archive/tar: optimize nanosecond parsing in parsePAXTime

Modified parsePAXTime to use a byte array for nanosecond parsing, providing a more straightforward implementation with better performance when handling decimal fraction part.
Here are benchmark results:
goos: darwin
goarch: amd64
pkg: archive/tar
cpu: Intel(R) Core(TM) i7-8569U CPU @ 2.80GHz
                                │   old.txt    │               new.txt                │
                                │    sec/op    │    sec/op     vs base                │
ParsePAXTIme/NoNanos-8            20.55n ±  4%   20.45n ± 12%        ~ (p=1.000 n=10)
ParsePAXTIme/ExactNanos-8         52.42n ±  2%   42.16n ±  3%  -19.57% (p=0.000 n=10)
ParsePAXTIme/WithNanoPadding-8    99.33n ±  2%   39.58n ±  2%  -60.16% (p=0.000 n=10)
ParsePAXTIme/WithNanoTruncate-8   54.78n ±  1%   43.64n ±  4%  -20.34% (p=0.000 n=10)
ParsePAXTIme/TrailingError-8      31.87n ±  4%   17.55n ±  2%  -44.94% (p=0.000 n=10)
ParsePAXTIme/LeadingError-8       31.03n ±  2%   15.81n ±  6%  -49.03% (p=0.000 n=10)

Change-Id: If05ef512137d0115db9cb6d3ab432335230628bb
GitHub-Last-Rev: 106d25e5cf
GitHub-Pull-Request: golang/go#73164
Reviewed-on: https://go-review.googlesource.com/c/go/+/662835
Auto-Submit: Michael Pratt <mpratt@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
This commit is contained in:
1911860538 2025-09-08 16:19:34 +00:00 committed by Gopher Robot
parent ea00650784
commit 5e6296f3f8
2 changed files with 73 additions and 8 deletions

View file

@ -213,15 +213,17 @@ func parsePAXTime(s string) (time.Time, error) {
} }
// Parse the nanoseconds. // Parse the nanoseconds.
if strings.Trim(sn, "0123456789") != "" { // Initialize an array with '0's to handle right padding automatically.
return time.Time{}, ErrHeader nanoDigits := [maxNanoSecondDigits]byte{'0', '0', '0', '0', '0', '0', '0', '0', '0'}
for i := range len(sn) {
switch c := sn[i]; {
case c < '0' || c > '9':
return time.Time{}, ErrHeader
case i < len(nanoDigits):
nanoDigits[i] = c
}
} }
if len(sn) < maxNanoSecondDigits { nsecs, _ := strconv.ParseInt(string(nanoDigits[:]), 10, 64) // Must succeed after validation
sn += strings.Repeat("0", maxNanoSecondDigits-len(sn)) // Right pad
} else {
sn = sn[:maxNanoSecondDigits] // Right truncate
}
nsecs, _ := strconv.ParseInt(sn, 10, 64) // Must succeed
if len(ss) > 0 && ss[0] == '-' { if len(ss) > 0 && ss[0] == '-' {
return time.Unix(secs, -1*nsecs), nil // Negative correction return time.Unix(secs, -1*nsecs), nil // Negative correction
} }

View file

@ -439,3 +439,66 @@ func TestFormatPAXRecord(t *testing.T) {
} }
} }
} }
func BenchmarkParsePAXTIme(b *testing.B) {
tests := []struct {
name string
in string
want time.Time
ok bool
}{
{
name: "NoNanos",
in: "123456",
want: time.Unix(123456, 0),
ok: true,
},
{
name: "ExactNanos",
in: "1.123456789",
want: time.Unix(1, 123456789),
ok: true,
},
{
name: "WithNanoPadding",
in: "1.123",
want: time.Unix(1, 123000000),
ok: true,
},
{
name: "WithNanoTruncate",
in: "1.123456789123",
want: time.Unix(1, 123456789),
ok: true,
},
{
name: "TrailingError",
in: "1.123abc",
want: time.Time{},
ok: false,
},
{
name: "LeadingError",
in: "1.abc123",
want: time.Time{},
ok: false,
},
}
for _, tt := range tests {
b.Run(tt.name, func(b *testing.B) {
b.ReportAllocs()
for b.Loop() {
ts, err := parsePAXTime(tt.in)
if (err == nil) != tt.ok {
if err != nil {
b.Fatal(err)
}
b.Fatal("expected error")
}
if !ts.Equal(tt.want) {
b.Fatalf("time mismatch: got %v, want %v", ts, tt.want)
}
}
})
}
}