mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-02 18:22:40 +01:00
Chris LuandClaude Opus 5.5
80e0bf97dd
* shell: dial scrubbed volume servers on their registered gRPC port volume.scrub, ec.scrub and volume.server.state built each data node's address from its HTTP address alone, so a volume server whose gRPC port is not the HTTP port + 10000 was dialed on the wrong port. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * shell: resolve -node volume servers to their registered gRPC port An explicit -node/-nodes list was dialed on HTTP port + 10000 too. Match each entry against the topology and take the data node's gRPC port; an address the master does not know is used as given. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * shell: keep a gRPC port given in -node A node given as host:port.grpcPort was rewritten to the registered gRPC port; only a bare host:port takes it from the topology. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * shell: dial -node volume servers when the topology is unavailable An explicit node list did not need the master before; keep using it as given if the volume list cannot be fetched. Selecting every node still requires the topology. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * shell: bound the topology lookup for an explicit -node list With the master down, volumeServer.state -nodes waited on the master forever instead of reaching the given volume servers. Give the lookup a 30s deadline and fall back to the addresses as given. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * shell: resolve volume server addresses from a topology-only listing Only the data nodes are needed to find each server's gRPC port, so ask the master for the topology without its volumes and ec shards. A large cluster no longer risks running past the -node lookup deadline and falling back to the HTTP port + 10000. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * shell: skip the topology lookup when every -node names its gRPC port A host:port.grpcPort entry is dialed as given, so a list made only of those does not need the master and no longer waits on it during an outage. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
98 lines
3.2 KiB
Go
98 lines
3.2 KiB
Go
package shell
|
|
|
|
import (
|
|
"flag"
|
|
"fmt"
|
|
"io"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/ec"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
|
|
)
|
|
|
|
func init() {
|
|
Commands = append(Commands, &commandEcVolumeScrub{})
|
|
}
|
|
|
|
type commandEcVolumeScrub struct {
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) Name() string {
|
|
return "ec.scrub"
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) Help() string {
|
|
return `scrubs EC volume contents on volume servers.
|
|
|
|
Supports either scrubbing only needle data, or deep scrubbing file contents as well.
|
|
|
|
Scrubbing can be limited to specific EC volume IDs for specific volume servers.
|
|
By default, all volume IDs across all servers are processed.
|
|
`
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) HasTag(CommandTag) bool {
|
|
return false
|
|
}
|
|
|
|
func (c *commandEcVolumeScrub) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
|
|
volScrubCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
|
nodesStr := volScrubCommand.String("node", "", "comma-separated list of volume server <host>:<port> (optional)")
|
|
volumeIDsStr := volScrubCommand.String("volumeId", "", "comma-separated EC volume IDs to process (optional)")
|
|
mode := volScrubCommand.String("mode", "local", "scrubbing mode (index/local/full/reads/checksum)")
|
|
maxParallelization := volScrubCommand.Int("maxParallelization", DefaultMaxParallelization, "run up to X tasks in parallel, whenever possible")
|
|
showDetails := volScrubCommand.Bool("details", false, "display scrub result details, if available")
|
|
forceDeletedNeedlesCheck := volScrubCommand.Bool("forceDeletedNeedlesCheck", false, "force strict verification of deleted needles (full and reads modes only); may report false positives when EC indexes disagree")
|
|
|
|
if err = volScrubCommand.Parse(args); err != nil {
|
|
return err
|
|
}
|
|
if err = commandEnv.confirmIsLocked(args); err != nil {
|
|
return
|
|
}
|
|
|
|
volumeServerAddrs, err := collectVolumeServerAddresses(commandEnv, *nodesStr)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
volumeIDs := []uint32{}
|
|
if *volumeIDsStr != "" {
|
|
for _, vids := range strings.Split(*volumeIDsStr, ",") {
|
|
vids = strings.TrimSpace(vids)
|
|
if vids == "" {
|
|
continue
|
|
}
|
|
if vid, err := strconv.ParseUint(vids, 10, 32); err == nil {
|
|
volumeIDs = append(volumeIDs, uint32(vid))
|
|
} else {
|
|
return fmt.Errorf("invalid volume ID %q", vids)
|
|
}
|
|
}
|
|
}
|
|
|
|
var scrubMode volume_server_pb.VolumeScrubMode
|
|
switch strings.ToUpper(*mode) {
|
|
case "INDEX":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_INDEX
|
|
case "LOCAL":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_LOCAL
|
|
case "FULL":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_FULL
|
|
case "CHECKSUM":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_CHECKSUM
|
|
case "READS":
|
|
scrubMode = volume_server_pb.VolumeScrubMode_READS
|
|
default:
|
|
return fmt.Errorf("unsupported scrubbing mode %q", *mode)
|
|
}
|
|
fmt.Fprintf(writer, "using %s mode\n", scrubMode.String())
|
|
if *forceDeletedNeedlesCheck &&
|
|
scrubMode != volume_server_pb.VolumeScrubMode_FULL && scrubMode != volume_server_pb.VolumeScrubMode_READS {
|
|
return fmt.Errorf("deleted needle checks are only supported for FULL and READS scrubs")
|
|
}
|
|
|
|
return ec.ScrubEcVolumes(commandEnv.ecEnv(), writer, volumeServerAddrs, volumeIDs, scrubMode, *forceDeletedNeedlesCheck, *maxParallelization, *showDetails)
|
|
}
|