[VOL-5486] Fix deprecated versions
Change-Id: I3e03ea246020547ae75fa92ce8cf5cbba7e8f3bb
Signed-off-by: Abhay Kumar <abhay.kumar@radisys.com>
diff --git a/vendor/go.etcd.io/raft/v3/tracker/inflights.go b/vendor/go.etcd.io/raft/v3/tracker/inflights.go
new file mode 100644
index 0000000..cb091e5
--- /dev/null
+++ b/vendor/go.etcd.io/raft/v3/tracker/inflights.go
@@ -0,0 +1,143 @@
+// Copyright 2019 The etcd Authors
+//
+// 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 tracker
+
+// inflight describes an in-flight MsgApp message.
+type inflight struct {
+ index uint64 // the index of the last entry inside the message
+ bytes uint64 // the total byte size of the entries in the message
+}
+
+// Inflights limits the number of MsgApp (represented by the largest index
+// contained within) sent to followers but not yet acknowledged by them. Callers
+// use Full() to check whether more messages can be sent, call Add() whenever
+// they are sending a new append, and release "quota" via FreeLE() whenever an
+// ack is received.
+type Inflights struct {
+ // the starting index in the buffer
+ start int
+
+ count int // number of inflight messages in the buffer
+ bytes uint64 // number of inflight bytes
+
+ size int // the max number of inflight messages
+ maxBytes uint64 // the max total byte size of inflight messages
+
+ // buffer is a ring buffer containing info about all in-flight messages.
+ buffer []inflight
+}
+
+// NewInflights sets up an Inflights that allows up to size inflight messages,
+// with the total byte size up to maxBytes. If maxBytes is 0 then there is no
+// byte size limit. The maxBytes limit is soft, i.e. we accept a single message
+// that brings it from size < maxBytes to size >= maxBytes.
+func NewInflights(size int, maxBytes uint64) *Inflights {
+ return &Inflights{
+ size: size,
+ maxBytes: maxBytes,
+ }
+}
+
+// Clone returns an *Inflights that is identical to but shares no memory with
+// the receiver.
+func (in *Inflights) Clone() *Inflights {
+ ins := *in
+ ins.buffer = append([]inflight(nil), in.buffer...)
+ return &ins
+}
+
+// Add notifies the Inflights that a new message with the given index and byte
+// size is being dispatched. Full() must be called prior to Add() to verify that
+// there is room for one more message, and consecutive calls to Add() must
+// provide a monotonic sequence of indexes.
+func (in *Inflights) Add(index, bytes uint64) {
+ if in.Full() {
+ panic("cannot add into a Full inflights")
+ }
+ next := in.start + in.count
+ size := in.size
+ if next >= size {
+ next -= size
+ }
+ if next >= len(in.buffer) {
+ in.grow()
+ }
+ in.buffer[next] = inflight{index: index, bytes: bytes}
+ in.count++
+ in.bytes += bytes
+}
+
+// grow the inflight buffer by doubling up to inflights.size. We grow on demand
+// instead of preallocating to inflights.size to handle systems which have
+// thousands of Raft groups per process.
+func (in *Inflights) grow() {
+ newSize := len(in.buffer) * 2
+ if newSize == 0 {
+ newSize = 1
+ } else if newSize > in.size {
+ newSize = in.size
+ }
+ newBuffer := make([]inflight, newSize)
+ copy(newBuffer, in.buffer)
+ in.buffer = newBuffer
+}
+
+// FreeLE frees the inflights smaller or equal to the given `to` flight.
+func (in *Inflights) FreeLE(to uint64) {
+ if in.count == 0 || to < in.buffer[in.start].index {
+ // out of the left side of the window
+ return
+ }
+
+ idx := in.start
+ var i int
+ var bytes uint64
+ for i = 0; i < in.count; i++ {
+ if to < in.buffer[idx].index { // found the first large inflight
+ break
+ }
+ bytes += in.buffer[idx].bytes
+
+ // increase index and maybe rotate
+ size := in.size
+ if idx++; idx >= size {
+ idx -= size
+ }
+ }
+ // free i inflights and set new start index
+ in.count -= i
+ in.bytes -= bytes
+ in.start = idx
+ if in.count == 0 {
+ // inflights is empty, reset the start index so that we don't grow the
+ // buffer unnecessarily.
