compress/flate: benchmark some English text, not just the digits of e.

The testdata/e.txt input is repeated on the longer benchmarks, but the
length of that data is less than flate's window size, so the numbers are
essentially measuring the performance of a trivial compression. A follow-up
CL will add more data to testdata/e.txt.

Sample output on my laptop (linux, amd64):

BenchmarkDecodeDigitsSpeed1e4	    5000	    603153 ns/op	  16.58 MB/s
BenchmarkDecodeDigitsSpeed1e5	    1000	   1465602 ns/op	  68.23 MB/s
BenchmarkDecodeDigitsSpeed1e6	     200	   8036050 ns/op	 124.44 MB/s
BenchmarkDecodeDigitsDefault1e4	    5000	    581796 ns/op	  17.19 MB/s
BenchmarkDecodeDigitsDefault1e5	    2000	    846653 ns/op	 118.11 MB/s
BenchmarkDecodeDigitsDefault1e6	     500	   3385782 ns/op	 295.35 MB/s
BenchmarkDecodeDigitsCompress1e4	    5000	    581180 ns/op	  17.21 MB/s
BenchmarkDecodeDigitsCompress1e5	    2000	    846209 ns/op	 118.17 MB/s
BenchmarkDecodeDigitsCompress1e6	     500	   3386174 ns/op	 295.32 MB/s
BenchmarkDecodeTwainSpeed1e4	    5000	    643563 ns/op	  15.54 MB/s
BenchmarkDecodeTwainSpeed1e5	     500	   5418408 ns/op	  18.46 MB/s
BenchmarkDecodeTwainSpeed1e6	      50	  52277520 ns/op	  19.13 MB/s
BenchmarkDecodeTwainDefault1e4	    5000	    583551 ns/op	  17.14 MB/s
BenchmarkDecodeTwainDefault1e5	     500	   4443428 ns/op	  22.51 MB/s
BenchmarkDecodeTwainDefault1e6	      50	  41862080 ns/op	  23.89 MB/s
BenchmarkDecodeTwainCompress1e4	    5000	    583490 ns/op	  17.14 MB/s
BenchmarkDecodeTwainCompress1e5	     500	   4426356 ns/op	  22.59 MB/s
BenchmarkDecodeTwainCompress1e6	      50	  41657940 ns/op	  24.01 MB/s
BenchmarkEncodeDigitsSpeed1e4	    2000	   1230907 ns/op	   8.12 MB/s
BenchmarkEncodeDigitsSpeed1e5	    1000	   2319129 ns/op	  43.12 MB/s
BenchmarkEncodeDigitsSpeed1e6	     100	  12378950 ns/op	  80.78 MB/s
BenchmarkEncodeDigitsDefault1e4	    1000	   1597865 ns/op	   6.26 MB/s
BenchmarkEncodeDigitsDefault1e5	     500	   3163458 ns/op	  31.61 MB/s
BenchmarkEncodeDigitsDefault1e6	     100	  18770240 ns/op	  53.28 MB/s
BenchmarkEncodeDigitsCompress1e4	    1000	   1603461 ns/op	   6.24 MB/s
BenchmarkEncodeDigitsCompress1e5	     500	   3168766 ns/op	  31.56 MB/s
BenchmarkEncodeDigitsCompress1e6	     100	  18855830 ns/op	  53.03 MB/s
BenchmarkEncodeTwainSpeed1e4	    1000	   1338049 ns/op	   7.47 MB/s
BenchmarkEncodeTwainSpeed1e5	     500	   7341622 ns/op	  13.62 MB/s
BenchmarkEncodeTwainSpeed1e6	      50	  67484600 ns/op	  14.82 MB/s
BenchmarkEncodeTwainDefault1e4	    1000	   1778399 ns/op	   5.62 MB/s
BenchmarkEncodeTwainDefault1e5	     100	  23261810 ns/op	   4.30 MB/s
BenchmarkEncodeTwainDefault1e6	      10	 243533600 ns/op	   4.11 MB/s
BenchmarkEncodeTwainCompress1e4	    1000	   1795469 ns/op	   5.57 MB/s
BenchmarkEncodeTwainCompress1e5	      50	  29447140 ns/op	   3.40 MB/s
BenchmarkEncodeTwainCompress1e6	       5	 321686800 ns/op	   3.11 MB/s
ok  	compress/flate	89.246s

