Benchmarks: measured on whole nodes
This page shows load-test results for cdnca nodes with 2, 4 and 8 cores, so you can size a node and plan capacity from your traffic.
Summary
Scenario: reverse proxy plus access control worst path (5 rules × 5 conditions, hit on the last condition of the 5th rule). HTTPS uses an RSA 2048 certificate.
| Node spec | HTTP sustainable throughput (QPS) | HTTPS sustainable throughput (QPS) |
|---|---|---|
| 2 cores (Intel Xeon E5-2686 v4 @ 2.30GHz) | 2,000 | 2,000 |
| 4 cores (Intel Xeon E5-2686 v4 @ 2.30GHz) | 4,000 | 4,000 |
| 8 cores (Intel Xeon E5-2686 v4 @ 2.30GHz) | 8,000 | 8,000 |
Detailed results
Same scenario. Each spec lists peak and sustainable figures for HTTP and HTTPS.
| Node spec | HTTP | HTTPS | ||
|---|---|---|---|---|
| 2 cores (Intel Xeon E5-2686 v4 @ 2.30GHz) | Peak throughput:2,248 QPS P99 latency 10,475.36 ms Error rate 0.00% | Sustainable throughput:2,000 QPS P99 latency 21.75 ms Error rate 0.00% | Peak throughput:2,129 QPS P99 latency 458.33 ms Error rate 0.00% | Sustainable throughput:2,000 QPS P99 latency 21.68 ms Error rate 0.00% |
| 4 cores (Intel Xeon E5-2686 v4 @ 2.30GHz) | Peak throughput:4,327 QPS P99 latency 414.36 ms Error rate 0.00% | Sustainable throughput:4,000 QPS P99 latency 26.44 ms Error rate 0.00% | Peak throughput:4,207 QPS P99 latency 447.02 ms Error rate 0.00% | Sustainable throughput:4,000 QPS P99 latency 42.76 ms Error rate 0.00% |
| 8 cores (Intel Xeon E5-2686 v4 @ 2.30GHz) | Peak throughput:8,396 QPS P99 latency 220.99 ms Error rate 0.00% | Sustainable throughput:8,000 QPS P99 latency 35.99 ms Error rate 0.00% | Peak throughput:8,342 QPS P99 latency 230.05 ms Error rate 0.00% | Sustainable throughput:8,000 QPS P99 latency 27.28 ms Error rate 0.00% |
Protection scenarios
Sustainable / peak QPS at 2, 4 and 8 cores for each protection mix (each cell shows “sustainable / peak”, in QPS).
| Configuration | 2 cores | 4 cores | 8 cores |
|---|---|---|---|
| Reverse proxy (origin fetch) | 2,000 / 2,476 | 4,500 / 4,756 | 9,000 / 9,317 |
| Cache hit | 2,000 / 2,658 | 4,500 / 4,912 | 10,000 / 9,996 |
| CC, 1 rule | 2,000 / 2,325 | 4,500 / 4,594 | 8,000 / 9,088 |
| CC, 10 rules all counting | 2,000 / 2,156 | 4,000 / 4,213 | 7,000 / 8,292 |
| CC worst path (10 rules × 3 conditions, 2-key count) | 2,000 / 2,318 | 4,000 / 4,513 | 8,000 / 8,786 |
| Access control worst path (5 rules × 5 conditions) | 2,000 / 2,248 | 4,000 / 4,327 | 8,000 / 8,396 |
| Managed WAF standard (CRS PL1) | 400 / 652 | 500 / 1,247 | 1,000 / 2,438 |
| Managed WAF strict (CRS PL2) | 200 / 400 | 250 / 760 | — / 1,474 |
| Managed WAF paranoid (CRS PL3) | 200 / 368 | 250 / 709 | — / 1,389 |
| JS challenge (every request gets the challenge page) | 3,500 / 4,000 | ≥ 6,000 / ≥ 6,000 | ≥ 12,000 / ≥ 12,000 |
| Automatic defense on (idle state) | 2,000 / 2,408 | 4,000 / 4,618 | 8,000 / 9,218 |
| Everything on (ACL 5×5 + CC worst path + CRS PL1 + automatic defense) | 400 / 615 | 750 / 1,192 | 1,000 / 2,305 |
| HTTPS reverse proxy (ECDSA P-256) | 2,000 / 2,182 | 4,000 / 4,197 | 8,000 / 8,473 |
| HTTPS reverse proxy (RSA 2048) | 2,000 / 2,129 | 4,000 / 4,207 | 8,000 / 8,342 |
| HTTPS, everything on | 400 / 588 | 500 / 1,150 | 1,000 / 2,117 |
“—”: a dash in the sustainable position means even the lowest step was outside the sustainable criteria; a dash for the whole cell means it was not measured this round. “≥”: the top step was still sustainable, so the real figure is higher.
