Bryan Cantrill on ARC: A Self-Tuning, Low Overhead Replacement Cache [PWL SF] 10/2017
PapersWeLove3 HN recommenders · recommended in 3 months, 2019-2024
13K views · 9 years ago · talk · evergreen
Bryan Cantrill presents the ARC (Adaptive Replacement Cache) paper by Megiddo and Modha at Papers We Love. He opens with a survey of caching strategies before digging into the self-tuning LRU/MFU design.
Recommended in cache-algorithm threads as a fun, informative walk through caching strategies and ARC.
1:31:05Bryan Cantrill from Joyent on Manta: internet-facing object storage facility that features compute
AI Council
25K views • 12 years ago
46:40Andrew Kelley: A Practical Guide to Applying Data Oriented Design (DoD)
ChimiChanga
415K views • 2 years ago
1:13:41CppCon 2014: Chandler Carruth "Efficiency with Algorithms, Performance with Data Structures"
CppCon
235K views • 12 years ago
1:16:58code::dive conference 2014 - Scott Meyers: Cpu Caches and Why You Care
NOKIA Technology Center Wrocław
231K views • 11 years ago
32:35Scale By The Bay 2019: Bryan Cantrill, Was He Wright All Along? Software After Moore's Law
FunctionalTV
11K views • 6 years ago
52:54Rust at speed — building a fast concurrent database
Jon Gjengset
225K views • 7 years ago
28:47Someone improved my code by 40,832,277,770%
Stand-up Maths
3.1M views • 4 years ago
46:37Zebras All the Way Down - Bryan Cantrill, Uptime 2017
Code & Supply
49K views • 9 years ago
58:36Advanced Topics in Programming Languages: A Lock-Free Hash Table
GoogleTalksArchive
29K views • 14 years ago
1:26:02Stanford Seminar - The Soul of a New Machine: Rethinking the Computer
Stanford Online
76K views • 6 years ago
59:34CppCon 2017: Matt Kulukundis “Designing a Fast, Efficient, Cache-friendly Hash Table, Step by Step”
CppCon
137K views • 9 years ago
1:29:55Sorting Algorithms: Speed Is Found In The Minds of People - Andrei Alexandrescu - CppCon 2019
CppCon
184K views • 7 years ago
30:37High-performance Tree Wrangling, the APL Way // Aaron Hsu // Dyalog '18
Dyalog User Meetings
6K views • 7 years ago
19:25New computers don't speed up old code
Matthias random stuff
187K views • 1 year ago
31:09Bringing the Unix Philosophy to Big Data by Bryan Cantrill: FutureStack13
New Relic
18K views • 12 years ago
59:21A Crash Course in Modern Hardware by Cliff Click
Devoxx
21K views • 9 years ago
40:18"Compacting the Uncompactable" by Bobby Powers
Strange Loop Conference
29K views • 7 years ago
59:11How to Speed up a Python Program 114,000 times.
InfoQ
171K views • 13 years ago
1:00:58CppCon 2017: Chandler Carruth “Going Nowhere Faster”
CppCon
113K views • 9 years ago
55:49CppCon 2016: Chandler Carruth “High Performance Code 201: Hybrid Data Structures"
CppCon
119K views • 10 years ago
4 comments from Hacker News
> it seemed natural to have a set of generations for items that have only been seen once, and then another generation for things that have been more active Have you looked at ARC? It sounds similar - it is a cache split between LRU and MFU areas, where the split point changes dynamically depending on the workload. ▶ this video is a fun watch on the topic.
Might I also recommend: Bryan Cantrill on ARC: A Self-Tuning, Low Overhead Replacement Cache [PWL SF] 10/2017 ▶ this video
Bryan Cantrill does a pretty good survey of caching strategies in the intro to this Papers We Love talk on the ARC in ZFS. ▶ this video
The author calls ARC autotuning “opaque” which surprised me given a well regarded paper has been published on it: link ▶ this video ...that said the author has been writing on the ARC for more than 10 years judging from his blog links so perhaps that paper did not answer his questions.