mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-15 02:50:45 +02:00
* proto: define MountRegister/MountList and MountPeer service Adds the wire types for peer chunk sharing between weed mount clients: * filer.proto: MountRegister / MountList RPCs so each mount can heartbeat its peer-serve address into a filer-hosted registry, and refresh the list of peers. Tiny payload; the filer stores only O(fleet_size) state. * mount_peer.proto (new): ChunkAnnounce / ChunkLookup RPCs for the mount-to-mount chunk directory. Each fid's directory entry lives on an HRW-assigned mount; announces and lookups route to that mount. No behavior yet — later PRs wire the RPCs into the filer and mount. See design-weed-mount-peer-chunk-sharing.md for the full design. * filer: add mount-server registry behind -peer.registry.enable Implements tier 1 of the peer chunk sharing design: an in-memory registry of live weed mount servers, keyed by peer address, refreshed by MountRegister heartbeats and served by MountList. * weed/filer/peer_registry.go: thread-safe map with TTL eviction; lazy sweep on List plus a background sweeper goroutine for bounded memory. * weed/server/filer_grpc_server_peer.go: MountRegister / MountList RPC handlers. When -peer.registry.enable is false (the default), both RPCs are silent no-ops so probing older filers is harmless. * -peer.registry.enable flag on weed filer; FilerOption.PeerRegistryEnabled wires it through. Phase 1 is single-filer (no cross-filer replication of the registry); mounts that fail over to another filer will re-register on the next heartbeat, so the registry self-heals within one TTL cycle. Part of the peer-chunk-sharing design; no behavior change at runtime until a later PR enables the flag on both filer and mount. * filer: nil-safe peerRegistryEnable + registry hardening Addresses review feedback on PR #9131. * Fix: nil pointer deref in the mini cluster. FilerOptions instances constructed outside weed/command/filer.go (e.g. miniFilerOptions in mini.go) do not populate peerRegistryEnable, so dereferencing the pointer panics at Filer startup. Use the same `nil && deref` idiom already used for distributedLock / writebackCache. * Hardening (gemini review): registry now enforces three invariants: - empty peer_addr is silently rejected (no client-controlled sentinel mass-inserts) - TTL is capped at 1 hour so a runaway client cannot pin entries - new-entry count is capped at 10000 to bound memory; renewals of existing entries are always honored, so a full registry still heartbeats its existing members correctly Covered by new unit tests. * filer: rename -peer.registry.enable flag to -mount.p2p Per review feedback: the old name "peer.registry.enable" leaked the implementation ("registry") into the CLI surface. "mount.p2p" is shorter and describes what it actually controls — whether this filer participates in mount-to-mount peer chunk sharing. Flag renames (all three keep default=true, idle cost is near-zero): -peer.registry.enable -> -mount.p2p (weed filer) -filer.peer.registry.enable -> -filer.mount.p2p (weed mini, weed server) Internal variable names (mountPeerRegistryEnable, MountPeerRegistry) keep their longer form — they describe the component, not the knob. * filer: MountList returns DataCenter + List uses RLock Two review follow-ups on the mount peer registry: * weed/server/filer_grpc_server_mount_peer.go: MountList was dropping the DataCenter on the wire. The whole point of carrying DC separately from Rack is letting the mount-side fetcher re-rank peers by the two-level locality hierarchy (same-rack > same-DC > cross-DC); without DC in the response every remote peer collapsed to "unknown locality." * weed/filer/mount_peer_registry.go: List() was taking a write lock so it could lazy-delete expired entries inline. But MountList is a read-heavy RPC hit on every mount's 30 s refresh loop, and Sweep is already wired as the sole reclamation path (same pattern as the mount-side PeerDirectory). Switch List to RLock + filter, let Sweep do the map mutation, so concurrent MountList callers don't serialize on each other. Test updated to reflect the new contract (List no longer mutates the map; Sweep is what drops expired entries).
