RunsOn r8a.xlarge · tmpfs vs Namespace 4x16 x64
RunsOn does each build for 5.0–6.8× less; on time, Namespace is faster on the Rust build and neither is clearly faster on the TypeScript and Docker builds. Both 4 vCPU x64.
All three builds 6.2× cheaper on RunsOn: $0.0145 vs $0.0900Namespace 1.1× faster: 7m 02s vs 7m 36s
Rust build 5.5× cheaper on RunsOn: $0.0036 vs $0.0198Namespace 1.2× faster: 1m 33s vs 1m 52s
TypeScript build 5.0× cheaper on RunsOn: $0.0021 vs $0.0106within run-to-run spread: 49s · 45s
Docker build 6.8× cheaper on RunsOn: $0.0088 vs $0.0596within run-to-run spread: 4m 55s · 4m 44s
RunsOn r8a.xlarge · tmpfs
jobs ran from Amazon.com (US)
Namespace 4x16
jobs ran from Namespace Labs (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 | Namespace | Gap |
|---|---|---|---|
| Cost | |||
| Cost per Rust build | $0.0036 | $0.0198 | 5.5× RunsOn |
| Cost per TypeScript build | $0.0021 | $0.0106 | 5.0× RunsOn |
| Cost per Docker build | $0.0088 | $0.0596 | 6.8× RunsOn |
| Price per minute | $0.0016 | $0.0120 overage rate | 7.6× RunsOn |
| Real builds, wall time | |||
| Rust build (spotify-player) | 1m 52s | 1m 33s | 1.2× Namespace |
| TypeScript build (opencode) | 49s | 45s | ≈ even |
| Docker build (PostHog) | 4m 55s | 4m 44s | ≈ even |
| CPU & memory | |||
| PassMark single-thread (points) | 3,816 | 4,628 | 1.2× Namespace |
| PassMark CPU Mark, all cores (points) | 13,502 | 15,965 | 1.2× Namespace |
| sysbench CPU, 1 thread (events/s) | 5,037 | 6,887 | 1.4× Namespace |
| 7-Zip compression (MIPS) | 38,655 | 33,572 | 1.2× RunsOn |
| Memory read bandwidth | 36.7 GiB/s | 44.7 GiB/s | 1.2× Namespace |
| Measurement | RunsOn | Namespace | Gap |
|---|---|---|---|
| Workspace disk (fio) | |||
| Random read, 4k QD32 (IOPS) | 4,201,526 | 1,202,685 | 3.5× RunsOn |
| Random write, 4k QD32 (IOPS) | 3,800,170 | 564,373 | 6.7× RunsOn |
| Random read, 4k QD1 (IOPS) | 1,102,306 | 104,443 | 10.6× RunsOn |
| QD1 read latency, p99 | <1 µs | 11 µs | 54.0× RunsOn |
| Sequential read | 17.8 GiB/s | 5.0 GiB/s | 3.6× RunsOn |
| Sequential write | 9.9 GiB/s | 3.4 GiB/s | 2.9× RunsOn |
| Sync write, 4k + fdatasync (IOPS) | 433,841 | 28,561 | 15.2× RunsOn |
| Network, cache & Docker | |||
| Download from GitHub | 173 MiB/s | 187 MiB/s | 1.1× Namespace |
| Cache restore, 4 GB (actions/cache) | 5s | 21s | 4.1× RunsOn |
| Cache save, 4 GB (actions/cache) | 7s | 13s | 1.9× RunsOn |
| docker pull | 4.5s | 3.2s | 1.4× Namespace |
| Database | |||
| pgbench read/write (TPS) | 21,548 | 13,662 | 1.6× RunsOn |
| pgbench read-only (TPS) | 144,626 | 114,631 | 1.3× RunsOn |
| Queue | |||
| Queue under burst load | 16s | 10s | 1.6× Namespace |
- ≈ even: under 5% apart, or a build inside both runners' run-to-run spread
- Queue: identical jobs queued at the same instant (burst suite)
- RunsOn at EC2 spot, its default (7-day average of the cheapest us-east-1 zone's spot price, fetched 16 Nov 2026); 16 of its jobs fell back to on-demand (AWS had no spot capacity for the type) and are priced at the spot rate over the same billed time
- Cost: a managed SaaS runner against RunsOn self-hosted on your AWS account; the effort of running it was not measured