etcd-io__etcd/raft/log_unstable.go

// Copyright 2015 CoreOS, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

package raft

import pb "github.com/coreos/etcd/raft/raftpb"

// unstable.entris[i] has raft log position i+unstable.offset.
// Note that unstable.offset may be less than the highest log
// position in storage; this means that the next write to storage
// might need to truncate the log before persisting unstable.entries.
type unstable struct {
	// the incoming unstable snapshot, if any.
	snapshot *pb.Snapshot
	// all entries that have not yet been written to storage.
	entries []pb.Entry
	offset  uint64
}

// maybeFirstIndex returns the index of the first possible entry in entries
// if it has a snapshot.
func (u *unstable) maybeFirstIndex() (uint64, bool) {
	if u.snapshot != nil {
		return u.snapshot.Metadata.Index + 1, true
	}
	return 0, false
}

// maybeLastIndex returns the last index if it has at least one
// unstable entry or snapshot.
func (u *unstable) maybeLastIndex() (uint64, bool) {
	if l := len(u.entries); l != 0 {
		return u.offset + uint64(l) - 1, true
	}
	if u.snapshot != nil {
		return u.snapshot.Metadata.Index, true
	}
	return 0, false
}

// myabeTerm returns the term of the entry at index i, if there
// is any.
func (u *unstable) maybeTerm(i uint64) (uint64, bool) {
	if i < u.offset {
		if u.snapshot == nil {
			return 0, false
		}
		if u.snapshot.Metadata.Index == i {
			return u.snapshot.Metadata.Term, true
		}
		return 0, false
	}

	last, ok := u.maybeLastIndex()
	if !ok {
		return 0, false
	}
	if i > last {
		return 0, false
	}
	return u.entries[i-u.offset].Term, true
}

func (u *unstable) stableTo(i, t uint64) {
	gt, ok := u.maybeTerm(i)
	if !ok {
		return
	}
	// if i < offest, term is matched with the snapshot
	// only update the unstalbe entries if term is matched with
	// an unstable entry.
	if gt == t && i >= u.offset {
		u.entries = u.entries[i+1-u.offset:]
		u.offset = i + 1
	}
}

func (u *unstable) stableSnapTo(i uint64) {
	if u.snapshot != nil && u.snapshot.Metadata.Index == i {
		u.snapshot = nil
	}
}

func (u *unstable) restore(s pb.Snapshot) {
	u.offset = s.Metadata.Index + 1
	u.entries = nil
	u.snapshot = &s
}

func (u *unstable) truncateAndAppend(ents []pb.Entry) {
	after := ents[0].Index - 1
	switch {
	case after == u.offset+uint64(len(u.entries))-1:
		// after is the last index in the u.entries
		// directly append
		u.entries = append(u.entries, ents...)
	case after < u.offset:
		raftLogger.Infof("replace the unstable entries from index %d", after+1)
		// The log is being truncated to before our current offset
		// portion, so set the offset and replace the entries
		u.offset = after + 1
		u.entries = ents
	default:
		// truncate to after and copy to u.entries
		// then append
		raftLogger.Infof("truncate the unstable entries to index %d", after)
		u.entries = append([]pb.Entry{}, u.slice(u.offset, after+1)...)
		u.entries = append(u.entries, ents...)
	}
}

func (u *unstable) slice(lo uint64, hi uint64) []pb.Entry {
	u.mustCheckOutOfBounds(lo, hi)
	return u.entries[lo-u.offset : hi-u.offset]
}

// u.offset <= lo <= hi <= u.offset+len(u.offset)
func (u *unstable) mustCheckOutOfBounds(lo, hi uint64) {
	if lo > hi {
		raftLogger.Panicf("invalid unstable.slice %d > %d", lo, hi)
	}
	upper := u.offset + uint64(len(u.entries))
	if lo < u.offset || hi > upper {
		raftLogger.Panicf("unstable.slice[%d,%d) out of bound [%d,%d]", lo, hi, u.offset, upper)
	}
}