mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-16 04:06:44 +00:00
Chris LuandGitHub
4f50c5b0d4
* feat: throughput limits for replicate, EC shard, and worker-driven moves VolumeCopy was the only rate-limitable transfer; EC shard copies, replica creation, and worker-driven moves all ran at whatever the receiving server's maintenance rate allowed, with no per-operation control. - proto: VolumeEcShardsCopyRequest and the balance / ec_balance task params and configs gain io_byte_per_second; 0 keeps today's behavior (the volume server's own maintenance rate governs). - volume server: VolumeEcShardsCopy throttles with one WriteThrottler per request, shared across the shard, .ecx, .ecj, .vif, and .ecsum copies so the limit caps the transfer as a whole - the same shape as VolumeCopy. - volume_move: ReplicateVolume accepts the limit; EcMoveOptions carries it through MoveEcShards/CopyAndMountEcShards into the copy request, with fake-client tests asserting propagation. - shell: ec.balance gains -ioBytePerSecond; volume.tier.move's replication top-up honors the command's existing -ioBytePerSecond instead of running unthrottled. - worker: balance and ec_balance configs gain io_byte_per_second (surfaced in the admin config schema), carried through detection and plugin job parameters into task params and handed to the shared mover; batch balance jobs inherit the limit from their detection results. The limit is per copy stream, so maxParallelization multiplies the aggregate ceiling. * worker plugins: expose io_byte_per_second in the plugin config and derive it The plugin-driven detection path derives its task Config from the plugin configuration values, and both balance and ec_balance left IoBytePerSecond at zero there - a configured limit silently reverted to the server maintenance rate. Both derive functions now read the field (clamped at zero), and the plugin descriptors expose it with defaults so the configuration form carries it.
94 lines
3.4 KiB
Go
94 lines
3.4 KiB
Go
package shell
|
|
|
|
import (
|
|
"flag"
|
|
"io"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/types"
|
|
)
|
|
|
|
func init() {
|
|
Commands = append(Commands, &commandEcBalance{})
|
|
}
|
|
|
|
type commandEcBalance struct {
|
|
}
|
|
|
|
func (c *commandEcBalance) Name() string {
|
|
return "ec.balance"
|
|
}
|
|
|
|
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>] [-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
|
|
}
|
|
|
|
func (c *commandEcBalance) HasTag(CommandTag) bool {
|
|
return false
|
|
}
|
|
|
|
func (c *commandEcBalance) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
|
|
balanceCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
|
collection := balanceCommand.String("collection", "EACH_COLLECTION", "collection name, or \"EACH_COLLECTION\" for each collection")
|
|
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")
|
|
ioBytePerSecond := balanceCommand.Int64("ioBytePerSecond", 0, "limit the speed of each shard copy; 0 falls back to the volume server's maintenance rate")
|
|
applyBalancing := balanceCommand.Bool("apply", false, "apply the balancing plan")
|
|
// TODO: remove this alias
|
|
applyBalancingAlias := balanceCommand.Bool("force", false, "apply the balancing plan (alias for -apply)")
|
|
|
|
if err = balanceCommand.Parse(args); err != nil {
|
|
return nil
|
|
}
|
|
|
|
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
|
|
}
|
|
|
|
var collections []string
|
|
if *collection == "EACH_COLLECTION" {
|
|
collections, err = ListCollectionNames(commandEnv, false, true)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
} else {
|
|
collections = append(collections, *collection)
|
|
}
|
|
glog.V(1).Infof("balanceEcVolumes collections %+v\n", len(collections))
|
|
|
|
rp, err := parseReplicaPlacementArg(commandEnv, *shardReplicaPlacement)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
diskType := types.ToDiskType(*diskTypeStr)
|
|
|
|
return EcBalance(commandEnv, collections, *dc, rp, diskType, *maxParallelization, *ioBytePerSecond, *applyBalancing, nil, volumeIds)
|
|
}
|