Motivation:
At the moment we have two problems:
- CompositeByteBuf.addComponent(...) will not add the supplied buffer to the CompositeByteBuf if its empty, which means it will not be released on CompositeByteBuf.release() call. This is a problem as a user will expect everything added will be released (the user not know we not added it).
- CompositeByteBuf.addComponents(...) will either add no buffers if none is readable and so has the same problem as addComponent(...) or directly release the ByteBuf if at least one ByteBuf is readable. Again this gives inconsistent handling and may lead to memory leaks.
Modifications:
- Always add the buffer to the CompositeByteBuf and so release it on release call.
Result:
Consistent handling and no buffer leaks.
Motivation:
When a CompositeByteBuf is empty (i.e. has no component), its internal
memory access operations do not always behave as expected.
Modifications:
Check if the nunmber of components is zero. If so, return an empty
array or an empty NIO buffer, etc.
Result:
More robustness
- Ensure an EmptyByteBuf has an array, an NIO buffer, and a memory
address at the same time
- Add an assertion that checks if EMPTY_BUFFER is an EmptyByteBuf,
just in case we make a mistake in the future
Motivation:
We expose no methods in ByteBuf to directly write a CharSequence into it. This leads to have the user either convert the CharSequence first to a byte array or use CharsetEncoder. Both cases have some overheads and we can do a lot better for well known Charsets like UTF-8 and ASCII.
Modifications:
Add ByteBufUtil.writeAscii(...) and ByteBufUtil.writeUtf8(...) which can do the task in an optimized way. This is especially true if the passed in ByteBuf extends AbstractByteBuf which is true for all of our implementations which not wrap another ByteBuf.
Result:
Writing an ASCII and UTF-8 CharSequence into a AbstractByteBuf is a lot faster then what the user could do by himself as we can make use of some package private methods and so eliminate reference and range checks. When the Charseq is not ASCII or UTF-8 we can still do a very good job and are on par in most of the cases with what the user would do.
The following benchmark shows the improvements:
Result: 2456866.966 ?(99.9%) 59066.370 ops/s [Average]
Statistics: (min, avg, max) = (2297025.189, 2456866.966, 2586003.225), stdev = 78851.914
Confidence interval (99.9%): [2397800.596, 2515933.336]
Benchmark Mode Samples Score Score error Units
i.n.m.b.ByteBufUtilBenchmark.writeAscii thrpt 50 9398165.238 131503.098 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeAsciiString thrpt 50 9695177.968 176684.821 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeAsciiStringViaArray thrpt 50 4788597.415 83181.549 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeAsciiStringViaArrayWrapped thrpt 50 4722297.435 98984.491 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeAsciiStringWrapped thrpt 50 4028689.762 66192.505 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeAsciiViaArray thrpt 50 3234841.565 91308.009 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeAsciiViaArrayWrapped thrpt 50 3311387.474 39018.933 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeAsciiWrapped thrpt 50 3379764.250 66735.415 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8 thrpt 50 5671116.821 101760.081 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8String thrpt 50 5682733.440 111874.084 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8StringViaArray thrpt 50 3564548.995 55709.512 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8StringViaArrayWrapped thrpt 50 3621053.671 47632.820 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8StringWrapped thrpt 50 2634029.071 52304.876 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8ViaArray thrpt 50 3397049.332 57784.119 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8ViaArrayWrapped thrpt 50 3318685.262 35869.562 ops/s
i.n.m.b.ByteBufUtilBenchmark.writeUtf8Wrapped thrpt 50 2473791.249 46423.114 ops/s
Tests run: 1, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 1,387.417 sec - in io.netty.microbench.buffer.ByteBufUtilBenchmark
Results :
Tests run: 1, Failures: 0, Errors: 0, Skipped: 0
Results :
Tests run: 1, Failures: 0, Errors: 0, Skipped: 0
The *ViaArray* benchmarks are basically doing a toString().getBytes(Charset) which the others are using ByteBufUtil.write*(...).
Motivation:
CompositeByteBuf.nioBuffers(...) returns an empty ByteBuffer array if the specified length is 0. This is not consistent with other ByteBuf implementations which return an ByteBuffer array of size 1 with an empty ByteBuffer included.
Modifications:
Make CompositeByteBuf.nioBuffers(...) consistent with other ByteBuf implementations.
Result:
Consistent and correct behaviour of nioBufffers(...)
Motivation:
When calling slice(...) on a ByteBuf the returned ByteBuf should be the slice of a ByteBuf and shares it's reference count. This is important as it is perfect legal to use buf.slice(...).release() and have both, the slice and the original ByteBuf released. At the moment this is only the case if the requested slice size is > 0. This makes the behavior inconsistent and so may lead to a memory leak.
Modifications:
- Never return Unpooled.EMPTY_BUFFER when calling slice(...).
- Adding test case for buffer.slice(...).release() and buffer.duplicate(...).release()
Result:
Consistent behaviour and so no more leaks possible.
Motivation:
Before we missed to check if a buffer was released before we return the backing byte array or memoryaddress. This could lead to JVM crashes when someone tried various bulk operations on the Unsafe*ByteBuf implementations.
