mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-13 10:00:41 +02:00
* fix(ec): carry source disk type on VolumeEcShardsMount (#9423) When EC shards land on a target whose disk type differs from the source volume's, master heartbeats wrongly reported under the target disk's type. Add source_disk_type to VolumeEcShardsMountRequest; the target server applies it to the in-memory EcVolume via SetDiskType so the mount notification and steady-state heartbeat both carry the source's disk type. Empty value falls back to the location's disk type (used by disk-scan reload paths). The override is not persisted with the volume — disk type stays an environmental property and .vif remains portable. * fix(ec): plumb source disk type through plugin worker (#9423) Add source_disk_type to ErasureCodingTaskParams (field 8; 7 reserved), populate it from the metric the detector already collects, thread it through ec_task into the MountEcShards helper, and forward it on the VolumeEcShardsMount RPC. * fix(ec): mirror source disk type plumbing in rust volume server (#9423) The volume_ec_shards_mount handler now forwards source_disk_type into mount_ec_shard → DiskLocation::mount_ec_shards. When non-empty it overrides ec_vol.disk_type (and each mounted shard's disk_type) via the new set_disk_type method; empty value keeps the location's disk type, so disk-scan reload and reconcile paths are unchanged. Also picks up two pre-existing proto drifts that 'make gen' synced from weed/pb (LockRingUpdate in master.proto, listing_cache_ttl_seconds in remote.proto). * feat(ec): bias placement toward preferred disk type (#9423) Add DiskCandidate.DiskType and PlacementRequest.PreferredDiskType. When PreferredDiskType is non-empty, SelectDestinations partitions suitable disks into matching/fallback tiers and runs the rack/server/ disk-diversity passes on the matching tier first; the fallback tier is only consulted if the matching pool can't satisfy ShardsNeeded. PlacementResult.SpilledToOtherDiskType lets callers warn on spillover. Empty PreferredDiskType keeps the existing single-pool behavior. * fix(ec): plumb source disk type into placement planner (#9423) diskInfosToCandidates now copies DiskInfo.DiskType into the placement candidate, and ecPlacementPlanner.selectDestinations forwards metric.DiskType as PreferredDiskType so EC shards land on disks matching the source volume's disk type when possible. A glog warning fires when placement had to spill to other disk types. * test(ec): integration coverage for source-disk-type plumbing (#9423) store_ec_disk_type_test exercises Store.MountEcShards end-to-end: a shard physically lives on an HDD location, MountEcShards is called with sourceDiskType="ssd", and the test asserts that the in-memory EcVolume, the mounted shard, the NewEcShardsChan notification, and the steady-state heartbeat all report under the source's disk type. A companion test pins the empty-source path so disk-scan reload keeps the location's disk type. detection_disk_type_test exercises the worker plumbing: with a cluster of nodes carrying both HDD and SSD disks, planECDestinations must place every shard on SSD when metric.DiskType="ssd"; with only one SSD node and 13 HDD nodes it must still satisfy a 10+4 layout via spillover (and log a warning). * revert(ec): drop unrelated proto drift in seaweed-volume/proto (#9423) make gen pulled two pre-existing OSS changes into the rust proto tree (LockRingUpdate / by_plugin in master.proto, listing_cache_ttl_seconds in remote.proto). Reviewers flagged it as scope creep — none of the rust EC fix references those fields. Restore both files to origin/master so this branch only touches EC-related symbols. * fix(ec placement): treat empty disk type as hdd and skip used racks on spill (#9423) partitionByDiskType used raw string comparison, so a PreferredDiskType of "hdd" never matched candidates whose DiskType is "" (the HardDriveType sentinel that weed/storage/types uses). EC encoding of an HDD source would spill onto any HDD reporting "" even when the cluster has plenty of matching capacity. Normalize both sides through normalizeDiskType, which lowercases and folds "" → "hdd", mirroring types.ToDiskType without taking a dependency on it. selectFromTier's rack-diversity pass also kept revisiting racks the preferred tier had already used when running on the fallback tier, which negated PreferDifferentRacks on spillover. Skip racks already in usedRacks so fallback placements still spread onto new racks. * fix(ec): empty-source remount must not clobber existing disk type (#9423) mount_ec_shards_with_idx_dir runs more than once per vid (RPC mount, disk-scan reload, orphan-shard reconcile). After an RPC sets the source-derived disk type, any later call passing source_disk_type="" was resetting ec_vol.disk_type back to the location's value, which reintroduces the heartbeat drift this PR is meant to fix. Only default to the location's disk type when the EC volume is fresh (no shards mounted yet); otherwise leave the recorded type alone so empty-source reloads preserve whatever the original mount RPC set.
