x64arm64 at 2 vCPU4 vCPU8 vCPU
Diskrandom reads per secondhigher is betterarm64 · 2 vCPU
Blacksmith has the fastest disk on small reads.
RunsOn is 5th of 8, the leader is 2.3× higher. Blacksmith to Warpbuild: 17× apart.
- Blacksmith 6 GB 31,028
- Avrea 8 GB 20,971
- NamespaceApple silicon 2x8 · 8 GB 19,957
- Namespace 2x8 · 8 GB 15,941
- RunsOn m9gd.large · local NVMe · 8 GB 13,533
- GitHub 8 GB 8,119
- Ubicloud standard · 8 GB 7,846
- Warpbuild 8 GB 1,777
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
- RunsOntmpfs workspace in RAM, no disk
- WarpbuildApple silicon no 2 vCPU arm64 runner
4k random reads one at a time (fio, QD1) in the job's workspace, each provider's best disk. It is a disk's limit: a build often never reaches it, so read it next to the builds. A tmpfs workspace is RAM and has no disk figure.