Merge pull request #343 from tendermint/restart_test

Crash/Restart tests

.gitignore

@@ -10,3 +10,5 @@ rpc/test/.tendermint
 remote_dump
 .revision
 vendor
+.vagrant
+test/p2p/data/

consensus/replay.go

@@ -101,6 +101,7 @@ func (cs *ConsensusState) catchupReplay(csHeight int) error {
 	// Search for height marker
 	gr, found, err = cs.wal.group.Search("#HEIGHT: ", makeHeightSearchFunc(csHeight))
 	if err == io.EOF {
+		log.Warn("Replay: wal.group.Search returned EOF", "height", csHeight)
 		return nil
 	} else if err != nil {
 		return err

consensus/state.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"errors"
 	"fmt"
+	"io"
 	"reflect"
 	"sync"
 	"time"
@@ -347,6 +348,23 @@ func (cs *ConsensusState) OnStart() error {
 		return err
 	}
 
+	// If the latest block was applied in the tmsp handshake,
+	// we may not have written the current height to the wal,
+	// so check here and write it if not found.
+	// TODO: remove this and run the handhsake/replay
+	// through the consensus state with a mock app
+	gr, found, err := cs.wal.group.Search("#HEIGHT: ", makeHeightSearchFunc(cs.Height))
+	if (err == io.EOF || !found) && cs.Step == RoundStepNewHeight {
+		log.Warn("Height not found in wal. Writing new height", "height", cs.Height)
+		rs := cs.RoundStateEvent()
+		cs.wal.Save(rs)
+	} else if err != nil {
+		return err
+	}
+	if gr != nil {
+		gr.Close()
+	}
+
 	// we need the timeoutRoutine for replay so
 	//  we don't block on the tick chan.
 	// NOTE: we will get a build up of garbage go routines

consensus/wal.go

@@ -104,4 +104,9 @@ func (wal *WAL) Save(wmsg WALMessage) {
 
 func (wal *WAL) writeHeight(height int) {
 	wal.group.WriteLine(Fmt("#HEIGHT: %v", height))
+
+	// TODO: only flush when necessary
+	if err := wal.group.Flush(); err != nil {
+		PanicQ(Fmt("Error flushing consensus wal buf to file. Error: %v \n", err))
+	}
 }

proxy/client.go

@@ -71,6 +71,8 @@ func DefaultClientCreator(config cfg.Config) ClientCreator {
 	switch addr {
 	case "dummy":
 		return NewLocalClientCreator(dummy.NewDummyApplication())
+	case "persistent_dummy":
+		return NewLocalClientCreator(dummy.NewPersistentDummyApplication(config.GetString("db_dir")))
 	case "nilapp":
 		return NewLocalClientCreator(nilapp.NewNilApplication())
 	default:

state/execution.go

@@ -56,7 +56,9 @@ func (s *State) ExecBlock(eventCache types.Fireable, proxyAppConn proxy.AppConnC
 
 	// save state with updated height/blockhash/validators
 	// but stale apphash, in case we fail between Commit and Save
-	s.Save()
+	s.SaveIntermediate()
+
+	fail.Fail() // XXX
 
 	return nil
 }
@@ -264,7 +266,6 @@ func (s *State) CommitStateUpdateMempool(proxyAppConn proxy.AppConnConsensus, bl
 
 	// Set the state's new AppHash
 	s.AppHash = res.Data
-	s.AppHashIsStale = false
 
 	// Update mempool.
 	mempool.Update(block.Height, block.Txs)
@@ -322,7 +323,7 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 		return nil
 	}
 
-	log.Notice("TMSP Handshake", "height", blockInfo.BlockHeight, "app_hash", blockInfo.AppHash)
+	log.Notice("TMSP Handshake", "appHeight", blockInfo.BlockHeight, "appHash", blockInfo.AppHash)
 
 	blockHeight := int(blockInfo.BlockHeight) // XXX: beware overflow
 	appHash := blockInfo.AppHash
@@ -343,6 +344,9 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 		return errors.New(Fmt("Error on replay: %v", err))
 	}
 
