mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-30 20:57:07 +00:00
* worker: move the collection filter parser into weed/util/wildcard
The parser sits beside the volume-list filtering it was written for, in
weed/plugin/worker, which imports weed/shell — so the shell commands that
parse the same filter three other ways can never call it. Move it down to
weed/util/wildcard, next to the comma-separated wildcard helper it already
replaced, leaving the behavior unchanged.
* shell: parse every collection filter the same way
The shell parsed a collection filter three ways: compileCollectionPattern
compiled one regex for ec.encode, ec.decode, volume.balance and the tier
commands; volume.list and volume.deleteEmpty matched a single wildcard; and
volume.tier.move, volume.fix.replication and volume.configure.replication
called filepath.Match on their own. None of them took a list, so
"ec.encode -collection=a,b" selected nothing, the same way the admin UI did.
They all go through the shared matcher now: a comma-separated list of names,
"*" and "?" wildcards, "_default" for the collection with no name, and regex
entries. The one thing that stays per-command is what an empty value means -
every collection for -collectionPattern, the unnamed collection for the ec
and tier -collection flag - so compileCollectionPattern keeps that mapping.
The matchers are compiled once per command instead of once per volume, and a
regex entry now has to match the whole name unless it anchors itself, so
-collection=bucket no longer picks up mybucket2.
* shell: keep dots in collection names, and commas inside a regex
A dot no longer marks an entry as a regex, so a collection named "my.bucket"
matches itself and not "my-bucket" - the difference decides which volumes
volume.deleteEmpty and volume.tier.move touch. A dot still counts when it is
quantified, so "bucket.*" stays a prefix regex.
The comma split also leaves alone the commas inside a character class or a
repetition count, so "bucket[0-9]{1,3}" stays one entry instead of becoming
two broken fragments.
* shell: let a regex entry match its own spelling
A collection named after regex syntax, say "logs(2024)", was unreachable:
the entry compiled to a pattern that matches "logs2024" instead. Match the
entry verbatim as well, so naming a collection always selects it, whatever
characters it holds.
* shell: reject a collection filter that names no collection
A value of "," parsed to no entries and then matched every collection, so a
typo widened ec.encode or volume.deleteEmpty to the whole cluster. Only a
genuinely empty filter means "all collections"; anything else has to name one.
* shell: keep commas inside a regex group out of the entry split
The split already left alone the commas inside a character class or a
repetition count, but not the ones inside a group, so "bucket(foo,bar)"
was cut into two fragments that no longer compile.
* shell: cover escaping a collection name that is not a regex
A name like "logs(2024" does not parse as a regex on its own; escaping it,
"logs\(2024", reaches it. Pin that so the escape hatch does not regress.
* shell: split entries only on commas inside a closed regex construct
An unmatched "{" or "[" made the splitter swallow every comma after it, so
"foo{bar,videos" became one entry that matches neither collection - the
silent no-op this filter work exists to remove. A construct now has to close
before its commas stop separating entries.
* shell: skip character classes while scanning a regex group
A ")" inside a class is a literal, so "(a[)],b)" ended its group early and
split into two fragments that no longer compile.
* shell: cover escaping a comma inside a collection name
A comma separates entries, so a name holding one is reached by escaping it.
* shell: follow the regexp parser when scanning a character class
A "]" leading a class is a member of it, and a POSIX class such as
"[:alpha:]" carries its own "]", so stopping at the first one cut a valid
filter like "(a[]),],b)" into fragments and rejected it.
244 lines
8.0 KiB
Go
244 lines
8.0 KiB
Go
package pluginworker
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"sort"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/admin/topology"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
|
|
workertypes "github.com/seaweedfs/seaweedfs/weed/worker/types"
|
|
"google.golang.org/grpc"
|
|
)
|
|
|
|
// CollectVolumeMetricsFromMasters dials the provided master addresses in order
|
|
// until one returns a usable volume list, then converts that into per-volume
|
|
// health metrics, an active-topology view, and a replica-location map.
