ec.balance: add a -volumeIds filter (#10667)

* ec.balance: add a -volumeIds filter

Collection scope is often too broad for maintenance. -volumeIds narrows the
plan to the given ec volume ids by leaving every other volume out of the
topology handed to the planner, so no phase, dedup included, can plan against
them. Ids with no ec shard in the selected collection, dataCenter and disk type
are rejected rather than silently skipped.

* ec.encode: key the orphan sweep without narrowing the volume id

int is 32-bit on 32-bit builds, so int(vid) wraps for volume ids above
MaxInt32. Format the id as the uint32 it is.

weed/shell/command_ec_balance.go

@@ -5,6 +5,7 @@ import (
 	"io"
 
 	"github.com/seaweedfs/seaweedfs/weed/glog"
+	"github.com/seaweedfs/seaweedfs/weed/storage/needle"
 	"github.com/seaweedfs/seaweedfs/weed/storage/types"
 )
 
@@ -22,10 +23,14 @@ func (c *commandEcBalance) Name() string {
 func (c *commandEcBalance) Help() string {
 	return `balance all ec shards among all racks and volume servers
 
-	ec.balance [-c EACH_COLLECTION|<collection_name>] [-apply] [-dataCenter <data_center>] [-shardReplicaPlacement <replica_placement>] [-diskType <disk_type>]
+	ec.balance [-c EACH_COLLECTION|<collection_name>] [-apply] [-dataCenter <data_center>] [-shardReplicaPlacement <replica_placement>] [-diskType <disk_type>] [-volumeIds <id>[,<id>...]]
 
 	Options:
 	  -diskType: the disk type for EC shards (hdd, ssd, or empty for default hdd)
+	  -volumeIds: only balance these ec volume ids, e.g. -volumeIds 123,456. The plan is
+	    built as if no other ec volume existed, so nothing else is moved or deduplicated.
+	    Ids without any ec shard in the selected collection, dataCenter and disk type are
+	    an error.
 
 	Algorithm:
 	` + ecBalanceAlgorithmDescription
@@ -41,6 +46,7 @@ func (c *commandEcBalance) Do(args []string, commandEnv *CommandEnv, writer io.W
 	dc := balanceCommand.String("dataCenter", "", "only apply the balancing for this dataCenter")
 	shardReplicaPlacement := balanceCommand.String("shardReplicaPlacement", "", "replica placement for EC shards, or master default if empty")
 	diskTypeStr := balanceCommand.String("diskType", "", "the disk type for EC shards (hdd, ssd, or empty for default hdd)")
+	volumeIdsStr := balanceCommand.String("volumeIds", "", "optional comma-separated list of ec volume ids to balance; defaults to all")
 	maxParallelization := balanceCommand.Int("maxParallelization", DefaultMaxParallelization, "run up to X tasks in parallel, whenever possible")
 	applyBalancing := balanceCommand.Bool("apply", false, "apply the balancing plan")
 	// TODO: remove this alias
@@ -53,6 +59,13 @@ func (c *commandEcBalance) Do(args []string, commandEnv *CommandEnv, writer io.W
 	handleDeprecatedForceFlag(writer, balanceCommand, applyBalancingAlias, applyBalancing)
 	infoAboutSimulationMode(writer, *applyBalancing, "-apply")
 
+	var volumeIds []needle.VolumeId
+	if *volumeIdsStr != "" {
+		if volumeIds, err = parseVolumeIdsFlag(*volumeIdsStr); err != nil {
+			return err
+		}
+	}
+
 	if err = commandEnv.confirmIsLocked(args); err != nil {
 		return
 	}
@@ -75,5 +88,5 @@ func (c *commandEcBalance) Do(args []string, commandEnv *CommandEnv, writer io.W
 
 	diskType := types.ToDiskType(*diskTypeStr)
 
-	return EcBalance(commandEnv, collections, *dc, rp, diskType, *maxParallelization, *applyBalancing, nil)
+	return EcBalance(commandEnv, collections, *dc, rp, diskType, *maxParallelization, *applyBalancing, nil, volumeIds)
 }