# Latchkey Runner Benchmarks

CoreMark, one execution thread, 2000-byte dataset. Higher iterations/s is better.

Linux/Windows require hard affinity to one logical CPU. macOS is explicitly **unpinned**: its one thread may migrate between CPUs. These are runner + compiler measurements; VM host scheduling, other workloads, turbo, and image updates can affect them.

## Benchmark parameters

Compare providers using the same parameter fingerprint. Runner selection and provider identity are excluded; measurement protocol is included.

| Profile | Protocol | CPU/disk samples | CPU seconds | Disk MiB | Cache MiB | Internet | Transfer MiB |
| --- | --- | ---: | ---: | ---: | ---: | --- | ---: |
| `866df6f892c3` | 5 | 5 | 30 | 1024 | 512 | Enabled | 1024 |

## Pinned results

| Runner | Binary | Median iterations/s | Min–max | Variation | CPU / group | Samples |
| --- | --- | ---: | ---: | ---: | --- | ---: |
| latchkey-linux-x64 | x64 (64-bit) | 30065.35 | 30043.11–30096.09 | 0.06% | 0 / 0 | 5 |

Variation is the population coefficient of variation across accepted samples.

## Disk I/O

One worker, queue depth one, 1 MiB sequential I/O, 4 KiB random I/O. OS file-cache bypass is required; write timings include the final flush. Protocol 2 and later repeat each operation for at least 5 seconds against the same file; total transferred bytes can exceed the file size. Medians across samples.

| Runner | Affinity | File MiB | Read MiB/s | Write MiB/s | Random read IOPS | Random write IOPS |
| --- | --- | ---: | ---: | ---: | ---: | ---: |
| latchkey-linux-x64 | Pinned | 1024 | 126.40 | 142.20 | 2051.53 | 1142.22 |

## Cache backends

Protocol 2 and later measure three unique-key save/restore pairs per backend. Each trial restores in a separate runner job after the save job completes; reused save OS instances are rejected. Backend order reverses on trial two. Archive services use zstd `--single-thread`; attached-volume transfers use one thread without compression. Linux/Windows action processes inherit one-CPU affinity; macOS is unpinned. Identical random payload bytes across trials and backends on each runner; an empty local target before restore, exact cache hit, SHA-256 and backend routing checked. Each time includes the action and adjacent step transitions; MiB/s uses logical payload bytes, including compression/extraction for archive services.

Profile `866df6f892c3` waits 120 seconds after the save job finishes, before allocating its first restore runner. All providers use this publication gap; it is excluded from transfer speeds. It gives cache publication time to settle but does not guarantee cache availability. Misses remain failures; there are no retries or payload fallbacks.


### archive-service

| Runner | Cache backend | Payload MiB | Verified pairs | Save s (median; range) | Save MiB/s | Save variation | Restore s (median; range) | Restore MiB/s | Restore variation |
| --- | --- | ---: | --- | --- | ---: | --- | --- | ---: | --- |
| latchkey-linux-x64 | GitHub Actions cache | 512.0 | 3/3 | 3.24; 3.22–4.60 | 158.14 | 17.57% | 4.83; 4.32–4.86 | 105.95 | 5.31% |
| latchkey-linux-x64 | Latchkey Fast Cache | 512.0 | 3/3 | 2.37; 2.20–4.40 | 216.13 | 33.35% | 3.91; 3.77–5.08 | 130.94 | 13.81% |

## Internet

One HTTP/1.1 stream at a time, three downloads and three uploads. Each sample transfers the configured payload through sequential requests of at most 32 MiB on one persistent connection. Mbps uses decimal megabits. Zero-byte HTTPS request time includes connection/TLS/DNS overhead and is not ICMP RTT. Compare only results using the same endpoint and payload size. Unavailable tests have no speed score.

- **LibreSpeed (Sharktech, Amsterdam)**: https://amsspeed.sharktech.net/backend/

| Runner | Service | Status | Transfer MiB | Download Mbps | Upload Mbps | HTTPS request ms |
| --- | --- | --- | ---: | ---: | ---: | ---: |
| latchkey-linux-x64 | LibreSpeed (Sharktech, Amsterdam) | ok | 1024 | 201.70 | 227.99 | 264.30 |

## Optional stages and notices

- **latchkey-linux-x64 / latchkey / trial 1 / cleanup**: The provider-managed cache entry is left to provider retention. Automatic native deletion requires a separately authenticated provider cleanup adapter; no deletion of unrelated entries was requested.
- **latchkey-linux-x64 / latchkey / trial 2 / cleanup**: The provider-managed cache entry is left to provider retention. Automatic native deletion requires a separately authenticated provider cleanup adapter; no deletion of unrelated entries was requested.
- **latchkey-linux-x64 / latchkey / trial 3 / cleanup**: The provider-managed cache entry is left to provider retention. Automatic native deletion requires a separately authenticated provider cleanup adapter; no deletion of unrelated entries was requested.

## Machine and build details

| Runner | CPU model | OS image | Compiler | Flags |
| --- | --- | --- | --- | --- |
| latchkey-linux-x64 | AMD EPYC 7R13 Processor | latchkey-1.0.0 | GNU 14.2.0 | -O2 -DNDEBUG; C99; MULTITHREAD=1; TOTAL_DATA_SIZE=2000; ITERATIONS=0 |