+ in.start = 0
+ }
+}
+
+// Full returns true if no more messages can be sent at the moment.
+func (in *Inflights) Full() bool {
+ return in.count == in.size || (in.maxBytes != 0 && in.bytes >= in.maxBytes)
+}
+
+// Count returns the number of inflight messages.
+func (in *Inflights) Count() int { return in.count }
+
+// reset frees all inflights.
+func (in *Inflights) reset() {
+ in.start = 0
+ in.count = 0
+ in.bytes = 0
+}
diff --git a/vendor/go.etcd.io/raft/v3/tracker/progress.go b/vendor/go.etcd.io/raft/v3/tracker/progress.go
new file mode 100644
index 0000000..5716661
--- /dev/null
+++ b/vendor/go.etcd.io/raft/v3/tracker/progress.go
@@ -0,0 +1,314 @@
+// Copyright 2019 The etcd Authors
+//
+// 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 tracker
+
+import (
+ "fmt"
+ "slices"
+ "strings"
+)
+
+// Progress represents a follower’s progress in the view of the leader. Leader
+// maintains progresses of all followers, and sends entries to the follower
+// based on its progress.
+//
+// NB(tbg): Progress is basically a state machine whose transitions are mostly
+// strewn around `*raft.raft`. Additionally, some fields are only used when in a
+// certain State. All of this isn't ideal.
+type Progress struct {
+ // Match is the index up to which the follower's log is known to match the
+ // leader's.
+ Match uint64
+ // Next is the log index of the next entry to send to this follower. All
+ // entries with indices in (Match, Next) interval are already in flight.
+ //
+ // Invariant: 0 <= Match < Next.
+ // NB: it follows that Next >= 1.
+ //
+ // In StateSnapshot, Next == PendingSnapshot + 1.
+ Next uint64
+
+ // sentCommit is the highest commit index in flight to the follower.
+ //
+ // Generally, it is monotonic, but con regress in some cases, e.g. when
+ // converting to `StateProbe` or when receiving a rejection from a follower.
+ //
+ // In StateSnapshot, sentCommit == PendingSnapshot == Next-1.
+ sentCommit uint64
+
+ // State defines how the leader should interact with the follower.
+ //
+ // When in StateProbe, leader sends at most one replication message
+ // per heartbeat interval. It also probes actual progress of the follower.
+ //
+ // When in StateReplicate, leader optimistically increases next
+ // to the latest entry sent after sending replication message. This is
+ // an optimized state for fast replicating log entries to the follower.
+ //
+ // When in StateSnapshot, leader should have sent out snapshot
+ // before and stops sending any replication message.
+ State StateType
+
+ // PendingSnapshot is used in StateSnapshot and tracks the last index of the
+ // leader at the time at which it realized a snapshot was necessary. This
+ // matches the index in the MsgSnap message emitted from raft.
+ //
+ // While there is a pending snapshot, replication to the follower is paused.
+ // The follower will transition back to StateReplicate if the leader
+ // receives an MsgAppResp from it that reconnects the follower to the
+ // leader's log (such an MsgAppResp is emitted when the follower applies a
+ // snapshot). It may be surprising that PendingSnapshot is not taken into
+ // account here, but consider that complex systems may delegate the sending
+ // of snapshots to alternative datasources (i.e. not the leader). In such
+ // setups, it is difficult to manufacture a snapshot at a particular index
+ // requested by raft and the actual index may be ahead or behind. This
+ // should be okay, as long as the snapshot allows replication to resume.
+ //
+ // The follower will transition to StateProbe if ReportSnapshot is called on
+ // the leader; if SnapshotFinish is passed then PendingSnapshot becomes the
+ // basis for the next attempt to append. In practice, the first mechanism is
+ // the one that is relevant in most cases. However, if this MsgAppResp is
+ // lost (fallible network) then the second mechanism ensures that in this
+ // case the follower does not erroneously remain in StateSnapshot.
