You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/java/rocksjni/comparatorjnicallback.h

142 lines
5.5 KiB

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// This file implements the callback "bridge" between Java and C++ for
// ROCKSDB_NAMESPACE::Comparator
#ifndef JAVA_ROCKSJNI_COMPARATORJNICALLBACK_H_
#define JAVA_ROCKSJNI_COMPARATORJNICALLBACK_H_
#include <jni.h>
#include <memory>
#include <string>
#include "port/port.h"
#include "rocksdb/comparator.h"
#include "rocksdb/slice.h"
#include "rocksjni/jnicallback.h"
Improve RocksJava Comparator (#6252) Summary: This is a redesign of the API for RocksJava comparators with the aim of improving performance. It also simplifies the class hierarchy. **NOTE**: This breaks backwards compatibility for existing 3rd party Comparators implemented in Java... so we need to consider carefully which release branches this goes into. Previously when implementing a comparator in Java the developer had a choice of subclassing either `DirectComparator` or `Comparator` which would use direct and non-direct byte-buffers resepectively (via `DirectSlice` and `Slice`). In this redesign there we have eliminated the overhead of using the Java Slice classes, and just use `ByteBuffer`s. The `ComparatorOptions` supplied when constructing a Comparator allow you to choose between direct and non-direct byte buffers by setting `useDirect`. In addition, the `ComparatorOptions` now allow you to choose whether a ByteBuffer is reused over multiple comparator calls, by setting `maxReusedBufferSize > 0`. When buffers are reused, ComparatorOptions provides a choice of mutex type by setting `useAdaptiveMutex`. --- [JMH benchmarks previously indicated](https://github.com/facebook/rocksdb/pull/6241#issue-356398306) that the difference between C++ and Java for implementing a comparator was ~7x slowdown in Java. With these changes, when reusing buffers and guarding access to them via mutexes the slowdown is approximately the same. However, these changes offer a new facility to not reuse mutextes, which reduces the slowdown to ~5.5x in Java. We also offer a `thread_local` mechanism for reusing buffers, which reduces slowdown to ~5.2x in Java (closes https://github.com/facebook/rocksdb/pull/4425). These changes also form a good base for further optimisation work such as further JNI lookup caching, and JNI critical. --- These numbers were captured without jemalloc. With jemalloc, the performance improves for all tests, and the Java slowdown reduces to between 4.8x and 5.x. ``` ComparatorBenchmarks.put native_bytewise thrpt 25 124483.795 ± 2032.443 ops/s ComparatorBenchmarks.put native_reverse_bytewise thrpt 25 114414.536 ± 3486.156 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 17228.250 ± 1288.546 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 16035.865 ± 1248.099 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_thread-local thrpt 25 21571.500 ± 871.521 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_adaptive-mutex thrpt 25 23613.773 ± 8465.660 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 16768.172 ± 5618.489 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_thread-local thrpt 25 23921.164 ± 8734.742 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_no-reuse thrpt 25 17899.684 ± 839.679 ops/s ComparatorBenchmarks.put java_bytewise_direct_no-reuse thrpt 25 22148.316 ± 1215.527 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 11311.126 ± 820.602 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 11421.311 ± 807.210 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_thread-local thrpt 25 11554.005 ± 960.556 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_adaptive-mutex thrpt 25 22960.523 ± 1673.421 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 18293.317 ± 1434.601 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_thread-local thrpt 25 24479.361 ± 2157.306 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_no-reuse thrpt 25 7942.286 ± 626.170 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_no-reuse thrpt 25 11781.955 ± 1019.843 ops/s ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/6252 Differential Revision: D19331064 Pulled By: pdillinger fbshipit-source-id: 1f3b794e6a14162b2c3ffb943e8c0e64a0c03738
5 years ago
#include "util/thread_local.h"
namespace ROCKSDB_NAMESPACE {
Improve RocksJava Comparator (#6252) Summary: This is a redesign of the API for RocksJava comparators with the aim of improving performance. It also simplifies the class hierarchy. **NOTE**: This breaks backwards compatibility for existing 3rd party Comparators implemented in Java... so we need to consider carefully which release branches this goes into. Previously when implementing a comparator in Java the developer had a choice of subclassing either `DirectComparator` or `Comparator` which would use direct and non-direct byte-buffers resepectively (via `DirectSlice` and `Slice`). In this redesign there we have eliminated the overhead of using the Java Slice classes, and just use `ByteBuffer`s. The `ComparatorOptions` supplied when constructing a Comparator allow you to choose between direct and non-direct byte buffers by setting `useDirect`. In addition, the `ComparatorOptions` now allow you to choose whether a ByteBuffer is reused over multiple comparator calls, by setting `maxReusedBufferSize > 0`. When buffers are reused, ComparatorOptions provides a choice of mutex type by setting `useAdaptiveMutex`. --- [JMH benchmarks previously indicated](https://github.com/facebook/rocksdb/pull/6241#issue-356398306) that the difference between C++ and Java for implementing a comparator was ~7x slowdown in Java. With these changes, when reusing buffers and guarding access to them via mutexes the slowdown is approximately the same. However, these changes offer a new facility to not reuse mutextes, which reduces the slowdown to ~5.5x in Java. We also offer a `thread_local` mechanism for reusing buffers, which reduces slowdown to ~5.2x in Java (closes https://github.com/facebook/rocksdb/pull/4425). These changes also form a good base for further optimisation work such as further JNI lookup caching, and