+	// Save the state
+	h.state.Save()
+
 	// TODO: (on restart) replay mempool
 
 	return nil
@@ -352,29 +356,45 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, appConnConsensus proxy.AppConnConsensus) error {
 
 	storeBlockHeight := h.store.Height()
-	if storeBlockHeight < appBlockHeight {
+	stateBlockHeight := h.state.LastBlockHeight
+	log.Notice("TMSP Replay Blocks", "appHeight", appBlockHeight, "storeHeight", storeBlockHeight, "stateHeight", stateBlockHeight)
+
+	if storeBlockHeight == 0 {
+		return nil
+	} else if storeBlockHeight < appBlockHeight {
 		// if the app is ahead, there's nothing we can do
 		return ErrAppBlockHeightTooHigh{storeBlockHeight, appBlockHeight}
 
 	} else if storeBlockHeight == appBlockHeight {
-		// if we crashed between Commit and SaveState,
-		// the state's app hash is stale
-		// otherwise we're synced
-		if h.state.AppHashIsStale {
-			h.state.AppHashIsStale = false
+		// We ran Commit, but if we crashed before state.Save(),
+		// load the intermediate state and update the state.AppHash.
+		// NOTE: If TMSP allowed rollbacks, we could just replay the
+		// block even though it's been committed
+		stateAppHash := h.state.AppHash
+		lastBlockAppHash := h.store.LoadBlock(storeBlockHeight).AppHash
+
+		if bytes.Equal(stateAppHash, appHash) {
+			// we're all synced up
+			log.Debug("TMSP RelpayBlocks: Already synced")
+		} else if bytes.Equal(stateAppHash, lastBlockAppHash) {
+			// we crashed after commit and before saving state,
+			// so load the intermediate state and update the hash
+			h.state.LoadIntermediate()
 			h.state.AppHash = appHash
+			log.Debug("TMSP RelpayBlocks: Loaded intermediate state and updated state.AppHash")
+		} else {
+			PanicSanity(Fmt("Unexpected state.AppHash: state.AppHash %X; app.AppHash %X, lastBlock.AppHash %X", stateAppHash, appHash, lastBlockAppHash))
+
 		}
 		return nil
 
-	} else if h.state.LastBlockHeight == appBlockHeight {
-		// store is ahead of app but core's state height is at apps height
-		// this happens if we crashed after saving the block,
-		// but before committing it. We should be 1 ahead
-		if storeBlockHeight != appBlockHeight+1 {
-			PanicSanity(Fmt("core.state.height == app.height but store.height (%d) > app.height+1 (%d)", storeBlockHeight, appBlockHeight+1))
-		}
+	} else if storeBlockHeight == appBlockHeight+1 &&
+		storeBlockHeight == stateBlockHeight+1 {
+		// We crashed after saving the block
+		// but before Commit (both the state and app are behind),
+		// so just replay the block
 
-		// check that the blocks last apphash is the states apphash
+		// check that the lastBlock.AppHash matches the state apphash
 		block := h.store.LoadBlock(storeBlockHeight)
 		if !bytes.Equal(block.Header.AppHash, appHash) {
 			return ErrLastStateMismatch{storeBlockHeight, block.Header.AppHash, appHash}
@@ -385,13 +405,22 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, appConnCon
 		h.nBlocks += 1
 		var eventCache types.Fireable // nil
 
-		// replay the block against the actual tendermint state
+		// replay the latest block
 		return h.state.ApplyBlock(eventCache, appConnConsensus, block, blockMeta.PartsHeader, MockMempool{})
-
+	} else if storeBlockHeight != stateBlockHeight {
+		// unless we failed before committing or saving state (previous 2 case),
+		// the store and state should be at the same height!
+		PanicSanity(Fmt("Expected storeHeight (%d) and stateHeight (%d) to match.", storeBlockHeight, stateBlockHeight))
 	} else {
-		// either we're caught up or there's blocks to replay
+		// store is more than one ahead,
+		// so app wants to replay many blocks
+
 		// replay all blocks starting with appBlockHeight+1
 		var eventCache types.Fireable // nil
+
+		// TODO: use stateBlockHeight instead and let the consensus state
+		// do the replay
+
 		var appHash []byte
 		for i := appBlockHeight + 1; i <= storeBlockHeight; i++ {
 			h.nBlocks += 1
@@ -413,8 +442,9 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, appConnCon
 			appHash = res.Data
 		}
 		if !bytes.Equal(h.state.AppHash, appHash) {
-			return errors.New(Fmt("Tendermint state.AppHash does not match AppHash after replay", "expected", h.state.AppHash, "got", appHash))
+			return errors.New(Fmt("Tendermint state.AppHash does not match AppHash after replay. Got %X, expected %X", appHash, h.state.AppHash))
 		}
 		return nil
 	}
+	return nil
 }