+ PendingSnapshot uint64
+
+ // RecentActive is true if the progress is recently active. Receiving any messages
+ // from the corresponding follower indicates the progress is active.
+ // RecentActive can be reset to false after an election timeout.
+ // This is always true on the leader.
+ RecentActive bool
+
+ // MsgAppFlowPaused is used when the MsgApp flow to a node is throttled. This
+ // happens in StateProbe, or StateReplicate with saturated Inflights. In both
+ // cases, we need to continue sending MsgApp once in a while to guarantee
+ // progress, but we only do so when MsgAppFlowPaused is false (it is reset on
+ // receiving a heartbeat response), to not overflow the receiver. See
+ // IsPaused().
+ MsgAppFlowPaused bool
+
+ // Inflights is a sliding window for the inflight messages.
+ // Each inflight message contains one or more log entries.
+ // The max number of entries per message is defined in raft config as MaxSizePerMsg.
+ // Thus inflight effectively limits both the number of inflight messages
+ // and the bandwidth each Progress can use.
+ // When inflights is Full, no more message should be sent.
+ // When a leader sends out a message, the index of the last
+ // entry should be added to inflights. The index MUST be added
+ // into inflights in order.
+ // When a leader receives a reply, the previous inflights should
+ // be freed by calling inflights.FreeLE with the index of the last
+ // received entry.
+ Inflights *Inflights
+
+ // IsLearner is true if this progress is tracked for a learner.
+ IsLearner bool
+}
+
+// ResetState moves the Progress into the specified State, resetting MsgAppFlowPaused,
+// PendingSnapshot, and Inflights.
+func (pr *Progress) ResetState(state StateType) {
+ pr.MsgAppFlowPaused = false
+ pr.PendingSnapshot = 0
+ pr.State = state
+ pr.Inflights.reset()
+}
+
+// BecomeProbe transitions into StateProbe. Next is reset to Match+1 or,
+// optionally and if larger, the index of the pending snapshot.
+func (pr *Progress) BecomeProbe() {
+ // If the original state is StateSnapshot, progress knows that
+ // the pending snapshot has been sent to this peer successfully, then
+ // probes from pendingSnapshot + 1.
+ if pr.State == StateSnapshot {
+ pendingSnapshot := pr.PendingSnapshot
+ pr.ResetState(StateProbe)
+ pr.Next = max(pr.Match+1, pendingSnapshot+1)
+ } else {
+ pr.ResetState(StateProbe)
+ pr.Next = pr.Match + 1
+ }
+ pr.sentCommit = min(pr.sentCommit, pr.Next-1)
+}
+
+// BecomeReplicate transitions into StateReplicate, resetting Next to Match+1.
+func (pr *Progress) BecomeReplicate() {
+ pr.ResetState(StateReplicate)
+ pr.Next = pr.Match + 1
+}
+
+// BecomeSnapshot moves the Progress to StateSnapshot with the specified pending
+// snapshot index.
+func (pr *Progress) BecomeSnapshot(snapshoti uint64) {
+ pr.ResetState(StateSnapshot)
+ pr.PendingSnapshot = snapshoti
+ pr.Next = snapshoti + 1
+ pr.sentCommit = snapshoti
+}
+
+// SentEntries updates the progress on the given number of consecutive entries
+// being sent in a MsgApp, with the given total bytes size, appended at log
+// indices >= pr.Next.
+//
+// Must be used with StateProbe or StateReplicate.
+func (pr *Progress) SentEntries(entries int, bytes uint64) {
+ switch pr.State {
+ case StateReplicate:
+ if entries > 0 {
+ pr.Next += uint64(entries)
+ pr.Inflights.Add(pr.Next-1, bytes)
+ }
+ // If this message overflows the in-flights tracker, or it was already full,
+ // consider this message being a probe, so that the flow is paused.
+ pr.MsgAppFlowPaused = pr.Inflights.Full()
+ case StateProbe:
+ // TODO(pavelkalinnikov): this condition captures the previous behaviour,
+ // but we should set MsgAppFlowPaused unconditionally for simplicity, because any
+ // MsgApp in StateProbe is a probe, not only non-empty ones.
