aboutsummaryrefslogtreecommitdiffstats
path: root/prototypes/workbench/baseline.test.mjs
diff options
context:
space:
mode:
authoreunhhu <[email protected]>2026-10-01 03:23:27 +0100
committereunhhu <[email protected]>2026-10-01 03:23:27 +0100
commitdb4ee9cc3ac5921830053d79efb09a0dc24da3d4 (patch)
treea21fb8bf4878df0027e6643c5c2366fc6d60e130 /prototypes/workbench/baseline.test.mjs
parenta05b9428c9d12ce0ea76f6e4539aa911f42b6eef (diff)
downloadpure-db4ee9cc3ac5921830053d79efb09a0dc24da3d4.tar.gz
pure-db4ee9cc3ac5921830053d79efb09a0dc24da3d4.zip
Keep a busy app on its worker while no other app waits (017)
A worker put its app back at the queue's tail after every turn, and the queue woke another worker for it: an app with steady work hopped between workers (and cores) each turn, and every turn woke a thread. Two busy scoreboard apps on two workers wrote 84k a second where two processes wrote 117k. Now an app takes its turns one after another on the same worker while it has work and no other app waits; it goes to the tail only when one does, and then without waking another worker, since this one takes the head. Due timers are looked at between its turns, so a timer of another app still gets a turn. A worker wakes another only when it leaves apps waiting behind the one it took. The two apps now write about as much as the two processes (measurements in research/experiments/026).
Diffstat (limited to 'prototypes/workbench/baseline.test.mjs')
0 files changed, 0 insertions, 0 deletions