# static_web

> Static web server benchmark workloads: Static web server latency, Static web server+client speed, Static web server (extrapolated) speed and 2 more.

Static web server

## Static web server latency {#static_web-latency}

Serving smaller (1-64 KiB) and larger (256-512 KiB) files using a static HTTP server (binserve) as a single process, and benchmarking each workload (wrk) using variable number of threads (and keeping the threads with the maximum performance) and connections (recorded after divided by the number of vCPUs to make it comparable with other servers with different vCPU count) on the same server. The average latency reported by wrk.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>static_web:latency</code></dd><dt>Unit of measurement</dt><dd>Seconds (sec)</dd><dt>Server types evaluated</dt><dd>3,655</dd><dt>Total measurements</dt><dd>102,340</dd><dt>Range of measurements</dt><dd>0.00000674 – 0.224 <small>sec</small></dd><dt>Better</dt><dd>↓ Lower is better</dd></dl>

Configuration options

| Field | Description | Example values |
| --- | --- | --- |
| `size` | Served file size (KiB). | `16k` `1k` `256k` `512k` `64k` |
| `connections_per_vcpus` | Open HTTP connections per vCPU(s). | `0.5` `0.8888888888888888` `1` `1.7777777777777777` `2` `3.5555555555555554` `4` `7.111111111111111` `8` `14.222222222222221` `16` `28.444444444444443` `32` |

:::warning

Latency is recorded during the static\_web:rps run, not as a standalone benchmark. As it reflects a characteristic of that throughput measurement, it is not recommended for comparing instances on its own; use it instead as a filter when interpreting the related throughput scores.

:::

Score distribution <small>(102,340 measurements)</small>

![Score distribution of Static web server latency](/benchmarks/histograms/static_web-latency.svg)

## Static web server+client speed {#static_web-rps}

Serving smaller (1-64 KiB) and larger (256-512 KiB) files using a static HTTP server (binserve) as a single process, and benchmarking each workload (wrk) using variable number of threads (and keeping the threads with the maximum performance) and connections (recorded after divided by the number of vCPUs to make it comparable with other servers with different vCPU count) on the same server. The measured RPS is not the maximum expected server speed, as the server shares CPU with the client.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>static_web:rps</code></dd><dt>Unit of measurement</dt><dd>Requests per second (rps)</dd><dt>Server types evaluated</dt><dd>3,655</dd><dt>Total measurements</dt><dd>102,340</dd><dt>Range of measurements</dt><dd>342 – 10M <small>rps</small></dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Configuration options

| Field | Description | Example values |
| --- | --- | --- |
| `size` | Served file size (KiB). | `16k` `1k` `256k` `512k` `64k` |
| `connections_per_vcpus` | Open HTTP connections per vCPU(s). | `0.5` `0.8888888888888888` `1` `1.7777777777777777` `2` `3.5555555555555554` `4` `7.111111111111111` `8` `14.222222222222221` `16` `28.444444444444443` `32` |

:::warning

This benchmark does not scale well on large instances (100+ vCPUs) due to a listener bottleneck in the single-process HTTP server.

:::

Score distribution <small>(102,340 measurements)</small>

![Score distribution of Static web server+client speed](/benchmarks/histograms/static_web-rps.svg)

## Static web server (extrapolated) speed {#static_web-rps-extrapolated}

Serving smaller (1-64 KiB) and larger (256-512 KiB) files using a static HTTP server (binserve) as a single process, and benchmarking each workload (wrk) using variable number of threads (and keeping the threads with the maximum performance) and connections (recorded after divided by the number of vCPUs to make it comparable with other servers with different vCPU count) on the same server. The extrapolated RPS is based on the measured RPS adjusted by the server's and client's time spent executing in user/system mode, so trying to control for the client resource usage.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>static_web:rps-extrapolated</code></dd><dt>Unit of measurement</dt><dd>Requests per second (rps)</dd><dt>Server types evaluated</dt><dd>3,655</dd><dt>Total measurements</dt><dd>102,340</dd><dt>Range of measurements</dt><dd>603.9 – 20.1M <small>rps</small></dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Derived from [`static_web:rps`](#static_web-rps): Measured RPS adjusted by server/client user+system CPU time to control for client resource usage.