|
|
func CollectVolumeMetricsFromMasters(
|
|
ctx context.Context,
|
|
masterAddresses []string,
|
|
collectionFilter string,
|
|
grpcDialOption grpc.DialOption,
|
|
) ([]*workertypes.VolumeHealthMetrics, *topology.ActiveTopology, map[uint32][]workertypes.ReplicaLocation, error) {
|
|
if grpcDialOption == nil {
|
|
return nil, nil, nil, fmt.Errorf("grpc dial option is not configured")
|
|
}
|
|
if len(masterAddresses) == 0 {
|
|
return nil, nil, nil, fmt.Errorf("no master addresses provided in cluster context")
|
|
}
|
|
|
|
for _, masterAddress := range masterAddresses {
|
|
response, err := FetchVolumeList(ctx, masterAddress, grpcDialOption)
|
|
if err != nil {
|
|
glog.Warningf("Plugin worker failed master volume list at %s: %v", masterAddress, err)
|
|
continue
|
|
}
|
|
|
|
metrics, activeTopology, replicaMap, buildErr := buildVolumeMetrics(response, collectionFilter)
|
|
if buildErr != nil {
|
|
// Configuration errors (e.g. invalid regex) will fail on every master,
|
|
// so return immediately instead of masking them with retries.
|
|
if isConfigError(buildErr) {
|
|
return nil, nil, nil, buildErr
|
|
}
|
|
glog.Warningf("Plugin worker failed to build metrics from master %s: %v", masterAddress, buildErr)
|
|
continue
|
|
}
|
|
return metrics, activeTopology, replicaMap, nil
|
|
}
|
|
|
|
return nil, nil, nil, fmt.Errorf("failed to load topology from all provided masters")
|
|
}
|
|
|
|
// FetchVolumeList dials the given master address (trying both the address as
|
|
// given and the gRPC port variant) and returns the master's volume list. Used
|
|
// by detection helpers that already know which master address to talk to.
|
|
// FetchDefaultReplicaPlacement returns the master's configured default replication
|
|
// (GetMasterConfiguration), used by detectors as the replica-placement fallback so
|
|
// the plugin path matches the shell. Returns "" if it cannot be fetched, so callers
|
|
// fall back to even spread rather than failing detection.
|
|
func FetchDefaultReplicaPlacement(ctx context.Context, masterAddresses []string, grpcDialOption grpc.DialOption) string {
|
|
if grpcDialOption == nil {
|
|
return ""
|
|
}
|
|
for _, address := range masterAddresses {
|
|
for _, candidate := range MasterAddressCandidates(address) {
|
|
if ctx.Err() != nil {
|
|
return ""
|
|
}
|
|
dialCtx, cancelDial := context.WithTimeout(ctx, 5*time.Second)
|
|
conn, err := pb.GrpcDial(dialCtx, candidate, false, grpcDialOption)
|
|
cancelDial()
|
|
if err != nil {
|
|
continue
|
|
}
|
|
client := master_pb.NewSeaweedClient(conn)
|
|
callCtx, cancelCall := context.WithTimeout(ctx, 10*time.Second)
|
|
resp, callErr := client.GetMasterConfiguration(callCtx, &master_pb.GetMasterConfigurationRequest{})
|
|
cancelCall()
|
|
_ = conn.Close()
|
|
if callErr == nil {
|
|
return resp.DefaultReplication
|
|
}
|
|
}
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func FetchVolumeList(ctx context.Context, address string, grpcDialOption grpc.DialOption) (*master_pb.VolumeListResponse, error) {
|
|
var lastErr error
|
|
for _, candidate := range MasterAddressCandidates(address) {
|
|
if ctx.Err() != nil {
|
|
return nil, ctx.Err()
|
|
}
|
|
|
|
dialCtx, cancelDial := context.WithTimeout(ctx, 5*time.Second)
|
|
conn, err := pb.GrpcDial(dialCtx, candidate, false, grpcDialOption)
|
|
cancelDial()
|
|
if err != nil {
|
|
lastErr = err
|
|
continue
|
|
}
|
|
|
|
client := master_pb.NewSeaweedClient(conn)
|
|
callCtx, cancelCall := context.WithTimeout(ctx, 10*time.Second)
|
|
response, callErr := pb.CollectVolumeList(callCtx, client, &master_pb.VolumeListRequest{})
|
|
cancelCall()
|
|
_ = conn.Close()
|
|
|
|
if callErr == nil {
|
|
return response, nil
|
|
}
|
|
lastErr = callErr
|
|
}
|
|
|
|
if lastErr == nil {
|
|
lastErr = fmt.Errorf("no valid master address candidate")
|
|
}
|
|
return nil, lastErr
|
|
}
|
|
|
|
func buildVolumeMetrics(
|
|
response *master_pb.VolumeListResponse,
|
|
collectionFilter string,
|
|
) ([]*workertypes.VolumeHealthMetrics, *topology.ActiveTopology, map[uint32][]workertypes.ReplicaLocation, error) {
|
|
if response == nil || response.TopologyInfo == nil {
|
|
return nil, nil, nil, fmt.Errorf("volume list response has no topology info")
|
|
}
|
|
|
|
activeTopology := topology.NewActiveTopology(10)
|
|
if err := activeTopology.UpdateTopology(response.TopologyInfo); err != nil {
|
|
return nil, nil, nil, err
|
|
}
|
|
|
|
collectionMatcher, err := wildcard.CompileCollectionMatcher(collectionFilter)
|
|
if err != nil {
|
|
return nil, nil, nil, &configError{err: err}
|
|
}
|
|
|
|
volumeSizeLimitBytes := uint64(response.VolumeSizeLimitMb) * 1024 * 1024
|
|
now := time.Now()
|
|
metrics := make([]*workertypes.VolumeHealthMetrics, 0, 256)
|
|
replicaMap := make(map[uint32][]workertypes.ReplicaLocation)
|
|
|
|
for _, dc := range response.TopologyInfo.DataCenterInfos {
|
|
for _, rack := range dc.RackInfos {
|
|
for _, node := range rack.DataNodeInfos {
|
|
for diskType, diskInfo := range node.DiskInfos {
|
|
for _, volume := range diskInfo.VolumeInfos {
|
|
// Build replica map from ALL volumes BEFORE collection filtering,
|
|
// since replicas may span filtered/unfiltered nodes.