Modifications:
Always check if the buffer is released before all to return the byte array and memoryaddress.
Result:
No more JVM crashes because of released buffers when doing bulk operations on Unsafe*ByteBuf implementations.
Motivation:
Found performance issues via FindBugs and PMD.
Modifications:
- Removed unnecessary boxing/unboxing operations in DefaultTextHeaders.convertToInt(CharSequence) and DefaultTextHeaders.convertToLong(CharSequence). A boxed primitive is created from a string, just to extract the unboxed primitive value.
- Added a static modifier for DefaultHttp2Connection.ParentChangedEvent class. This class is an inner class, but does not use its embedded reference to the object which created it. This reference makes the instances of the class larger, and may keep the reference to the creator object alive longer than necessary.
- Added a static compiled Pattern to avoid compile it each time it is used when we need to replace some part of authority.
- Improved using of StringBuilders.
Result:
Performance improvements.
Motivation:
We introduced a PoolThreadCache which is used in our PooledByteBufAllocator to reduce the synchronization overhead on PoolArenas when allocate / deallocate PooledByteBuf instances. This cache is used for both the allocation path and deallocation path by:
- Look for cached memory in the PoolThreadCache for the Thread that tries to allocate a new PooledByteBuf and if one is found return it.
- Add the memory that is used by a PooledByteBuf to the PoolThreadCache of the Thread that release the PooledByteBuf
This works out very well when all allocation / deallocation is done in the EventLoop as the EventLoop will be used for read and write. On the otherside this can lead to surprising side-effects if the user allocate from outside the EventLoop and and pass the ByteBuf over for writing. The problem here is that the memory will be added to the PoolThreadCache that did the actual write on the underlying transport and not on the Thread that previously allocated the buffer.
Modifications:
Don't cache if different Threads are used for allocating/deallocating
Result:
Less confusing behavior for users that allocate PooledByteBufs from outside the EventLoop.
Motivation:
When MemoryRegionCache.trim() is called, some unused cache entries will be freed (started from head). However, in MeoryRegionCache.trim() the head is not updated, which make entry list's head point to an entry whose chunk is null now and following allocate of MeoryRegionCache will return false immediately.
In other word, cache is no longer usable once trim happen.
Modifications:
Update head to correct idx after free entries in trim().
Result:
MemoryRegionCache behaves correctly even after calling trim().
Motivation:
We received a bug-report that the ByteBuf.refCnt() does sometimes not show the correct value when release() and refCnt() is called from different Threads.
Modifications:
Add test-case which shows that all is working like expected
Result:
Test-case added which shows everything is ok.
Related issue: #2028
Motivation:
Some copiedBuffer() methods in Unpooled allocated a direct buffer. An
allocation of a direct buffer is an expensive operation, and thus should
be avoided for unpooled buffers.
Modifications:
- Use heap buffers in all copiedBuffer() methods
Result:
Unpooled.copiedBuffers() are less expensive now.
Motivation:
While porting some changes from 4.0 to 4.1 and master branch I changed the default allocator from pooled to unpooled by mistake. This should be reverted. The guilty commit is 4a3ef90381.
Thanks to @blucas for spotting this.
Modifications:
Revert changes related to allocator.
Result:
Use the correct default allocator again.
Motivation:
We did various changes related to the ChannelOutboundBuffer in 4.0 branch. This commit port all of them over and so make sure our branches are synced in terms of these changes.
Related to [#2734], [#2709], [#2729], [#2710] and [#2693] .
Modification:
Port all changes that was done on the ChannelOutboundBuffer.
This includes the port of the following commits:
- 73dfd7c01b
- 997d8c32d2
- e282e504f1
- 5e5d1a58fd
- 8ee3575e72
- d6f0d12a86
- 16e50765d1
- 3f3e66c31a
Result:
- Less memory usage by ChannelOutboundBuffer
- Same code as in 4.0 branch
- Make it possible to use ChannelOutboundBuffer with Channel implementation that not extends AbstractChannel
Modifications:
- Added a static modifier for CompositeByteBuf.Component.
This class is an inner class, but does not use its embedded reference to the object which created it. This reference makes the instances of the class larger, and may keep the reference to the creator object alive longer than necessary.
- Removed unnecessary boxing/unboxing operations in HttpResponseDecoder, RtspResponseDecoder, PerMessageDeflateClientExtensionHandshaker and PerMessageDeflateServerExtensionHandshaker
A boxed primitive is created from a String, just to extract the unboxed primitive value.
- Removed unnecessary 3 times calculations in DiskAttribute.addContent(...).
- Removed unnecessary checks if file exists before call mkdirs() in NativeLibraryLoader and PlatformDependent.
Because the method mkdirs() has this check inside.
- Removed unnecessary `instanceof AsciiString` check in StompSubframeAggregator.contentLength(StompHeadersSubframe) and StompSubframeDecoder.getContentLength(StompHeaders, long).
Because StompHeaders.get(CharSequence) always returns java.lang.String.
