open-consul/vendor/github.com/hashicorp/raft/fsm.go
James Phillips bc29610124 Adds support for snapshots and restores. (#2396)
* Updates Raft library to get new snapshot/restore API.

* Basic backup and restore working, but need some cleanup.

* Breaks out a snapshot module and adds a SHA256 integrity check.

* Adds snapshot ACL and fills in some missing comments.

* Require a consistent read for snapshots.

* Make sure snapshot works if ACLs aren't enabled.

* Adds a bit of package documentation.

* Returns an empty response from restore to avoid EOF errors.

* Adds API client support for snapshots.

* Makes internal file names match on-disk file snapshots.

* Adds DC and token coverage for snapshot API test.

* Adds missing documentation.

* Adds a unit test for the snapshot client endpoint.

* Moves the connection pool out of the client for easier testing.

* Fixes an incidental issue in the prepared query unit test.

I realized I had two servers in bootstrap mode so this wasn't a good setup.

* Adds a half close to the TCP stream and fixes panic on error.

* Adds client and endpoint tests for snapshots.

* Moves the pool back into the snapshot RPC client.

* Adds a TLS test and fixes half-closes for TLS connections.

* Tweaks some comments.

* Adds a low-level snapshot test.

This is independent of Consul so we can pull this out into a library
later if we want to.

* Cleans up snapshot and archive and completes archive tests.

* Sends a clear error for snapshot operations in dev mode.

Snapshots require the Raft snapshots to be readable, which isn't supported
in dev mode. Send a clear error instead of a deep-down Raft one.

* Adds docs for the snapshot endpoint.

* Adds a stale mode and index feedback for snapshot saves.

This gives folks a way to extract data even if the cluster has no
leader.

* Changes the internal format of a snapshot from zip to tgz.

* Pulls in Raft fix to cancel inflight before a restore.

* Pulls in new Raft restore interface.

* Adds metadata to snapshot saves and a verify function.

* Adds basic save and restore snapshot CLI commands.

* Gets rid of tarball extensions and adds restore message.

* Fixes an incidental bad link in the KV docs.

* Adds documentation for the snapshot CLI commands.

* Scuttle any request body when a snapshot is saved.

* Fixes archive unit test error message check.

* Allows for nil output writers in snapshot RPC handlers.

* Renames hash list Decode to DecodeAndVerify.

* Closes the client connection for snapshot ops.

* Lowers timeout for restore ops.

* Updates Raft vendor to get new Restore signature and integrates with Consul.

* Bounces the leader's internal state when we do a restore.
2016-10-25 19:20:24 -07:00

137 lines
3.5 KiB
Go

package raft
import (
"fmt"
"io"
"time"
"github.com/armon/go-metrics"
)
// FSM provides an interface that can be implemented by
// clients to make use of the replicated log.
type FSM interface {
// Apply log is invoked once a log entry is committed.
// It returns a value which will be made available in the
// ApplyFuture returned by Raft.Apply method if that
// method was called on the same Raft node as the FSM.
Apply(*Log) interface{}
// Snapshot is used to support log compaction. This call should
// return an FSMSnapshot which can be used to save a point-in-time
// snapshot of the FSM. Apply and Snapshot are not called in multiple
// threads, but Apply will be called concurrently with Persist. This means
// the FSM should be implemented in a fashion that allows for concurrent
// updates while a snapshot is happening.
Snapshot() (FSMSnapshot, error)
// Restore is used to restore an FSM from a snapshot. It is not called
// concurrently with any other command. The FSM must discard all previous
// state.
Restore(io.ReadCloser) error
}
// FSMSnapshot is returned by an FSM in response to a Snapshot
// It must be safe to invoke FSMSnapshot methods with concurrent
// calls to Apply.
type FSMSnapshot interface {
// Persist should dump all necessary state to the WriteCloser 'sink',
// and call sink.Close() when finished or call sink.Cancel() on error.
Persist(sink SnapshotSink) error
// Release is invoked when we are finished with the snapshot.
Release()
}
// runFSM is a long running goroutine responsible for applying logs
// to the FSM. This is done async of other logs since we don't want
// the FSM to block our internal operations.
func (r *Raft) runFSM() {
var lastIndex, lastTerm uint64
commit := func(req *commitTuple) {
// Apply the log if a command
var resp interface{}
if req.log.Type == LogCommand {
start := time.Now()
resp = r.fsm.Apply(req.log)
metrics.MeasureSince([]string{"raft", "fsm", "apply"}, start)
}
// Update the indexes
lastIndex = req.log.Index
lastTerm = req.log.Term
// Invoke the future if given
if req.future != nil {
req.future.response = resp
req.future.respond(nil)
}
}
restore := func(req *restoreFuture) {
// Open the snapshot
meta, source, err := r.snapshots.Open(req.ID)
if err != nil {
req.respond(fmt.Errorf("failed to open snapshot %v: %v", req.ID, err))
return
}
// Attempt to restore
start := time.Now()
if err := r.fsm.Restore(source); err != nil {
req.respond(fmt.Errorf("failed to restore snapshot %v: %v", req.ID, err))
source.Close()
return
}
source.Close()
metrics.MeasureSince([]string{"raft", "fsm", "restore"}, start)
// Update the last index and term
lastIndex = meta.Index
lastTerm = meta.Term
req.respond(nil)
}
snapshot := func(req *reqSnapshotFuture) {
// Is there something to snapshot?
if lastIndex == 0 {
req.respond(ErrNothingNewToSnapshot)
return
}
// Start a snapshot
start := time.Now()
snap, err := r.fsm.Snapshot()
metrics.MeasureSince([]string{"raft", "fsm", "snapshot"}, start)
// Respond to the request
req.index = lastIndex
req.term = lastTerm
req.snapshot = snap
req.respond(err)
}
for {
select {
case ptr := <-r.fsmMutateCh:
switch req := ptr.(type) {
case *commitTuple:
commit(req)
case *restoreFuture:
restore(req)
default:
panic(fmt.Errorf("bad type passed to fsmMutateCh: %#v", ptr))
}
case req := <-r.fsmSnapshotCh:
snapshot(req)
case <-r.shutdownCh:
return
}
}
}