state/state.go

@@ -14,7 +14,8 @@ import (
 )
 
 var (
-	stateKey = []byte("stateKey")
+	stateKey             = []byte("stateKey")
+	stateIntermediateKey = []byte("stateIntermediateKey")
 )
 
 //-----------------------------------------------------------------------------
@@ -36,15 +37,17 @@ type State struct {
 	Validators      *types.ValidatorSet
 	LastValidators  *types.ValidatorSet // block.LastCommit validated against this
 
-	// AppHash is updated after Commit;
-	// it's stale after ExecBlock and before Commit
-	AppHashIsStale bool
-	AppHash        []byte
+	// AppHash is updated after Commit
+	AppHash []byte
 }
 
 func LoadState(db dbm.DB) *State {
+	return loadState(db, stateKey)
+}
+
+func loadState(db dbm.DB, key []byte) *State {
 	s := &State{db: db}
-	buf := db.Get(stateKey)
+	buf := db.Get(key)
 	if len(buf) == 0 {
 		return nil
 	} else {
@@ -60,9 +63,6 @@ func LoadState(db dbm.DB) *State {
 }
 
 func (s *State) Copy() *State {
-	if s.AppHashIsStale {
-		PanicSanity(Fmt("App hash is stale: %v", s))
-	}
 	return &State{
 		db:              s.db,
 		GenesisDoc:      s.GenesisDoc,
@@ -72,7 +72,6 @@ func (s *State) Copy() *State {
 		LastBlockTime:   s.LastBlockTime,
 		Validators:      s.Validators.Copy(),
 		LastValidators:  s.LastValidators.Copy(),
-		AppHashIsStale:  false,
 		AppHash:         s.AppHash,
 	}
 }
@@ -83,6 +82,35 @@ func (s *State) Save() {
 	s.db.SetSync(stateKey, s.Bytes())
 }
 
+func (s *State) SaveIntermediate() {
+	s.mtx.Lock()
+	defer s.mtx.Unlock()
+	s.db.SetSync(stateIntermediateKey, s.Bytes())
+}
+
+// Load the intermediate state into the current state
+// and do some sanity checks
+func (s *State) LoadIntermediate() {
+	s2 := loadState(s.db, stateIntermediateKey)
+	if s.ChainID != s2.ChainID {
+		PanicSanity(Fmt("State mismatch for ChainID. Got %v, Expected %v", s2.ChainID, s.ChainID))
+	}
+
+	if s.LastBlockHeight+1 != s2.LastBlockHeight {
+		PanicSanity(Fmt("State mismatch for LastBlockHeight. Got %v, Expected %v", s2.LastBlockHeight, s.LastBlockHeight+1))
+	}
+
+	if !bytes.Equal(s.Validators.Hash(), s2.LastValidators.Hash()) {
+		PanicSanity(Fmt("State mismatch for LastValidators. Got %X, Expected %X", s2.LastValidators.Hash(), s.Validators.Hash()))
+	}
+
+	if !bytes.Equal(s.AppHash, s2.AppHash) {
+		PanicSanity(Fmt("State mismatch for AppHash. Got %X, Expected %X", s2.AppHash, s.AppHash))
+	}
+
+	s.setBlockAndValidators(s2.LastBlockHeight, s2.LastBlockID, s2.LastBlockTime, s2.Validators.Copy(), s2.LastValidators.Copy())
+}
+
 func (s *State) Equals(s2 *State) bool {
 	return bytes.Equal(s.Bytes(), s2.Bytes())
 }
@@ -97,15 +125,22 @@ func (s *State) Bytes() []byte {
 }
 
