31
15 Years of Concurrency
Joe Duffy's Blog | Adventures in the high-tech underbelly
Topics /
Systems & Performance
The most popular blog posts about systems & performance on Hacker News. 250 posts.
32
33
Git for Windows accidentally creates NTFS alternate data streams
As part of the small minority of devs at my company who primarily run Windows, I’m accustomed to working around occasional Unix-specific behaviors in our build and deployment systems. Cygwin makes most stuff just work, I can fix simple incompatibilities myself, and as a last resort I can always boot into OSX for a…
34
Gentoo Tesla – T2 Edition
Location Voiture Electrique à la journée, le week-end ou au mois. Dès 50€/jour. Oubliez les agences de location. Assurance tous risques.
35
36
37
Stack Overflow: The Architecture – 2016 Edition
This is #1 in a very long series of posts on Stack Overflow’s architecture. Welcome.Previous post (#0): Stack Overflow: A Technical DeconstructionNext post...
38
Why is a Rust executable large?
Update (2016-10-07): The official FAQ has an entry for this exact problem now. I'll leave this post as more curiously minded people.
39
40
My Most Important Project Was a Bytecode Interpreter
In online forums, I often see questions from people new to C++ asking for recommended reading. I usually respond with a certain set of trusted books, with the caveat that no amount of reading makes up for practice: you have to actually work on something. But what would be a good project to work on? Something that…
41
Why do CPUs have multiple cache levels?
This is a reader question from “jlforrest” that seems worth answering in more detail than just a single sentence: I understand the need for a cache but I don’t understand why there are …
42
43
Following a Select Statement Through Postgres Internals (2014)
This is the third of a series of four posts based on a presentation I did at the Barcelona Ruby Conference called “20,000 Leagues Under ActiveRecord.” (posts: one two four and video ).
44
ZFS: Apple’s New Filesystem That Wasn’t
Prologue (2006) I attended my first WWDC in 2006 to participate in Apple’s launch of their DTrace port to the next version of Mac OS X (Leopard). Apple…
45
Jepsen: VoltDB 6.3
In the last Jepsen post, we found that RethinkDB could lose data when a network partition occurred during cluster reconfiguration. In this analysis, we’ll show that although VoltDB 6.3 claims strict serializability, internal optimizations and bugs lead to stale reads, dirty reads, and even lost updates; fixes are now…
46
Why the Apple II ProDOS 2.4 Release Is the OS News of the Year
In September of 2016, a talented programmer released his own cooked update to a major company’s legacy operating system, purely because it needed to be done. A raft of new features, wrap-in p…
47
No More Full Table Vacuums in PostgreSQL
I just committed a very important patch to PostgreSQL. The short summary for the patch is " Don't vacuum all-frozen pages. " and it follows...
48
Don't tug on that, you never know what it might be attached to
From the highly eclectic blog of Mark Dominus
49
Baby Steps: Slowly Porting Musl to Rust
ramblings by Adam Perry
50
Unix’s file durability problem
You're probably reading this page because you've attempted to access some part of my blog (Wandering Thoughts) or CSpace , the wiki thing it's part of. Unfortunately you're using a browser version that my anti-crawler precautions consider suspicious, most often because it's too old (most often this applies to versions…
51
ZFS is the FS for Containers in Ubuntu 16.04
Ubuntu 16.04 LTS (Xenial) is only a few short weeks away , and with it comes one of the most exciting new features Linux has seen in a ve...
52
Why is Python slow
In case you missed it, Marius recently wrote a post on the Pyston blog about our baseline JIT tier. Our baseline JIT sits between our interpreter tier and our LLVM JIT tier, providing better speed…
53
54
Does a compiler use all x86 instructions? (2010)
On the Z80 CPU there are so few registers and instructions that you can easily know and use them all and wish there were more of them. However, half of the time it feels like the only on you really use is ld. I imagine that if ld took half the number of clock cycles, average code would run twice as fast.
55
How to do distributed locking
As part of the research for my book , I came across an algorithm called Redlock on the Redis website. The algorithm claims to implement fault-tolerant distributed locks (or rather, leases [1]) on top of Redis, and the page asks for feedback from people who are into distributed systems. The algorithm instinctively set…
56
Haskell in the Datacentre
Bluesky: @simonmar.bsky.social Github: simonmar Email: marlowsd@gmail.com LinkedIn: Simon Marlow
57
58
59
60
The Ethernet PAUSE frame
This is a bizarre one. It all started when the internet seemed to go out at my house. My desktop, phone, TV, everything stopped working. The usual solution at a time like this is to power cycle the modem and router. While this fixed the situation temporarily, soon after the problem returned. What made me think this…