T3 Code · Performance over time

Reader lock wait p95

All metrics
58 / 120
Reader lock wait p95 (lower is better)
29.0ms
18 Nov+5.5% vs the median of up to 7 previous complete nightlies, within noiseFork perf.9 5.03 ms, −80.6% 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 of the time a read transaction waited for its connection.

Lower is better. Noise band 29.7% on Linux x64 (n = 6), so a change counts beyond 34.7%.

Unit
ms
Better
lower
Noise band
29.7%, threshold 34.7% (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"].p95_lock_wait_ms

Reader lock wait 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.20261118.490329.0 ms27.7 to 31.03+5.5%within noise
17 Nov 2026v0.1.11-nightly.20261117.485127.5 ms22.4 to 28.53−11.4%within noise
16 Nov 2026v0.1.10-nightly.20261116.480022.3 ms18.6 to 31.33−29.9%improved beyond noise
15 Nov 2026v0.1.10-nightly.20261115.474923.2 ms23 to 24.23−28.9%improved beyond noise
14 Nov 2026v0.1.10-nightly.20261114.470924.5 ms22.8 to 35.73−28.7%improved beyond noise
13 Nov 2026v0.1.10-nightly.20261113.465642.5 ms39.3 to 42.93+30.1%regressed beyond noise
12 Nov 2026v0.1.10-nightly.20261112.460689.8 ms78.3 to 1033+175.1%regressed beyond noise
11 Nov 2026v0.1.10-nightly.20261111.454456.8 ms50.7 to 62.43+74.0%regressed beyond noise
10 Nov 2026v0.1.9-nightly.20261110.449150.2 ms34.2 to 54.33+53.8%regressed beyond noise
9 Nov 2026v0.1.9-nightly.20261109.444339.7 ms37.7 to 46.63+21.6%within noise
8 Nov 2026v0.1.8-nightly.20261108.438039.1 ms36.5 to 43.33+19.8%within noise
7 Nov 2026v0.1.8-nightly.20261107.434039.4 ms37.0 to 46.73+20.6%within noise
6 Nov 2026v0.1.8-nightly.20261106.428839.1 ms37.1 to 45.63+19.9%within noise
5 Nov 2026v0.1.8-nightly.20261105.423431.0 ms28.9 to 32.43−5.0%within noise, thin reference
4 Nov 2026v0.1.8-nightly.20261104.419232.6 ms29.4 to 39.53−9.2%within noise, thin reference
3 Nov 2026v0.1.7-nightly.20261103.413836.0 ms32.1 to 39.43no reference yet
2 Nov 2026v0.1.7-nightly.20261102.4093236 ms212 to 2363no reference yet
1 Nov 2026v0.1.7-nightly.20261101.4048218 ms215 to 2303no reference yet
31 Oct 2026v0.1.7-nightly.20261031.4004218 ms214 to 2453no reference yet
30 Oct 2026v0.1.6-nightly.20261030.3940226 ms187 to 2273no reference yet
29 Oct 2026v0.1.6-nightly.20261029.3892537 ms522 to 5393no reference yet
28 Oct 2026v0.1.4-nightly.20261028.3841543 ms538 to 5503no reference yet
27 Oct 2026v0.1.4-nightly.20261027.3796550 ms544 to 5823no reference yet
26 Oct 2026v0.1.3-nightly.20261026.3740592 ms579 to 6253no reference yet
25 Oct 2026v0.1.3-nightly.20261025.3682523 ms501 to 5263no reference yet
24 Oct 2026v0.1.3-nightly.20261024.3643508 ms496 to 5413no reference yet
23 Oct 2026v0.1.3-nightly.20261023.3592539 ms518 to 5913no reference yet
22 Oct 2026v0.1.2-nightly.20261022.35410.036 ms0.032 to 0.0383no reference yet
21 Oct 2026v0.1.2-nightly.20261021.34990.036 ms0.033 to 0.0683no reference yet
20 Oct 2026v0.1.1-nightly.20261020.34380.041 ms0.041 to 0.0453no reference yet
19 Oct 2026v0.1.1-nightly.20261019.33730.004 ms0.004 to 0.0073no noise band yet, no verdict
18 Oct 2026v0.1.1-nightly.20261018.33350.005 ms0.004 to 0.0053no noise band yet, no verdict
17 Oct 2026v0.1.1-nightly.20261017.32720.004 ms0.004 to 0.0063no noise band yet, no verdict
Ladder as a table
AgentsNightly 18 NovFork perf.9
10.86 ms1.47 ms
5029.0 ms5.03 ms
10035.6 ms8.76 ms
15031.5 ms9.07 ms
20032 ms9.14 ms
25029.8 ms9.27 ms
Download this series