Motivation:
I introduced ensureAccessible() class as part of 6c47cc9711 in some places. Unfortunally I also added some where these are not needed and so caused a performance regression.
Modification:
Remove calls where not needed.
Result:
Fixed performance regression.
Motivation:
I introduced range checks as part of 6c47cc9711 in some places. Unfortunally I also added some where these are not needed and so caused a performance regression.
Modification:
Remove range checks where not needed
Result:
Fixed performance regression.
Motivation:
CompositeByteBuf.deallocate generates unnecessary GC pressure when using the 'foreach' loop, as a 'foreach' loop creates an iterator when looping.
Modification:
Convert 'foreach' loop into regular 'for' loop.
Result:
Less GC pressure (and possibly more throughput) as the 'for' loop does not create an iterator
Motivation:
AbstractByteBufTest.testInternalBuffer() uses writeByte() operations to
populate the sample data. Usually, this isn't a problem, but it starts
to take a lot of time when the resource leak detection level gets
higher.
In our CI machine, testInternalBuffer() takes more than 30 minutes,
causing the build timeout when the 'leak' profile is active (paranoid
level resource detection.)
Modification:
Populate the sample data using ThreadLocalRandom.nextBytes() instead of
using millions of writeByte() operations.
Result:
Test runs much faster when leak detection level is high.
Motivation:
Because of how we use reference counting we need to check for the reference count before each operation that touches the underlying memory. This is especially true as we use sun.misc.Cleaner.clean() to release the memory ASAP when possible. Because of this the user may cause a SEGFAULT if an operation is called that tries to access the backing memory after it was released.
Modification:
Correctly check the reference count on all methods that access the underlying memory or expose it via a ByteBuffer.
Result:
Safer usage of ByteBuf
- Using short[] for memoryMap did not improve performance. Reverting
back to the original dual-byte[] structure in favor of simplicity.
- Optimize allocateRun() which yields small performence improvement
- Use local variable when member fields are accessed more than once
Motivation:
Depth-first search is not always efficient for buddy allocation.
Modification:
Employ a new faster search algorithm with different memoryMap layout.
Result:
With thread-local cache disabled, we see a lot of performance
improvment, especially when the size of the allocation is as small as
the page size, which had the largest search space previously.
Motivation:
Persuit for the consistency in method naming
Modifications:
- Remove the 'get' prefix from all HTTP/SPDY message classes
- Fix some inspector warnings
Result:
Consistency
Motivation:
MessageToByteEncoder always starts with ByteBuf that use initalCapacity == 0 when preferDirect is used. This is really wasteful in terms of performance as every first write into the buffer will cause an expand of the buffer itself.
Modifications:
- Change ByteBufAllocator.ioBuffer() use the same default initialCapacity as heapBuffer() and directBuffer()
- Add new allocateBuffer method to MessageToByteEncoder that allow the user to do some smarter allocation based on the message that will be encoded.
Result:
Less expanding of buffer and more flexibilty when allocate the buffer for encoding.
Motivation:
Depth-first search is not always efficient for buddy allocation.
Modification:
Employ a new faster search algorithm with different memoryMap layout.
Result:
With thread-local cache disabled, we see a lot of performance
improvment, especially when the size of the allocation is as small as
the page size, which had the largest search space previously:
-- master head --
Benchmark (size) Mode Score Error Units
pooledDirectAllocAndFree 8192 thrpt 215.392 1.565 ops/ms
pooledDirectAllocAndFree 16384 thrpt 594.625 2.154 ops/ms
pooledDirectAllocAndFree 65536 thrpt 1221.520 18.965 ops/ms
pooledHeapAllocAndFree 8192 thrpt 217.175 1.653 ops/ms
pooledHeapAllocAndFree 16384 thrpt 587.250 14.827 ops/ms
pooledHeapAllocAndFree 65536 thrpt 1217.023 44.963 ops/ms
-- changes --
Benchmark (size) Mode Score Error Units
pooledDirectAllocAndFree 8192 thrpt 3656.744 94.093 ops/ms
pooledDirectAllocAndFree 16384 thrpt 4087.152 22.921 ops/ms
pooledDirectAllocAndFree 65536 thrpt 4058.814 29.276 ops/ms
pooledHeapAllocAndFree 8192 thrpt 3640.355 44.418 ops/ms
pooledHeapAllocAndFree 16384 thrpt 4030.206 24.365 ops/ms
pooledHeapAllocAndFree 65536 thrpt 4103.991 70.991 ops/ms
Motivation:
To improve the speed of ByteBuf with order LITTLE_ENDIAN and where the native order is also LITTLE_ENDIAN (intel) we introduces a new special SwappedByteBuf before in commit 4ad3984c8b. Unfortunally the commit has a flaw which does not handle correctly the case when a ByteBuf expands. This was caused because the memoryAddress was cached and never changed again even if the underlying buffer expanded. This can lead to corrupt data or even to SEGFAULT the JVM if you are lucky enough.
Modification:
Always lookup the actual memoryAddress of the wrapped ByteBuf.