144 lines
4.5 KiB
Go
144 lines
4.5 KiB
Go
package placement
|
|
|
|
import (
|
|
"strconv"
|
|
"testing"
|
|
)
|
|
|
|
// makeDisk builds a DiskCandidate with sensible defaults; tests override
|
|
// only the fields they care about.
|
|
func makeDisk(node, rack, diskType string, diskID uint32) *DiskCandidate {
|
|
return &DiskCandidate{
|
|
NodeID: node,
|
|
DiskID: diskID,
|
|
DataCenter: "dc1",
|
|
Rack: rack,
|
|
DiskType: diskType,
|
|
VolumeCount: 0,
|
|
MaxVolumeCount: 100,
|
|
FreeSlots: 100,
|
|
}
|
|
}
|
|
|
|
func disksByType(disks []*DiskCandidate) map[string]int {
|
|
out := map[string]int{}
|
|
for _, d := range disks {
|
|
out[d.DiskType]++
|
|
}
|
|
return out
|
|
}
|
|
|
|
func newRequest(shards int, preferred string) PlacementRequest {
|
|
return PlacementRequest{
|
|
ShardsNeeded: shards,
|
|
PreferDifferentServers: true,
|
|
PreferDifferentRacks: true,
|
|
PreferredDiskType: preferred,
|
|
}
|
|
}
|
|
|
|
// Plenty of SSD disks available: placement should fill entirely from SSD
|
|
// when PreferredDiskType="ssd", leaving HDDs untouched and not flagging
|
|
// spillover.
|
|
func TestSelectDestinations_PrefersMatchingDiskType(t *testing.T) {
|
|
var disks []*DiskCandidate
|
|
for i := 0; i < 6; i++ {
|
|
disks = append(disks, makeDisk("ssd-"+strconv.Itoa(i), "r"+strconv.Itoa(i%3), "ssd", uint32(i)))
|
|
}
|
|
for i := 0; i < 6; i++ {
|
|
disks = append(disks, makeDisk("hdd-"+strconv.Itoa(i), "r"+strconv.Itoa(i%3), "", uint32(i)))
|
|
}
|
|
|
|
result, err := SelectDestinations(disks, newRequest(4, "ssd"))
|
|
if err != nil {
|
|
t.Fatalf("SelectDestinations: %v", err)
|
|
}
|
|
if got := len(result.SelectedDisks); got != 4 {
|
|
t.Fatalf("selected %d disks, want 4", got)
|
|
}
|
|
if counts := disksByType(result.SelectedDisks); counts["ssd"] != 4 {
|
|
t.Fatalf("disk-type counts = %v, want ssd=4", counts)
|
|
}
|
|
if result.SpilledToOtherDiskType {
|
|
t.Fatalf("SpilledToOtherDiskType should be false when preferred pool was sufficient")
|
|
}
|
|
}
|
|
|
|
// Only one SSD disk available but 4 shards needed: placement must consume
|
|
// the SSD first, then spill to HDD for the remainder, and report spillover.