+ if entries > 0 {
+ pr.MsgAppFlowPaused = true
+ }
+ default:
+ panic(fmt.Sprintf("sending append in unhandled state %s", pr.State))
+ }
+}
+
+// CanBumpCommit returns true if sending the given commit index can potentially
+// advance the follower's commit index.
+func (pr *Progress) CanBumpCommit(index uint64) bool {
+ // Sending the given commit index may bump the follower's commit index up to
+ // Next-1 in normal operation, or higher in some rare cases. Allow sending a
+ // commit index eagerly only if we haven't already sent one that bumps the
+ // follower's commit all the way to Next-1.
+ return index > pr.sentCommit && pr.sentCommit < pr.Next-1
+}
+
+// SentCommit updates the sentCommit.
+func (pr *Progress) SentCommit(commit uint64) {
+ pr.sentCommit = commit
+}
+
+// MaybeUpdate is called when an MsgAppResp arrives from the follower, with the
+// index acked by it. The method returns false if the given n index comes from
+// an outdated message. Otherwise it updates the progress and returns true.
+func (pr *Progress) MaybeUpdate(n uint64) bool {
+ if n <= pr.Match {
+ return false
+ }
+ pr.Match = n
+ pr.Next = max(pr.Next, n+1) // invariant: Match < Next
+ pr.MsgAppFlowPaused = false
+ return true
+}
+
+// MaybeDecrTo adjusts the Progress to the receipt of a MsgApp rejection. The
+// arguments are the index of the append message rejected by the follower, and
+// the hint that we want to decrease to.
+//
+// Rejections can happen spuriously as messages are sent out of order or
+// duplicated. In such cases, the rejection pertains to an index that the
+// Progress already knows were previously acknowledged, and false is returned
+// without changing the Progress.
+//
+// If the rejection is genuine, Next is lowered sensibly, and the Progress is
+// cleared for sending log entries.
+func (pr *Progress) MaybeDecrTo(rejected, matchHint uint64) bool {
+ if pr.State == StateReplicate {
+ // The rejection must be stale if the progress has matched and "rejected"
+ // is smaller than "match".
+ if rejected <= pr.Match {
+ return false
+ }
+ // Directly decrease next to match + 1.
+ //
+ // TODO(tbg): why not use matchHint if it's larger?
+ pr.Next = pr.Match + 1
+ // Regress the sentCommit since it unlikely has been applied.
+ pr.sentCommit = min(pr.sentCommit, pr.Next-1)
+ return true
+ }
+
+ // The rejection must be stale if "rejected" does not match next - 1. This
+ // is because non-replicating followers are probed one entry at a time.
+ // The check is a best effort assuming message reordering is rare.
+ if pr.Next-1 != rejected {
+ return false
+ }
+
+ pr.Next = max(min(rejected, matchHint+1), pr.Match+1)
+ // Regress the sentCommit since it unlikely has been applied.
+ pr.sentCommit = min(pr.sentCommit, pr.Next-1)
+ pr.MsgAppFlowPaused = false
+ return true
+}
+
+// IsPaused returns whether sending log entries to this node has been throttled.
+// This is done when a node has rejected recent MsgApps, is currently waiting
+// for a snapshot, or has reached the MaxInflightMsgs limit. In normal
+// operation, this is false. A throttled node will be contacted less frequently
+// until it has reached a state in which it's able to accept a steady stream of
+// log entries again.