 // Mutate state variables to match block and validators
-// Since we don't have the new AppHash yet, we set s.AppHashIsStale=true
+// after running EndBlock
 func (s *State) SetBlockAndValidators(header *types.Header, blockPartsHeader types.PartSetHeader, prevValSet, nextValSet *types.ValidatorSet) {
-	s.LastBlockHeight = header.Height
-	s.LastBlockID = types.BlockID{header.Hash(), blockPartsHeader}
-	s.LastBlockTime = header.Time
+	s.setBlockAndValidators(header.Height,
+		types.BlockID{header.Hash(), blockPartsHeader}, header.Time,
+		prevValSet, nextValSet)
+}
+
+func (s *State) setBlockAndValidators(
+	height int, blockID types.BlockID, blockTime time.Time,
+	prevValSet, nextValSet *types.ValidatorSet) {
+
+	s.LastBlockHeight = height
+	s.LastBlockID = blockID
+	s.LastBlockTime = blockTime
 	s.Validators = nextValSet
 	s.LastValidators = prevValSet
-
-	s.AppHashIsStale = true
 }
 
 func (s *State) GetValidators() (*types.ValidatorSet, *types.ValidatorSet) {

test/docker/Dockerfile

@@ -21,5 +21,8 @@ COPY . $REPO
 RUN go install ./cmd/tendermint
 RUN bash scripts/install_tmsp_apps.sh
 
+# expose the volume for debugging
+VOLUME $REPO
+
 EXPOSE 46656
 EXPOSE 46657

test/p2p/client.sh

@@ -6,13 +6,14 @@ NETWORK_NAME=$2
 ID=$3
 CMD=$4
 
+NAME=test_container_$ID
+
 echo "starting test client container with CMD=$CMD"
 # run the test container on the local network
-docker run -t \
+docker run -t --rm \
 	-v $GOPATH/src/github.com/tendermint/tendermint/test/p2p/:/go/src/github.com/tendermint/tendermint/test/p2p \
 	--net=$NETWORK_NAME \
 	--ip=$(test/p2p/ip.sh "-1") \
-	--name test_container_$ID \
+	--name $NAME \
 	--entrypoint bash \
 	$DOCKER_IMAGE $CMD
-

test/p2p/fast_sync/test.sh

@@ -4,12 +4,13 @@ set -eu
 DOCKER_IMAGE=$1
 NETWORK_NAME=$2
 N=$3
+PROXY_APP=$4
 
 cd $GOPATH/src/github.com/tendermint/tendermint
 
 # run it on each of them
 for i in `seq 1 $N`; do
-	bash test/p2p/fast_sync/test_peer.sh $DOCKER_IMAGE $NETWORK_NAME $i $N
+	bash test/p2p/fast_sync/test_peer.sh $DOCKER_IMAGE $NETWORK_NAME $i $N $PROXY_APP
 done
 
 

test/p2p/fast_sync/test_peer.sh

@@ -3,8 +3,9 @@ set -eu
 
 DOCKER_IMAGE=$1
 NETWORK_NAME=$2
-COUNT=$3
+ID=$3
 N=$4
+PROXY_APP=$5
 
 ###############################################################
 # this runs on each peer:
@@ -14,22 +15,22 @@ N=$4
 ###############################################################
 
 
-echo "Testing fasysync on node $COUNT"
+echo "Testing fastsync on node $ID"
 
-# kill peer 
+# kill peer
 set +e # circle sigh :(
-docker rm -vf local_testnet_$COUNT
-set -e 
+docker rm -vf local_testnet_$ID
+set -e
 
