tree: ce77be499c9f64315c6887c723f16fae498106a3 [path history] [tgz]
  1. fuchsia/
  2. host/
  3. src/

Fuchsia Filesystem Benchmarks


There are 12 benchmarks that get run for every filesystem. The currently supported filesystems are Fxfs, F2fs, Memfs, and Minfs.

IO Benchmarks

The IO benchmarks are all of the combinations of read/write, sequential/random, and warm/cold. Every read/write call uses an 8KiB buffer and each operation is performed 1024 times spread across an 8MiB file. The benchmarks measure how long each read/write operation takes.

  • Read: makes pread calls to the file.
  • Write: makes pwrite call to the file.
  • Sequential: the reads/writes are performed sequentially from the start of the file to the end of the file.
  • Random: the reads/writes are performed randomly across the entire file. Every part of the file is accessed exactly once.
  • Warm: the reads/writes are performed on a file that was recently written and likely still cached in memory.
  • Cold: the reads/writes are performed on a file that was not cached when the benchmark started. If the filesystem supports read-ahead then some of the operations may still hit cached data.
  • Fsync: the fsync is performed for every write.

WalkDirectoryTree Benchmarks

The WalkDirectoryTree benchmarks measure how long it takes to walk a directory tree with POSIX readdir calls. The directory tree consists of 62 directories and 189 files and is traversed 20 times by the benchmarks. The “cold” variant of the benchmarks remounts the filesystem between each traversal and the “warm” variant does not.

“Cold” Benchmarks

At the beginning of most benchmarks is a setup phase that creates files within the filesystem. Simply closing all handles to those files doesn‘t guarantee that the filesystem will immediately clear all caches related to those files. If the caches aren’t cleared then the benchmark may only ever hit cached (warm) data. To support benchmarking uncached (cold) operations, the Fuchsia Filesystem Benchmarks support remounting the filesystem. Remounting the filesystem between the setup and recording phases guarantees that all data related the file that isn't normally cached gets dropped.

Memfs and “Cold” Benchmarks

Memfs is an in-memory filesystem that doesn't support remounting. The “warm” and “cold” results should be the same for most benchmarks except for cold writes. When cold writing to memfs, the kernel needs to allocate pages for the VMO backing the file as the pages are used. This causes cold writes to be slower than warm writes which have the pages already allocated.


The Fuchsia Filesystem Benchmarks use a custom framework for timing filesystem operations. Filesystems hold state external to the read or write operations being benchmarked which can lead to drastically different timings between consecutive operations. For other performance tests, we want to treat the initial one or more iterations as warm-up iterations and drop their timings. (For example, for some IPC performance tests, the initial iteration doesn‘t complete until a subprocess has finished starting up, making it much slower than the later iterations.) These storage tests differ in that we don’t want to drop the initial iterations' timings.

Ex. On the first read operation to a file in Minfs, Minfs reads the entire file into memory and each subsequent read is served from memory. The warm-up phase of fuchsia-criterion would hide the extremely slow read call.

Running the Benchmarks

  1. Include //src/storage/benchmarks in fx set.
  2. Run fx test fuchsia-pkg://

The set of benchmarks and filesystems can filtered with the --filter flag.