R=rsc, r
CC=golang-dev
https://golang.org/cl/6195055

src/pkg/compress/flate/reader_test.go

@@ -12,20 +12,47 @@ import (
 	"testing"
 )
 
-func benchmarkDecoder(b *testing.B, level, n int) {
+const (
+	digits = iota
+	twain
+)
+
+var testfiles = []string{
+	// Digits is the digits of the irrational number e. Its decimal representation
+	// does not repeat, but there are only 10 posible digits, so it should be
+	// reasonably compressible.
+	//
+	// TODO(nigeltao): e.txt is only 10K long, so when benchmarking 100K or 1000K
+	// of input, the digits are just repeated from the beginning, and flate can
+	// trivially compress this as a length/distance copy operation. Thus,
+	// BenchmarkDecodeDigitsXxx1e6 is essentially just measuring the speed of the
+	// forwardCopy implementation, but isn't particularly representative of real
+	// usage. The TODO is to replace e.txt with 100K digits, not just 10K digits,
+	// since that's larger than the windowSize 1<<15 (= 32768).
+	digits: "../testdata/e.txt",
+	// Twain is Project Gutenberg's edition of Mark Twain's classic English novel.
+	twain: "../testdata/Mark.Twain-Tom.Sawyer.txt",
+}
+
+func benchmarkDecode(b *testing.B, testfile, level, n int) {
 	b.StopTimer()
 	b.SetBytes(int64(n))
-	buf0, err := ioutil.ReadFile("../testdata/e.txt")
+	buf0, err := ioutil.ReadFile(testfiles[testfile])
 	if err != nil {
 		b.Fatal(err)
 	}
-	buf0 = buf0[:10000]
+	if len(buf0) == 0 {
+		b.Fatalf("test file %q has no data", testfiles[testfile])
+	}
 	compressed := new(bytes.Buffer)
 	w, err := NewWriter(compressed, level)
 	if err != nil {
 		b.Fatal(err)
 	}
 	for i := 0; i < n; i += len(buf0) {
+		if len(buf0) > n-i {
+			buf0 = buf0[:n-i]
+		}
 		io.Copy(w, bytes.NewBuffer(buf0))
 	}
 	w.Close()
@@ -38,38 +65,29 @@ func benchmarkDecoder(b *testing.B, level, n int) {
 	}
 }
 
-func BenchmarkDecoderBestSpeed1K(b *testing.B) {
+// These short names are so that gofmt doesn't break the BenchmarkXxx function
-	benchmarkDecoder(b, BestSpeed, 1e4)
+// bodies below over multiple lines.
-}
+const (
+	speed    = BestSpeed
+	default_ = DefaultCompression
+	compress = BestCompression
+)
 