100,000 sites
The node agent’s dynamic routing runtime loading 10,000 and 100,000 sites (2 domains each) with the OpenResty from the same 1.0.35 release, 2 workers, a 10-core 6 GB container.
| Item | 10,000 sites | 100,000 sites |
|---|---|---|
| First load of all sites | 2273.1ms | 18062.2ms, 17958.7ms |
| Change 1 site until live | 812.4ms | 1436.2ms, 1572.6ms |
| Reload on site change | No | No, No |
| Warm request p50 (1 client) | 707us | 820us, 826us |
| Warm request p99 (1 client) | 1285us | 1781us, 1628us |
| Warm request p99 (16 clients) | 5882us | 12563us, 12428us |
| OpenResty total PSS (after load) | 268.0MiB | 379.5MiB, 382.6MiB |
| Node restart until serving | 990.6ms | 9202.1ms, 8725.9ms |
Test environment and topology
- Host CPU: Intel Xeon E5-2686 v4 @ 2.30GHz (KVM, one thread per core), 32 vCPU / 31 GB in total.
- Node, origin and load generator run on the same host, split by cpuset: node 2 / 4 / 8 cores, origin 4 cores, load generator (k6) 16 cores, over loopback.
- Software: cdnca 1.0.35 (source commit 6d69d0480), OpenResty 1.31.1.1, Ubuntu 24.04 in the container; worker count equals the node core count (worker_processes auto).
- Load tool: k6.
- Configuration: sites and rules are created on a control plane, published through the normal pipeline to a real node, and the published site objects, index, nginx.conf, certificates and rule plans are copied from that node and replayed.
Topology: k6 (client) → node → origin (keepalive)
Metric definitions
- Target QPS: the request arrival rate configured in k6 constant-arrival-rate.
- Achieved QPS: the rate at which requests actually complete.
- Peak: the highest achieved QPS over all steps.
- Sustainable: the highest target rate where error rate < 0.1%, P99 ≤ 50 ms and achieved ≥ 99% of target; use it for capacity planning.
- Saturation: the first step where raising the target no longer raises achieved QPS in step and P99 rises above twice the sustainable P99.
- Error rate: 5xx, timeouts and connection errors only; 4xx and challenge pages returned by protection by design are not counted.
Method
- Request: GET a 1 KB static page, Accept-Encoding: identity, desktop Chrome User-Agent; the origin answers no-store (origin fetch) or no cache headers (cache-hit row).
- HTTP: HTTP/1.1 keepalive. HTTPS: TLS 1.3 + HTTP/2 with connection reuse. Origin: HTTP/1.1 keepalive. CC and automatic-defense rows rotate 4,096 X-Forwarded-For addresses.
- Stepped load: k6 constant-arrival-rate, 30 s per step with 5 s gaps; the first 5 s of each step are dropped from CPU figures. Step targets follow the core count: 2 cores 500 to 4,000 in steps of 500; 4 cores 1,000, 2,000, 3,000, 3,500, 4,000, 4,500, 5,000, 6,000; 8 cores 2,000, 4,000, 6,000, 7,000, 8,000, 9,000, 10,000, 12,000.