1
Why modern software is slow
I apologize for this title because there are many things that can make modern software slow. Blindly applying one explanation without a bit of investigation is the software equivalent of a cargo cu…
Bruce Dawson
Forecast for randomascii: programming, tech topics, with a chance of unicycling
- Popular posts
- 42
- Total points
- 11,119
- HN comments
- 5,573
- Rank
- #70 personal
Visit randomascii.wordpress.com → RSS feedOn Hacker News Jul 2013 – Aug 2025
Systems & Performance 39Software Engineering 31Hardware & Electronics 6Math & Algorithms 2Society, Policy & Culture 1Security & Privacy 1
2
24-core CPU and I can’t type an email
I wasn’t looking for trouble. I wasn’t trying to compile a huge project in the background (24-core CPU and I can’t move my mouse), I was just engaging in that most mundane of 21st century tasks, wr…
3
O(n^2), again, now in Windows Management Instrumentation
I recently hit some multi-minute delays on my workstation. After investigating I found that the problem was due to a lock being held for five minutes, and during that time the lock-holder was mostl…
4
63 Cores Blocked by Seven Instructions
I seem to have a habit of writing about super powerful machines whose many cores are laid low by misuse of locks. So. Yeah. It’s that again. But this one seems particularly impressive. I mean, how …
5
No Start Menu for You
I tend to launch most programs on my Windows 10 laptop by typing the <Win> key, then a few letters of the program name, and then hitting enter. On my powerful laptop (SSD and 32 GB of RAM) th…
6
Arranging Invisible Icons in Quadratic Time
Near the end of January I was pointed to a twitter thread where a Windows user with a powerful machine was hitting random hangs in explorer. Lots of unscientific theories were being proposed. I don…
7
A Not-Called Function Can Cause a 5X Slowdown
Subtitle: Making Windows Slower Part 3: Process Destruction In the summer of 2017 I wrestled with a Windows performance problem. Process destruction was slow, serialized, and was blocking the syste…
8
You Got Your Web Browser in my Compiler
I recently discovered that Microsoft’s VC++ compiler loads mshtml.dll – also known as Internet Explorer. The compiler does this whenever the /analyze option (requesting static code analysis) is use…
9
24-core CPU and I can’t type an email – part two
In my last post I promised to give more details about some rabbit holes that I went down during the investigation, including page tables, locks, WMI, and a vmmap bug. Those details are here, along …
10
Compiler bug? Linker bug? Windows Kernel bug
See the end of the post for an October 2018 bug fix update, or read the whole story: Flaky failures are the worst. In this particular investigation, which spanned twenty months, we suspected hardwa…
11
Please restore our registers when you’re done with them
“Hey, you. Yes you, that function over there. When you’re cleaning up please remember to restore all of my registers. Yes, that one too – what do you think this is, Linux?”That’s the problem I was …
12
ARM and Lock-Free Programming
I was inspired by the release of Apple’s M1 ARM processor to tweet about the perils of lock-free programming which led to some robust discussion. The discussion went pretty well given the inanity o…
13
Finding Windows HANDLE leaks, in Chromium and others
Three years ago I found a 32 GB memory leak caused by CcmExec.exe failing to close process handles. That bug is fixed, but ever since then I have had the handles column in Windows Task Manager ena…
14
Making Windows Slower Part 2: Process Creation
Windows has long had a reputation for slow file operations and slow process creation. Have you ever wanted to make these operations even slower? This weeks’ blog post covers a technique you can use…
15
Localization Failure: Temperature Is Hard
The Guardian is one of my favorite news sources. I’m a subscriber (support news organizations!) and I read it daily. But it is not immune to errors, as this headline shows:68 °F above average is a …
16
32 MiB Working Sets on a 64 GiB machine
Memory is a relatively scarce resource on many consumer computers, so a feature to limit how much memory a process uses seems like a good idea, and Microsoft did indeed implement such a feature. Ho…
17
Delete an inline function, save 794 kB
In the previous episode of “Simple Changes to Shrink Chrome” I discussed how deleting ‘const’ from a few key locations could lead to dramatic size savings, due to a VC++ com…
18
O(N^2) in CreateProcess
So many possible introductions to this one: Windows 7: Sheesh, I sure am slow at creating processes Windows 10: Hold my beer… Or how about: A) How long does CreateProcess take on Windows? B) How lo…
19
What is Windows doing while hogging that lock?
Earlier this month I wrote about how Windows 10 holds a lock during too much of process destruction, which both serializes this task and causes mouse-cursor hitches and UI hangs (because the same l…
20
Add a const here, delete a const there
Update, February 2019: Two years later the VC++ bug I reported here still exists, even in VS 2019 preview. However Chromium no longer builds with VC++ so I’m reverting the changes where I del…
21
Compiler Bugs Found When Porting Chromium to VC++ 2015
Moving a big software project to a new compiler can be a lot of work, and few projects are bigger than Chromium. In addition to the main Chromium repository, which includes all of Blink, there are …
22
Zombie Processes Are Eating Your Memory
Zombies probably won’t consume 32 GB of your memory like they did to me, but zombie processes do exist, and I can help you find them and make sure that developers fix them. Tool source link is at t…
23
Zeroing Memory is Hard: VC++ 2015 arrays
Quick, what’s the difference between these two C/C++ definitions of initialized local variables? char buffer[32] = { 0 };char buffer[32] = {}; One difference is that the first is legal in C a…
24
The surprising subtleties of zeroing a register (2012)
Zeroing out a CPU register seems like the simplest and most basic operation imaginable, but in fact x86 CPUs contain a surprising amount of special logic to make this operation run smoothly. The mo…
25
Hidden Costs of Memory Allocation
It’s important to understand the cost of memory allocations, but this cost can be surprisingly tricky to measure. It seems reasonable to measure this cost by wrapping calls to new[] and delet…
26
Windows Timer Resolution: The Great Rule Change
The behavior of the Windows scheduler changed significantly in Windows 10 2004 (aka, the April 2020 version of Windows), in a way that will break a few applications, and there appears to have been …
27
Exercises in Emulation: Xbox 360’s FMA Instruction
Years ago I worked in the Xbox 360 group at Microsoft. We were thinking about releasing a new console, and we thought it would be nice if that console could run the games of the previous console. E…
28
50 Bytes of Code That Took 4 GB to Compile (2013)
While doing evil things with macros and the inline assembler (trying to run a weird test whose purpose is not really relevant) I managed to write a program that caused Visual Studio’s C++ compiler …
29
What Outranks Thread Priority?
This investigation started, as so many of mine do, with me minding my own business, not looking for trouble. In this case all I was doing was opening my laptop lid and trying to log on.The first fe…
30
Floating-Point Determinism (2013)
Is IEEE floating-point math deterministic? Will you always get the same results from the same inputs? The answer is an unequivocal “yes”. Unfortunately the answer is also an unequivocal “no”. I’m a…