internal/impl: add fast-path marshal implementation
This is a port of the v1 table marshaler, with some substantial
cleanup and refactoring.
Benchstat results from the protobuf reference benchmark data comparing the
v1 package with v2, with AllowPartial:true set for the new package. This
is not an apples-to-apples comparison, since v1 doesn't have a way to
disable required field checks. Required field checks in v2 package
currently go through reflection, which performs terribly; my initial
experimentation indicates that fast-path required field checks will
not add a large amount of cost; these results are incomplete but not
wholly inaccurate.
name old time/op new time/op delta
/dataset.google_message3_1.pb/Marshal-12 219ms ± 1% 232ms ± 1% +5.85% (p=0.004 n=6+5)
/dataset.google_message2.pb/Marshal-12 261µs ± 3% 248µs ± 1% -5.14% (p=0.002 n=6+6)
/dataset.google_message1_proto2.pb/Marshal-12 681ns ± 2% 637ns ± 3% -6.53% (p=0.002 n=6+6)
/dataset.google_message1_proto3.pb/Marshal-12 1.10µs ± 8% 0.99µs ± 3% -9.63% (p=0.002 n=6+6)
/dataset.google_message3_3.pb/Marshal-12 44.2ms ± 3% 35.2ms ± 1% -20.28% (p=0.004 n=6+5)
/dataset.google_message4.pb/Marshal-12 91.4ms ± 2% 94.9ms ± 2% +3.78% (p=0.002 n=6+6)
/dataset.google_message3_2.pb/Marshal-12 78.7ms ± 6% 80.8ms ± 4% ~ (p=0.310 n=6+6)
/dataset.google_message3_4.pb/Marshal-12 10.6ms ± 3% 10.6ms ± 8% ~ (p=0.662 n=5+6)
/dataset.google_message3_5.pb/Marshal-12 675ms ± 4% 510ms ± 2% -24.40% (p=0.002 n=6+6)
/dataset.google_message3_1.pb/Marshal 219ms ± 1% 236ms ± 7% +8.06% (p=0.004 n=5+6)
/dataset.google_message2.pb/Marshal 257µs ± 1% 250µs ± 3% ~ (p=0.052 n=5+6)
/dataset.google_message1_proto2.pb/Marshal 685ns ± 1% 628ns ± 1% -8.41% (p=0.008 n=5+5)
/dataset.google_message1_proto3.pb/Marshal 1.08µs ± 1% 0.98µs ± 2% -9.31% (p=0.004 n=5+6)
/dataset.google_message3_3.pb/Marshal 43.7ms ± 1% 35.1ms ± 1% -19.76% (p=0.002 n=6+6)
/dataset.google_message4.pb/Marshal 93.4ms ± 4% 94.9ms ± 2% ~ (p=0.180 n=6+6)
/dataset.google_message3_2.pb/Marshal 105ms ± 2% 98ms ± 7% -6.81% (p=0.009 n=5+6)
/dataset.google_message3_4.pb/Marshal 16.3ms ± 6% 15.7ms ± 3% -3.44% (p=0.041 n=6+6)
/dataset.google_message3_5.pb/Marshal 676ms ± 4% 504ms ± 2% -25.50% (p=0.004 n=6+5)
Change-Id: I72cc4597117f4cf5d236ef505777d49dd4a5f75d
Reviewed-on: https://go-review.googlesource.com/c/protobuf/+/171020
Reviewed-by: Joe Tsai <thebrokentoaster@gmail.com>
diff --git a/internal/impl/pointer_unsafe.go b/internal/impl/pointer_unsafe.go
index 16078bd..f04a561 100644
--- a/internal/impl/pointer_unsafe.go
+++ b/internal/impl/pointer_unsafe.go
@@ -20,6 +20,15 @@
return offset(f.Offset)
}
+// IsValid reports whether the offset is valid.
+func (f offset) IsValid() bool { return f != invalidOffset }
+
+// invalidOffset is an invalid field offset.
+var invalidOffset = ^offset(0)
+
+// zeroOffset is a noop when calling pointer.Apply.
+var zeroOffset = offset(0)
+
// pointer is a pointer to a message struct or field.
type pointer struct{ p unsafe.Pointer }
@@ -63,3 +72,44 @@
// TODO: Use tricky unsafe magic to directly create ifaceHeader.
return p.AsValueOf(t).Interface()
}
+
+func (p pointer) Bool() *bool { return (*bool)(p.p) }
+func (p pointer) BoolPtr() **bool { return (**bool)(p.p) }
+func (p pointer) BoolSlice() *[]bool { return (*[]bool)(p.p) }
+func (p pointer) Int32() *int32 { return (*int32)(p.p) }
+func (p pointer) Int32Ptr() **int32 { return (**int32)(p.p) }
+func (p pointer) Int32Slice() *[]int32 { return (*[]int32)(p.p) }
+func (p pointer) Int64() *int64 { return (*int64)(p.p) }
+func (p pointer) Int64Ptr() **int64 { return (**int64)(p.p) }
+func (p pointer) Int64Slice() *[]int64 { return (*[]int64)(p.p) }
+func (p pointer) Uint32() *uint32 { return (*uint32)(p.p) }
+func (p pointer) Uint32Ptr() **uint32 { return (**uint32)(p.p) }
+func (p pointer) Uint32Slice() *[]uint32 { return (*[]uint32)(p.p) }
+func (p pointer) Uint64() *uint64 { return (*uint64)(p.p) }
+func (p pointer) Uint64Ptr() **uint64 { return (**uint64)(p.p) }
+func (p pointer) Uint64Slice() *[]uint64 { return (*[]uint64)(p.p) }
+func (p pointer) Float32() *float32 { return (*float32)(p.p) }
+func (p pointer) Float32Ptr() **float32 { return (**float32)(p.p) }
+func (p pointer) Float32Slice() *[]float32 { return (*[]float32)(p.p) }
+func (p pointer) Float64() *float64 { return (*float64)(p.p) }
+func (p pointer) Float64Ptr() **float64 { return (**float64)(p.p) }
+func (p pointer) Float64Slice() *[]float64 { return (*[]float64)(p.p) }
+func (p pointer) String() *string { return (*string)(p.p) }
+func (p pointer) StringPtr() **string { return (**string)(p.p) }
+func (p pointer) StringSlice() *[]string { return (*[]string)(p.p) }
+func (p pointer) Bytes() *[]byte { return (*[]byte)(p.p) }
+func (p pointer) BytesSlice() *[][]byte { return (*[][]byte)(p.p) }
+func (p pointer) Extensions() *legacyExtensionMap { return (*legacyExtensionMap)(p.p) }
+
+func (p pointer) Elem() pointer {
+ return pointer{p: *(*unsafe.Pointer)(p.p)}
+}
+
+// PointerSlice loads []*T from p as a []pointer.
+// The value returned is aliased with the original slice.
+// This behavior differs from the implementation in pointer_reflect.go.
+func (p pointer) PointerSlice() []pointer {
+ // Super-tricky - p should point to a []*T where T is a
+ // message type. We load it as []pointer.
+ return *(*[]pointer)(p.p)
+}