ed14061578
* Work on raft backend * Add logstore locally * Add encryptor and unsealable interfaces * Add clustering support to raft * Remove client and handler * Bootstrap raft on init * Cleanup raft logic a bit * More raft work * Work on TLS config * More work on bootstrapping * Fix build * More work on bootstrapping * More bootstrapping work * fix build * Remove consul dep * Fix build * merged oss/master into raft-storage * Work on bootstrapping * Get bootstrapping to work * Clean up FMS and node-id * Update local node ID logic * Cleanup node-id change * Work on snapshotting * Raft: Add remove peer API (#906) * Add remove peer API * Add some comments * Fix existing snapshotting (#909) * Raft get peers API (#912) * Read raft configuration * address review feedback * Use the Leadership Transfer API to step-down the active node (#918) * Raft join and unseal using Shamir keys (#917) * Raft join using shamir * Store AEAD instead of master key * Split the raft join process to answer the challenge after a successful unseal * get the follower to standby state * Make unseal work * minor changes * Some input checks * reuse the shamir seal access instead of new default seal access * refactor joinRaftSendAnswer function * Synchronously send answer in auto-unseal case * Address review feedback * Raft snapshots (#910) * Fix existing snapshotting * implement the noop snapshotting * Add comments and switch log libraries * add some snapshot tests * add snapshot test file * add TODO * More work on raft snapshotting * progress on the ConfigStore strategy * Don't use two buckets * Update the snapshot store logic to hide the file logic * Add more backend tests * Cleanup code a bit * [WIP] Raft recovery (#938) * Add recovery functionality * remove fmt.Printfs * Fix a few fsm bugs * Add max size value for raft backend (#942) * Add max size value for raft backend * Include physical.ErrValueTooLarge in the message * Raft snapshot Take/Restore API (#926) * Inital work on raft snapshot APIs * Always redirect snapshot install/download requests * More work on the snapshot APIs * Cleanup code a bit * On restore handle special cases * Use the seal to encrypt the sha sum file * Add sealer mechanism and fix some bugs * Call restore while state lock is held * Send restore cb trigger through raft log * Make error messages nicer * Add test helpers * Add snapshot test * Add shamir unseal test * Add more raft snapshot API tests * Fix locking * Change working to initalize * Add underlying raw object to test cluster core * Move leaderUUID to core * Add raft TLS rotation logic (#950) * Add TLS rotation logic * Cleanup logic a bit * Add/Remove from follower state on add/remove peer * add comments * Update more comments * Update request_forwarding_service.proto * Make sure we populate all nodes in the followerstate obj * Update times * Apply review feedback * Add more raft config setting (#947) * Add performance config setting * Add more config options and fix tests * Test Raft Recovery (#944) * Test raft recovery * Leave out a node during recovery * remove unused struct * Update physical/raft/snapshot_test.go * Update physical/raft/snapshot_test.go * fix vendoring * Switch to new raft interface * Remove unused files * Switch a gogo -> proto instance * Remove unneeded vault dep in go.sum * Update helper/testhelpers/testhelpers.go Co-Authored-By: Calvin Leung Huang <cleung2010@gmail.com> * Update vault/cluster/cluster.go * track active key within the keyring itself (#6915) * track active key within the keyring itself * lookup and store using the active key ID * update docstring * minor refactor * Small text fixes (#6912) * Update physical/raft/raft.go Co-Authored-By: Calvin Leung Huang <cleung2010@gmail.com> * review feedback * Move raft logical system into separate file * Update help text a bit * Enforce cluster addr is set and use it for raft bootstrapping * Fix tests * fix http test panic * Pull in latest raft-snapshot library * Add comment
172 lines
3.8 KiB
Go
172 lines
3.8 KiB
Go
package raft
|
|
|
|
import (
|
|
"sync"
|
|
"sync/atomic"
|
|
)
|
|
|
|
// RaftState captures the state of a Raft node: Follower, Candidate, Leader,
|
|
// or Shutdown.
|
|
type RaftState uint32
|
|
|
|
const (
|
|
// Follower is the initial state of a Raft node.
|
|
Follower RaftState = iota
|
|
|
|
// Candidate is one of the valid states of a Raft node.
|
|
Candidate
|
|
|
|
// Leader is one of the valid states of a Raft node.
|
|
Leader
|
|
|
|
// Shutdown is the terminal state of a Raft node.
|
|
Shutdown
|
|
)
|
|
|
|
func (s RaftState) String() string {
|
|
switch s {
|
|
case Follower:
|
|
return "Follower"
|
|
case Candidate:
|
|
return "Candidate"
|
|
case Leader:
|
|
return "Leader"
|
|
case Shutdown:
|
|
return "Shutdown"
|
|
default:
|
|
return "Unknown"
|
|
}
|
|
}
|
|
|
|
// raftState is used to maintain various state variables
|
|
// and provides an interface to set/get the variables in a
|
|
// thread safe manner.
