Top all-time · #7271
Code Blueprint
Personal blog · codeblueprint.co.uksystemsprogramming
Code Blueprint is a personal blog at codeblueprint.co.uk about systems and programming. Since 2017, 11 different Hacker News readers have linked it 13 times, most often “The Linux X86 ORC Stack Unwinder”. The last post was in 2020, but the archive is still widely read.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
Linked in threads on a DIY electronic leadscrew for a metal lathe and on software memory management without virtual memory. Commenters discuss real-time scheduling and kernel CPU isolation, not the writing itself.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Thoughts and ramblings of an open source developer. Mainly discussing the Linux kernel and performance engineering.
Most-linked posts?
- The Linux X86 ORC Stack Unwinder3 people · 3 mentions · first linked 2017-08-01
- Linux kernel preemption and the latency-throughput tradeoff2 people · 2 mentions · first linked 2019-12-23
- Reducing jitter on Linux with task isolation2 people · 2 mentions · first linked 2020-05-03
What Hacker News says?
Tldw? What do you mean by timing? Measuring time (down to nanoseconds) is easy. Hard realtime scheduling with microsecond precision... just forget about it, unless you're building a custom distro & custom kernel and have in-depth knowledge about all the drivers that are going to be running on the system (you almost definitely do not). EDIT: I found a relatively recent socket benchmark with worst case scheduling late…
Comment linking /2019/12/23/linux-preemption-latency-throughput.html
on “DIY electronic leadscrew for metalworking lathe [video]”Submitted Does simultaneous multithreading still make sense? as a story · 87 points
HN discussionI'll admit I shouldn't have said "any" latency requirements but I was speaking specifically about optional cooperative concurrency within an OS thread. I realize that this doesn't magically give you a platform on par with the kind of hard real time deterministic performance you get out of e.g. the new Cortex-R82. But as for kernel bookkeeping tasks still causing preemptions, I'm talking about using isolcpus and nohz…
Comment linking /2020/05/03/reducing-jitter-on-linux-with-task-isolation.html
on “The Cost of Software-Based Memory Management Without Virtual Memory”Submitted Does SMT still make sense? as a story · 5 points
HN discussionSubmitted The Linux X86 ORC Stack Unwinder as a story · 4 points
HN discussionSubmitted Linux kernel preemption and the latency-throughput tradeoff as a story · 3 points
HN discussionSubmitted Dear Btrfs, Where the fsck is my free space? as a story · 3 points
HN discussionSubmitted Reducing jitter on Linux with task isolation as a story · 2 points
HN discussionSubmitted The ORC Unwinder as a story · 2 points
HN discussionSubmitted The Linux X86 ORC Stack Unwinder as a story · 2 points
HN discussionSubmitted A Kernel Dev's Approach to Improving Mutt's Performance as a story · 2 points
HN discussionSubmitted The Linux x86 Orc Stack Unwinder as a story · 1 points
HN discussionSubmitted Isolcpus Is Deprecated, Kinda as a story · 1 points
HN discussion
