Generic DOM: Add DomBackend abstraction and JSON support

This change adds a `DomBackend` interface and a `DomBackendRegistry` for backend discovery (currently not hooked up to anything) alongside a JSON backend implementation.

The JSON backend comes with a small suite of unit and performance tests. The unit tests validate generic DOM conversion to and from serialized JSON and rapidjson::Document objects (the support for which lives in `JsonSerializationUtils.h`).

The performance tests show a throughput decrease compared to directly using the rapidjson serializer when mirroring our current pattern of copying strings from the serialized JSON representation, but with the coming in-memory store we have the opportunity to keep the buffer in memory and deserialize in-situ using rapidjson's API, which is consistently at least 100MiB/s faster on my machine (Ryzen Threadripper 3970X). The first parameter is the nested object complexity (N*N, objects with N keys comprised of arrays with N values) and the second parameter is the base size of the strings within each entry of this object.
```
----------------------------------------------------------------------------------------------------------------------
Benchmark                                                            Time             CPU   Iterations UserCounters...
----------------------------------------------------------------------------------------------------------------------
DomJsonBenchmark/DomDeserializeToDocumentInPlace/10/5            0.050 ms        0.050 ms        10000 bytes_per_second=355.816M/s
DomJsonBenchmark/DomDeserializeToDocumentInPlace/10/50           0.057 ms        0.057 ms        11200 bytes_per_second=386.064M/s
DomJsonBenchmark/DomDeserializeToDocumentInPlace/100/5            4.77 ms         4.88 ms          112 bytes_per_second=364.046M/s
DomJsonBenchmark/DomDeserializeToDocumentInPlace/100/500          11.6 ms         11.7 ms           64 bytes_per_second=554.518M/s
DomJsonBenchmark/DomDeserializeToDocumentWithCopies/10/5         0.084 ms        0.084 ms         7467 bytes_per_second=212.55M/s
DomJsonBenchmark/DomDeserializeToDocumentWithCopies/10/50        0.099 ms        0.100 ms         6400 bytes_per_second=220.608M/s
DomJsonBenchmark/DomDeserializeToDocumentWithCopies/100/5         8.22 ms         8.16 ms           90 bytes_per_second=217.847M/s
DomJsonBenchmark/DomDeserializeToDocumentWithCopies/100/500       23.2 ms         22.9 ms           30 bytes_per_second=283.56M/s
DomJsonBenchmark/JsonUtilsDeserializeToDocument/10/5             0.070 ms        0.070 ms        11200 bytes_per_second=255.049M/s
DomJsonBenchmark/JsonUtilsDeserializeToDocument/10/50            0.086 ms        0.087 ms         8960 bytes_per_second=253.258M/s
DomJsonBenchmark/JsonUtilsDeserializeToDocument/100/5             6.86 ms         6.84 ms          112 bytes_per_second=260.033M/s
DomJsonBenchmark/JsonUtilsDeserializeToDocument/100/500           22.8 ms         22.9 ms           32 bytes_per_second=283.158M/s
```

For `AZ::DOM::Document`, the current plan is to offer helper methods that can load from a file path or string using a given backend that can take advantage of in-place parsing by internally storing the serialized buffer.

Signed-off-by: Nicholas Van Sickle <nvsickle@amazon.com>
This commit is contained in:
Nicholas Van Sickle
2021-11-10 12:14:07 -08:00
parent cebf6e2de3
commit e9a57380bb
14 changed files with 1599 additions and 10 deletions
@@ -0,0 +1,184 @@
/*
* Copyright (c) Contributors to the Open 3D Engine Project.
* For complete copyright and license terms please see the LICENSE at the root of this distribution.
