T3 Code · Performance over time

Reader transaction, mean

All metrics
55 / 120
Reader transaction, mean (lower is better)
34.9ms
18 Nov+10.3% vs the median of up to 7 previous complete nightlies, within noiseFork perf.9 4.57 ms, −86.5% 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.

Mean duration of read transactions on the reader connections.

Lower is better. Noise band 22.4% on Linux x64 (n = 6), so a change counts beyond 27.4%.

Unit
ms
Better
lower
Noise band
22.4%, threshold 27.4% (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["sql.transaction|reader"].avg_ms

Reader transaction, mean (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.20261118.490334.9 ms34.7 to 36.83+10.3%within noise
17 Nov 2026v0.1.11-nightly.20261117.485137.4 ms32.8 to 37.73+21.1%within noise
16 Nov 2026v0.1.10-nightly.20261116.480030.9 ms25.6 to 41.53+0.4%within noise
15 Nov 2026v0.1.10-nightly.20261115.474931.6 ms30.4 to 33.13+5.7%within noise
14 Nov 2026v0.1.10-nightly.20261114.470933.1 ms32.3 to 46.83+11.3%within noise
13 Nov 2026v0.1.10-nightly.20261113.465647.7 ms43.5 to 49.43+61.6%regressed beyond noise
12 Nov 2026v0.1.10-nightly.20261112.460667.4 ms55.5 to 71.33+128.1%regressed beyond noise
11 Nov 2026v0.1.10-nightly.20261111.454433.2 ms30.1 to 35.33+12.3%within noise
10 Nov 2026v0.1.9-nightly.20261110.449140.5 ms32.5 to 41.83+37.3%regressed beyond noise
9 Nov 2026v0.1.9-nightly.20261109.444332.8 ms32.4 to 38.03+11.0%within noise
8 Nov 2026v0.1.8-nightly.20261108.438034.0 ms29.4 to 34.43+15.1%within noise
7 Nov 2026v0.1.8-nightly.20261107.434031.2 ms30.7 to 33.33+5.7%within noise
6 Nov 2026v0.1.8-nightly.20261106.428832.5 ms32.3 to 36.13+10.0%within noise
5 Nov 2026v0.1.8-nightly.20261105.423427.4 ms27.0 to 28.73−7.3%within noise, thin reference
4 Nov 2026v0.1.8-nightly.20261104.419229.5 ms28.2 to 32.03−1.3%within noise, thin reference
3 Nov 2026v0.1.7-nightly.20261103.413829.9 ms29.1 to 31.43no reference yet
2 Nov 2026v0.1.7-nightly.20261102.409366.1 ms62.2 to 70.93no reference yet
1 Nov 2026v0.1.7-nightly.20261101.404865.4 ms61.9 to 66.23no reference yet
31 Oct 2026v0.1.7-nightly.20261031.400460.4 ms57.8 to 64.53no reference yet
30 Oct 2026v0.1.6-nightly.20261030.394065.4 ms55.1 to 66.63no reference yet
29 Oct 2026v0.1.6-nightly.20261029.3892146 ms145 to 1463no reference yet
28 Oct 2026v0.1.4-nightly.20261028.3841144 ms143 to 1523no reference yet
27 Oct 2026v0.1.4-nightly.20261027.3796152 ms150 to 1553no reference yet
26 Oct 2026v0.1.3-nightly.20261026.3740165 ms153 to 1673no reference yet
25 Oct 2026v0.1.3-nightly.20261025.3682143 ms129 to 1453no reference yet
24 Oct 2026v0.1.3-nightly.20261024.3643138 ms134 to 1493no reference yet
23 Oct 2026v0.1.3-nightly.20261023.3592149 ms145 to 1583no reference yet
22 Oct 2026v0.1.2-nightly.20261022.354161.2 ms40.5 to 83.93no reference yet
21 Oct 2026v0.1.2-nightly.20261021.349970.9 ms38.7 to 96.43no reference yet
20 Oct 2026v0.1.1-nightly.20261020.343852.0 ms27.0 to 88.53no reference yet
19 Oct 2026v0.1.1-nightly.20261019.3373136 ms125 to 2113no noise band yet, no verdict
18 Oct 2026v0.1.1-nightly.20261018.3335155 ms140 to 1683no noise band yet, no verdict
17 Oct 2026v0.1.1-nightly.20261017.3272143 ms113 to 1483no noise band yet, no verdict
Ladder as a table
AgentsNightly 18 NovFork perf.9
14.38 ms3.07 ms
5034.9 ms4.57 ms
10052.2 ms6.28 ms
15050.1 ms6.33 ms
20050.6 ms6.57 ms
25048.3 ms6.89 ms
Download this series