aboutsummaryrefslogtreecommitdiffstats
path: root/research/experiments/030-app-lifecycle/2026-10-04-window-stop-start-1000.jsonl
diff options
context:
space:
mode:
authoreunhhu <[email protected]>2026-10-04 10:31:09 +0100
committereunhhu <[email protected]>2026-10-04 10:31:09 +0100
commit93261d1c157e50f1ed2bbc14cf68f2822553b69c (patch)
treea7f520cce249cb22425460371a8e73b461aebbd5 /research/experiments/030-app-lifecycle/2026-10-04-window-stop-start-1000.jsonl
parent71e319b63edfbe7e0c54f75e4cafa849d9ced28d (diff)
downloadpure-93261d1c157e50f1ed2bbc14cf68f2822553b69c.tar.gz
pure-93261d1c157e50f1ed2bbc14cf68f2822553b69c.zip
Measure how long an app changing module cannot answer, against a host restart (030)
An app of a million items (a list grown by doubling) or of a thousand, in a host of apps, its store in RAM: the longest gap between two answered writes while it changes module on SIGHUP (stopped and started again from its store, 71e319b), and while the host is restarted. A thousand items: 1.59 ms against 3.05 (median of 20 and 10). A million: 150.64 ms against 149.73 (10 and 5): both are the store read again (pure_app_start, 142 ms), so changing does not answer sooner than restarting.
Diffstat (limited to 'research/experiments/030-app-lifecycle/2026-10-04-window-stop-start-1000.jsonl')
-rw-r--r--research/experiments/030-app-lifecycle/2026-10-04-window-stop-start-1000.jsonl31
1 files changed, 31 insertions, 0 deletions
diff --git a/research/experiments/030-app-lifecycle/2026-10-04-window-stop-start-1000.jsonl b/research/experiments/030-app-lifecycle/2026-10-04-window-stop-start-1000.jsonl
new file mode 100644
index 0000000..93e8e93
--- /dev/null
+++ b/research/experiments/030-app-lifecycle/2026-10-04-window-stop-start-1000.jsonl
@@ -0,0 +1,31 @@
+{"items": 1024, "way": "changed", "gap_ms": 0.7, "reading_ms": 0.69}
+{"items": 1024, "way": "changed", "gap_ms": 5.06, "reading_ms": 1.65}
+{"items": 1024, "way": "changed", "gap_ms": 1.65, "reading_ms": 0.63}
+{"items": 1024, "way": "changed", "gap_ms": 2.97, "reading_ms": 0.63}
+{"items": 1024, "way": "changed", "gap_ms": 0.49, "reading_ms": 0.53}
+{"items": 1024, "way": "changed", "gap_ms": 0.59, "reading_ms": 0.61}
+{"items": 1024, "way": "changed", "gap_ms": 5.67, "reading_ms": 1.59}
+{"items": 1024, "way": "changed", "gap_ms": 0.59, "reading_ms": 0.6}
+{"items": 1024, "way": "changed", "gap_ms": 1.68, "reading_ms": 1.67}
+{"items": 1024, "way": "changed", "gap_ms": 1.58, "reading_ms": 1.67}
+{"items": 1024, "way": "changed", "gap_ms": 2.04, "reading_ms": 0.62}
+{"items": 1024, "way": "changed", "gap_ms": 0.49, "reading_ms": 0.54}
+{"items": 1024, "way": "changed", "gap_ms": 1.46, "reading_ms": 1.63}
+{"items": 1024, "way": "changed", "gap_ms": 0.57, "reading_ms": 0.57}
+{"items": 1024, "way": "changed", "gap_ms": 1.59, "reading_ms": 1.7}
+{"items": 1024, "way": "changed", "gap_ms": 1.72, "reading_ms": 1.65}
+{"items": 1024, "way": "changed", "gap_ms": 1.85, "reading_ms": 0.66}
+{"items": 1024, "way": "changed", "gap_ms": 0.53, "reading_ms": 0.57}
+{"items": 1024, "way": "changed", "gap_ms": 1.58, "reading_ms": 1.66}
+{"items": 1024, "way": "changed", "gap_ms": 2.13, "reading_ms": 1.6}
+{"items": 1024, "way": "restarted", "gap_ms": 2.58}
+{"items": 1024, "way": "restarted", "gap_ms": 4.15}
+{"items": 1024, "way": "restarted", "gap_ms": 3.09}
+{"items": 1024, "way": "restarted", "gap_ms": 2.44}
+{"items": 1024, "way": "restarted", "gap_ms": 3.52}
+{"items": 1024, "way": "restarted", "gap_ms": 2.71}
+{"items": 1024, "way": "restarted", "gap_ms": 3.01}
+{"items": 1024, "way": "restarted", "gap_ms": 4.08}
+{"items": 1024, "way": "restarted", "gap_ms": 3.9}
+{"items": 1024, "way": "restarted", "gap_ms": 2.44}
+{"items": 1024, "changed_median_ms": 1.59, "restarted_median_ms": 3.05, "refused": 172, "answered": 62355}