+func (pr *Progress) IsPaused() bool {
+ switch pr.State {
+ case StateProbe:
+ return pr.MsgAppFlowPaused
+ case StateReplicate:
+ return pr.MsgAppFlowPaused
+ case StateSnapshot:
+ return true
+ default:
+ panic("unexpected state")
+ }
+}
+
+func (pr *Progress) String() string {
+ var buf strings.Builder
+ fmt.Fprintf(&buf, "%s match=%d next=%d", pr.State, pr.Match, pr.Next)
+ if pr.IsLearner {
+ fmt.Fprint(&buf, " learner")
+ }
+ if pr.IsPaused() {
+ fmt.Fprint(&buf, " paused")
+ }
+ if pr.PendingSnapshot > 0 {
+ fmt.Fprintf(&buf, " pendingSnap=%d", pr.PendingSnapshot)
+ }
+ if !pr.RecentActive {
+ fmt.Fprint(&buf, " inactive")
+ }
+ if n := pr.Inflights.Count(); n > 0 {
+ fmt.Fprintf(&buf, " inflight=%d", n)
+ if pr.Inflights.Full() {
+ fmt.Fprint(&buf, "[full]")
+ }
+ }
+ return buf.String()
+}
+
+// ProgressMap is a map of *Progress.
+type ProgressMap map[uint64]*Progress
+
+// String prints the ProgressMap in sorted key order, one Progress per line.
+func (m ProgressMap) String() string {
+ ids := make([]uint64, 0, len(m))
+ for k := range m {
+ ids = append(ids, k)
+ }
+ slices.Sort(ids)
+ var buf strings.Builder
+ for _, id := range ids {
+ fmt.Fprintf(&buf, "%d: %s\n", id, m[id])
+ }
+ return buf.String()
+}
diff --git a/vendor/go.etcd.io/raft/v3/tracker/state.go b/vendor/go.etcd.io/raft/v3/tracker/state.go
new file mode 100644
index 0000000..7dbdd63
--- /dev/null
+++ b/vendor/go.etcd.io/raft/v3/tracker/state.go
@@ -0,0 +1,42 @@
+// Copyright 2019 The etcd Authors
+//
+// 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 tracker
+
+// StateType is the state of a tracked follower.
+type StateType uint64
+
+const (
+ // StateProbe indicates a follower whose last index isn't known. Such a
+ // follower is "probed" (i.e. an append sent periodically) to narrow down
+ // its last index. In the ideal (and common) case, only one round of probing
+ // is necessary as the follower will react with a hint. Followers that are
+ // probed over extended periods of time are often offline.
+ StateProbe StateType = iota
+ // StateReplicate is the state steady in which a follower eagerly receives
+ // log entries to append to its log.
+ StateReplicate
+ // StateSnapshot indicates a follower that needs log entries not available
+ // from the leader's Raft log. Such a follower needs a full snapshot to
+ // return to StateReplicate.
+ StateSnapshot
+)
+
+var prstmap = [...]string{
+ "StateProbe",
+ "StateReplicate",
+ "StateSnapshot",
+}
+
+func (st StateType) String() string { return prstmap[st] }
diff --git a/vendor/go.etcd.io/raft/v3/tracker/tracker.go b/vendor/go.etcd.io/raft/v3/tracker/tracker.go
new file mode 100644
index 0000000..17c4c93
--- /dev/null
+++ b/vendor/go.etcd.io/raft/v3/tracker/tracker.go
@@ -0,0 +1,281 @@
+// Copyright 2019 The etcd Authors
+//
+// 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 tracker
+
+import (
+ "fmt"
+ "slices"
+ "strings"
+
+ "go.etcd.io/raft/v3/quorum"
+ pb "go.etcd.io/raft/v3/raftpb"
+)
+
+// Config reflects the configuration tracked in a ProgressTracker.
+type Config struct {
+ Voters quorum.JointConfig
+ // AutoLeave is true if the configuration is joint and a transition to the
+ // incoming configuration should be carried out automatically by Raft when
+ // this is possible. If false, the configuration will be joint until the
+ // application initiates the transition manually.
+ AutoLeave bool
+ // Learners is a set of IDs corresponding to the learners active in the
+ // current configuration.
+ //
+ // Invariant: Learners and Voters does not intersect, i.e. if a peer is in
+ // either half of the joint config, it can't be a learner; if it is a
+ // learner it can't be in either half of the joint config. This invariant
+ // simplifies the implementation since it allows peers to have clarity about
+ // its current role without taking into account joint consensus.