170 lines
5.2 KiB
Go
170 lines
5.2 KiB
Go
package filer
|
|
|
|
import (
|
|
"fmt"
|
|
"sort"
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
func testClock(t time.Time) func() time.Time {
|
|
return func() time.Time { return t }
|
|
}
|
|
|
|
func TestMountPeerRegistry_RegisterAndList(t *testing.T) {
|
|
start := time.Unix(1000, 0)
|
|
current := start
|
|
r := newMountPeerRegistryWithClock(func() time.Time { return current })
|
|
|
|
r.Register("mount-a:18080", "", "rack1", 30*time.Second)
|
|
r.Register("mount-b:18080", "", "rack2", 30*time.Second)
|
|
|
|
list := r.List()
|
|
if len(list) != 2 {
|
|
t.Fatalf("expected 2 entries, got %d", len(list))
|
|
}
|
|
|
|
sort.Slice(list, func(i, j int) bool { return list[i].PeerAddr < list[j].PeerAddr })
|
|
if list[0].PeerAddr != "mount-a:18080" || list[0].Rack != "rack1" {
|
|
t.Errorf("entry 0 unexpected: %+v", list[0])
|
|
}
|
|
if list[1].PeerAddr != "mount-b:18080" || list[1].Rack != "rack2" {
|
|
t.Errorf("entry 1 unexpected: %+v", list[1])
|
|
}
|
|
}
|
|
|
|
func TestMountPeerRegistry_RenewExtendsExpiry(t *testing.T) {
|
|
current := time.Unix(1000, 0)
|
|
r := newMountPeerRegistryWithClock(func() time.Time { return current })
|
|
|
|
r.Register("mount-a:18080", "", "rack1", 30*time.Second)
|
|
|
|
// Advance time past original expiry.
|
|
current = current.Add(25 * time.Second)
|
|
// Renew — should push expiry to now+30.
|
|
r.Register("mount-a:18080", "", "rack1-updated", 30*time.Second)
|
|
|
|
// Advance to where original expiry would have triggered eviction.
|
|
current = current.Add(10 * time.Second)
|
|
list := r.List()
|
|
if len(list) != 1 {
|
|
t.Fatalf("expected 1 entry after renew, got %d", len(list))
|
|
}
|
|
if list[0].Rack != "rack1-updated" {
|
|
t.Errorf("rack not updated on renew: %q", list[0].Rack)
|
|
}
|
|
}
|
|
|
|
func TestMountPeerRegistry_ExpirationDropsEntry(t *testing.T) {
|
|
current := time.Unix(1000, 0)
|
|
r := newMountPeerRegistryWithClock(func() time.Time { return current })
|
|
|
|
r.Register("mount-a:18080", "", "", 10*time.Second)
|
|
if n := r.Len(); n != 1 {
|
|
t.Fatalf("expected 1 entry, got %d", n)
|
|
}
|
|
|
|
current = current.Add(15 * time.Second)
|
|
list := r.List()
|
|
if len(list) != 0 {
|
|
t.Errorf("expected 0 entries after expiry, got %d", len(list))
|
|
}
|
|
// List no longer deletes — it's RLock-only so concurrent callers can
|
|
// proceed in parallel. Sweep is the sole reclamation path.