 # restart peer - should have an empty blockchain
 SEEDS="$(test/p2p/ip.sh 1):46656"
 for j in `seq 2 $N`; do
 	SEEDS="$SEEDS,$(test/p2p/ip.sh $j):46656"
 done
-bash test/p2p/peer.sh $DOCKER_IMAGE $NETWORK_NAME $COUNT $SEEDS
+bash test/p2p/peer.sh $DOCKER_IMAGE $NETWORK_NAME $ID $PROXY_APP $SEEDS
 
 # wait for peer to sync and check the app hash
-bash test/p2p/client.sh $DOCKER_IMAGE $NETWORK_NAME fs_$COUNT "test/p2p/fast_sync/check_peer.sh $COUNT"
+bash test/p2p/client.sh $DOCKER_IMAGE $NETWORK_NAME fs_$ID "test/p2p/fast_sync/check_peer.sh $ID"
 
 echo ""
 echo "PASS"

test/p2p/kill_all/check_peers.sh

@@ -0,0 +1,48 @@
+#! /bin/bash
+set -eu
+
+NUM_OF_PEERS=$1
+
+# how many attempts for each peer to catch up by height
+MAX_ATTEMPTS_TO_CATCH_UP=10
+
+echo "Waiting for nodes to come online"
+set +e
+for i in $(seq 1 "$NUM_OF_PEERS"); do
+  addr=$(test/p2p/ip.sh "$i"):46657
+  curl -s "$addr/status" > /dev/null
+  ERR=$?
+  while [ "$ERR" != 0 ]; do
+    sleep 1
+    curl -s "$addr/status" > /dev/null
+    ERR=$?
+  done
+  echo "... node $i is up"
+done
+set -e
+
+# get the first peer's height
+addr=$(test/p2p/ip.sh 1):46657
+h1=$(curl -s "$addr/status" | jq .result[1].latest_block_height)
+echo "1st peer is on height $h1"
+
+echo "Waiting until other peers reporting a height higher than the 1st one"
+for i in $(seq 2 "$NUM_OF_PEERS"); do
+  attempt=1
+  hi=0
+
+  while [[ $hi -le $h1 ]] ; do
+    addr=$(test/p2p/ip.sh "$i"):46657
+    hi=$(curl -s "$addr/status" | jq .result[1].latest_block_height)
+
+    echo "... peer $i is on height $hi"
+
+    ((attempt++))
+    if [ "$attempt" -ge $MAX_ATTEMPTS_TO_CATCH_UP ] ; then
+      echo "$attempt unsuccessful attempts were made to catch up"
+      exit 1
+    fi
+
+    sleep 1
+  done
+done

test/p2p/kill_all/test.sh

@@ -0,0 +1,32 @@
+#! /bin/bash
+set -eu
+
+DOCKER_IMAGE=$1
+NETWORK_NAME=$2
+NUM_OF_PEERS=$3
+NUM_OF_CRASHES=$4
+
+cd "$GOPATH/src/github.com/tendermint/tendermint"
+
+###############################################################
+# NUM_OF_CRASHES times:
+# 	restart all peers
+# 	wait for them to sync and check that they are making progress
+###############################################################
+
+for i in $(seq 1 "$NUM_OF_CRASHES"); do
+  echo ""
+  echo "Restarting all peers! Take $i ..."
+
+  # restart all peers
+  for j in $(seq 1 "$NUM_OF_PEERS"); do
+    docker stop "local_testnet_$j"
+    docker start "local_testnet_$j"
+  done
+
+  bash test/p2p/client.sh "$DOCKER_IMAGE" "$NETWORK_NAME" kill_all_$i "test/p2p/kill_all/check_peers.sh $NUM_OF_PEERS"
+done
+
+echo ""
+echo "PASS"
+echo ""

test/p2p/local_testnet_start.sh

@@ -4,6 +4,7 @@ set -eu
 DOCKER_IMAGE=$1
 NETWORK_NAME=$2
 N=$3
+APP_PROXY=$4
 
 cd $GOPATH/src/github.com/tendermint/tendermint
 
@@ -17,5 +18,5 @@ done
 echo "Seeds: $seeds"
 
 for i in `seq 1 $N`; do
-	bash test/p2p/peer.sh $DOCKER_IMAGE $NETWORK_NAME $i $seeds
+	bash test/p2p/peer.sh $DOCKER_IMAGE $NETWORK_NAME $i $APP_PROXY $seeds
 done

