mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-28 03:46:24 +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.
104 lines
3.2 KiB
Go
104 lines
3.2 KiB
Go
package shell
|
|
|
|
import (
|
|
"context"
|
|
"flag"
|
|
"io"
|
|
"log"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/super_block"
|
|
"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
|
|
)
|
|
|
|
func init() {
|
|
Commands = append(Commands, &commandVolumeDeleteEmpty{})
|
|
}
|
|
|
|
type commandVolumeDeleteEmpty struct {
|
|
}
|
|
|
|
func (c *commandVolumeDeleteEmpty) Name() string {
|
|
return "volume.deleteEmpty"
|
|
}
|
|
|
|
func (c *commandVolumeDeleteEmpty) Help() string {
|
|
return `delete empty volumes from all volume servers
|
|
|
|
volume.deleteEmpty -quietFor=24h -apply
|
|
volume.deleteEmpty -collectionPattern=important* -quietFor=24h -apply
|
|
|
|
This command deletes all empty volumes from one volume server.
|
|
|
|
`
|
|
}
|
|
|
|
func (c *commandVolumeDeleteEmpty) HasTag(CommandTag) bool {
|
|
return false
|
|
}
|
|
|
|
func (c *commandVolumeDeleteEmpty) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
|
|
|
|
volDeleteCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
|
quietPeriod := volDeleteCommand.Duration("quietFor", 24*time.Hour, "select empty volumes with no recent writes, avoid newly created ones")
|
|
collectionPattern := volDeleteCommand.String("collectionPattern", "", "comma-separated collection names, with '*' and '?' wildcards; empty matches all")
|
|
applyBalancing := volDeleteCommand.Bool("apply", false, "apply to delete empty volumes")
|
|
// TODO: remove this alias
|
|
applyBalancingAlias := volDeleteCommand.Bool("force", false, "apply to delete empty volumes (alias for -apply)")
|
|
if err = volDeleteCommand.Parse(args); err != nil {
|
|
return nil
|
|
}
|
|
|
|
handleDeprecatedForceFlag(writer, volDeleteCommand, applyBalancingAlias, applyBalancing)
|
|
infoAboutSimulationMode(writer, *applyBalancing, "-apply")
|
|
|
|
if err = commandEnv.confirmIsLocked(args); err != nil {
|
|
return
|
|
}
|
|
|
|
// collect topology information
|
|
topologyInfo, _, err := collectTopologyInfo(commandEnv, 0)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
collectionMatcher, err := wildcard.CompileCollectionMatcher(*collectionPattern)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
quietSeconds := int64(*quietPeriod / time.Second)
|
|
nowUnixSeconds := time.Now().Unix()
|
|
|
|
eachDataNode(topologyInfo, func(dc DataCenterId, rack RackId, dn *master_pb.DataNodeInfo) {
|
|
for _, diskInfo := range dn.DiskInfos {
|
|
for _, v := range diskInfo.VolumeInfos {
|
|
if isEmptyVolumeDeleteCandidate(v, quietSeconds, nowUnixSeconds, collectionMatcher) {
|
|
if *applyBalancing {
|
|
log.Printf("deleting empty volume %d from %s", v.Id, dn.Id)
|
|
if deleteErr := deleteVolume(context.Background(), commandEnv.option.GrpcDialOption, needle.VolumeId(v.Id),
|
|
pb.NewServerAddressFromDataNode(dn), true, false); deleteErr != nil {
|
|
err = deleteErr
|
|
}
|
|
continue
|
|
} else {
|
|
log.Printf("empty volume %d from %s", v.Id, dn.Id)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
})
|
|
|
|
return
|
|
}
|
|
|
|
func isEmptyVolumeDeleteCandidate(v *master_pb.VolumeInformationMessage, quietSeconds, nowUnixSeconds int64, collectionMatcher *wildcard.CollectionMatcher) bool {
|
|
return collectionMatcher.Matches(v.Collection) &&
|
|
v.Size <= super_block.SuperBlockSize &&
|
|
v.ModifiedAtSecond > 0 &&
|
|
v.ModifiedAtSecond+quietSeconds < nowUnixSeconds
|
|
}
|