JNI critical. --- These numbers were captured without jemalloc. With jemalloc, the performance improves for all tests, and the Java slowdown reduces to between 4.8x and 5.x. ``` ComparatorBenchmarks.put native_bytewise thrpt 25 124483.795 ± 2032.443 ops/s ComparatorBenchmarks.put native_reverse_bytewise thrpt 25 114414.536 ± 3486.156 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 17228.250 ± 1288.546 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 16035.865 ± 1248.099 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_thread-local thrpt 25 21571.500 ± 871.521 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_adaptive-mutex thrpt 25 23613.773 ± 8465.660 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 16768.172 ± 5618.489 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_thread-local thrpt 25 23921.164 ± 8734.742 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_no-reuse thrpt 25 17899.684 ± 839.679 ops/s ComparatorBenchmarks.put java_bytewise_direct_no-reuse thrpt 25 22148.316 ± 1215.527 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 11311.126 ± 820.602 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 11421.311 ± 807.210 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_thread-local thrpt 25 11554.005 ± 960.556 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_adaptive-mutex thrpt 25 22960.523 ± 1673.421 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 18293.317 ± 1434.601 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_thread-local thrpt 25 24479.361 ± 2157.306 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_no-reuse thrpt 25 7942.286 ± 626.170 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_no-reuse thrpt 25 11781.955 ± 1019.843 ops/s ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/6252 Differential Revision: D19331064 Pulled By: pdillinger fbshipit-source-id: 1f3b794e6a14162b2c3ffb943e8c0e64a0c03738
5 years ago
enum ReusedSynchronisationType {
/**
* Standard mutex.
*/
MUTEX,
/**
* Use adaptive mutex, which spins in the user space before resorting
* to kernel. This could reduce context switch when the mutex is not
* heavily contended. However, if the mutex is hot, we could end up
* wasting spin time.
*/
ADAPTIVE_MUTEX,
/**
* There is a reused buffer per-thread.
*/
THREAD_LOCAL
};
struct ComparatorJniCallbackOptions {
Improve RocksJava Comparator (#6252) Summary: This is a redesign of the API for RocksJava comparators with the aim of improving performance. It also simplifies the class hierarchy. **NOTE**: This breaks backwards compatibility for existing 3rd party Comparators implemented in Java... so we need to consider carefully which release branches this goes into. Previously when implementing a comparator in Java the developer had a choice of subclassing either `DirectComparator` or `Comparator` which would use direct and non-direct byte-buffers resepectively (via `DirectSlice` and `Slice`). In this redesign there we have eliminated the overhead of using the Java Slice classes, and just use `ByteBuffer`s. The `ComparatorOptions` supplied when constructing a Comparator allow you to choose between direct and non-direct byte buffers by setting `useDirect`. In addition, the `ComparatorOptions` now allow you to choose whether a ByteBuffer is reused over multiple comparator calls, by setting `maxReusedBufferSize > 0`. When buffers are reused, ComparatorOptions provides a choice of mutex type by setting `useAdaptiveMutex`. --- [JMH benchmarks previously indicated](https://github.com/facebook/rocksdb/pull/6241#issue-356398306) that the difference between C++ and Java for implementing a comparator was ~7x slowdown in Java. With these changes, when reusing buffers and guarding access to them via mutexes the slowdown is approximately the same. However, these changes offer a new facility to not reuse mutextes, which reduces the slowdown to ~5.5x in Java. We also offer a `thread_local` mechanism for reusing buffers, which reduces slowdown to ~5.2x in Java (closes https://github.com/facebook/rocksdb/pull/4425). These changes also form a good base for further optimisation work such as further JNI lookup caching, and JNI critical. --- These numbers were captured without jemalloc. With jemalloc, the performance improves for all tests, and the Java slowdown reduces to between 4.8x and 5.x. ``` ComparatorBenchmarks.put native_bytewise thrpt 25 124483.795 ± 2032.443 ops/s ComparatorBenchmarks.put native_reverse_bytewise thrpt 25 114414.536 ± 3486.156 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 17228.250 ± 1288.546 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 16035.865 ± 1248.099 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_thread-local thrpt 25 21571.500 ± 871.521 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_adaptive-mutex thrpt 25 23613.773 ± 8465.660 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 16768.172 ± 5618.489 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_thread-local thrpt 25 23921.164 ± 8734.742 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_no-reuse thrpt 25 17899.684 ± 839.679 ops/s ComparatorBenchmarks.put java_bytewise_direct_no-reuse thrpt 25 22148.316 ± 1215.527 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 11311.126 ± 820.602 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 11421.311 ± 807.210 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_thread-local thrpt 25 11554.005 ± 960.556 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_adaptive-mutex thrpt 25 22960.523 ± 1673.421 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 18293.317 ± 1434.601 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_thread-local thrpt 25 24479.361 ± 2157.306 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_no-reuse thrpt 25 7942.286 ± 626.170 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_no-reuse thrpt 25 11781.955 ± 1019.843 ops/s ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/6252 Differential Revision: D19331064 Pulled By: pdillinger fbshipit-source-id: 1f3b794e6a14162b2c3ffb943e8c0e64a0c03738
5 years ago
// Set the synchronisation type used to guard the reused buffers.
