database/sql: add additional Stats to DBStats

Provide better statistics for the database pool. Add counters
for waiting on the pool and closes. Too much waiting or too many
connection closes could indicate a problem.

Fixes #24683
Fixes #22138

Change-Id: I9e1e32a0487edf41c566b8d9c07cb55e04078fec
Reviewed-on: https://go-review.googlesource.com/108536
Run-TryBot: Daniel Theophanes <kardianos@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>

src/database/sql/sql.go

@@ -343,6 +343,10 @@ var ErrNoRows = errors.New("sql: no rows in result set")
 // connection is returned to DB's idle connection pool. The pool size
 // can be controlled with SetMaxIdleConns.
 type DB struct {
+	// Atomic access only. At top of struct to prevent mis-alignment
+	// on 32-bit platforms. Of type time.Duration.
+	waitDuration int64 // Total time waited for new connections.
+
 	connector driver.Connector
 	// numClosed is an atomic counter which represents a total number of
 	// closed connections. Stmt.openStmt checks it before cleaning closed
@@ -368,6 +372,9 @@ type DB struct {
 	maxOpen           int                    // <= 0 means unlimited
 	maxLifetime       time.Duration          // maximum amount of time a connection may be reused
 	cleanerCh         chan struct{}
+	waitCount         int64 // Total number of connections waited for.
+	maxIdleClosed     int64 // Total number of connections closed due to idle.
+	maxLifetimeClosed int64 // Total number of connections closed due to max free limit.
 
 	stop func() // stop cancels the connection opener and the session resetter.
 }
@@ -796,6 +803,9 @@ func (db *DB) maxIdleConnsLocked() int {
 // then the new MaxIdleConns will be reduced to match the MaxOpenConns limit.
 //
 // If n <= 0, no idle connections are retained.
+//
+// The default max idle connections is currently 2. This may change in
+// a future release.
 func (db *DB) SetMaxIdleConns(n int) {
 	db.mu.Lock()
 	if n > 0 {
@@ -815,6 +825,7 @@ func (db *DB) SetMaxIdleConns(n int) {
 		closing = db.freeConn[maxIdle:]
 		db.freeConn = db.freeConn[:maxIdle]
 	}
+	db.maxIdleClosed += int64(len(closing))
 	db.mu.Unlock()
 	for _, c := range closing {
 		c.Close()
@@ -907,6 +918,7 @@ func (db *DB) connectionCleaner(d time.Duration) {
 				i--
 			}
 		}
+		db.maxLifetimeClosed += int64(len(closing))
 		db.mu.Unlock()
 
 		for _, c := range closing {
@@ -922,17 +934,39 @@ func (db *DB) connectionCleaner(d time.Duration) {
 
 // DBStats contains database statistics.
 type DBStats struct {
-	// OpenConnections is the number of open connections to the database.
-	OpenConnections int
+	MaxOpenConnections int // Maximum number of open connections to the database.
+
+	// Pool Status
+	OpenConnections int // The number of established connections both in use and idle.
+	InUse           int // The number of connections currently in use.
+	Idle            int // The number of idle connections.
+
+	// Counters
+	WaitCount         int64         // The total number of connections waited for.
+	WaitDuration      time.Duration // The total time blocked waiting for a new connection.
+	MaxIdleClosed     int64         // The total number of connections closed due to SetMaxIdleConns.
+	MaxLifetimeClosed int64         // The total number of connections closed due to SetConnMaxLifetime.
 }
 
 // Stats returns database statistics.
 func (db *DB) Stats() DBStats {
+	wait := atomic.LoadInt64(&db.waitDuration)
+
 	db.mu.Lock()
+	defer db.mu.Unlock()
+
 	stats := DBStats{
+		MaxOpenConnections: db.maxOpen,
+
+		Idle:            len(db.freeConn),
 		OpenConnections: db.numOpen,
+		InUse:           db.numOpen - len(db.freeConn),
+
+		WaitCount:         db.waitCount,
+		WaitDuration:      time.Duration(wait),
+		MaxIdleClosed:     db.maxIdleClosed,
+		MaxLifetimeClosed: db.maxLifetimeClosed,
 	}
-	db.mu.Unlock()
 	return stats
 }
 
@@ -1085,8 +1119,11 @@ func (db *DB) conn(ctx context.Context, strategy connReuseStrategy) (*driverConn
 		req := make(chan connRequest, 1)
 		reqKey := db.nextRequestKeyLocked()
 		db.connRequests[reqKey] = req
+		db.waitCount++
 		db.mu.Unlock()
 
+		waitStart := time.Now()
+
 		// Timeout the connection request with the context.
 		select {
 		case <-ctx.Done():
@@ -1095,6 +1132,9 @@ func (db *DB) conn(ctx context.Context, strategy connReuseStrategy) (*driverConn
 			db.mu.Lock()
 			delete(db.connRequests, reqKey)
 			db.mu.Unlock()
+
+			atomic.AddInt64(&db.waitDuration, int64(time.Since(waitStart)))
+
 			select {
 			default:
 			case ret, ok := <-req:
@@ -1104,6 +1144,8 @@ func (db *DB) conn(ctx context.Context, strategy connReuseStrategy) (*driverConn
 			}
 			return nil, ctx.Err()
 		case ret, ok := <-req:
+			atomic.AddInt64(&db.waitDuration, int64(time.Since(waitStart)))
+
 			if !ok {
 				return nil, errDBClosed
 			}
@@ -1278,6 +1320,7 @@ func (db *DB) putConnDBLocked(dc *driverConn, err error) bool {
 		return true
 	} else if err == nil && !db.closed && db.maxIdleConnsLocked() > len(db.freeConn) {
 		db.freeConn = append(db.freeConn, dc)
+		db.maxIdleClosed++
 		db.startCleanerLocked()
 		return true
 	}