mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-02 18:22:40 +01:00
* 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>
165 lines
4.5 KiB
Go
165 lines
4.5 KiB
Go
package shell
|
|
|
|
import (
|
|
"context"
|
|
"flag"
|
|
"fmt"
|
|
"io"
|
|
"slices"
|
|
"strings"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/operation"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
|
|
"google.golang.org/protobuf/proto"
|
|
)
|
|
|
|
func init() {
|
|
Commands = append(Commands, &commandVolumeServerState{})
|
|
}
|
|
|
|
type commandVolumeServerState struct {
|
|
env *CommandEnv
|
|
writer io.Writer
|
|
}
|
|
|
|
func (c *commandVolumeServerState) Name() string {
|
|
return "volumeServer.state"
|
|
}
|
|
|
|
func (c *commandVolumeServerState) Help() string {
|
|
return `query/update volume server state settings
|
|
|
|
volumeServer.state [-nodes <host:port>] [..state flags...]
|
|
|
|
This command display volume server state flags for the provided
|
|
list of nodes; if empty, all nodes in the topology are queried.
|
|
For example:
|
|
|
|
volumeServer.state --nodes 192.168.10.111:9000,192.168.10.112:9000
|
|
|
|
Additionally, if any flags are provided, these are applied
|
|
to the selected node(s). The command will display the resulting
|
|
state for each node *after* the state is updated. For example...
|
|
|
|
volumeServer.state --nodes 192.168.10.111:9000 --maintenanceOn
|
|
|
|
...will set the specified volume server to maintenance mode.
|
|
|
|
`
|
|
}
|
|
|
|
func (c *commandVolumeServerState) HasTag(CommandTag) bool {
|
|
return false
|
|
}
|
|
|
|
func (c *commandVolumeServerState) write(format string, a ...any) {
|
|
format = strings.TrimRight(format, " ")
|
|
if len(format) == 0 {
|
|
format = "\n"
|
|
}
|
|
fmt.Fprintf(c.writer, format, a...)
|
|
|
|
last := format[len(format)-1:]
|
|
if last != "\n" && last != "\r" {
|
|
fmt.Fprint(c.writer, "\n")
|
|
}
|
|
}
|
|
|
|
func (c *commandVolumeServerState) bool2Str(b bool) string {
|
|
if b {
|
|
return "yes"
|
|
}
|
|
return "no"
|
|
}
|
|
|
|
func (c *commandVolumeServerState) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
|
|
vsStateCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
|
nodesStr := vsStateCommand.String("nodes", "", "comma-separated list of volume servers <host>:<port> (optional)")
|
|
maintenanceOn := vsStateCommand.Bool("maintenanceOn", false, "enables maintenance mode on the server")
|
|
maintenanceOff := vsStateCommand.Bool("maintenanceOff", false, "disables maintenance mode on the server")
|
|
if err = vsStateCommand.Parse(args); err != nil {
|
|
return err
|
|
}
|
|
|
|
if *maintenanceOn && *maintenanceOff {
|
|
return fmt.Errorf("--maintenanceOn and --maintenanceOff are mutually exclusive")
|
|
}
|
|
|
|
volumeServerAddrs, err := collectVolumeServerAddresses(commandEnv, *nodesStr)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
slices.Sort(volumeServerAddrs)
|
|
if len(volumeServerAddrs) == 0 {
|
|
return fmt.Errorf("no volume servers specified")
|
|
}
|
|
|
|
c.env = commandEnv
|
|
c.writer = writer
|
|
|
|
for _, addr := range volumeServerAddrs {
|
|
state, err := c.getVolumeServerState(addr)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to load state from %v: %v", addr, err)
|
|
}
|
|
|
|
stateOrig := &volume_server_pb.VolumeServerState{}
|
|
proto.Merge(stateOrig, state)
|
|
|
|
// apply updates, if any
|
|
switch {
|
|
case *maintenanceOn:
|
|
state.Maintenance = true
|
|
case *maintenanceOff:
|
|
state.Maintenance = false
|
|
}
|
|
|
|
// update volume server state if settings changed
|
|
if !proto.Equal(state, stateOrig) {
|
|
state, err = c.setVolumeServerState(addr, state)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to update state for %v: %v", addr, err)
|
|
}
|
|
}
|
|
|
|
c.write("%v\t -> Maintenance mode: %s\n", addr.String(), c.bool2Str(state.GetMaintenance()))
|
|
}
|
|
|
|
return
|
|
}
|
|
|
|
func (c *commandVolumeServerState) getVolumeServerState(volumeServerAddress pb.ServerAddress) (*volume_server_pb.VolumeServerState, error) {
|
|
var state *volume_server_pb.VolumeServerState
|
|
|
|
err := operation.WithVolumeServerClient(false, volumeServerAddress, c.env.option.GrpcDialOption, func(volumeServerClient volume_server_pb.VolumeServerClient) error {
|
|
res, err := volumeServerClient.GetState(context.Background(), &volume_server_pb.GetStateRequest{})
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
state = res.GetState()
|
|
return nil
|
|
})
|
|
|
|
return state, err
|
|
}
|
|
|
|
func (c *commandVolumeServerState) setVolumeServerState(volumeServerAddress pb.ServerAddress, state *volume_server_pb.VolumeServerState) (*volume_server_pb.VolumeServerState, error) {
|
|
var stateAfter *volume_server_pb.VolumeServerState
|
|
|
|
err := operation.WithVolumeServerClient(false, volumeServerAddress, c.env.option.GrpcDialOption, func(volumeServerClient volume_server_pb.VolumeServerClient) error {
|
|
res, err := volumeServerClient.SetState(context.Background(), &volume_server_pb.SetStateRequest{
|
|
State: state,
|
|
})
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
stateAfter = res.GetState()
|
|
return nil
|
|
})
|
|
|
|
return stateAfter, err
|
|
}
|