Configuration options

| Field | Description | Example values |
| --- | --- | --- |
| `size` | Served file size (KiB). | `16k` `1k` `256k` `512k` `64k` |
| `connections_per_vcpus` | Open HTTP connections per vCPU(s). | `0.5` `0.8888888888888888` `1` `1.7777777777777777` `2` `3.5555555555555554` `4` `7.111111111111111` `8` `14.222222222222221` `16` `28.444444444444443` `32` |

:::warning

This benchmark does not scale well on large instances (100+ vCPUs) due to a listener bottleneck in the single-process HTTP server.

:::

Score distribution <small>(102,340 measurements)</small>

![Score distribution of Static web server (extrapolated) speed](/benchmarks/histograms/static_web-rps-extrapolated.svg)

## Static web server+client throughput {#static_web-throughput}

Serving smaller (1-64 KiB) and larger (256-512 KiB) files using a static HTTP server (binserve) as a single process, and benchmarking each workload (wrk) using variable number of threads (and keeping the threads with the maximum performance) and connections (recorded after divided by the number of vCPUs to make it comparable with other servers with different vCPU count) on the same server. Throughput is calculated by multiplying the RPS with the served file size. The measured RPS is not the maximum expected server speed, as the server shares CPU with the client.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>static_web:throughput</code></dd><dt>Unit of measurement</dt><dd>Bytes per second (Bps)</dd><dt>Server types evaluated</dt><dd>3,655</dd><dt>Total measurements</dt><dd>102,340</dd><dt>Range of measurements</dt><dd>4.6M – 475.8G <small>Bps</small></dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Configuration options

| Field | Description | Example values |
| --- | --- | --- |
| `size` | Served file size (KiB). | `16k` `1k` `256k` `512k` `64k` |
| `connections_per_vcpus` | Open HTTP connections per vCPU(s). | `0.5` `0.8888888888888888` `1` `1.7777777777777777` `2` `3.5555555555555554` `4` `7.111111111111111` `8` `14.222222222222221` `16` `28.444444444444443` `32` |

:::warning

This benchmark does not scale well on large instances (100+ vCPUs) due to a listener bottleneck in the single-process HTTP server.

:::

Score distribution <small>(102,340 measurements)</small>

![Score distribution of Static web server+client throughput](/benchmarks/histograms/static_web-throughput.svg)

## Static web server (extrapolated) throughput {#static_web-throughput-extrapolated}

Serving smaller (1-64 KiB) and larger (256-512 KiB) files using a static HTTP server (binserve) as a single process, and benchmarking each workload (wrk) using variable number of threads (and keeping the threads with the maximum performance) and connections (recorded after divided by the number of vCPUs to make it comparable with other servers with different vCPU count) on the same server. Extrapolated throughput is calculated by multiplying the extrapolated RPS with the served file size. The extrapolated RPS is based on the measured RPS adjusted by the server's and client's time spent executing in user/system mode, so trying to control for the client resource usage.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>static_web:throughput-extrapolated</code></dd><dt>Unit of measurement</dt><dd>Bytes per second (Bps)</dd><dt>Server types evaluated</dt><dd>3,655</dd><dt>Total measurements</dt><dd>102,340</dd><dt>Range of measurements</dt><dd>10M – 1T <small>Bps</small></dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Derived from [`static_web:throughput`](#static_web-throughput): Measured throughput adjusted by server/client user+system CPU time to control for client resource usage.

Configuration options

| Field | Description | Example values |
| --- | --- | --- |
| `size` | Served file size (KiB). | `16k` `1k` `256k` `512k` `64k` |
| `connections_per_vcpus` | Open HTTP connections per vCPU(s). | `0.5` `0.8888888888888888` `1` `1.7777777777777777` `2` `3.5555555555555554` `4` `7.111111111111111` `8` `14.222222222222221` `16` `28.444444444444443` `32` |

:::warning

This benchmark does not scale well on large instances (100+ vCPUs) due to a listener bottleneck in the single-process HTTP server.

:::

Score distribution <small>(102,340 measurements)</small>

![Score distribution of Static web server (extrapolated) throughput](/benchmarks/histograms/static_web-throughput-extrapolated.svg)