Result:
No more data-corruption for ByteBuf with order LITTLE_ENDIAN and no JVM crashes.
Motivation:
When Netty runs in a managed environment such as web application server,
Netty needs to provide an explicit way to remove the thread-local
variables it created to prevent class loader leaks.
FastThreadLocal uses different execution paths for storing a
thread-local variable depending on the type of the current thread.
It increases the complexity of thread-local removal.
Modifications:
- Moved FastThreadLocal and FastThreadLocalThread out of the internal
package so that a user can use it.
- FastThreadLocal now keeps track of all thread local variables it has
initialized, and calling FastThreadLocal.removeAll() will remove all
thread-local variables of the caller thread.
- Added FastThreadLocal.size() for diagnostics and tests
- Introduce InternalThreadLocalMap which is a mixture of hard-wired
thread local variable fields and extensible indexed variables
- FastThreadLocal now uses InternalThreadLocalMap to implement a
thread-local variable.
- Added ThreadDeathWatcher.unwatch() so that PooledByteBufAllocator
tells it to stop watching when its thread-local cache has been freed
by FastThreadLocal.removeAll().
- Added FastThreadLocalTest to ensure that removeAll() works
- Added microbenchmark for FastThreadLocal and JDK ThreadLocal
- Upgraded to JMH 0.9
Result:
- A user can remove all thread-local variables Netty created, as long as
he or she did not exit from the current thread. (Note that there's no
way to remove a thread-local variable from outside of the thread.)
- FastThreadLocal exposes more useful operations such as isSet() because
we always implement a thread local variable via InternalThreadLocalMap
instead of falling back to JDK ThreadLocal.
- FastThreadLocalBenchmark shows that this change improves the
performance of FastThreadLocal even more.
Motivation:
Currently we have the algorithm of calculate the new capacity of a ByteBuf implemented in AbstractByteBuf. The problem with this is that it is impossible for a user to change it if it not fits well it's use-case. We should better move it to ByteBufAllocator and so let the user implement it's own by either write his/her own ByteBufAllocator or just override the default implementation in one of our provided ByteBufAllocators.
Modifications:
Move calculateNewCapacity(...) to ByteBufAllocator and move the implementation (which was part of AbstractByteBuf) to AbstractByteBufAllocator.
Result:
The user can now override the default calculation algorithm when needed.
Motivation:
UnpooledUnsafeDirectByteBuf.setBytes(int,ByteBuf,int,int) fails to use fast-path when src uses an array as backing storage. This is because the if else uses the wrong ByteBuf for its check.
Modifications:
- Use correct ByteBuf when check for array as backing storage
- Also eliminate unecessary check in UnpooledDirectByteBuf which always fails anyway
Result:
Faster setBytes(...) when src ByteBuf is backed by an array.
No more IndexOutOfBoundsException or data-corruption.
Motivation:
Provide a faster ThreadLocal implementation
Modification:
Add a "FastThreadLocal" which uses an EnumMap and a predefined fixed set of possible thread locals (all of the static instances created by netty) that is around 10-20% faster than standard ThreadLocal in my benchmarks (and can be seen having an effect in the direct PooledByteBufAllocator benchmark that uses the DEFAULT ByteBufAllocator which uses this FastThreadLocal, as opposed to normal instantiations that do not, and in the new RecyclableArrayList benchmark);
Result:
Improved performance
Motivation:
Our Unsafe*ByteBuf implementation always invert bytes when the native ByteOrder is LITTLE_ENDIAN (this is true on intel), even when the user calls order(ByteOrder.LITTLE_ENDIAN). This is not optimal for performance reasons as the user should be able to set the ByteOrder to LITTLE_ENDIAN and so write bytes without the extra inverting.
Modification:
- Introduce a new special SwappedByteBuf (called UnsafeDirectSwappedByteBuf) that is used by all the Unsafe*ByteBuf implementation and allows to write without inverting the bytes.
- Add benchmark
- Upgrade jmh to 0.8
Result:
The user is be able to get the max performance even on servers that have ByteOrder.LITTLE_ENDIAN as their native ByteOrder.
Motivation:
PooledByteBufAllocator's thread local cache and
ReferenceCountUtil.releaseLater() are in need of a way to run an
arbitrary logic when a certain thread is terminated.
Modifications:
- Add ThreadDeathWatcher, which spawns a low-priority daemon thread
that watches a list of threads periodically (every second) and
invokes the specified tasks when the associated threads are not alive
anymore
- Start-stop logic based on CAS operation proposed by @tea-dragon
- Add debug-level log messages to see if ThreadDeathWatcher works
Result:
- Fixes#2519 because we don't use GlobalEventExecutor anymore
- Cleaner code
Motivation:
If we make allocateRun/SubpageSimple() always try the left node first and make allocateRun/Subpage() always tries the right node first, it is more likely that allocateRun/Subpage() will find a node with ST_UNUSED sooner.
Modifications:
- Make allocateRunSimple() and allocateSubpageSimple() always try the left node first.
- Make allocateRun() and allocateSubpage() always try the right node first.