test/p2p/local_testnet_stop.sh

@@ -0,0 +1,12 @@
+#! /bin/bash
+set -u
+
+NETWORK_NAME=$1
+N=$2
+
+for i in `seq 1 $N`; do
+  docker stop local_testnet_$i
+  docker rm -vf local_testnet_$i
+done
+
+docker network rm $NETWORK_NAME

test/p2p/peer.sh

@@ -4,9 +4,10 @@ set -eu
 DOCKER_IMAGE=$1
 NETWORK_NAME=$2
 ID=$3
+APP_PROXY=$4
 
 set +u
-SEEDS=$4
+SEEDS=$5
 set -u
 if [[ "$SEEDS" != "" ]]; then
 	SEEDS=" --seeds $SEEDS "
@@ -15,9 +16,9 @@ fi
 echo "starting tendermint peer ID=$ID"
 # start tendermint container on the network
 docker run -d \
-	--net=$NETWORK_NAME \
-	--ip=$(test/p2p/ip.sh $ID) \
-	--name local_testnet_$ID \
-	--entrypoint tendermint \
-	-e TMROOT=/go/src/github.com/tendermint/tendermint/test/p2p/data/mach$ID/core \
-	$DOCKER_IMAGE node $SEEDS --proxy_app=dummy
+  --net=$NETWORK_NAME \
+  --ip=$(test/p2p/ip.sh $ID) \
+  --name local_testnet_$ID \
+  --entrypoint tendermint \
+  -e TMROOT=/go/src/github.com/tendermint/tendermint/test/p2p/data/mach$ID/core \
+  $DOCKER_IMAGE node $SEEDS --proxy_app=$APP_PROXY

test/p2p/test.sh

@@ -4,11 +4,18 @@ set -eu
 DOCKER_IMAGE=$1
 NETWORK_NAME=local_testnet
 N=4
+PROXY_APP=persistent_dummy
 
 cd $GOPATH/src/github.com/tendermint/tendermint
 
+# stop the existing testnet and remove local network
+set +e
+bash test/p2p/local_testnet_stop.sh $NETWORK_NAME $N
+set -e
+
 # start the testnet on a local network
-bash test/p2p/local_testnet.sh $DOCKER_IMAGE $NETWORK_NAME $N
+# NOTE we re-use the same network for all tests
+bash test/p2p/local_testnet_start.sh $DOCKER_IMAGE $NETWORK_NAME $N $PROXY_APP
 
 # test basic connectivity and consensus
 # start client container and check the num peers and height for all nodes
@@ -20,4 +27,7 @@ bash test/p2p/client.sh $DOCKER_IMAGE $NETWORK_NAME ab "test/p2p/atomic_broadcas
 
 # test fast sync (from current state of network):
 # for each node, kill it and readd via fast sync
-bash test/p2p/fast_sync/test.sh $DOCKER_IMAGE $NETWORK_NAME $N
+bash test/p2p/fast_sync/test.sh $DOCKER_IMAGE $NETWORK_NAME $N $PROXY_APP
+
+# test killing all peers
+bash test/p2p/kill_all/test.sh $DOCKER_IMAGE $NETWORK_NAME $N 3

