search

nodejs / performance

Node.js team focusing on performance
MIT License
376 stars 7 forks source link

Node.js Performance Team Meeting 2023-05-29 #85

Closed mhdawson closed 1 year ago

mhdawson commented 1 year ago

Time

UTC Mon 29-May-2023 17:00 (05:00 PM):

Timezone Date/Time
US / Pacific Mon 29-May-2023 10:00 (10:00 AM)
US / Mountain Mon 29-May-2023 11:00 (11:00 AM)
US / Central Mon 29-May-2023 12:00 (12:00 PM)
US / Eastern Mon 29-May-2023 13:00 (01:00 PM)
EU / Western Mon 29-May-2023 18:00 (06:00 PM)
EU / Central Mon 29-May-2023 19:00 (07:00 PM)
EU / Eastern Mon 29-May-2023 20:00 (08:00 PM)
Moscow Mon 29-May-2023 20:00 (08:00 PM)
Chennai Mon 29-May-2023 22:30 (10:30 PM)
Hangzhou Tue 30-May-2023 01:00 (01:00 AM)
Tokyo Tue 30-May-2023 02:00 (02:00 AM)
Sydney Tue 30-May-2023 03:00 (03:00 AM)

Or in your local time:

Links

Agenda

Extracted from performance-agenda labelled issues and pull requests from the nodejs org prior to the meeting.

nodejs/performance

Invited

Observers/Guests

Notes

The agenda comes from issues labelled with performance-agenda across all of the repositories in the nodejs org. Please label any additional issues that should be on the agenda before the meeting starts.

Joining the meeting

tniessen commented 1 year ago

While it might not exactly be an achievement of this particular team, https://github.com/nodejs/node/pull/48078 might still be worth mentioning during the announcements since it might be one of the most impactful performance improvements in a long time (thanks to @santigimeno and @bnoordhuis).

santigimeno commented 1 year ago

thanks to @santigimeno and @bnoordhuis

Thanks for the mention but I would rephrase this a bit.

Thanks to @bnoordhuis and @isc-projects which iiuc sponsored some of his work.

kvakil commented 1 year ago

I'd like to mention that startup has gotten a good bit faster in the most recent release (v20.1.0 -> v20.2.0), as a result of nodejs/node#47055+nodejs/node#47144+nodejs/node#47958:

                                                                                     confidence improvement accuracy (*)   (**)  (***)
misc/startup.js count=30 mode='process' script='benchmark/fixtures/require-builtins'        ***     23.94 %       ±0.64% ±0.88% ±1.20%
misc/startup.js count=30 mode='process' script='test/fixtures/semicolon'                    ***     17.58 %       ±0.43% ±0.61% ±0.85%
misc/startup.js count=30 mode='worker' script='benchmark/fixtures/require-builtins'         ***     28.64 %       ±0.47% ±0.66% ±0.91%
misc/startup.js count=30 mode='worker' script='test/fixtures/semicolon'                     ***     24.70 %       ±0.88% ±1.25% ±1.81%

Be aware that when doing many comparisons the risk of a false-positive result increases.
In this case, there are 4 comparisons, you can thus expect the following amount of false-positive results:
  0.20 false positives, when considering a   5% risk acceptance (*, **, ***),
  0.04 false positives, when considering a   1% risk acceptance (**, ***),
  0.00 false positives, when considering a 0.1% risk acceptance (***)

I am working on some further improvements too.

ronag commented 1 year ago

De we have a meeting today?

anonrig commented 1 year ago

De we have a meeting today?

I was couple of minutes late, but I'm here.