RunsOn m9g.xlarge · tmpfs vs Blacksmith 4 vCPU arm64
RunsOn does the Rust and TypeScript builds for 2.7–2.9× less and 2.5–3.1× faster. Both 4 vCPU arm64.
Price per minute 2.9× cheaper on RunsOn: $0.0018 vs $0.0050the builds are not all compared on cost yet
Rust build 2.9× cheaper on RunsOn: $0.0091 vs $0.0267RunsOn 2.5× faster: 2m 04s vs 5m 04s
TypeScript build 2.7× cheaper on RunsOn: $0.0049 vs $0.0132RunsOn 3.1× faster: 46s vs 2m 21s
Docker build 12m 12s Blacksmith only · RunsOn not run
RunsOn m9g.xlarge · tmpfs
jobs ran from Amazon.com (US)
Blacksmith 4 vCPU
jobs ran from Secured Servers (US)
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 | Blacksmith | Gap |
|---|---|---|---|
| Cost | |||
| Cost per Rust build | $0.0091 | $0.0267 | 2.9× RunsOn |
| Cost per TypeScript build | $0.0049 | $0.0132 | 2.7× 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. | $0.0654 | — |
| Price per minute | $0.0018 | $0.0050 | 2.9× RunsOn |
| Real builds, wall time | |||
| Rust build (spotify-player) | 2m 04s | 5m 04s | 2.5× RunsOn |
| TypeScript build (opencode) | 46s | 2m 21s | 3.1× 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 12s | — |
| CPU & memory | |||
| PassMark single-thread (points) | 2,464 | 1,343 | 1.8× RunsOn |
| PassMark CPU Mark, all cores (points) | 5,606 | 3,778 | 1.5× RunsOn |
| sysbench CPU, 1 thread (events/s) | 4,019 | 930 | 4.3× RunsOn |
| 7-Zip compression (MIPS) | 34,272 | 15,351 | 2.2× RunsOn |
| Memory read bandwidth | 27.9 GiB/s | 9.0 GiB/s | 3.1× RunsOn |
| Measurement | RunsOn | Blacksmith | Gap |
|---|---|---|---|
| Workspace disk (fio) | |||
| Random read, 4k QD32 (IOPS) | 2,690,916 | 155,975 | 17.3× RunsOn |
| Random write, 4k QD32 (IOPS) | 2,487,599 | 24,132 | 103.1× RunsOn |
| Random read, 4k QD1 (IOPS) | 674,926 | 24,897 | 27.1× RunsOn |
| QD1 read latency, p99 | <1 µs | 39 µs | 130.7× RunsOn |
| Sequential read | 15.1 GiB/s | 1.7 GiB/s | 8.7× RunsOn |
| Sequential write | 4.6 GiB/s | 742 MiB/s | 6.4× RunsOn |
| Sync write, 4k + fdatasync (IOPS) | 634,741 | 7,118 | 89.2× RunsOn |
| Network, cache & Docker | |||
| Download from GitHub | 254 MiB/s | 85 MiB/s | 3.0× RunsOn |
| Cache restore, 4 GB (actions/cache) | 8s | 36s | 4.5× RunsOn |
| Cache save, 4 GB (actions/cache) | 7s | 21s | 3.0× RunsOn |
| docker pull | 5.3s | 13.7s | 2.6× RunsOn |
| Database | |||
| pgbench read/write (TPS) | 9,905 | 1,893 | 5.2× RunsOn |
| pgbench read-only (TPS) | 64,651 | 14,786 | 4.4× RunsOn |
| Queue | |||
| Queue under burst load | 17s | 15s | 1.1× Blacksmith |
- ≈ 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