- Remove randome
Result:
We get the same performance without using random numbers.
Motivation:
We still have a room for improvement in PoolChunk.allocateRun() and
Subpage.allocate().
Modifications:
- Unroll the recursion in PoolChunk.allocateRun()
- Subpage.allocate() makes use of the 'nextAvail' value set by previous
free().
Result:
- PoolChunk.allocateRun() optimization yields 10%+ improvements in
allocation throughput for non-subpage allocations.
- Subpage.allocate() optimization makes the subpage allocations for
tiny buffers as fast as non-tiny buffers even when the pageSize is
huge (e.g. 1048576) because it doesn't need to perform a linear search
in most cases.
Motivation:
4 and 5 were diverged long time ago and we recently reverted some of the
early commits in master. We must make sure 4.1 and master are not very
different now.
Modification:
Fix found differences
Result:
4.1 and master got closer.
Motivation:
PoolArena's 'normalizeCapacity' function was micro-optimized some
time ago to remove a while loop. However, there was a change of
behavior in the function as a result. Capacities passed into it
that are already powers of 2 (and >= 512) are doubled in size. So
if I ask for a buffer with a capacity of 1024, I will get back one
that actually uses 2048 bytes (stored in maxLength).
Aligning to powers of two for book keeping ease is reasonable,
and if someone tries to expand a buffer, you might as well use some
of the previously wasted space. However, since this distinction
between 'easily expanded' and 'costly to expand' space is not
supported at all by the APIs, I cannot imagine this change to
doubling is desirable or intentional.
This is especially costly when using composite buffers. They
frequently allocate components with a capacity that is a power of
2, and they never attempt to expand components themselves. The end
result is that heavy use of pool-backed composite buffers wastes
almost half of the memory pool (the smaller / initial components are
<512 and so are not affected by the off-by-one bug).
Modifications:
Although I find it difficult to believe that such an optimization
is really helpful, I left it in and fixed the off-by-one issue by
decrementing the value at the start.
I also added a simple test to both attempt to verify that the
decrement fixes the issue without introducing any other change, and
to make it easy for a reviewer to test the existing behavior. PoolArena
does not seem to have much testing or testability support though so
the test is kind of a hack and will break for unrelated changes. I
suggest either removing it or factoring out the single non-static
portion of normalizeCapacity so that the fragile dummy PoolArena is
not required.
Result:
Pooled allocators will allocate less resources to the highly
inefficient and undocumented buffer section between length and
maxLength.
Composite buffers of non-trivial size that are backed by pooled
allocators will use about half as much memory.
Motivation:
At the moment we create new ThreadPoolCache whenever a Thread tries either allocate or release something on the PooledByteBufAllocator. When something is released we put it then in its ThreadPoolCache. The problem is we never check if a Thread is not alive anymore and so we may end up with memory that is never freed again if a user create many short living Threads that use the PooledByteBufAllocator.
Modifications:
Periodically check if the Thread is still alive that has a ThreadPoolCache assinged and if not free it.
Result:
Memory is freed up correctly even for short living Threads.
Motivation:
Remove the synchronization bottleneck in PoolArena and so speed up things
Modifications:
This implementation uses kind of the same technics as outlined in the jemalloc paper and jemalloc
blogpost https://www.facebook.com/notes/facebook-engineering/scalable-memory-allocation-using-jemalloc/480222803919.
At the moment we only cache for "known" Threads (that powers EventExecutors) and not for others to keep the overhead
minimal when need to free up unused buffers in the cache and free up cached buffers once the Thread completes. Here
we use multi-level caches for tiny, small and normal allocations. Huge allocations are not cached at all to keep the
memory usage at a sane level. All the different cache configurations can be adjusted via system properties or the constructor
directly where it makes sense.
Result:
Less conditions as most allocations can be served by the cache itself
Motivation:
6e8ba291cf introduced a regression in Android because Android does not have sun.nio.ch.DirectBuffer (see #2330.) I also found PlatformDependent0.freeDirectBuffer() and freeDirectBufferUnsafe() are pretty much same after the commit and the unsafe version should be removed.
Modifications:
- Do not use the pooled allocator in Android because it's too resource hungry for Androids.
- Merge PlatformDependent0.freeDirectBuffer() and freeDirectBufferUnsafe() into one method.
- Make the Unsafe unavailable when sun.nio.ch.DirectBuffer is unavailable. We could keep the Unsafe available and handle the sun.nio.ch.DirectBuffer case separately, but I don't want to complicate our code just because of that. All supported JDK versions have sun.nio.ch.DirectBuffer if the Unsafe is available.
Result:
Simpler code. Fixes Android support (#2330)
Motivation:
I was studying the code and thought this was simpler and easier to
understand.
Modifications:
Replaced the for loop and if conditions, with a simple implementation.
Result:
Code is easier to understand.
Motivation:
When starting with a read-only NIO buffer, wrapping it in a ByteBuf,
and then later retrieving a re-wrapped NIO buffer the limit was getting
too short.
