Commit Latency vs Throughput
Commit Latency vs Throughput
Analysis of how commit latency scales with achieved throughput.
Values shown as mean ± standard deviation across seeds.
num_tables = 1
| Throughput (c/s) | Success Rate (%) | P50 Latency (s) | P95 Latency (s) | P99 Latency (s) | Mean Retries |
|---|
| 0.2 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 1.33 ± 0.35 | 4.49 ± 1.35 | 1.0 |
| 0.4 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 2.14 ± 0.35 | 8.85 ± 1.28 | 1.1 |
| 0.8 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 4.46 ± 0.94 | 19.66 ± 3.23 | 1.3 |
| 1.7 ± 0.0 | 100.0 ± 0.0 | 0.38 ± 0.00 | 9.55 ± 1.03 | 43.69 ± 5.92 | 1.6 |
| 2.1 ± 0.0 | 99.9 ± 0.0 | 0.39 ± 0.00 | 11.84 ± 2.01 | 56.37 ± 8.49 | 1.7 |
| 2.7 ± 0.0 | 99.6 ± 0.2 | 0.46 ± 0.00 | 16.33 ± 2.83 | 77.51 ± 6.58 | 2.1 |
| 3.9 ± 0.0 | 96.3 ± 0.2 | 0.56 ± 0.01 | 16.40 ± 0.77 | 95.78 ± 4.71 | 2.9 |
| 5.5 ± 0.0 | 67.4 ± 0.3 | 0.86 ± 0.01 | 1.97 ± 0.01 | 33.18 ± 6.35 | 4.5 |
| 6.3 ± 0.0 | 38.6 ± 0.1 | 1.00 ± 0.01 | 1.95 ± 0.01 | 2.14 ± 0.02 | 5.0 |
| 7.2 ± 0.0 | 17.5 ± 0.1 | 1.07 ± 0.01 | 1.94 ± 0.00 | 2.08 ± 0.01 | 5.3 |
num_tables = 2
| Throughput (c/s) | Success Rate (%) | P50 Latency (s) | P95 Latency (s) | P99 Latency (s) | Mean Retries |
|---|
| 0.2 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.79 ± 0.17 | 2.40 ± 0.55 | 1.0 |
| 0.4 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 1.25 ± 0.38 | 5.55 ± 1.52 | 1.1 |
| 0.8 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 2.64 ± 0.29 | 10.06 ± 1.46 | 1.2 |
| 1.6 ± 0.0 | 100.0 ± 0.0 | 0.37 ± 0.00 | 4.57 ± 0.91 | 21.20 ± 2.96 | 1.4 |
| 2.1 ± 0.0 | 100.0 ± 0.0 | 0.37 ± 0.00 | 5.93 ± 0.48 | 28.38 ± 2.04 | 1.5 |
| 2.7 ± 0.0 | 100.0 ± 0.0 | 0.38 ± 0.00 | 8.65 ± 0.25 | 39.84 ± 0.86 | 1.7 |
| 4.1 ± 0.0 | 99.9 ± 0.0 | 0.41 ± 0.00 | 11.31 ± 1.17 | 56.32 ± 3.16 | 2.1 |
| 7.8 ± 0.0 | 94.8 ± 0.2 | 0.60 ± 0.00 | 12.78 ± 1.44 | 85.13 ± 7.60 | 3.7 |
| 10.5 ± 0.0 | 63.9 ± 0.1 | 0.89 ± 0.00 | 1.81 ± 0.01 | 18.12 ± 1.99 | 5.3 |
| 11.8 ± 0.0 | 28.8 ± 0.1 | 0.97 ± 0.00 | 1.79 ± 0.00 | 1.98 ± 0.01 | 5.7 |
num_tables = 5
| Throughput (c/s) | Success Rate (%) | P50 Latency (s) | P95 Latency (s) | P99 Latency (s) | Mean Retries |
|---|
| 0.2 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.55 ± 0.05 | 1.04 ± 0.25 | 1.0 |
| 0.4 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.92 ± 0.09 | 3.05 ± 0.64 | 1.1 |
| 0.8 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 1.33 ± 0.23 | 4.27 ± 0.56 | 1.2 |
| 1.6 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 2.27 ± 0.17 | 9.25 ± 0.68 | 1.3 |
| 2.0 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 2.62 ± 0.20 | 11.87 ± 1.31 | 1.4 |
| 2.7 ± 0.0 | 100.0 ± 0.0 | 0.37 ± 0.00 | 3.42 ± 0.43 | 14.98 ± 1.08 | 1.5 |
| 4.1 ± 0.0 | 100.0 ± 0.0 | 0.37 ± 0.00 | 5.22 ± 0.28 | 23.57 ± 0.60 | 1.8 |
| 8.2 ± 0.0 | 100.0 ± 0.0 | 0.40 ± 0.00 | 9.35 ± 0.75 | 45.15 ± 2.41 | 2.4 |
| 16.0 ± 0.1 | 97.6 ± 0.1 | 0.55 ± 0.00 | 14.50 ± 0.92 | 79.73 ± 2.03 | 3.7 |
| 25.5 ± 0.0 | 62.2 ± 0.2 | 0.89 ± 0.00 | 1.76 ± 0.00 | 17.47 ± 2.22 | 5.6 |
num_tables = 10
| Throughput (c/s) | Success Rate (%) | P50 Latency (s) | P95 Latency (s) | P99 Latency (s) | Mean Retries |
