derp: make writeUint32 and readUint32 not allocate

The allocations are small, but they're easy enough to avoid.
And it removes some clutter from the pprof output.

name                      old time/op    new time/op    delta
SendRecv/msgsize=10-8       10.1µs ± 9%     9.7µs ± 7%    -3.45%  (p=0.035 n=14+14)
SendRecv/msgsize=100-8      8.12µs ± 7%    7.38µs ± 9%    -9.02%  (p=0.000 n=15+15)
SendRecv/msgsize=1000-8     9.51µs ±25%    8.76µs ±22%      ~     (p=0.202 n=15+15)
SendRecv/msgsize=10000-8    21.1µs ±25%    19.9µs ±14%      ~     (p=0.270 n=15+14)
WriteUint32-8               25.1ns ± 4%    21.3ns ±12%   -15.01%  (p=0.000 n=14+14)
ReadUint32-8                35.4ns ± 4%    21.9ns ± 4%   -38.06%  (p=0.000 n=15+15)

name                      old alloc/op   new alloc/op   delta
SendRecv/msgsize=10-8         182B ± 2%      169B ± 1%    -7.22%  (p=0.000 n=15+13)
SendRecv/msgsize=100-8        282B ± 1%      265B ± 1%    -5.85%  (p=0.000 n=15+15)
SendRecv/msgsize=1000-8     1.19kB ± 1%    1.18kB ± 0%    -1.26%  (p=0.000 n=14+15)
SendRecv/msgsize=10000-8    19.3kB ± 4%    18.7kB ± 4%    -3.44%  (p=0.006 n=12+12)
WriteUint32-8                4.00B ± 0%     0.00B       -100.00%  (p=0.000 n=15+15)
ReadUint32-8                 4.00B ± 0%     0.00B       -100.00%  (p=0.000 n=15+15)

name                      old allocs/op  new allocs/op  delta
SendRecv/msgsize=10-8         8.00 ± 0%      4.00 ± 0%   -50.00%  (p=0.000 n=15+15)
SendRecv/msgsize=100-8        8.00 ± 0%      4.00 ± 0%   -50.00%  (p=0.000 n=15+15)
SendRecv/msgsize=1000-8       8.00 ± 0%      4.00 ± 0%   -50.00%  (p=0.000 n=15+15)
SendRecv/msgsize=10000-8      8.47 ±17%      5.00 ± 0%   -40.94%  (p=0.000 n=15+14)
WriteUint32-8                 1.00 ± 0%      0.00       -100.00%  (p=0.000 n=15+15)
ReadUint32-8                  1.00 ± 0%      0.00       -100.00%  (p=0.000 n=15+15)

Signed-off-by: Josh Bleecher Snyder <josharian@gmail.com>

derp/derp.go

@@ -108,16 +108,31 @@ var bin = binary.BigEndian
 func writeUint32(bw *bufio.Writer, v uint32) error {
 	var b [4]byte
 	bin.PutUint32(b[:], v)
-	_, err := bw.Write(b[:])
+	// Writing a byte at a time is a bit silly,
+	// but it causes b not to escape,
+	// which more than pays for the silliness.
+	for _, c := range &b {
+		err := bw.WriteByte(c)
+		if err != nil {
 			return err
 		}
+	}
+	return nil
+}
 
 func readUint32(br *bufio.Reader) (uint32, error) {
-	b := make([]byte, 4)
+	var b [4]byte
-	if _, err := io.ReadFull(br, b); err != nil {
+	// Reading a byte at a time is a bit silly,
+	// but it causes b not to escape,
+	// which more than pays for the silliness.
+	for i := range &b {
+		c, err := br.ReadByte()
+		if err != nil {
 			return 0, err
 		}
-	return bin.Uint32(b), nil
+		b[i] = c
+	}
+	return bin.Uint32(b[:]), nil
 }
 
 func readFrameTypeHeader(br *bufio.Reader, wantType frameType) (frameLen uint32, err error) {