RunsOn r8a.xlarge · tmpfs vs GitHub 4-core x64
RunsOn does the Rust and TypeScript builds for 7.2–7.4× less and 1.8–2.4× faster. Both 4 vCPU x64.
Price per minute 5.7× cheaper on RunsOn: $0.0021 vs $0.0120the builds are not all compared on cost yet
Rust build 7.2× cheaper on RunsOn: $0.0065 vs $0.0466RunsOn 1.8× faster: 2m 06s vs 3m 47s
TypeScript build 7.4× cheaper on RunsOn: $0.0036 vs $0.0268RunsOn 2.4× faster: 48s vs 1m 56s
Docker build 12m 44s GitHub only · RunsOn not run
RunsOn r8a.xlarge · tmpfs
jobs ran from Amazon.com (US)
GitHub 4-core
jobs ran from Microsoft (US, CA)
Side by side
Every measurement both runners share, cost first. The dot marks the better value; gap is the larger over the smaller.
| Measurement | RunsOn | GitHub | Gap |
|---|---|---|---|
| Cost | |||
| Cost per Rust build | $0.0065 | $0.0466 | 7.2× RunsOn |
| Cost per TypeScript build | $0.0036 | $0.0268 | 7.4× RunsOn |
| Cost per Docker build | n/a: Not run: needs more than 32 GB of RAM with tmpfs, where Docker's data root lives in RAM; PostHog's layers plus the build's own memory exceeded it and the runner was shut down mid-build. The 64 GB tmpfs runner builds it. | $0.1764 | — |
| Price per minute | $0.0021 | $0.0120 | 5.7× RunsOn |
| Real builds, wall time | |||
| Rust build (spotify-player) | 2m 06s | 3m 47s | 1.8× RunsOn |
| TypeScript build (opencode) | 48s | 1m 56s | 2.4× RunsOn |
| Docker build (PostHog) | n/a: Not run: needs more than 32 GB of RAM with tmpfs, where Docker's data root lives in RAM; PostHog's layers plus the build's own memory exceeded it and the runner was shut down mid-build. The 64 GB tmpfs runner builds it. | 12m 44s | — |
| CPU & memory | |||
| PassMark single-thread (points) | 3,799 | 2,370 | 1.6× RunsOn |
| PassMark CPU Mark, all cores (points) | 13,460 | 6,130 | 2.2× RunsOn |
| sysbench CPU, 1 thread (events/s) | 5,534 | 3,670 | 1.5× RunsOn |
| 7-Zip compression (MIPS) | 28,331 | 16,137 | 1.8× RunsOn |
| Memory read bandwidth | 36.5 GiB/s | 20.9 GiB/s | 1.7× RunsOn |
| Measurement | RunsOn | GitHub | Gap |
|---|---|---|---|
| Workspace disk (fio) | |||
| Random read, 4k QD32 (IOPS) | 4,014,510 | 19,587 | 205.0× RunsOn |
| Random write, 4k QD32 (IOPS) | 3,665,859 | 11,712 | 313.0× RunsOn |
| Random read, 4k QD1 (IOPS) | 1,054,041 | 6,843 | 154.0× RunsOn |
| QD1 read latency, p99 | <1 µs | 251 µs | 1254.5× RunsOn |
| Sequential read | 18.2 GiB/s | 394 MiB/s | 47.3× RunsOn |
| Sequential write | 9.9 GiB/s | 394 MiB/s | 25.6× RunsOn |
| Sync write, 4k + fdatasync (IOPS) | 912,188 | 3,262 | 279.6× RunsOn |
| Network, cache & Docker | |||
| Download from GitHub | 330 MiB/s | 91 MiB/s | 3.6× RunsOn |
| Cache restore, 4 GB (actions/cache) | 8s | 41s | 5.1× RunsOn |
| Cache save, 4 GB (actions/cache) | 13s | 30s | 2.3× RunsOn |
| docker pull | 5.1s | 16.4s | 3.2× RunsOn |
| Database | |||
| pgbench read/write (TPS) | 20,139 | 2,797 | 7.2× RunsOn |
| pgbench read-only (TPS) | 147,043 | 20,013 | 7.3× RunsOn |
| Queue | |||
| Queue under burst load | 17s | 4s | 4.3× GitHub |
- ≈ even: under 5% apart, or a build inside both runners' run-to-run spread
- Queue: identical jobs queued at the same instant (burst suite)
- 2 missing on one side or both
- RunsOn at EC2 spot, its default (7-day average of the cheapest us-east-1 zone's spot price, fetched 5 Oct 2026); the jobs ran on spot
- Cost: a managed SaaS runner against RunsOn self-hosted on your AWS account; the effort of running it was not measured