← Back to comparison

Blocky

Port: 15555 | Image: blocky:bench

Results by Scenario

Cache hit

All queries resolve from server cache — measures peak throughput.

Provider QPS Avg (ms) Lost % Total Qrys Base Mem (MB)
Quad9 932.72 97.78 0.20 28123 32.44
Cloudflare 802.31 100.45 0.51 24269 37.56
Google 929.89 98.44 0.17 28083 34.33
OpenDNS 909.27 96.06 0.27 27536 33.64
Quad9 896.22 97.67 0.28 27043 35.07
Cloudflare 897.98 99.88 0.24 27093 31.92
Google 931.74 95.88 0.22 28272 33.74
OpenDNS 954.16 97.19 0.15 28846 33.62

Cache miss

Every query requires full upstream resolution — measures worst-case performance. In common-denominator mode some servers report near-zero QPS when plain-DNS upstream forwarding fails.

Provider QPS Avg (ms) Lost % Total Qrys Base Mem (MB)
Quad9 199.42 102.30 0.11 6000 33.11
Cloudflare 199.25 101.20 0.19 6000 38.56
Google 199.46 102.59 0.09 6000 35.95
OpenDNS 199.22 103.67 0.19 6000 33.57
Quad9 82.50 214.42 11.60 2887 39.43
Cloudflare 199.52 105.85 0.06 6000 36.82
Google 199.47 99.35 0.10 6000 38.61
OpenDNS 199.49 102.89 0.07 6000 36.07

Mixed

90% cached + 10% unique domains — simulates real-world mixed workload.

Provider QPS Avg (ms) Lost % Total Qrys Base Mem (MB)
Quad9 896.13 96.60 0.33 27054 34.85
Cloudflare 916.28 94.12 0.31 27654 35.98
Google 912.17 98.22 0.22 27731 36.72
OpenDNS 939.70 98.97 0.16 28372 36.05
Quad9 941.25 97.38 0.17 28377 40.69
Cloudflare 926.42 97.50 0.22 27940 34.20
Google 929.53 95.83 0.21 28311 37.43
OpenDNS 983.97 93.44 0.16 29722 37.36

Blocked

Domains on the sinkhole blocklist — measures filtering throughput.

Provider QPS Avg (ms) Lost % Total Qrys Base Mem (MB)
Quad9 928.68 97.18 0.22 28013 35.29
Cloudflare 856.71 98.48 0.41 25902 41.28
Google 872.71 101.42 0.14 27884 40.21
OpenDNS 953.02 94.84 0.20 28870 34.98
Quad9 395.00 105.21 2.49 14014 42.81
Cloudflare 949.44 94.44 0.22 28634 35.91
Google 865.76 98.81 0.32 26436 39.43
OpenDNS 859.35 100.00 0.24 27032 34.95

Methodology

Transport Protocol Confound

This server uses DoH for best-of-breed mode. Comparisons against servers using different protocols (DoH, DoT, plain) partly reflect protocol overhead. The common-denominator mode forces all servers to plain UDP 53 to isolate server-side performance.

Warmup

Before each scenario, a 5-second dnsperf warmup pass is run to stabilize connections and fill the TCP congestion window. For cache-hit and mixed scenarios, the server cache is also pre-warmed. The measurement window (-l 30) begins only after both warmup phases complete.

Test Parameters

Back to comparison | Generated 2026-07-01T21:33:06Z