*
* SPDX-License-Identifier: Apache-2.0 OR MIT
*
*/
#if defined(HAVE_BENCHMARK)
#include <AzCore/DOM/Backends/JSON/JsonBackend.h>
#include <AzCore/DOM/Backends/JSON/JsonSerializationUtils.h>
#include <AzCore/JSON/document.h>
#include <AzCore/Name/NameDictionary.h>
#include <AzCore/Serialization/Json/JsonUtils.h>
#include <AzCore/UnitTest/TestTypes.h>
namespace Benchmark
{
class DomJsonBenchmark : public UnitTest::AllocatorsBenchmarkFixture
{
public:
void SetUp([[maybe_unused]] const ::benchmark::State& st) override
{
UnitTest::AllocatorsBenchmarkFixture::SetUp(st);
AZ::NameDictionary::Create();
}
void SetUp([[maybe_unused]] ::benchmark::State& st) override
{
UnitTest::AllocatorsBenchmarkFixture::SetUp(st);
AZ::NameDictionary::Create();
}
void TearDown([[maybe_unused]] ::benchmark::State& st) override
{
AZ::NameDictionary::Destroy();
UnitTest::AllocatorsBenchmarkFixture::TearDown(st);
}
void TearDown([[maybe_unused]] const ::benchmark::State& st) override
{
AZ::NameDictionary::Destroy();
UnitTest::AllocatorsBenchmarkFixture::TearDown(st);
}
AZStd::string GenerateDomJsonBenchmarkPayload(int64_t entryCount = 100, int64_t stringTemplateLength = 5)
{
rapidjson::Document document;
document.SetObject();
AZStd::string entryTemplate;
while (entryTemplate.size() < static_cast<size_t>(stringTemplateLength))
{
entryTemplate += "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor ";
}
entryTemplate.resize(stringTemplateLength);
AZStd::string buffer;
auto createString = [&](int n) -> rapidjson::Value
{
buffer = AZStd::string::format("#%i %s", n, entryTemplate.c_str());
return rapidjson::Value(buffer.data(), static_cast<rapidjson::SizeType>(buffer.size()), document.GetAllocator());
};
auto createEntry = [&](int n) -> rapidjson::Value
{
rapidjson::Value entry(rapidjson::kObjectType);
entry.AddMember("string", createString(n), document.GetAllocator());
entry.AddMember("int", rapidjson::Value(n), document.GetAllocator());
entry.AddMember("double", rapidjson::Value(static_cast<double>(n) * 0.5), document.GetAllocator());
entry.AddMember("bool", rapidjson::Value(n % 2 == 0), document.GetAllocator());
entry.AddMember("null", rapidjson::Value(rapidjson::kNullType), document.GetAllocator());
return entry;
};
auto createArray = [&]() -> rapidjson::Value
{
rapidjson::Value array;
array.SetArray();
for (int i = 0; i < entryCount; ++i)
{
array.PushBack(createEntry(i), document.GetAllocator());
}
return array;
};
auto createObject = [&]() -> rapidjson::Value
{
rapidjson::Value object;
object.SetObject();
for (int i = 0; i < entryCount; ++i)
{
buffer = AZStd::string::format("Key%i", i);
rapidjson::Value key;
key.SetString(buffer.data(), static_cast<rapidjson::SizeType>(buffer.length()), document.GetAllocator());
object.AddMember(key.Move(), createArray(), document.GetAllocator());
}
return object;
};
document.SetObject();
document.AddMember("entries", createObject(), document.GetAllocator());
AZStd::string serializedJson;
auto result = AZ::JsonSerializationUtils::WriteJsonString(document, serializedJson);
AZ_Assert(result.IsSuccess(), "Failed to serialize generated JSON");
return serializedJson;
}
};
// Helper macro for registering JSON benchmarks
#define BENCHMARK_REGISTER_JSON(BaseClass, Method) \
BENCHMARK_REGISTER_F(BaseClass, Method) \
->Args({ 10, 5 }) \
->Args({ 10, 500 }) \
->Args({ 100, 5 }) \
->Args({ 100, 500 }) \
->Unit(benchmark::kMillisecond);
BENCHMARK_DEFINE_F(DomJsonBenchmark, DomDeserializeToDocumentInPlace)(benchmark::State& state)
{
AZ::DOM::JsonBackend backend;
AZStd::string serializedPayload = GenerateDomJsonBenchmarkPayload(state.range(0), state.range(1));
for (auto _ : state)
{
state.PauseTiming();
AZStd::string payloadCopy = serializedPayload;
state.ResumeTiming();
auto result = AZ::DOM::Json::WriteToRapidJsonDocument(
[&](AZ::DOM::Visitor* visitor)
{
return backend.ReadFromStringInPlace(payloadCopy, visitor);
});
benchmark::DoNotOptimize(result.GetValue());
}
state.SetBytesProcessed(serializedPayload.size() * state.iterations());
}
BENCHMARK_REGISTER_JSON(DomJsonBenchmark, DomDeserializeToDocumentInPlace)
BENCHMARK_DEFINE_F(DomJsonBenchmark, DomDeserializeToDocument)(benchmark::State& state)
{
AZ::DOM::JsonBackend backend;
AZStd::string serializedPayload = GenerateDomJsonBenchmarkPayload(state.range(0), state.range(1));
for (auto _ : state)
{
auto result = AZ::DOM::Json::WriteToRapidJsonDocument(
[&](AZ::DOM::Visitor* visitor)
{
return backend.ReadFromString(serializedPayload, AZ::DOM::Lifetime::Temporary, visitor);
});
benchmark::DoNotOptimize(result.GetValue());
}
state.SetBytesProcessed(serializedPayload.size() * state.iterations());
}
BENCHMARK_REGISTER_JSON(DomJsonBenchmark, DomDeserializeToDocument)
BENCHMARK_DEFINE_F(DomJsonBenchmark, JsonUtilsDeserializeToDocument)(benchmark::State& state)
{
AZ::DOM::JsonBackend backend;
AZStd::string serializedPayload = GenerateDomJsonBenchmarkPayload(state.range(0), state.range(1));
for (auto _ : state)
{
auto result = AZ::JsonSerializationUtils::ReadJsonString(serializedPayload);
benchmark::DoNotOptimize(result.GetValue());
}
state.SetBytesProcessed(serializedPayload.size() * state.iterations());
}
BENCHMARK_REGISTER_JSON(DomJsonBenchmark, JsonUtilsDeserializeToDocument)
#undef BENCHMARK_REGISTER_JSON
} // namespace Benchmark
#endif // defined(HAVE_BENCHMARK)
@@ -0,0 +1,288 @@
/*
* Copyright (c) Contributors to the Open 3D Engine Project.