|---|
| 0.2 ± 0.0 | 100.0 ± 0.0 | 0.34 ± 0.00 | 0.50 ± 0.04 | 0.88 ± 0.14 | 1.0 |
| 0.4 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.56 ± 0.04 | 1.39 ± 0.17 | 1.1 |
| 0.8 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.75 ± 0.09 | 2.36 ± 0.19 | 1.2 |
| 1.7 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 1.23 ± 0.04 | 4.78 ± 0.38 | 1.3 |
| 2.0 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 1.48 ± 0.10 | 5.68 ± 0.44 | 1.4 |
| 2.7 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 1.86 ± 0.10 | 7.68 ± 0.58 | 1.5 |
| 4.1 ± 0.0 | 100.0 ± 0.0 | 0.37 ± 0.00 | 2.62 ± 0.19 | 11.35 ± 0.42 | 1.7 |
| 8.2 ± 0.0 | 100.0 ± 0.0 | 0.38 ± 0.00 | 5.24 ± 0.09 | 22.85 ± 1.07 | 2.1 |
| 16.4 ± 0.0 | 99.9 ± 0.0 | 0.41 ± 0.00 | 9.75 ± 0.47 | 44.09 ± 1.37 | 2.8 |
| 37.5 ± 0.1 | 91.7 ± 0.0 | 0.64 ± 0.00 | 10.23 ± 0.54 | 77.52 ± 1.13 | 4.6 |
num_tables = 20
| Throughput (c/s) | Success Rate (%) | P50 Latency (s) | P95 Latency (s) | P99 Latency (s) | Mean Retries |
|---|
| 0.2 ± 0.0 | 100.0 ± 0.0 | 0.32 ± 0.00 | 0.45 ± 0.02 | 0.57 ± 0.06 | 1.0 |
| 0.4 ± 0.0 | 100.0 ± 0.0 | 0.34 ± 0.00 | 0.51 ± 0.04 | 0.90 ± 0.05 | 1.1 |
| 0.8 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.58 ± 0.03 | 1.42 ± 0.12 | 1.2 |
| 1.7 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 0.84 ± 0.05 | 2.45 ± 0.22 | 1.3 |
| 2.0 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 0.88 ± 0.11 | 3.06 ± 0.28 | 1.4 |
| 2.7 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 1.10 ± 0.06 | 4.07 ± 0.25 | 1.5 |
| 4.1 ± 0.0 | 100.0 ± 0.0 | 0.37 ± 0.00 | 1.49 ± 0.09 | 5.72 ± 0.36 | 1.6 |
| 8.2 ± 0.0 | 100.0 ± 0.0 | 0.38 ± 0.00 | 2.67 ± 0.11 | 11.61 ± 0.48 | 2.0 |
| 16.4 ± 0.1 | 100.0 ± 0.0 | 0.39 ± 0.00 | 4.94 ± 0.21 | 22.30 ± 0.59 | 2.4 |
| 40.5 ± 0.1 | 98.9 ± 0.0 | 0.46 ± 0.00 | 11.28 ± 0.33 | 54.13 ± 1.41 | 3.6 |
num_tables = 50
| Throughput (c/s) | Success Rate (%) | P50 Latency (s) | P95 Latency (s) | P99 Latency (s) | Mean Retries |
|---|
| 0.2 ± 0.0 | 100.0 ± 0.0 | 0.24 ± 0.01 | 0.43 ± 0.01 | 0.52 ± 0.03 | 1.0 |
| 0.4 ± 0.0 | 100.0 ± 0.0 | 0.32 ± 0.00 | 0.45 ± 0.01 | 0.59 ± 0.03 | 1.0 |
| 0.8 ± 0.0 | 100.0 ± 0.0 | 0.34 ± 0.00 | 0.48 ± 0.00 | 0.86 ± 0.09 | 1.1 |
| 1.6 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.56 ± 0.02 | 1.27 ± 0.14 | 1.3 |
| 2.0 ± 0.0 | 100.0 ± 0.0 | 0.35 ± 0.00 | 0.58 ± 0.01 | 1.43 ± 0.08 | 1.3 |
| 2.7 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 0.69 ± 0.04 | 1.85 ± 0.03 | 1.4 |
| 4.1 ± 0.0 | 100.0 ± 0.0 | 0.36 ± 0.00 | 0.81 ± 0.03 | 2.55 ± 0.08 | 1.6 |
| 8.2 ± 0.0 | 100.0 ± 0.0 | 0.37 ± 0.00 | 1.28 ± 0.08 | 4.89 ± 0.18 | 1.9 |
| 16.4 ± 0.1 | 100.0 ± 0.0 | 0.38 ± 0.00 | 2.19 ± 0.04 | 9.24 ± 0.24 | 2.3 |
| 40.7 ± 0.0 | 99.4 ± 0.0 | 0.40 ± 0.00 | 4.87 ± 0.08 | 22.34 ± 0.49 | 3.1 |
Notes
- Latencies reported in seconds (converted from milliseconds)
- Values shown as mean ± standard deviation across multiple seeds
- Throughput = commits per second during steady-state window
- Success rate = percentage of transactions that committed successfully
- Mean retries = average number of retry attempts per committed transaction