Modifications:
Changed ReadOnlyByteBufferBuf.nioBuffer(int,int) to compute the
limit in the same manner as the internalNioBuffer method.
Result:
Round-trip conversion from NIO to ByteBuf to NIO will work reliably.
- Related: #2163
- Add ResourceLeakHint to allow a user to provide a meaningful information about the leak when touching it
- DefaultChannelHandlerContext now implements ResourceLeakHint to tell where the message is going.
- Cleaner resource leak report by excluding noisy stack trace elements
This implementation does not produce as much GC pressure as CompositeByteBuf and so is prefered,
for writing an array of ByteBufs. Be aware that FixedCompositeByteBuf is readonly.
When using this in a project that make heavy use of CompositeByteBuf for writes we was able to cut
down allocation to a half.
- Fixes#1810
- Add a new interface ChannelId and its default implementation which generates globally unique channel ID.
- Replace AbstractChannel.hashCode with ChannelId.hashCode() and ChannelId.shortValue()
- Add variants of ByteBuf.hexDump() which accept byte[] instead of ByteBuf.
- Remove the reference to ResourceLeak from the buffer implementations
and use wrappers instead:
- SimpleLeakAwareByteBuf and AdvancedLeakAwareByteBuf
- It is now allocator's responsibility to create a leak-aware buffer.
- Added AbstractByteBufAllocator.toLeakAwareBuffer() for easier
implementation
- Add WrappedByteBuf to reduce duplication between *LeakAwareByteBuf and
UnreleasableByteBuf
- Raise the level of leak reports to ERROR - because it will break the
app eventually
- Replace enabled/disabled property with the leak detection level
- Only print stack trace when level is ADVANCED or above to avoid user
confusion
- Add the 'leak' build profile, which enables highly detailed leak
reporting during the build
- Remove ResourceLeakException which is unsed anymore
- Fixes#2003 properly
- Instead of using 'bundle' packaging, use 'jar' packaging. This is
more robust because some strict build tools fail to retrieve the
artifacts from a Maven repository unless their packaging is not 'jar'.
- All artifacts now contain META-INF/io.netty.version.properties, which
provides the detailed information about the build and repository.
- Removed OSGi testsuite temporarily because it gives false errors
during split package test and examination.
- Add io.netty.util.Version for easy retrieval of version information
Beside this it also helps to reduce CPU usage as nioBufferCount() is quite expensive when used on CompositeByteBuf which are
nested and contains a lot of components
that are not assigned to the same EventLoop. In general get* operations should always be safe to be used from different Threads.
This aslo include unit tests that show the issue
This is needed because of otherwise the JDK itself will do an extra ByteBuffer copy with it's own pool implementation. Even worth it will be done
multiple times if the ByteBuffer is always only partial written. With this change the copy is done inside of netty using it's own allocator and
only be done one time in all cases.
- A user can create multiple duplicates of a buffer and access their internal NIO buffers. (e.g. write multiple duplicates to multiple channels assigned to different event loop.) Because the derived buffers' internalNioBuffer() simply delegates the call to the original buffer, all derived buffers and the original buffer's internalNioBuffer() will return the same buffer, which will lead to a race condition.
- Fixes#1739
- 5% improvement in throughput (HelloWorldServer example)
- Made CompositeByteBuf a concrete class (renamed from DefaultCompositeByteBuf) because there's no multiple inheritance in Java
Fixes#1536
- Fixes#1528
It's not really easy to provide a general-purpose abstraction for fast-yet-safe iteration. Instead of making forEachByte() less optimal, let's make it do what it does really well, and allow a user to implement potentially unsafe-yet-fast loop using unsafe operations.
* The problem with the release(..) calls here was that it would have called release on an unsupported message and then throw an exception. This exception will trigger ChannelOutboundBuffer.fail(..), which will also try to release the message again.
* Also use the same exception type for unsupported messages as in other channel impls.
- Related: #1378
- They now accept only one argument.
- A user who wants to use a buffer for more complex use cases, he or she can always access the buffer directly via memoryAddress() and array()
.. by avoiding the overly frequent removal of a subpage from a pool
This change makes sure that the unused subpage is not removed when there's no subpage left in the pool. If the last subpage is removed from the pool, it is very likely that the allocator will create a new subpage very soon again, so it's better not remove it.
- No need to have fine-grained lookup table because the buffer pool has
much more coarse capacities available
- No need to use a loop to normalize a buffer capacity
- Fixes#1445
- Add PlatformDependent.maxDirectMemory()
- Ensure the default number or arenas is decreased if the max memory of the VM is not large enough.
- Related issue: #1397
- Resource leak detection should be turned off and the maxCapacity has to be Integer.MAX_VALUE
- It's technically possible to pool PooledByteBufs with different maxCapacity, which will be addressed in another commit.
The API changes made so far turned out to increase the memory footprint
and consumption while our intention was actually decreasing them.
Memory consumption issue:
When there are many connections which does not exchange data frequently,
the old Netty 4 API spent a lot more memory than 3 because it always
allocates per-handler buffer for each connection unless otherwise
explicitly stated by a user. In a usual real world load, a client
doesn't always send requests without pausing, so the idea of having a
buffer whose life cycle if bound to the life cycle of a connection
didn't work as expected.