// Only used if max_reused_buffer_size > 0.
// Default: ADAPTIVE_MUTEX
ReusedSynchronisationType reused_synchronisation_type =
ReusedSynchronisationType::ADAPTIVE_MUTEX;
// Indicates if a direct byte buffer (i.e. outside of the normal
// garbage-collected heap) is used for the callbacks to Java,
// as opposed to a non-direct byte buffer which is a wrapper around
// an on-heap byte[].
// Default: true
bool direct_buffer = true;
// Maximum size of a buffer (in bytes) that will be reused.
// Comparators will use 5 of these buffers,
// so the retained memory size will be 5 * max_reused_buffer_size.
// When a buffer is needed for transferring data to a callback,
// if it requires less than max_reused_buffer_size, then an
// existing buffer will be reused, else a new buffer will be
// allocated just for that callback. -1 to disable.
// Default: 64 bytes
int32_t max_reused_buffer_size = 64;
};
/**
* This class acts as a bridge between C++
* and Java. The methods in this class will be
* called back from the RocksDB storage engine (C++)
* we then callback to the appropriate Java method
* this enables Comparators to be implemented in Java.
*
* The design of this Comparator caches the Java Slice
* objects that are used in the compare and findShortestSeparator
* method callbacks. Instead of creating new objects for each callback
* of those functions, by reuse via setHandle we are a lot
* faster; Unfortunately this means that we have to
* introduce independent locking in regions of each of those methods
* via the mutexs mtx_compare and mtx_findShortestSeparator respectively
*/
Improve RocksJava Comparator (#6252) Summary: This is a redesign of the API for RocksJava comparators with the aim of improving performance. It also simplifies the class hierarchy. **NOTE**: This breaks backwards compatibility for existing 3rd party Comparators implemented in Java... so we need to consider carefully which release branches this goes into. Previously when implementing a comparator in Java the developer had a choice of subclassing either `DirectComparator` or `Comparator` which would use direct and non-direct byte-buffers resepectively (via `DirectSlice` and `Slice`). In this redesign there we have eliminated the overhead of using the Java Slice classes, and just use `ByteBuffer`s. The `ComparatorOptions` supplied when constructing a Comparator allow you to choose between direct and non-direct byte buffers by setting `useDirect`. In addition, the `ComparatorOptions` now allow you to choose whether a ByteBuffer is reused over multiple comparator calls, by setting `maxReusedBufferSize > 0`. When buffers are reused, ComparatorOptions provides a choice of mutex type by setting `useAdaptiveMutex`. --- [JMH benchmarks previously indicated](https://github.com/facebook/rocksdb/pull/6241#issue-356398306) that the difference between C++ and Java for implementing a comparator was ~7x slowdown in Java. With these changes, when reusing buffers and guarding access to them via mutexes the slowdown is approximately the same. However, these changes offer a new facility to not reuse mutextes, which reduces the slowdown to ~5.5x in Java. We also offer a `thread_local` mechanism for reusing buffers, which reduces slowdown to ~5.2x in Java (closes https://github.com/facebook/rocksdb/pull/4425). These changes also form a good base for further optimisation work such as further JNI lookup caching, and JNI critical. --- These numbers were captured without jemalloc. With jemalloc, the performance improves for all tests, and the Java slowdown reduces to between 4.8x and 5.x. ``` ComparatorBenchmarks.put native_bytewise thrpt 25 124483.795 ± 2032.443 ops/s ComparatorBenchmarks.put native_reverse_bytewise thrpt 25 114414.536 ± 3486.156 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 17228.250 ± 1288.546 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 16035.865 ± 