|
|
if n := r.Len(); n != 1 {
|
|
t.Errorf("List should not delete expired entries; Len=%d want 1", n)
|
|
}
|
|
if evicted := r.Sweep(); evicted != 1 {
|
|
t.Errorf("Sweep should have evicted the expired entry; got %d", evicted)
|
|
}
|
|
if n := r.Len(); n != 0 {
|
|
t.Errorf("after Sweep, Len=%d want 0", n)
|
|
}
|
|
}
|
|
|
|
func TestMountPeerRegistry_SweepCountsEvictions(t *testing.T) {
|
|
current := time.Unix(1000, 0)
|
|
r := newMountPeerRegistryWithClock(func() time.Time { return current })
|
|
|
|
r.Register("mount-a:18080", "", "", 10*time.Second)
|
|
r.Register("mount-b:18080", "", "", 60*time.Second)
|
|
|
|
current = current.Add(30 * time.Second)
|
|
got := r.Sweep()
|
|
if got != 1 {
|
|
t.Errorf("expected 1 eviction, got %d", got)
|
|
}
|
|
if n := r.Len(); n != 1 {
|
|
t.Errorf("expected 1 surviving entry, got %d", n)
|
|
}
|
|
}
|
|
|
|
func TestMountPeerRegistry_NegativeTTLFallsBackToDefault(t *testing.T) {
|
|
current := time.Unix(1000, 0)
|
|
r := newMountPeerRegistryWithClock(func() time.Time { return current })
|
|
|
|
r.Register("mount-a:18080", "", "", -5*time.Second)
|
|
if n := r.Len(); n != 1 {
|
|
t.Fatalf("expected 1 entry even with bad ttl, got %d", n)
|
|
}
|
|
|
|
// Advance past the default (60s) and confirm it expires.
|
|
current = current.Add(61 * time.Second)
|
|
list := r.List()
|
|
if len(list) != 0 {
|
|
t.Errorf("expected entry to expire after default ttl, got %d entries", len(list))
|
|
}
|
|
}
|
|
|
|
func TestMountPeerRegistry_EmptyList(t *testing.T) {
|
|
r := NewMountPeerRegistry()
|
|
list := r.List()
|
|
if len(list) != 0 {
|
|
t.Errorf("expected empty list, got %d", len(list))
|
|
}
|
|
_ = testClock // keep helper exported for future tests
|
|
}
|
|
|
|
func TestMountPeerRegistry_EmptyPeerAddrRejected(t *testing.T) {
|
|
r := NewMountPeerRegistry()
|
|
r.Register("", "", "rack", 30*time.Second)
|
|
if n := r.Len(); n != 0 {
|
|
t.Errorf("empty peer_addr should not insert; Len=%d", n)
|
|
}
|
|
}
|
|
|
|
func TestMountPeerRegistry_TTLCapped(t *testing.T) {
|
|
current := time.Unix(1000, 0)
|
|
r := newMountPeerRegistryWithClock(func() time.Time { return current })
|
|
|
|
// Request a ridiculous TTL; should be capped to maxMountPeerRegistryTTL.
|
|
r.Register("mount-a:18080", "", "", 24*time.Hour)
|
|
|
|
// Advance past the cap; entry should now be expired.
|
|
current = current.Add(maxMountPeerRegistryTTL + time.Second)
|
|
if list := r.List(); len(list) != 0 {
|
|
t.Errorf("expected entry to expire after maxMountPeerRegistryTTL, got %d", len(list))
|
|
}
|
|
}
|
|
|
|
func TestMountPeerRegistry_CapacityLimit(t *testing.T) {
|
|
r := NewMountPeerRegistry()
|
|
// Fill to capacity.
|
|
for i := 0; i < maxMountPeerRegistryEntries; i++ {
|
|
r.Register(fmt.Sprintf("mount-%d:18080", i), "", "", 60*time.Second)
|
|
}
|
|
if n := r.Len(); n != maxMountPeerRegistryEntries {
|
|
t.Fatalf("expected %d entries, got %d", maxMountPeerRegistryEntries, n)
|
|
}
|
|
// A brand-new address beyond the cap is rejected.
|
|
r.Register("new-mount:18080", "", "", 60*time.Second)
|
|
if n := r.Len(); n != maxMountPeerRegistryEntries {
|
|
t.Errorf("new entry past cap should be rejected; Len=%d", n)
|
|
}
|
|
// A renewal of an existing entry still succeeds.
|
|
r.Register("mount-0:18080", "", "rack-renewed", 60*time.Second)
|
|
if n := r.Len(); n != maxMountPeerRegistryEntries {
|
|
t.Errorf("renewal should not increase size; Len=%d", n)
|
|
}
|
|
}
|