Memory footprint issue:
The old Netty 4 API decreased overall memory footprint by a great deal
in many cases. It was mainly because the old Netty 4 API did not
allocate a new buffer and event object for each read. Instead, it
created a new buffer for each handler in a pipeline. This works pretty
well as long as the number of handlers in a pipeline is only a few.
However, for a highly modular application with many handlers which
handles connections which lasts for relatively short period, it actually
makes the memory footprint issue much worse.
Changes:
All in all, this is about retaining all the good changes we made in 4 so
far such as better thread model and going back to the way how we dealt
with message events in 3.
To fix the memory consumption/footprint issue mentioned above, we made a
hard decision to break the backward compatibility again with the
following changes:
- Remove MessageBuf
- Merge Buf into ByteBuf
- Merge ChannelInboundByte/MessageHandler and ChannelStateHandler into ChannelInboundHandler
- Similar changes were made to the adapter classes
- Merge ChannelOutboundByte/MessageHandler and ChannelOperationHandler into ChannelOutboundHandler
- Similar changes were made to the adapter classes
- Introduce MessageList which is similar to `MessageEvent` in Netty 3
- Replace inboundBufferUpdated(ctx) with messageReceived(ctx, MessageList)
- Replace flush(ctx, promise) with write(ctx, MessageList, promise)
- Remove ByteToByteEncoder/Decoder/Codec
- Replaced by MessageToByteEncoder<ByteBuf>, ByteToMessageDecoder<ByteBuf>, and ByteMessageCodec<ByteBuf>
- Merge EmbeddedByteChannel and EmbeddedMessageChannel into EmbeddedChannel
- Add SimpleChannelInboundHandler which is sometimes more useful than
ChannelInboundHandlerAdapter
- Bring back Channel.isWritable() from Netty 3
- Add ChannelInboundHandler.channelWritabilityChanges() event
- Add RecvByteBufAllocator configuration property
- Similar to ReceiveBufferSizePredictor in Netty 3
- Some existing configuration properties such as
DatagramChannelConfig.receivePacketSize is gone now.
- Remove suspend/resumeIntermediaryDeallocation() in ByteBuf
This change would have been impossible without @normanmaurer's help. He
fixed, ported, and improved many parts of the changes.
- Fixes#1364
- Even if a user creates a duplicate/slice, lastAccessed was shared between the derived buffers and it's updated even by a read operation, which made multithread access impossible
- Fixes#1282 (not perfectly, but to the extent it's possible with the current API)
- Add AddressedEnvelope and DefaultAddressedEnvelope
- Make DatagramPacket extend DefaultAddressedEnvelope<ByteBuf, InetSocketAddress>
- Rename ByteBufHolder.data() to content() so that a message can implement both AddressedEnvelope and ByteBufHolder (DatagramPacket does) without introducing two getter methods for the content
- Datagram channel implementations now understand ByteBuf and ByteBufHolder as a message with unspecified remote address.
- Fixes#1315
If a user specifies the arena size of 0, the pool is now disabled
instead of raising an IllegalArgumentException. Using this, you can
disable only heap or direct buffer pool easily. Once disabled,
PooledByteBufAllocator will delegate the allocation request to
UnpooledByteBufAllocator.
- Fixes#1229
- Primarily written by @normanmaurer and revised by @trustin
This commit removes the notion of unfolding from the codec framework
completely. Unfolding was introduced in Netty 3.x to work around the
shortcoming of the codec framework where encode() and decode() did not
allow generating multiple messages.
Such a shortcoming can be fixed by changing the signature of encode()
and decode() instead of introducing an obscure workaround like
unfolding. Therefore, we changed the signature of them in 4.0.
The change is simple, but backward-incompatible. encode() and decode()
do not return anything. Instead, the codec framework will pass a
MessageBuf<Object> so encode() and decode() can add the generated
messages into the MessageBuf.
This pull request provides a framework for exchanging a very large
stream between handlers, typically between a decoder and an inbound
handler (or between a handler that writes a message and an encoder that
encodes that message).
For example, an HTTP decoder, previously, generates multiple
micro-messages to decode an HTTP message (i.e. HttpRequest +
HttpChunks). With the streaming API, The HTTP decoder can simply
generate a single HTTP message whose content is a Stream. And then the
inbound handler can consume the Stream via the buffer you created when
you begin to read the stream. If you create a buffer whose capacity is
bounded, you can handle a very large stream without allocating a lot of
memory. If you just want to wait until the whole content is ready, you
can also do that with an unbounded buffer.
The streaming API also supports a limited form of communication between
a producer (i.e. decoder) and a consumer. A producer can abort the
stream if the stream is not valid anymore. A consumer can choose to
reject or discard the stream, where rejection is for unrecoverable
failure and discard is for recoverable failure.
P.S. Special thanks to @jpinner for the initial input.