* For complete copyright and license terms please see the LICENSE at the root of this distribution.
*
* SPDX-License-Identifier: Apache-2.0 OR MIT
*
*/
#include <AzCore/DOM/Backends/JSON/JsonBackend.h>
#include <AzCore/DOM/Backends/JSON/JsonSerializationUtils.h>
#include <AzCore/Name/NameDictionary.h>
#include <AzCore/Serialization/Json/JsonUtils.h>
#include <AzCore/UnitTest/TestTypes.h>
namespace AZ::DOM::Tests
{
class DomJsonTests : public UnitTest::AllocatorsFixture
{
public:
void SetUp() override
{
UnitTest::AllocatorsFixture::SetUp();
NameDictionary::Create();
m_document = AZStd::make_unique<rapidjson::Document>();
}
void TearDown() override
{
m_document.reset();
NameDictionary::Destroy();
UnitTest::AllocatorsFixture::TearDown();
}
static bool DeepCompare(const rapidjson::Value& lhs, const rapidjson::Value& rhs)
{
if (lhs.GetType() != rhs.GetType())
{
return false;
}
switch (lhs.GetType())
{
case rapidjson::kNullType:
return true;
case rapidjson::kFalseType:
return true;
case rapidjson::kTrueType:
return true;
case rapidjson::kObjectType:
{
if (lhs.MemberCount() != rhs.MemberCount())
{
return false;
}
auto lhsIt = lhs.MemberBegin();
auto rhsIt = rhs.MemberBegin();
while (lhsIt != lhs.MemberEnd())
{
if (lhsIt->name != rhsIt->name)
{
return false;
}
if (!DeepCompare(lhsIt->value, rhsIt->value))
{
return false;
}
++lhsIt;
++rhsIt;
}
return true;
}
case rapidjson::kArrayType:
{
if (lhs.Size() != rhs.Size())
{
return false;
}
auto lhsIt = lhs.Begin();
auto rhsIt = rhs.Begin();
while (lhsIt != lhs.End())
{
if (!DeepCompare(*lhsIt, *rhsIt))
{
return false;
}
++lhsIt;
++rhsIt;
}
return true;
}
case rapidjson::kStringType:
return lhs == rhs;
case rapidjson::kNumberType:
return lhs == rhs;
}
AZ_Assert(false, "Unexpected JSON value type");
return false;
}
rapidjson::Value CreateString(const AZStd::string& text)
{
rapidjson::Value key;
key.SetString(text.c_str(), static_cast<rapidjson::SizeType>(text.length()), m_document->GetAllocator());
return key;
}
template <class T>
void AddValue(const AZStd::string& key, T value)
{
m_document->AddMember(CreateString(key), rapidjson::Value(value), m_document->GetAllocator());
}
// Validate round-trip serialization to and from rapidjson::Document and a UTF-8 encoded string
void PerformSerializationChecks()
{
// Generate a canonical serializaed representation of this document using rapidjson
// This will be pretty-printed using the same rapidjson pretty printer we use, so should be binary identical
// to any output generated by the visitor API
AZStd::string canonicalSerializedDocument;
AZ::JsonSerializationUtils::WriteJsonString(*m_document, canonicalSerializedDocument);
auto visitDocumentFn = [this](AZ::DOM::Visitor* visitor)
{
return Json::VisitRapidJsonValue(*m_document, visitor, Lifetime::Persistent);
};
// Document -> Document
{
auto result = Json::WriteToRapidJsonDocument(visitDocumentFn);
EXPECT_TRUE(result.IsSuccess());
EXPECT_TRUE(DeepCompare(*m_document, result.GetValue()));
}
// Document -> string
{
AZStd::string serializedDocument;
JsonBackend backend;
auto result = backend.WriteToString(serializedDocument, visitDocumentFn);
EXPECT_TRUE(result.IsSuccess());
EXPECT_EQ(canonicalSerializedDocument, serializedDocument);
}
// string -> Document
{
auto result = Json::WriteToRapidJsonDocument(
[&canonicalSerializedDocument](AZ::DOM::Visitor* visitor)
{
JsonBackend backend;
return backend.ReadFromString(canonicalSerializedDocument, AZ::DOM::Lifetime::Temporary, visitor);