-func BenchmarkDecoderBestSpeed10K(b *testing.B) {
+func BenchmarkDecodeDigitsSpeed1e4(b *testing.B)    { benchmarkDecode(b, digits, speed, 1e4) }
-	benchmarkDecoder(b, BestSpeed, 1e5)
+func BenchmarkDecodeDigitsSpeed1e5(b *testing.B)    { benchmarkDecode(b, digits, speed, 1e5) }
-}
+func BenchmarkDecodeDigitsSpeed1e6(b *testing.B)    { benchmarkDecode(b, digits, speed, 1e6) }
-
+func BenchmarkDecodeDigitsDefault1e4(b *testing.B)  { benchmarkDecode(b, digits, default_, 1e4) }
-func BenchmarkDecoderBestSpeed100K(b *testing.B) {
+func BenchmarkDecodeDigitsDefault1e5(b *testing.B)  { benchmarkDecode(b, digits, default_, 1e5) }
-	benchmarkDecoder(b, BestSpeed, 1e6)
+func BenchmarkDecodeDigitsDefault1e6(b *testing.B)  { benchmarkDecode(b, digits, default_, 1e6) }
-}
+func BenchmarkDecodeDigitsCompress1e4(b *testing.B) { benchmarkDecode(b, digits, compress, 1e4) }
-
+func BenchmarkDecodeDigitsCompress1e5(b *testing.B) { benchmarkDecode(b, digits, compress, 1e5) }
-func BenchmarkDecoderDefaultCompression1K(b *testing.B) {
+func BenchmarkDecodeDigitsCompress1e6(b *testing.B) { benchmarkDecode(b, digits, compress, 1e6) }
-	benchmarkDecoder(b, DefaultCompression, 1e4)
+func BenchmarkDecodeTwainSpeed1e4(b *testing.B)     { benchmarkDecode(b, twain, speed, 1e4) }
-}
+func BenchmarkDecodeTwainSpeed1e5(b *testing.B)     { benchmarkDecode(b, twain, speed, 1e5) }
-
+func BenchmarkDecodeTwainSpeed1e6(b *testing.B)     { benchmarkDecode(b, twain, speed, 1e6) }
-func BenchmarkDecoderDefaultCompression10K(b *testing.B) {
+func BenchmarkDecodeTwainDefault1e4(b *testing.B)   { benchmarkDecode(b, twain, default_, 1e4) }
-	benchmarkDecoder(b, DefaultCompression, 1e5)
+func BenchmarkDecodeTwainDefault1e5(b *testing.B)   { benchmarkDecode(b, twain, default_, 1e5) }
-}
+func BenchmarkDecodeTwainDefault1e6(b *testing.B)   { benchmarkDecode(b, twain, default_, 1e6) }
-
+func BenchmarkDecodeTwainCompress1e4(b *testing.B)  { benchmarkDecode(b, twain, compress, 1e4) }
-func BenchmarkDecoderDefaultCompression100K(b *testing.B) {
+func BenchmarkDecodeTwainCompress1e5(b *testing.B)  { benchmarkDecode(b, twain, compress, 1e5) }
-	benchmarkDecoder(b, DefaultCompression, 1e6)
+func BenchmarkDecodeTwainCompress1e6(b *testing.B)  { benchmarkDecode(b, twain, compress, 1e6) }
-}
-
-func BenchmarkDecoderBestCompression1K(b *testing.B) {
-	benchmarkDecoder(b, BestCompression, 1e4)
-}
-
-func BenchmarkDecoderBestCompression10K(b *testing.B) {
-	benchmarkDecoder(b, BestCompression, 1e5)
-}
-
-func BenchmarkDecoderBestCompression100K(b *testing.B) {
-	benchmarkDecoder(b, BestCompression, 1e6)
-}

src/pkg/compress/flate/writer_test.go

@@ -10,16 +10,21 @@ import (
 	"testing"
 )
 
-func benchmarkEncoder(b *testing.B, level, n int) {
+func benchmarkEncoder(b *testing.B, testfile, level, n int) {
 	b.StopTimer()
 	b.SetBytes(int64(n))
-	buf0, err := ioutil.ReadFile("../testdata/e.txt")
+	buf0, err := ioutil.ReadFile(testfiles[testfile])
 	if err != nil {
 		b.Fatal(err)
 	}
-	buf0 = buf0[:10000]
+	if len(buf0) == 0 {
+		b.Fatalf("test file %q has no data", testfiles[testfile])
+	}
 	buf1 := make([]byte, n)
 	for i := 0; i < n; i += len(buf0) {
+		if len(buf0) > n-i {
+			buf0 = buf0[:n-i]
+		}
 		copy(buf1[i:], buf0)
 	}
 	buf0 = nil
@@ -35,38 +40,21 @@ func benchmarkEncoder(b *testing.B, level, n int) {
 	}
 }
 
