flush buffered state in executor-benchmark

[msmouse]

Description

expect more reasonable and predicatable numbers.

gonna run calibration and see how it affects numbers

How Has This Been Tested?

Key Areas to Review

Type of Change

• New feature

Which Components or Systems Does This Change Impact?

• Other (specify) -- benchmarking

[trunk-io]

⏱️ 2h 24m total CI duration on this PR

Slowest 15 Jobs	Cumulative Duration	Recent Runs
execution-performance / single-node-performance	1h 40m	🟩 🟩
rust-move-tests	13m	🟩
execution-performance / test-target-determinator	10m	🟩 🟩
check-dynamic-deps	6m	🟩 🟩 🟩
rust-doc-tests	5m	🟩
test-target-determinator	4m	🟩
rust-cargo-deny	2m	🟩
fetch-last-released-docker-image-tag	1m	🟩
semgrep/ci	1m	🟩 🟩 🟩
general-lints	26s	🟩
file_change_determinator	26s	🟩 ⬜ 🟩
file_change_determinator	10s	🟩
permission-check	8s	🟩 🟩 🟩
permission-check	7s	🟩 🟩 🟩
permission-check	5s	🟩 🟩

🚨 1 job on the last run was significantly faster/slower than expected

Job	Duration	vs 7d avg	Delta
check-dynamic-deps	3m	1m

_{settings ⋅ feedback ⋅ docs ⋅ learn more about trunk.io}

[github-actions]

✅ Forge suite compat success on 6593fb81261f25490ffddc2252a861c994234c2a ==> 75074390c7ce8e46dac0962e01416e8041228165

Compatibility test results for 6593fb81261f25490ffddc2252a861c994234c2a ==> 75074390c7ce8e46dac0962e01416e8041228165 (PR)
1. Check liveness of validators at old version: 6593fb81261f25490ffddc2252a861c994234c2a
compatibility::simple-validator-upgrade::liveness-check : committed: 17749.18 txn/s, latency: 1927.85 ms, (p50: 1500 ms, p70: 1600, p90: 2100 ms, p99: 17400 ms), latency samples: 611500
2. Upgrading first Validator to new version: 75074390c7ce8e46dac0962e01416e8041228165
compatibility::simple-validator-upgrade::single-validator-upgrading : committed: 8602.35 txn/s, latency: 3447.96 ms, (p50: 3800 ms, p70: 4100, p90: 4600 ms, p99: 4900 ms), latency samples: 155880
compatibility::simple-validator-upgrade::single-validator-upgrade : committed: 8586.33 txn/s, latency: 3890.40 ms, (p50: 4200 ms, p70: 4300, p90: 4500 ms, p99: 4800 ms), latency samples: 285260
3. Upgrading rest of first batch to new version: 75074390c7ce8e46dac0962e01416e8041228165
compatibility::simple-validator-upgrade::half-validator-upgrading : committed: 8427.85 txn/s, latency: 3575.34 ms, (p50: 4100 ms, p70: 4200, p90: 4400 ms, p99: 4400 ms), latency samples: 154020
compatibility::simple-validator-upgrade::half-validator-upgrade : committed: 8691.80 txn/s, latency: 3831.49 ms, (p50: 4100 ms, p70: 4300, p90: 4400 ms, p99: 4800 ms), latency samples: 290200
4. upgrading second batch to new version: 75074390c7ce8e46dac0962e01416e8041228165
compatibility::simple-validator-upgrade::rest-validator-upgrading : committed: 14624.93 txn/s, latency: 1968.06 ms, (p50: 2200 ms, p70: 2300, p90: 2300 ms, p99: 2400 ms), latency samples: 249700
compatibility::simple-validator-upgrade::rest-validator-upgrade : committed: 14741.18 txn/s, latency: 2195.92 ms, (p50: 2300 ms, p70: 2300, p90: 2400 ms, p99: 2500 ms), latency samples: 473040
5. check swarm health
Compatibility test for 6593fb81261f25490ffddc2252a861c994234c2a ==> 75074390c7ce8e46dac0962e01416e8041228165 passed
Test Ok

• Grafana dashboard
• Humio Logs
• Axiom Logs
• Validator CPU Profile
• Fullnode CPU Profile
• Test runner output
• Test run is land-blocking

[github-actions]

✅ Forge suite realistic_env_max_load success on 75074390c7ce8e46dac0962e01416e8041228165

two traffics test: inner traffic : committed: 15244.96 txn/s, latency: 2608.67 ms, (p50: 2700 ms, p70: 2700, p90: 2700 ms, p99: 3300 ms), latency samples: 5796560
two traffics test : committed: 99.97 txn/s, latency: 1335.30 ms, (p50: 1300 ms, p70: 1400, p90: 1500 ms, p99: 2600 ms), latency samples: 1720
Latency breakdown for phase 0: ["MempoolToBlockCreation: max: 1.545, avg: 1.484", "ConsensusProposalToOrdered: max: 0.287, avg: 0.281", "ConsensusOrderedToCommit: max: 0.289, avg: 0.284", "ConsensusProposalToCommit: max: 0.570, avg: 0.566"]
Max non-epoch-change gap was: 0 rounds at version 0 (avg 0.00) [limit 4], 0.54s no progress at version 28270 (avg 0.19s) [limit 15].
Max epoch-change gap was: 0 rounds at version 0 (avg 0.00) [limit 4], 0.54s no progress at version 2836004 (avg 0.54s) [limit 16].
Test Ok

• Grafana dashboard
• Humio Logs
• Axiom Logs
• Validator CPU Profile
• Fullnode CPU Profile
• Test runner output
• Test run is land-blocking

[msmouse]

Okay, to my surprise this didn't change any number much, but still a good peace of mind to have I think..

@igor-aptos @grao1991 ?