1248.099 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_reused-64_thread-local thrpt 25 21571.500 ± 871.521 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_adaptive-mutex thrpt 25 23613.773 ± 8465.660 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 16768.172 ± 5618.489 ops/s ComparatorBenchmarks.put java_bytewise_direct_reused-64_thread-local thrpt 25 23921.164 ± 8734.742 ops/s ComparatorBenchmarks.put java_bytewise_non-direct_no-reuse thrpt 25 17899.684 ± 839.679 ops/s ComparatorBenchmarks.put java_bytewise_direct_no-reuse thrpt 25 22148.316 ± 1215.527 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_adaptive-mutex thrpt 25 11311.126 ± 820.602 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_non-adaptive-mutex thrpt 25 11421.311 ± 807.210 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_reused-64_thread-local thrpt 25 11554.005 ± 960.556 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_adaptive-mutex thrpt 25 22960.523 ± 1673.421 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_non-adaptive-mutex thrpt 25 18293.317 ± 1434.601 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_reused-64_thread-local thrpt 25 24479.361 ± 2157.306 ops/s ComparatorBenchmarks.put java_reverse_bytewise_non-direct_no-reuse thrpt 25 7942.286 ± 626.170 ops/s ComparatorBenchmarks.put java_reverse_bytewise_direct_no-reuse thrpt 25 11781.955 ± 1019.843 ops/s ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/6252 Differential Revision: D19331064 Pulled By: pdillinger fbshipit-source-id: 1f3b794e6a14162b2c3ffb943e8c0e64a0c03738
5 years ago
class ComparatorJniCallback : public JniCallback, public Comparator {
public:
ComparatorJniCallback(JNIEnv* env, jobject jcomparator,
const ComparatorJniCallbackOptions* options);
~ComparatorJniCallback();
virtual const char* Name() const;
virtual int Compare(const Slice& a, const Slice& b) const;
virtual void FindShortestSeparator(std::string* start,
const Slice& limit) const;
virtual void FindShortSuccessor(std::string* key) const;
const ComparatorJniCallbackOptions* m_options;
private:
struct ThreadLocalBuf {
ThreadLocalBuf(JavaVM* _jvm, bool _direct_buffer, jobject _jbuf)
: jvm(_jvm), direct_buffer(_direct_buffer), jbuf(_jbuf) {}
JavaVM* jvm;
bool direct_buffer;
jobject jbuf;
};
inline void MaybeLockForReuse(const std::unique_ptr<port::Mutex>& mutex,
const bool cond) const;
inline void MaybeUnlockForReuse(const std::unique_ptr<port::Mutex>& mutex,
const bool cond) const;
jobject GetBuffer(JNIEnv* env, const Slice& src, bool reuse_buffer,
ThreadLocalPtr* tl_buf, jobject jreuse_buffer) const;
jobject ReuseBuffer(JNIEnv* env, const Slice& src,
jobject jreuse_buffer) const;
jobject NewBuffer(JNIEnv* env, const Slice& src) const;
void DeleteBuffer(JNIEnv* env, jobject jbuffer) const;
// used for synchronisation in compare method
std::unique_ptr<port::Mutex> mtx_compare;
// used for synchronisation in findShortestSeparator method
std::unique_ptr<port::Mutex> mtx_shortest;
// used for synchronisation in findShortSuccessor method
std::unique_ptr<port::Mutex> mtx_short;
std::unique_ptr<const char[]> m_name;
jclass m_abstract_comparator_jni_bridge_clazz; // TODO(AR) could we make this
// static somehow?
jclass m_jbytebuffer_clazz; // TODO(AR) we could cache this globally for the
// entire VM if we switch more APIs to use
// ByteBuffer // TODO(AR) could we make this
// static somehow?
jmethodID m_jcompare_mid; // TODO(AR) could we make this static somehow?
jmethodID m_jshortest_mid; // TODO(AR) could we make this static somehow?
jmethodID m_jshort_mid; // TODO(AR) could we make this static somehow?
jobject m_jcompare_buf_a;
jobject m_jcompare_buf_b;
jobject m_jshortest_buf_start;
jobject m_jshortest_buf_limit;
jobject m_jshort_buf_key;
ThreadLocalPtr* m_tl_buf_a;
ThreadLocalPtr* m_tl_buf_b;
};
} // namespace ROCKSDB_NAMESPACE
#endif // JAVA_ROCKSJNI_COMPARATORJNICALLBACK_H_