-func BenchmarkEncoderBestSpeed1K(b *testing.B) {
+func BenchmarkEncodeDigitsSpeed1e4(b *testing.B)    { benchmarkEncoder(b, digits, speed, 1e4) }
-	benchmarkEncoder(b, BestSpeed, 1e4)
+func BenchmarkEncodeDigitsSpeed1e5(b *testing.B)    { benchmarkEncoder(b, digits, speed, 1e5) }
-}
+func BenchmarkEncodeDigitsSpeed1e6(b *testing.B)    { benchmarkEncoder(b, digits, speed, 1e6) }
-
+func BenchmarkEncodeDigitsDefault1e4(b *testing.B)  { benchmarkEncoder(b, digits, default_, 1e4) }
-func BenchmarkEncoderBestSpeed10K(b *testing.B) {
+func BenchmarkEncodeDigitsDefault1e5(b *testing.B)  { benchmarkEncoder(b, digits, default_, 1e5) }
-	benchmarkEncoder(b, BestSpeed, 1e5)
+func BenchmarkEncodeDigitsDefault1e6(b *testing.B)  { benchmarkEncoder(b, digits, default_, 1e6) }
-}
+func BenchmarkEncodeDigitsCompress1e4(b *testing.B) { benchmarkEncoder(b, digits, compress, 1e4) }
-
+func BenchmarkEncodeDigitsCompress1e5(b *testing.B) { benchmarkEncoder(b, digits, compress, 1e5) }
-func BenchmarkEncoderBestSpeed100K(b *testing.B) {
+func BenchmarkEncodeDigitsCompress1e6(b *testing.B) { benchmarkEncoder(b, digits, compress, 1e6) }
-	benchmarkEncoder(b, BestSpeed, 1e6)
+func BenchmarkEncodeTwainSpeed1e4(b *testing.B)     { benchmarkEncoder(b, twain, speed, 1e4) }
-}
+func BenchmarkEncodeTwainSpeed1e5(b *testing.B)     { benchmarkEncoder(b, twain, speed, 1e5) }
-
+func BenchmarkEncodeTwainSpeed1e6(b *testing.B)     { benchmarkEncoder(b, twain, speed, 1e6) }
-func BenchmarkEncoderDefaultCompression1K(b *testing.B) {
+func BenchmarkEncodeTwainDefault1e4(b *testing.B)   { benchmarkEncoder(b, twain, default_, 1e4) }
-	benchmarkEncoder(b, DefaultCompression, 1e4)
+func BenchmarkEncodeTwainDefault1e5(b *testing.B)   { benchmarkEncoder(b, twain, default_, 1e5) }
-}
+func BenchmarkEncodeTwainDefault1e6(b *testing.B)   { benchmarkEncoder(b, twain, default_, 1e6) }
-
+func BenchmarkEncodeTwainCompress1e4(b *testing.B)  { benchmarkEncoder(b, twain, compress, 1e4) }
-func BenchmarkEncoderDefaultCompression10K(b *testing.B) {
+func BenchmarkEncodeTwainCompress1e5(b *testing.B)  { benchmarkEncoder(b, twain, compress, 1e5) }
-	benchmarkEncoder(b, DefaultCompression, 1e5)
+func BenchmarkEncodeTwainCompress1e6(b *testing.B)  { benchmarkEncoder(b, twain, compress, 1e6) }
-}
-
-func BenchmarkEncoderDefaultCompression100K(b *testing.B) {
-	benchmarkEncoder(b, DefaultCompression, 1e6)
-}
-
-func BenchmarkEncoderBestCompression1K(b *testing.B) {
-	benchmarkEncoder(b, BestCompression, 1e4)
-}
-
-func BenchmarkEncoderBestCompression10K(b *testing.B) {
-	benchmarkEncoder(b, BestCompression, 1e5)
-}
-
-func BenchmarkEncoderBestCompression100K(b *testing.B) {
-	benchmarkEncoder(b, BestCompression, 1e6)
-}