|
|
func TestSelectDestinations_SpillsWhenPreferredScarce(t *testing.T) {
|
|
disks := []*DiskCandidate{
|
|
makeDisk("ssd-0", "r0", "ssd", 0),
|
|
makeDisk("hdd-0", "r1", "", 0),
|
|
makeDisk("hdd-1", "r2", "", 0),
|
|
makeDisk("hdd-2", "r3", "", 0),
|
|
}
|
|
|
|
result, err := SelectDestinations(disks, newRequest(4, "ssd"))
|
|
if err != nil {
|
|
t.Fatalf("SelectDestinations: %v", err)
|
|
}
|
|
if got := len(result.SelectedDisks); got != 4 {
|
|
t.Fatalf("selected %d disks, want 4", got)
|
|
}
|
|
counts := disksByType(result.SelectedDisks)
|
|
if counts["ssd"] != 1 || counts[""] != 3 {
|
|
t.Fatalf("disk-type counts = %v, want ssd=1 hdd=3", counts)
|
|
}
|
|
if !result.SpilledToOtherDiskType {
|
|
t.Fatalf("SpilledToOtherDiskType should be true after falling back to HDD")
|
|
}
|
|
}
|
|
|
|
// PreferredDiskType="hdd" must match disks whose DiskType is "" (the
|
|
// HardDriveType sentinel) — otherwise EC encoding of an HDD source would
|
|
// always spill onto HDDs that happen to report disk_type="" even though
|
|
// the cluster has plenty of matching capacity.
|
|
func TestSelectDestinations_PreferredHddMatchesEmptyDiskType(t *testing.T) {
|
|
disks := []*DiskCandidate{
|
|
makeDisk("hdd-0", "r0", "", 0), // HardDriveType sentinel
|
|
makeDisk("hdd-1", "r1", "", 0), // HardDriveType sentinel
|
|
makeDisk("ssd-0", "r2", "ssd", 0),
|
|
}
|
|
|
|
result, err := SelectDestinations(disks, newRequest(2, "hdd"))
|
|
if err != nil {
|
|
t.Fatalf("SelectDestinations: %v", err)
|
|
}
|
|
if got := len(result.SelectedDisks); got != 2 {
|
|
t.Fatalf("selected %d disks, want 2", got)
|
|
}
|
|
// Both selected disks must be HDD-reporting (i.e. DiskType == ""),
|
|
// and no spillover should have been required.
|
|
for _, d := range result.SelectedDisks {
|
|
if d.DiskType != "" {
|
|
t.Errorf("selected disk %s has DiskType=%q, want \"\" (HardDriveType)", d.NodeID, d.DiskType)
|
|
}
|
|
}
|
|
if result.SpilledToOtherDiskType {
|
|
t.Fatalf("SpilledToOtherDiskType should be false when HDD pool matches preferred=hdd")
|
|
}
|
|
}
|
|
|
|
// Empty PreferredDiskType: pre-#9423 behavior, single pool, no spillover
|
|
// flag regardless of disk-type mix.
|
|
func TestSelectDestinations_EmptyPreferredDiskTypeKeepsPriorBehavior(t *testing.T) {
|
|
disks := []*DiskCandidate{
|
|
makeDisk("ssd-0", "r0", "ssd", 0),
|
|
makeDisk("hdd-0", "r1", "", 0),
|
|
makeDisk("hdd-1", "r2", "", 0),
|
|
makeDisk("ssd-1", "r3", "ssd", 0),
|
|
}
|
|
|
|
result, err := SelectDestinations(disks, newRequest(3, ""))
|
|
if err != nil {
|
|
t.Fatalf("SelectDestinations: %v", err)
|
|
}
|
|
if got := len(result.SelectedDisks); got != 3 {
|
|
t.Fatalf("selected %d disks, want 3", got)
|
|
}
|
|
if result.SpilledToOtherDiskType {
|
|
t.Fatalf("SpilledToOtherDiskType should never be set when PreferredDiskType is empty")
|
|
}
|
|
}
|