+ Learners map[uint64]struct{}
+ // When we turn a voter into a learner during a joint consensus transition,
+ // we cannot add the learner directly when entering the joint state. This is
+ // because this would violate the invariant that the intersection of
+ // voters and learners is empty. For example, assume a Voter is removed and
+ // immediately re-added as a learner (or in other words, it is demoted):
+ //
+ // Initially, the configuration will be
+ //
+ // voters: {1 2 3}
+ // learners: {}
+ //
+ // and we want to demote 3. Entering the joint configuration, we naively get
+ //
+ // voters: {1 2} & {1 2 3}
+ // learners: {3}
+ //
+ // but this violates the invariant (3 is both voter and learner). Instead,
+ // we get
+ //
+ // voters: {1 2} & {1 2 3}
+ // learners: {}
+ // next_learners: {3}
+ //
+ // Where 3 is now still purely a voter, but we are remembering the intention
+ // to make it a learner upon transitioning into the final configuration:
+ //
+ // voters: {1 2}
+ // learners: {3}
+ // next_learners: {}
+ //
+ // Note that next_learners is not used while adding a learner that is not
+ // also a voter in the joint config. In this case, the learner is added
+ // right away when entering the joint configuration, so that it is caught up
+ // as soon as possible.
+ LearnersNext map[uint64]struct{}
+}
+
+func (c Config) String() string {
+ var buf strings.Builder
+ fmt.Fprintf(&buf, "voters=%s", c.Voters)
+ if c.Learners != nil {
+ fmt.Fprintf(&buf, " learners=%s", quorum.MajorityConfig(c.Learners).String())
+ }
+ if c.LearnersNext != nil {
+ fmt.Fprintf(&buf, " learners_next=%s", quorum.MajorityConfig(c.LearnersNext).String())
+ }
+ if c.AutoLeave {
+ fmt.Fprint(&buf, " autoleave")
+ }
+ return buf.String()
+}
+
+// Clone returns a copy of the Config that shares no memory with the original.
+func (c *Config) Clone() Config {
+ clone := func(m map[uint64]struct{}) map[uint64]struct{} {
+ if m == nil {
+ return nil
+ }
+ mm := make(map[uint64]struct{}, len(m))
+ for k := range m {
+ mm[k] = struct{}{}
+ }
+ return mm
+ }
+ return Config{
+ Voters: quorum.JointConfig{clone(c.Voters[0]), clone(c.Voters[1])},
+ Learners: clone(c.Learners),
+ LearnersNext: clone(c.LearnersNext),
+ }
+}
+
+// ProgressTracker tracks the currently active configuration and the information
+// known about the nodes and learners in it. In particular, it tracks the match
+// index for each peer which in turn allows reasoning about the committed index.
+type ProgressTracker struct {
+ Config
+
+ Progress ProgressMap
+
+ Votes map[uint64]bool
+
+ MaxInflight int
+ MaxInflightBytes uint64
+}
+
+// MakeProgressTracker initializes a ProgressTracker.
+func MakeProgressTracker(maxInflight int, maxBytes uint64) ProgressTracker {
+ p := ProgressTracker{
+ MaxInflight: maxInflight,
+ MaxInflightBytes: maxBytes,
+ Config: Config{
+ Voters: quorum.JointConfig{
+ quorum.MajorityConfig{},
+ nil, // only populated when used
+ },
+ Learners: nil, // only populated when used
+ LearnersNext: nil, // only populated when used
+ },
+ Votes: map[uint64]bool{},
+ Progress: map[uint64]*Progress{},
+ }
+ return p
+}
+
+// ConfState returns a ConfState representing the active configuration.
+func (p *ProgressTracker) ConfState() pb.ConfState {
+ return pb.ConfState{
+ Voters: p.Voters[0].Slice(),
+ VotersOutgoing: p.Voters[1].Slice(),
+ Learners: quorum.MajorityConfig(p.Learners).Slice(),
+ LearnersNext: quorum.MajorityConfig(p.LearnersNext).Slice(),
+ AutoLeave: p.AutoLeave,
+ }
+}
+
+// IsSingleton returns true if (and only if) there is only one voting member
+// (i.e. the leader) in the current configuration.
