37f55e4f71
Aere Network public source. Everything here can be checked against the live chain (chain id 2800, https://rpc.aere.network). Scope note, stated up front rather than buried: consensus on chain 2800 is classical secp256k1 ECDSA QBFT. The post-quantum work in this repository is at the signature, precompile, account and transport layers. Nothing here makes the consensus post-quantum, and no document in it should be read as claiming so.
74 lines
5.2 KiB
Plaintext
74 lines
5.2 KiB
Plaintext
=======================================================
|
|
BLOCK-STM END-TO-END BLOCK-PRODUCTION THROUGHPUT
|
|
machine threads available : 16
|
|
txns per batch : 20000
|
|
simulated EVM cost per tx : 200 keccak-rounds
|
|
timing : median of 5 runs (ms)
|
|
pipeline : exec (parallel) + commit (serial) + state-root (serial)
|
|
serial-equivalence : par state == seq state AND keccak roots identical, EVERY run
|
|
=======================================================
|
|
|
|
### 0% designed conflict (disjoint accounts, 64 contracts spread)
|
|
committed state keys : 49637
|
|
sequential exec 1724.47 ms | root 9.46 ms | END-TO-END 1733.93 ms | root-share 0.5%
|
|
sequential end-to-end TPS: 11535
|
|
W | exec commit root e2e_ms | execSpd e2eSpd | TPS abort% | root%e2e | equiv
|
|
1 | 1732.47 8.95 9.31 1750.73 | 1.00x 0.99x | 11424 0.0% | 1.0% | PASS
|
|
2 | 872.83 9.82 10.15 892.80 | 1.98x 1.94x | 22402 0.0% | 2.2% | PASS
|
|
4 | 443.14 8.61 8.70 460.44 | 3.89x 3.77x | 43436 0.1% | 3.8% | PASS
|
|
8 | 224.20 9.49 10.65 244.34 | 7.69x 7.10x | 81854 0.2% | 8.2% | PASS
|
|
16 | 127.82 8.57 8.52 144.91 | 13.49x 11.97x | 138021 0.3% | 11.8% | PASS
|
|
Amdahl: serial tail (commit+root) = 17.72 ms; end-to-end speedup ceiling @16w = 11.54x, @infinite cores = 97.86x
|
|
|
|
### 10% designed conflict (100 hot accts, 16 contracts)
|
|
committed state keys : 18342
|
|
sequential exec 1660.34 ms | root 3.02 ms | END-TO-END 1663.36 ms | root-share 0.2%
|
|
sequential end-to-end TPS: 12024
|
|
W | exec commit root e2e_ms | execSpd e2eSpd | TPS abort% | root%e2e | equiv
|
|
1 | 1763.89 4.87 4.27 1773.02 | 0.94x 0.94x | 11280 0.0% | 0.5% | PASS
|
|
2 | 867.29 4.93 3.98 876.21 | 1.91x 1.90x | 22826 0.1% | 1.0% | PASS
|
|
4 | 428.26 5.18 4.03 437.47 | 3.88x 3.80x | 45717 0.3% | 2.1% | PASS
|
|
8 | 218.20 5.32 3.80 227.31 | 7.61x 7.32x | 87986 0.7% | 4.0% | PASS
|
|
16 | 131.28 5.16 3.23 139.68 | 12.65x 11.91x | 143189 1.3% | 6.0% | PASS
|
|
Amdahl: serial tail (commit+root) = 8.43 ms; end-to-end speedup ceiling @16w = 12.04x, @infinite cores = 197.38x
|
|
|
|
### 50% designed conflict (20 hot accts, 4 contracts)
|
|
committed state keys : 9006
|
|
sequential exec 1663.44 ms | root 1.41 ms | END-TO-END 1664.84 ms | root-share 0.1%
|
|
sequential end-to-end TPS: 12013
|
|
W | exec commit root e2e_ms | execSpd e2eSpd | TPS abort% | root%e2e | equiv
|
|
1 | 1696.76 2.52 1.54 1700.82 | 0.98x 0.98x | 11759 0.0% | 0.2% | PASS
|
|
2 | 872.94 2.49 1.74 877.18 | 1.91x 1.90x | 22800 2.2% | 0.5% | PASS
|
|
4 | 460.75 2.57 1.59 464.91 | 3.61x 3.58x | 43019 5.8% | 0.9% | PASS
|
|
8 | 256.91 2.32 1.57 260.79 | 6.47x 6.38x | 76690 11.1% | 1.5% | PASS
|
|
16 | 170.84 1.96 1.48 174.29 | 9.74x 9.55x | 114753 18.2% | 2.0% | PASS
|
|
Amdahl: serial tail (commit+root) = 3.51 ms; end-to-end speedup ceiling @16w = 9.21x, @infinite cores = 474.53x
|
|
|
|
### PATHOLOGICAL ~100% (single hot slot, no parallelism)
|
|
committed state keys : 1996
|
|
sequential exec 1624.41 ms | root 0.29 ms | END-TO-END 1624.71 ms | root-share 0.0%
|
|
sequential end-to-end TPS: 12310
|
|
W | exec commit root e2e_ms | execSpd e2eSpd | TPS abort% | root%e2e | equiv
|
|
1 | 1670.23 0.06 0.38 1670.67 | 0.97x 0.97x | 11971 0.0% | 0.0% | PASS
|
|
2 | 896.96 0.05 0.37 897.37 | 1.81x 1.81x | 22287 6.6% | 0.0% | PASS
|
|
4 | 503.18 0.05 0.68 503.91 | 3.23x 3.22x | 39689 14.5% | 0.1% | PASS
|
|
8 | 311.47 0.07 0.57 312.11 | 5.22x 5.21x | 64081 21.3% | 0.2% | PASS
|
|
16 | 294.20 0.04 0.36 294.60 | 5.52x 5.51x | 67888 24.1% | 0.1% | PASS
|
|
Amdahl: serial tail (commit+root) = 0.38 ms; end-to-end speedup ceiling @16w = 5.93x, @infinite cores = 4288.05x
|
|
|
|
=======================================================
|
|
SERIAL-EQUIVALENCE: 100 checks, 0 mismatches
|
|
RESULT: PASS -- every parallel run committed the exact sequential state + root
|
|
=======================================================
|
|
|
|
HONEST READING:
|
|
- execSpd is the EXECUTION-PHASE speedup (comparable to the documented ~9.4x).
|
|
- e2eSpd is the END-TO-END block-production speedup. It is LOWER, because the
|
|
commit (state materialization) and state-root (keccak) phases are serial and
|
|
do not shrink with more workers -- the Amdahl serial tail.
|
|
- TPS is the real end-to-end transactions/second of THIS pipeline on THIS box
|
|
(shared-vCPU cloud). It is a measured rollup-batch number, NOT the 273k TPS
|
|
documented-conditions marketing ceiling and does not reach or imply it.
|
|
- Under total conflict (pathological) there is no parallelism; end-to-end can be
|
|
<= 1x. That is the correct, honest behavior of Block-STM.
|