clist: speedup Next by removing defers (#2511)

This change doubles the speed of the mempool's reaping.
Before:

BenchmarkReap-8   	    5000	    365390 ns/op	  122887 B/op

After:

BenchmarkReap-8   	   10000	    158274 ns/op	  122882 B/op

mempool/bench_test.go

@@ -0,0 +1,55 @@
+package mempool
+
+import (
+	"encoding/binary"
+	"testing"
+
+	"github.com/tendermint/tendermint/abci/example/kvstore"
+	"github.com/tendermint/tendermint/proxy"
+)
+
+func BenchmarkReap(b *testing.B) {
+	app := kvstore.NewKVStoreApplication()
+	cc := proxy.NewLocalClientCreator(app)
+	mempool := newMempoolWithApp(cc)
+
+	size := 10000
+	for i := 0; i < size; i++ {
+		tx := make([]byte, 8)
+		binary.BigEndian.PutUint64(tx, uint64(i))
+		mempool.CheckTx(tx, nil)
+	}
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		mempool.ReapMaxBytesMaxGas(100000000, 10000000)
+	}
+}
+
+func BenchmarkCacheInsertTime(b *testing.B) {
+	cache := newMapTxCache(b.N)
+	txs := make([][]byte, b.N)
+	for i := 0; i < b.N; i++ {
+		txs[i] = make([]byte, 8)
+		binary.BigEndian.PutUint64(txs[i], uint64(i))
+	}
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		cache.Push(txs[i])
+	}
+}
+
+// This benchmark is probably skewed, since we actually will be removing
+// txs in parallel, which may cause some overhead due to mutex locking.
+func BenchmarkCacheRemoveTime(b *testing.B) {
+	cache := newMapTxCache(b.N)
+	txs := make([][]byte, b.N)
+	for i := 0; i < b.N; i++ {
+		txs[i] = make([]byte, 8)
+		binary.BigEndian.PutUint64(txs[i], uint64(i))
+		cache.Push(txs[i])
+	}
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		cache.Remove(txs[i])
+	}
+}