarily done by the FS cache, by buffers. Yes, it's going to write out those small files, but if DragonflyBSD has any kind of respectable kernel, though should be a solid curve, not lots of bursts. I would love if my old colleague Przemek from Wikia would talk about the SSD wear on our MySQL servers which had about 100k-200k databases per shard. We wore the _fuck_ out of some SSDs. You should replace your HDDs with SSDs, though, for a number of reasons, and take the long view, as kryptistk noted the OP is doing. Really compare the cost of SAS 15k drives and Intel 320s or 530s. But I think in his place, you can take the words of the inimitable Mr. Bergman: ▶ this video Stop wasting your life. But don't expect a machine that does lots of random IO, like a database, to have 1-2% SSD wear after two years. It might not last two years. If it does, use it more. Aren't you making money with these drives? ;)
▶ this video link The memory hierarchy of a modern CPU with spinning rust might as well be the Parker Solar Probe waiting on a sea anemone. I am remiss how someone these days can buy a laptop with spinning rust and 4 GiB and then complain it's "slow." Maybe they should've bought a real laptop for real work that's repairable and upgradable?
I find it a bit disturbing how this post reaches the top of HN. But I suppose I shouldn't be surprised. I probably live in my own little bubble, but only lately have I realized that NoSQL has two audiences: (1) People for whom normalization can't work because of their application's characteristics and the limitations of current hardware. (2) People who just don't understand basic relational concepts, or why they were invented in the first place. It's kinda sad. I've consulted on projects where people implemented sharding before adding any indices to MySQL. The thing about being in group (1) is that you can also recognize when the ground shifts beneath your feet. Artur Bergman is one of those guys. ▶ this video
Come on, now. Would this "Artur on SSDs" video be nearly as memorable (and therefore efficacious) without all the swearing? ▶ this video