+func (p *ProgressTracker) IsSingleton() bool {
+ return len(p.Voters[0]) == 1 && len(p.Voters[1]) == 0
+}
+
+type matchAckIndexer map[uint64]*Progress
+
+var _ quorum.AckedIndexer = matchAckIndexer(nil)
+
+// AckedIndex implements IndexLookuper.
+func (l matchAckIndexer) AckedIndex(id uint64) (quorum.Index, bool) {
+ pr, ok := l[id]
+ if !ok {
+ return 0, false
+ }
+ return quorum.Index(pr.Match), true
+}
+
+// Committed returns the largest log index known to be committed based on what
+// the voting members of the group have acknowledged.
+func (p *ProgressTracker) Committed() uint64 {
+ return uint64(p.Voters.CommittedIndex(matchAckIndexer(p.Progress)))
+}
+
+// Visit invokes the supplied closure for all tracked progresses in stable order.
+func (p *ProgressTracker) Visit(f func(id uint64, pr *Progress)) {
+ n := len(p.Progress)
+ // We need to sort the IDs and don't want to allocate since this is hot code.
+ // The optimization here mirrors that in `(MajorityConfig).CommittedIndex`,
+ // see there for details.
+ var sl [7]uint64
+ var ids []uint64
+ if len(sl) >= n {
+ ids = sl[:n]
+ } else {
+ ids = make([]uint64, n)
+ }
+ for id := range p.Progress {
+ n--
+ ids[n] = id
+ }
+ slices.Sort(ids)
+ for _, id := range ids {
+ f(id, p.Progress[id])
+ }
+}
+
+// QuorumActive returns true if the quorum is active from the view of the local
+// raft state machine. Otherwise, it returns false.
+func (p *ProgressTracker) QuorumActive() bool {
+ votes := map[uint64]bool{}
+ p.Visit(func(id uint64, pr *Progress) {
+ if pr.IsLearner {
+ return
+ }
+ votes[id] = pr.RecentActive
+ })
+
+ return p.Voters.VoteResult(votes) == quorum.VoteWon
+}
+
+// VoterNodes returns a sorted slice of voters.
+func (p *ProgressTracker) VoterNodes() []uint64 {
+ m := p.Voters.IDs()
+ nodes := make([]uint64, 0, len(m))
+ for id := range m {
+ nodes = append(nodes, id)
+ }
+ slices.Sort(nodes)
+ return nodes
+}
+
+// LearnerNodes returns a sorted slice of learners.
+func (p *ProgressTracker) LearnerNodes() []uint64 {
+ if len(p.Learners) == 0 {
+ return nil
+ }
+ nodes := make([]uint64, 0, len(p.Learners))
+ for id := range p.Learners {
+ nodes = append(nodes, id)
+ }
+ slices.Sort(nodes)
+ return nodes
+}
+
+// ResetVotes prepares for a new round of vote counting via recordVote.
+func (p *ProgressTracker) ResetVotes() {
+ p.Votes = map[uint64]bool{}
+}
+
+// RecordVote records that the node with the given id voted for this Raft
+// instance if v == true (and declined it otherwise).
+func (p *ProgressTracker) RecordVote(id uint64, v bool) {
+ _, ok := p.Votes[id]
+ if !ok {
+ p.Votes[id] = v
+ }
+}
+
+// TallyVotes returns the number of granted and rejected Votes, and whether the
+// election outcome is known.
+func (p *ProgressTracker) TallyVotes() (granted int, rejected int, _ quorum.VoteResult) {
+ // Make sure to populate granted/rejected correctly even if the Votes slice
+ // contains members no longer part of the configuration. This doesn't really
+ // matter in the way the numbers are used (they're informational), but might
+ // as well get it right.
+ for id, pr := range p.Progress {
+ if pr.IsLearner {
+ continue
+ }
+ v, voted := p.Votes[id]
+ if !voted {
+ continue
+ }
+ if v {
+ granted++
+ } else {
+ rejected++
+ }
+ }
+ result := p.Voters.VoteResult(p.Votes)
+ return granted, rejected, result
+}