});
EXPECT_TRUE(result.IsSuccess());
EXPECT_TRUE(DeepCompare(*m_document, result.GetValue()));
}
// string -> string
{
AZStd::string serializedDocument;
JsonBackend backend;
auto result = backend.WriteToString(
serializedDocument,
[&backend, &canonicalSerializedDocument](AZ::DOM::Visitor* visitor)
{
return backend.ReadFromString(canonicalSerializedDocument, AZ::DOM::Lifetime::Temporary, visitor);
});
EXPECT_TRUE(result.IsSuccess());
EXPECT_EQ(canonicalSerializedDocument, serializedDocument);
}
}
AZStd::unique_ptr<rapidjson::Document> m_document;
};
TEST_F(DomJsonTests, EmptyArray)
{
m_document->SetArray();
PerformSerializationChecks();
}
TEST_F(DomJsonTests, SimpleArray)
{
m_document->SetArray();
for (int i = 0; i < 5; ++i)
{
m_document->PushBack(i, m_document->GetAllocator());
}
PerformSerializationChecks();
}
TEST_F(DomJsonTests, NestedArrays)
{
m_document->SetArray();
for (int j = 0; j < 7; ++j)
{
rapidjson::Value nestedArray(rapidjson::kArrayType);
for (int i = 0; i < 5; ++i)
{
nestedArray.PushBack(i, m_document->GetAllocator());
}
m_document->PushBack(nestedArray.Move(), m_document->GetAllocator());
}
PerformSerializationChecks();
}
TEST_F(DomJsonTests, EmptyObject)
{
m_document->SetObject();
PerformSerializationChecks();
}
TEST_F(DomJsonTests, SimpleObject)
{
m_document->SetObject();
for (int i = 0; i < 5; ++i)
{
m_document->AddMember(CreateString(AZStd::string::format("Key%i", i)), rapidjson::Value(i), m_document->GetAllocator());
}
PerformSerializationChecks();
}
TEST_F(DomJsonTests, NestedObjects)
{
m_document->SetObject();
for (int j = 0; j < 7; ++j)
{
rapidjson::Value nestedObject(rapidjson::kObjectType);
for (int i = 0; i < 5; ++i)
{
nestedObject.AddMember(CreateString(AZStd::string::format("Key%i", i)), rapidjson::Value(i), m_document->GetAllocator());
}
m_document->AddMember(CreateString(AZStd::string::format("Obj%i", j)), nestedObject.Move(), m_document->GetAllocator());
}
PerformSerializationChecks();
}
TEST_F(DomJsonTests, Int64)
{
m_document->SetObject();
AddValue("int64_min", AZStd::numeric_limits<int64_t>::min());
AddValue("int64_max", AZStd::numeric_limits<int64_t>::max());
PerformSerializationChecks();
}
TEST_F(DomJsonTests, Uint64)
{
m_document->SetObject();
AddValue("uint64_min", AZStd::numeric_limits<uint64_t>::min());
AddValue("uint64_max", AZStd::numeric_limits<uint64_t>::max());
PerformSerializationChecks();
}
TEST_F(DomJsonTests, Double)
{
m_document->SetObject();
AddValue("double_min", AZStd::numeric_limits<double>::min());
AddValue("double_max", AZStd::numeric_limits<double>::max());
PerformSerializationChecks();
}
TEST_F(DomJsonTests, Null)
{
m_document->SetObject();
m_document->AddMember(CreateString("null_value"), rapidjson::Value(rapidjson::kNullType), m_document->GetAllocator());
PerformSerializationChecks();
}
TEST_F(DomJsonTests, Bool)
{
m_document->SetObject();
AddValue("true_value", true);
AddValue("false_value", false);
PerformSerializationChecks();
}
TEST_F(DomJsonTests, String)
{
m_document->SetObject();
m_document->AddMember(CreateString("empty_string"), CreateString(""), m_document->GetAllocator());
m_document->AddMember(CreateString("short_string"), CreateString("test"), m_document->GetAllocator());
m_document->AddMember(CreateString("long_string"), CreateString("abcdefghijklmnopqrstuvwxyz0123456789"), m_document->GetAllocator());
PerformSerializationChecks();
}
} // namespace AZ::DOM::Tests