← All Workloads

Web Serving

Static file serving, API throughput, and request handling performance for web applications.

Nginx Requests/sec

Higher is better -- sorted by performance

Our Recommendations

C3c3-standard-8

Maximum throughput and lowest latency

Highest single-core performance on GCP translates directly to the fastest request handling. The 4th-gen Intel Xeon Scalable processors deliver 82K Nginx req/s -- 21% more than the next best option.

N2n2-standard-8

Production web servers with good price-performance

Strong performance at a lower price point than C3. 68K Nginx req/s covers most production web workloads comfortably. Up to 100 Gbps network bandwidth for traffic-heavy sites.

T2Dt2d-standard-8

Cost-optimized scale-out deployments

Best price-per-request for steady-state workloads. Tau VMs are optimized for scale-out architectures where you run many instances behind a load balancer.

Budget PickE2(e2-standard-4)

E2 VMs offer the lowest cost for development, staging, and low-traffic production sites. Performance is adequate for most sites under 1000 concurrent users.

Price-Performance: Nginx Requests/sec

VM SeriesMachine TypePerformanceCost/hrPerf/$
C3Dc3d-standard-876,000 req$0.384197,917
C3c3-standard-882,000 req$0.418196,172
T2Dt2d-standard-858,000 req$0.308188,312
N2n2-standard-868,000 req$0.388175,258
E2e2-standard-842,000 req$0.268156,716

All Benchmark Data

VM SeriesMachine TypeMetricResultNotes
E2e2-standard-8Nginx Requests/sec42,000 req/sStatic file serving, 100 concurrent connections, wrk benchmark
N2n2-standard-8Nginx Requests/sec68,000 req/sStatic file serving, 100 concurrent connections, wrk benchmark
N2Dn2d-standard-8Nginx Requests/sec64,000 req/sStatic file serving, 100 concurrent connections, wrk benchmark
T2Dt2d-standard-8Nginx Requests/sec58,000 req/sStatic file serving, 100 concurrent connections, wrk benchmark
C3c3-standard-8Nginx Requests/sec82,000 req/sStatic file serving, 100 concurrent connections, wrk benchmark
C3Dc3d-standard-8Nginx Requests/sec76,000 req/sStatic file serving, 100 concurrent connections, wrk benchmark
E2e2-standard-8Node.js API Requests/sec12,400 req/sExpress.js JSON API, 50 concurrent connections
N2n2-standard-8Node.js API Requests/sec18,600 req/sExpress.js JSON API, 50 concurrent connections
C3c3-standard-8Node.js API Requests/sec24,200 req/sExpress.js JSON API, 50 concurrent connections
C3Dc3d-standard-8Node.js API Requests/sec21,800 req/sExpress.js JSON API, 50 concurrent connections