|
|
replicaMap[volume.Id] = append(replicaMap[volume.Id], workertypes.ReplicaLocation{
|
|
DataCenter: dc.Id,
|
|
Rack: rack.Id,
|
|
NodeID: node.Id,
|
|
Host: pb.NewServerAddressFromDataNode(node).ToHost(),
|
|
})
|
|
|
|
if !collectionMatcher.Matches(volume.Collection) {
|
|
continue
|
|
}
|
|
|
|
metric := &workertypes.VolumeHealthMetrics{
|
|
VolumeID: volume.Id,
|
|
Server: node.Id,
|
|
ServerAddress: string(pb.NewServerAddressFromDataNode(node)),
|
|
DiskType: diskType,
|
|
DiskId: volume.DiskId,
|
|
DataCenter: dc.Id,
|
|
Rack: rack.Id,
|
|
Collection: volume.Collection,
|
|
Size: volume.Size,
|
|
DeletedBytes: volume.DeletedByteCount,
|
|
LastModified: time.Unix(volume.ModifiedAtSecond, 0),
|
|
ReplicaCount: 1,
|
|
ExpectedReplicas: int(volume.ReplicaPlacement),
|
|
IsReadOnly: volume.ReadOnly,
|
|
HasRemoteCopy: volume.RemoteStorageName != "",
|
|
}
|
|
if metric.Size > 0 {
|
|
metric.GarbageRatio = float64(metric.DeletedBytes) / float64(metric.Size)
|
|
}
|
|
if volumeSizeLimitBytes > 0 {
|
|
metric.FullnessRatio = float64(metric.Size) / float64(volumeSizeLimitBytes)
|
|
}
|
|
metric.Age = now.Sub(metric.LastModified)
|
|
metrics = append(metrics, metric)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
replicaCounts := make(map[uint32]int)
|
|
for _, metric := range metrics {
|
|
replicaCounts[metric.VolumeID]++
|
|
}
|
|
for _, metric := range metrics {
|
|
metric.ReplicaCount = replicaCounts[metric.VolumeID]
|
|
}
|
|
|
|
return metrics, activeTopology, replicaMap, nil
|
|
}
|
|
|
|
// configError wraps configuration errors that should not be retried across masters.
|
|
type configError struct {
|
|
err error
|
|
}
|
|
|
|
func (e *configError) Error() string { return e.err.Error() }
|
|
func (e *configError) Unwrap() error { return e.err }
|
|
|
|
func isConfigError(err error) bool {
|
|
var ce *configError
|
|
return errors.As(err, &ce)
|
|
}
|
|
|
|
// MasterAddressCandidates returns address forms to try when dialing a master:
|
|
// the address as given plus the gRPC variant (port + 10000). Both are tried
|
|
// because callers may pass either an HTTP-port or gRPC-port address.
|
|
func MasterAddressCandidates(address string) []string {
|
|
trimmed := strings.TrimSpace(address)
|
|
if trimmed == "" {
|
|
return nil
|
|
}
|
|
candidateSet := map[string]struct{}{
|
|
trimmed: {},
|
|
}
|
|
converted := pb.ServerToGrpcAddress(trimmed)
|
|
candidateSet[converted] = struct{}{}
|
|
|
|
candidates := make([]string, 0, len(candidateSet))
|
|
for candidate := range candidateSet {
|
|
candidates = append(candidates, candidate)
|
|
}
|
|
sort.Strings(candidates)
|
|
return candidates
|
|
}
|