|
|
type raftState struct {
|
|
// currentTerm commitIndex, lastApplied, must be kept at the top of
|
|
// the struct so they're 64 bit aligned which is a requirement for
|
|
// atomic ops on 32 bit platforms.
|
|
|
|
// The current term, cache of StableStore
|
|
currentTerm uint64
|
|
|
|
// Highest committed log entry
|
|
commitIndex uint64
|
|
|
|
// Last applied log to the FSM
|
|
lastApplied uint64
|
|
|
|
// protects 4 next fields
|
|
lastLock sync.Mutex
|
|
|
|
// Cache the latest snapshot index/term
|
|
lastSnapshotIndex uint64
|
|
lastSnapshotTerm uint64
|
|
|
|
// Cache the latest log from LogStore
|
|
lastLogIndex uint64
|
|
lastLogTerm uint64
|
|
|
|
// Tracks running goroutines
|
|
routinesGroup sync.WaitGroup
|
|
|
|
// The current state
|
|
state RaftState
|
|
}
|
|
|
|
func (r *raftState) getState() RaftState {
|
|
stateAddr := (*uint32)(&r.state)
|
|
return RaftState(atomic.LoadUint32(stateAddr))
|
|
}
|
|
|
|
func (r *raftState) setState(s RaftState) {
|
|
stateAddr := (*uint32)(&r.state)
|
|
atomic.StoreUint32(stateAddr, uint32(s))
|
|
}
|
|
|
|
func (r *raftState) getCurrentTerm() uint64 {
|
|
return atomic.LoadUint64(&r.currentTerm)
|
|
}
|
|
|
|
func (r *raftState) setCurrentTerm(term uint64) {
|
|
atomic.StoreUint64(&r.currentTerm, term)
|
|
}
|
|
|
|
func (r *raftState) getLastLog() (index, term uint64) {
|
|
r.lastLock.Lock()
|
|
index = r.lastLogIndex
|
|
term = r.lastLogTerm
|
|
r.lastLock.Unlock()
|
|
return
|
|
}
|
|
|
|
func (r *raftState) setLastLog(index, term uint64) {
|
|
r.lastLock.Lock()
|
|
r.lastLogIndex = index
|
|
r.lastLogTerm = term
|
|
r.lastLock.Unlock()
|
|
}
|
|
|
|
func (r *raftState) getLastSnapshot() (index, term uint64) {
|
|
r.lastLock.Lock()
|
|
index = r.lastSnapshotIndex
|
|
term = r.lastSnapshotTerm
|
|
r.lastLock.Unlock()
|
|
return
|
|
}
|
|
|
|
func (r *raftState) setLastSnapshot(index, term uint64) {
|
|
r.lastLock.Lock()
|
|
r.lastSnapshotIndex = index
|
|
r.lastSnapshotTerm = term
|
|
r.lastLock.Unlock()
|
|
}
|
|
|
|
func (r *raftState) getCommitIndex() uint64 {
|
|
return atomic.LoadUint64(&r.commitIndex)
|
|
}
|
|
|
|
func (r *raftState) setCommitIndex(index uint64) {
|
|
atomic.StoreUint64(&r.commitIndex, index)
|
|
}
|
|
|
|
func (r *raftState) getLastApplied() uint64 {
|
|
return atomic.LoadUint64(&r.lastApplied)
|
|
}
|
|
|
|
func (r *raftState) setLastApplied(index uint64) {
|
|
atomic.StoreUint64(&r.lastApplied, index)
|
|
}
|
|
|
|
// Start a goroutine and properly handle the race between a routine
|
|
// starting and incrementing, and exiting and decrementing.
|
|
func (r *raftState) goFunc(f func()) {
|
|
r.routinesGroup.Add(1)
|
|
go func() {
|
|
defer r.routinesGroup.Done()
|
|
f()
|
|
}()
|
|
}
|
|
|
|
func (r *raftState) waitShutdown() {
|
|
r.routinesGroup.Wait()
|
|
}
|
|
|
|
// getLastIndex returns the last index in stable storage.
|
|
// Either from the last log or from the last snapshot.
|
|
func (r *raftState) getLastIndex() uint64 {
|
|
r.lastLock.Lock()
|
|
defer r.lastLock.Unlock()
|
|
return max(r.lastLogIndex, r.lastSnapshotIndex)
|
|
}
|
|
|
|
// getLastEntry returns the last index and term in stable storage.
|
|
// Either from the last log or from the last snapshot.
|
|
func (r *raftState) getLastEntry() (uint64, uint64) {
|
|
r.lastLock.Lock()
|
|
defer r.lastLock.Unlock()
|
|
if r.lastLogIndex >= r.lastSnapshotIndex {
|
|
return r.lastLogIndex, r.lastLogTerm
|
|
}
|
|
return r.lastSnapshotIndex, r.lastSnapshotTerm
|
|
}
|