Category Archives: Investigative Reporting

Finding Windows HANDLE leaks, in Chromium and others

Posted on July 25, 2021 by brucedawson

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 enabled, just in case … Continue reading →

Posted in Bugs, Code Reliability, Investigative Reporting, uiforetw, xperf | Tagged , | 18 Comments

Arranging Invisible Icons in Quadratic Time

Posted on February 16, 2021 by brucedawson

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’t generally do random analysis of … Continue reading →

Posted in Investigative Reporting, Performance, Programming, Quadratic, Rants, Symbols | Tagged , | 18 Comments

Windows Timer Resolution: The Great Rule Change

Posted on October 4, 2020 by brucedawson

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 no announcement, and the documentation has … Continue reading →

Posted in Environment, Investigative Reporting, Performance, Rants | Tagged , | 58 Comments

What Outranks Thread Priority?

Posted on April 14, 2020 by brucedawson

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 few times … Continue reading →

Posted in Investigative Reporting, Performance, uiforetw, xperf | Tagged , , | 7 Comments

O(n^2), again, now in WMI

Posted on December 8, 2019 by brucedawson

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 mostly just spinning in a nine-instruction loop. … Continue reading →

Posted in Investigative Reporting, Programming, Quadratic, Rants, uiforetw, xperf | Tagged , , , , | 23 Comments

63 Cores Blocked by Seven Instructions

Posted on October 20, 2019 by brucedawson

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 often do you have … Continue reading →

Posted in Investigative Reporting, Performance, Programming, Quadratic, uiforetw, xperf | Tagged , , | 12 Comments

Taskbar Latency and Kernel Calls

Posted on September 8, 2019 by brucedawson

I work quickly on my computer and I get frustrated when I am forced to wait on an operation that should be fast. A persistent nuisance on my over-powered home laptop is that closing windows on the taskbar is slow. … Continue reading →

Posted in Investigative Reporting, Performance, uiforetw, xperf | Tagged , , , | 33 Comments

O(n^2) in CreateProcess

Posted on April 21, 2019 by brucedawson

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 long would you like it … Continue reading →

Posted in Investigative Reporting, Performance, Quadratic, xperf | Tagged | 14 Comments

When Your Profiler Lies

Posted on December 9, 2018 by brucedawson

Last week I wrote about the performance consequences of inadvertently loading gdi32.dll into processes that are created and destroyed at very high rates. This week I want to share some techniques for digging deeper into this behavior, and the odd … Continue reading →

Posted in Investigative Reporting, Performance, Programming, uiforetw, xperf | Tagged , , | 12 Comments

A Not-Called Function Can Cause a 5X Slowdown

Posted on December 3, 2018 by brucedawson

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 system input queue, leading to repeated short mouse-movement hangs when building … Continue reading →

Posted in Investigative Reporting, Performance, Programming | Tagged , , | Leave a comment