Files
s3/weed/mount/peer_hrw_test.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.

- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
  "Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
  SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
  (replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
  keep their upstream import paths with zero churn. Internal identifiers and
  import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
  help/usage/flag strings, shell autocomplete program name, and the product name
  in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
  (e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
  `cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
  updated to ignore the `s3` build output.
2026-06-18 23:41:25 -07:00

91 lines
2.5 KiB
Go

package mount
import (
"fmt"
"testing"
)
func mkSeeds(addrs ...string) []SeedPeer {
out := make([]SeedPeer, len(addrs))
for i, a := range addrs {
out[i] = SeedPeer{PeerAddr: a}
}
return out
}
func TestOwnerFor_EmptySeeds(t *testing.T) {
if got := OwnerFor("3,01637037d6", nil); got != "" {
t.Errorf("expected empty owner for empty seed list, got %q", got)
}
}
func TestOwnerFor_Deterministic(t *testing.T) {
seeds := mkSeeds("a:1", "b:1", "c:1", "d:1")
fid := "3,01637037d6"
first := OwnerFor(fid, seeds)
for i := 0; i < 100; i++ {
if got := OwnerFor(fid, seeds); got != first {
t.Fatalf("non-deterministic: iter %d got %q first %q", i, got, first)
}
}
}
func TestOwnerFor_DistributesEvenly(t *testing.T) {
const N = 4
seeds := mkSeeds("a:1", "b:1", "c:1", "d:1")
counts := map[string]int{}
for i := 0; i < 10000; i++ {
fid := fmt.Sprintf("%d,%x", i, i*17)
counts[OwnerFor(fid, seeds)]++
}
// Each seed should get roughly 25% (±10% slack for a 10k sample).
for addr, c := range counts {
ratio := float64(c) / 10000.0
if ratio < 0.225 || ratio > 0.275 {
t.Errorf("HRW distribution skewed: %s got %.3f", addr, ratio)
}
}
if len(counts) != N {
t.Errorf("expected %d distinct owners, got %d", N, len(counts))
}
}
func TestOwnerFor_MinimalShuffleOnSeedChange(t *testing.T) {
// Adding one seed should move ~1/(N+1) fids to the new seed and leave
// the rest on their prior owners. Tolerance generous for a 10k sample.
const trials = 10000
before := mkSeeds("a:1", "b:1", "c:1")
after := mkSeeds("a:1", "b:1", "c:1", "d:1")
moved := 0
toNewSeed := 0
for i := 0; i < trials; i++ {
fid := fmt.Sprintf("%d,%x", i, i*31)
pre := OwnerFor(fid, before)
post := OwnerFor(fid, after)
if pre != post {
moved++
if post == "d:1" {
toNewSeed++
}
}
}
// Expected: ~1/4 = 25% of fids move, all to the new seed.
ratio := float64(moved) / float64(trials)
if ratio < 0.20 || ratio > 0.30 {
t.Errorf("expected ~25%% fids to move on seed-add, got %.3f", ratio)
}
if moved != toNewSeed {
t.Errorf("expected every moved fid to land on the new seed; moved=%d toNewSeed=%d", moved, toNewSeed)
}
}
func TestOwnerFor_TieBreakerDeterministic(t *testing.T) {
// Two seeds with equal hash score (engineered collision is unlikely in
// practice, but we guarantee determinism by lex-comparing addresses).
// This test just confirms OwnerFor runs without panicking on duplicates.
seeds := mkSeeds("a:1", "a:1", "b:1")
fid := "3,01637037d6"
_ = OwnerFor(fid, seeds)
}