Velocity 2011: Artur Bergman, "Artur on SSD's"
O'Reilly1 HN recommenders · 2011–2021
30K views · talk · dated · Uploaded 2011-06-20
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.
40:20"Testing Distributed Systems w/ Deterministic Simulation" by Will Wilson
Strange Loop Conference
31:44The Value of Values with Rich Hickey
InfoQ
19:10Velocity NY 2013: Richard Cook, "Resilience In Complex Adaptive Systems"
O'Reilly
52:35Debugging Under Fire: Keep your Head when Systems have Lost their Mind • Bryan Cantrill • GOTO 2017
GOTO Conferences
59:56AWS re:Invent 2018: Amazon DynamoDB Deep Dive: Advanced Design Patterns for DynamoDB (DAT401)
Amazon Web Services
36:47Harder Drive: Hard drives we didn't want or need
suckerpinch
47:43"Turning the database inside out with Apache Samza" by Martin Kleppmann
Strange Loop Conference
28:36Literate Devops with Emacs
Howard Abrams
4 comments from Hacker News
Come on, now. Would this "Artur on SSDs" video be nearly as memorable (and therefore efficacious) without all the swearing? [VIDEO]
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. [VIDEO]
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: [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? ;)
[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?