T3 Code · Performance over time

Reader statement p95

All metrics
59 / 120
Reader statement p95 (lower is better)
40.2ms
18 Nov+9.7% vs the median of up to 7 previous complete nightlies, within noiseFork perf.9 3.89 ms, −90.3% vs its upstream base
AgentsRange

When upstream merges a fix, the lines meet.

Upstream nightlyPerformance forkNoise bandRange of attempts green = better, red = worse, beyond the noise band

As agents grow.

95th percentile duration of single statements on the reader connections.

Lower is better. Noise band 37.6% on Linux x64 (n = 6), so a change counts beyond 42.6%.

Unit
ms
Better
lower
Noise band
37.6%, threshold 42.6% (n = 6)
Recorded from
17 Oct 2026; before that the series is a gap, never a zero
Platforms
Linux x64
Lane
Every record, inside the agent ladder
Upstream builds
Every upstream build
Source
result.json: metrics.sql["sqlite|reader"].p95_ms

Reader statement p95 (lower is better) at 1 to 250 agents, Linux x64

against
Records, 50 agents
DateTagMedianMin to maxValidvs up to 7 previousVerdict
18 Nov 2026v0.1.11-nightly.20261118.490340.2 ms39.7 to 45.23+9.7%within noise
17 Nov 2026v0.1.11-nightly.20261117.485141.1 ms37.9 to 43.53+15.2%within noise
16 Nov 2026v0.1.10-nightly.20261116.480036.6 ms28.0 to 50.73+23.2%within noise
15 Nov 2026v0.1.10-nightly.20261115.474936.7 ms35.3 to 37.33+54.3%regressed beyond noise
14 Nov 2026v0.1.10-nightly.20261114.470935.7 ms35.2 to 55.23+54.5%regressed beyond noise
13 Nov 2026v0.1.10-nightly.20261113.465658.4 ms57.3 to 63.83+160.4%regressed beyond noise
12 Nov 2026v0.1.10-nightly.20261112.4606103 ms86.5 to 1113+359.6%regressed beyond noise
11 Nov 2026v0.1.10-nightly.20261111.454456.8 ms53.8 to 66.23+153.3%regressed beyond noise
10 Nov 2026v0.1.9-nightly.20261110.449151.0 ms34.3 to 51.53+127.7%regressed beyond noise
9 Nov 2026v0.1.9-nightly.20261109.444341.8 ms38.0 to 44.23+86.7%regressed beyond noise
8 Nov 2026v0.1.8-nightly.20261108.438036.0 ms32.1 to 44.83+60.7%regressed beyond noise
7 Nov 2026v0.1.8-nightly.20261107.434037.6 ms36.0 to 38.53+67.6%regressed beyond noise
6 Nov 2026v0.1.8-nightly.20261106.428839.5 ms38.5 to 42.33+76.2%regressed beyond noise
5 Nov 2026v0.1.8-nightly.20261105.423421.9 ms20.2 to 22.23−2.1%within noise, thin reference
4 Nov 2026v0.1.8-nightly.20261104.419222.4 ms21.7 to 22.93−5.7%within noise, thin reference
3 Nov 2026v0.1.7-nightly.20261103.413823.8 ms22.1 to 24.03no reference yet
2 Nov 2026v0.1.7-nightly.20261102.409323.4 ms23.0 to 27.53no reference yet
1 Nov 2026v0.1.7-nightly.20261101.404827.7 ms27.3 to 29.63no reference yet
31 Oct 2026v0.1.7-nightly.20261031.400427.4 ms24.5 to 30.53no reference yet
30 Oct 2026v0.1.6-nightly.20261030.394031.9 ms28.5 to 33.03no reference yet
29 Oct 2026v0.1.6-nightly.20261029.389287.6 ms69.2 to 89.33no reference yet
28 Oct 2026v0.1.4-nightly.20261028.384185.3 ms77.7 to 88.43no reference yet
27 Oct 2026v0.1.4-nightly.20261027.379689.6 ms89.0 to 98.33no reference yet
26 Oct 2026v0.1.3-nightly.20261026.3740100 ms81.1 to 1123no reference yet
25 Oct 2026v0.1.3-nightly.20261025.368283.7 ms66.8 to 91.53no reference yet
24 Oct 2026v0.1.3-nightly.20261024.364372.7 ms72.5 to 89.73no reference yet
23 Oct 2026v0.1.3-nightly.20261023.359293.4 ms88.5 to 1013no reference yet
Ladder as a table
AgentsNightly 18 NovFork perf.9
18.41 ms7.37 ms
5040.2 ms3.89 ms
10041.1 ms5.23 ms
15042.1 ms5.28 ms
20047.3 ms5.87 ms
25044.7 ms5.99 ms
Download this series