test/persist/test.sh

@@ -1,70 +1,5 @@
 #! /bin/bash
 
+cd $GOPATH/src/github.com/tendermint/tendermint
 
-export TMROOT=$HOME/.tendermint_persist
-
-rm -rf $TMROOT
-tendermint init
-
-function start_procs(){
-	name=$1
-	echo "Starting persistent dummy and tendermint"
-	dummy --persist $TMROOT/dummy &> "dummy_${name}.log" &
-	PID_DUMMY=$!
-	tendermint node &> tendermint_${name}.log &
-	PID_TENDERMINT=$!
-	sleep 5
-}
-
-function kill_procs(){
-	kill -9 $PID_DUMMY $PID_TENDERMINT
-}
-
-
-function send_txs(){
-	# send a bunch of txs over a few blocks
-	echo "Sending txs"
-	for i in `seq 1 5`; do
-		for j in `seq 1 100`; do
-			tx=`head -c 8 /dev/urandom | hexdump -ve '1/1 "%.2X"'`
-			curl -s 127.0.0.1:46657/broadcast_tx_async?tx=\"$tx\" &> /dev/null
-		done
-		sleep 1
-	done
-}
-
-
-start_procs 1
-send_txs
-kill_procs
-
-start_procs 2
-
-# wait for node to handshake and make a new block
-addr="localhost:46657"
-curl -s $addr/status > /dev/null
-ERR=$?
-i=0
-while [ "$ERR" != 0 ]; do
-	sleep 1	
-	curl -s $addr/status > /dev/null
-	ERR=$?
-	i=$(($i + 1))
-	if [[ $i == 10 ]]; then
-		echo "Timed out waiting for tendermint to start"
-		exit 1
-	fi
-done
-
-# wait for a new block
-h1=`curl -s $addr/status | jq .result[1].latest_block_height`
-h2=$h1
-while [ "$h2" == "$h1" ]; do
-	sleep 1
-	h2=`curl -s $addr/status | jq .result[1].latest_block_height`
-done
-
-kill_procs
-sleep 2
-
-echo "Passed Test: Persistence"
+bash ./test/persist/test_failure_indices.sh

test/persist/test_failure_indices.sh

@@ -14,11 +14,11 @@ function start_procs(){
 	PID_DUMMY=$!
 	if [[ "$indexToFail" == "" ]]; then
 		# run in background, dont fail
-		tendermint node &> tendermint_${name}.log &
+		tendermint node --log_level=debug &> tendermint_${name}.log &
 		PID_TENDERMINT=$!
 	else
 		# run in foreground, fail
-		FAIL_TEST_INDEX=$indexToFail tendermint node &> tendermint_${name}.log
+		FAIL_TEST_INDEX=$indexToFail tendermint node --log_level=debug &> tendermint_${name}.log
 		PID_TENDERMINT=$!
 	fi
 }

test/persist/test_simple.sh

@@ -0,0 +1,70 @@
+#! /bin/bash
+
+
+export TMROOT=$HOME/.tendermint_persist
+
+rm -rf $TMROOT
+tendermint init
+
+function start_procs(){
+	name=$1
+	echo "Starting persistent dummy and tendermint"
+	dummy --persist $TMROOT/dummy &> "dummy_${name}.log" &
+	PID_DUMMY=$!
+	tendermint node &> tendermint_${name}.log &
+	PID_TENDERMINT=$!
+	sleep 5
+}
+
+function kill_procs(){
+	kill -9 $PID_DUMMY $PID_TENDERMINT
+}
+
+
+function send_txs(){
+	# send a bunch of txs over a few blocks
+	echo "Sending txs"
+	for i in `seq 1 5`; do
+		for j in `seq 1 100`; do
+			tx=`head -c 8 /dev/urandom | hexdump -ve '1/1 "%.2X"'`
+			curl -s 127.0.0.1:46657/broadcast_tx_async?tx=\"$tx\" &> /dev/null
+		done
+		sleep 1
+	done
+}
+
+
+start_procs 1
+send_txs
+kill_procs
+
+start_procs 2
+
+# wait for node to handshake and make a new block
+addr="localhost:46657"
+curl -s $addr/status > /dev/null
+ERR=$?
+i=0
+while [ "$ERR" != 0 ]; do
+	sleep 1	
+	curl -s $addr/status > /dev/null
+	ERR=$?
+	i=$(($i + 1))
+	if [[ $i == 10 ]]; then
+		echo "Timed out waiting for tendermint to start"
+		exit 1
+	fi
+done
+
+# wait for a new block
+h1=`curl -s $addr/status | jq .result[1].latest_block_height`
+h2=$h1
+while [ "$h2" == "$h1" ]; do
+	sleep 1
+	h2=`curl -s $addr/status | jq .result[1].latest_block_height`
+done
+
+kill_procs
+sleep 2
+
+echo "Passed Test: Persistence"