HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
gsauthof
osjitter
C2025–2025
gsauthof / osjitter

osjitter

Measure how much the OS interrupts programs

2Distinct people
2Mentions
0Explicit recommenders
44GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Measure how much the OS interrupts programs

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 10:50:02 AM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour2 dated mentions

Observed mentions: 2025-09-28 06:47:12 UTC to 2025-09-28 23:10:57 UTC.

012025-09-28 06:00:00 UTC to 2025-09-28 07:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsSep 28, 06:002025-09-28 07:00:00 UTC to 2025-09-28 08:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 08:00:00 UTC to 2025-09-28 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 09:00:00 UTC to 2025-09-28 10:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 10:00:00 UTC to 2025-09-28 11:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 11:00:00 UTC to 2025-09-28 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 12:00:00 UTC to 2025-09-28 13:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 13:00:00 UTC to 2025-09-28 14:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 14:00:00 UTC to 2025-09-28 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsSep 28, 14:002025-09-28 15:00:00 UTC to 2025-09-28 16:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 16:00:00 UTC to 2025-09-28 17:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 17:00:00 UTC to 2025-09-28 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 18:00:00 UTC to 2025-09-28 19:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 19:00:00 UTC to 2025-09-28 20:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 20:00:00 UTC to 2025-09-28 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 21:00:00 UTC to 2025-09-28 22:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 22:00:00 UTC to 2025-09-28 23:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-28 23:00:00 UTC to 2025-09-29 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsSep 28, 23:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Sep 28, 06:002025-09-28 06:00:00 UTC2025-09-28 07:00:00 UTC101
Sep 28, 07:002025-09-28 07:00:00 UTC2025-09-28 08:00:00 UTC000
Sep 28, 08:002025-09-28 08:00:00 UTC2025-09-28 09:00:00 UTC000
Sep 28, 09:002025-09-28 09:00:00 UTC2025-09-28 10:00:00 UTC000
Sep 28, 10:002025-09-28 10:00:00 UTC2025-09-28 11:00:00 UTC000
Sep 28, 11:002025-09-28 11:00:00 UTC2025-09-28 12:00:00 UTC000
Sep 28, 12:002025-09-28 12:00:00 UTC2025-09-28 13:00:00 UTC000
Sep 28, 13:002025-09-28 13:00:00 UTC2025-09-28 14:00:00 UTC000
Sep 28, 14:002025-09-28 14:00:00 UTC2025-09-28 15:00:00 UTC000
Sep 28, 15:002025-09-28 15:00:00 UTC2025-09-28 16:00:00 UTC000
Sep 28, 16:002025-09-28 16:00:00 UTC2025-09-28 17:00:00 UTC000
Sep 28, 17:002025-09-28 17:00:00 UTC2025-09-28 18:00:00 UTC000
Sep 28, 18:002025-09-28 18:00:00 UTC2025-09-28 19:00:00 UTC000
Sep 28, 19:002025-09-28 19:00:00 UTC2025-09-28 20:00:00 UTC000
Sep 28, 20:002025-09-28 20:00:00 UTC2025-09-28 21:00:00 UTC000
Sep 28, 21:002025-09-28 21:00:00 UTC2025-09-28 22:00:00 UTC000
Sep 28, 22:002025-09-28 22:00:00 UTC2025-09-28 23:00:00 UTC000
Sep 28, 23:002025-09-28 23:00:00 UTC2025-09-29 00:00:00 UTC101

What Hacker News says

1 sources
Benchmark is simple but I find it worthwhile because of the fact that (1) it is run across 15 different platforms (different CPUs, libc's) and results are pretty much reproducible, and (2) it is run through gbenchmark which has a mechanism to make the measurements statistically significant. Interesting thing that enforces their hypothesis, and measurements, is the fact that, for example, getpid and clock_gettime_mono_raw on some platforms run much faster (vDSO) than on the rest. Also, the variance between different CPUs is what IMO is enforcing their results and not the other way around - I don't expect the same call to have the same cost on different CPU models. Different CPUs, different cores, different clock frequencies, different tradeoffs in design, etc. The code is here: https://github.com/gsauthof/osjitter/blob/master/bench_sysca..
Read the rest
. syscall() row invokes a simple syscall(423) and it seems to be expensive. Other calls such as close(999), getpid(), getuid(), clock_gettime(CLOCK_MONOTONIC_RAW, &ts), and sched_yield() are also producing the similar results. All of them basically an order of magnitude larger than 50ns. As for the register renaming, I know what this is, but I still don't get it what register renaming has to do with making the state (registers) storage a cheaper operation. This is from Intel manual: Instructions following a SYSCALL may be fetched from memory before earlier instructions complete execution, but they will not execute (even speculatively) until all instructions prior to the SYSCALL have completed execution (the later instructions may execute before data stored by the earlier instructions have become globally visible). So, I wrongly assumed that the core has to wait before the data is completely written but it seems it acts more like a memory barrier but with relaxed properties - instructions are serialized but the data written doesn't have to become globally visible. I think the most important aspect of it is "until all instructions prior to the SYSCALL have completed". This means that the whole pipeline has to be drained. With 20+ deep instruction pipeline, and whatnot instructions in it, I can imagine that this can likely become the most expensive part of the syscall.
In Fast UDP I/O for Firefox in Rust

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.