- Make PoolSubpage a linked list node in the pool
- Now that a subpage is added to and removed from the pool correctly, allocating a subpage from the pool became vastly simpler.
- Rename directbyDefault to preferDirect
- Add a system property 'io.netty.prederDirect' to allow a user from changing the preference on launch-time
- Merge UnpooledByteBufAllocator.DEFAULT_BY_* to DEFAULT
- Rename ChannelHandlerAdapter to ChannelDuplexHandler
- Add ChannelHandlerAdapter that implements only ChannelHandler
- Rename CombinedChannelHandler to CombinedChannelDuplexHandler and
improve runtime validation
- Remove ChannelInbound/OutboundHandlerAdapter which are not useful
- Make ChannelOutboundByteHandlerAdapter similar to
ChannelInboundByteHandlerAdapter
- Make the tail and head handler of DefaultChannelPipeline accept both
bytes and messages. ChannelHandlerContext.hasNext*() were removed
because they always return true now.
- Removed various unnecessary null checks.
- Correct method/field names:
inboundBufferSuspended -> channelReadSuspended
- Move common methods from ByteBuf to Buf
- Rename ensureWritableBytes() to ensureWritable()
- Rename readable() to isReadable()
- Rename writable() to isWritable()
- Add isReadable(int) and isWritable(int)
- Add AbstractMessageBuf
- Rewrite DefaultMessageBuf and QueueBackedMessageBuf
- based on Josh Bloch's public domain ArrayDeque impl
- Rename message types for clarity
- HttpMessage -> FullHttpMessage
- HttpHeader -> HttpMessage
- HttpRequest -> FullHttpRequest
- HttpResponse -> FulllHttpResponse
- HttpRequestHeader -> HttpRequest
- HttpResponseHeader -> HttpResponse
- HttpContent now extends ByteBufHolder; no more content() method
- Make HttpHeaders abstract, make its header access methods public, and
add DefaultHttpHeaders
- Header accessor methods in HttpMessage and LastHttpContent are
replaced with HttpMessage.headers() and
LastHttpContent.trailingHeaders(). Both methods return HttpHeaders.
- Remove setters wherever possible and remove 'get' prefix
- Instead of calling setContent(), a user can either specify the content
when constructing a message or write content into the buffer.
(e.g. m.content().writeBytes(...))
- Overall cleanup & fixes
Now that we are going to use buffer pooling by default, it is obvious
that a user will forget to call .free() and report memory leak. In this
case, we should have a tool to determine if it is a bug in our allocator
implementation or in the user's code.
This pull request adds a system property flag called
'io.netty.resourceLeakDetection'. If set, when a user forgets to call
.free(), the ResourceLeakDetector will detect it and log a message with
detailed stack trace to tell where the leaked buffer has been allocated.
Because obtaining stack trace is an expensive operation, I used sampling
technique. Allocation is recorded only for every 113th allocation. I
chose 113 because it's a prime number.
In production, a user might not want to enable this option due to
potential performance impact. If a user does not specify the
'-Dio.netty.resourceLeakDetection' option leak detection is disabled.
Even if the leak detection is enabled, the overhead should be less than
5% because only ~1% of allocations are monitored.
I also replaced SharedResourceMisuseDetector with ResourceLeakDetector.
- Add PooledUnsafeDirectByteBuf, a variant of PooledDirectByteBuf, which
accesses its underlying direct ByteBuffer using sun.misc.Unsafe.
- To decouple Netty from sun.misc.*, sun.misc.Unsafe is accessed via
PlatformDependent.
- This change solely introduces about 8+% improvement in direct memory
access according to the tests conducted as described in #918
- Rename capacity variables to reqCapacity or normCapacity to distinguish if its the request capacity or the normalized capacity
- Do not reallocate on ByteBuf.capacity(int) if reallocation is unnecessary; just update the index range.
- Revert the workaround in DefaultChannelHandlerContext
- Fixes#826
Unsafe.isFreed(), free(), suspend/resumeIntermediaryAllocations() are not that dangerous. internalNioBuffer() and internalNioBuffers() are dangerous but it seems like nobody is using it even inside Netty. Removing those two methods also removes the necessity to keep Unsafe interface at all.
This pull request introduces the new default ByteBufAllocator implementation based on jemalloc, with a some differences:
* Minimum possible buffer capacity is 16 (jemalloc: 2)
* Uses binary heap with random branching (jemalloc: red-black tree)
* No thread-local cache yet (jemalloc has thread-local cache)
* Default page size is 8 KiB (jemalloc: 4 KiB)
* Default chunk size is 16 MiB (jemalloc: 2 MiB)
* Cannot allocate a buffer bigger than the chunk size (jemalloc: possible) because we don't have control over memory layout in Java. A user can work around this issue by creating a composite buffer, but it's not always a feasible option. Although 16 MiB is a pretty big default, a user's handler might need to deal with the bounded buffers when the user wants to deal with a large message.
Also, to ensure the new allocator performs good enough, I wrote a microbenchmark for it and made it a dedicated Maven module. It uses Google's Caliper framework to run and publish the test result (example)
Miscellaneous changes:
* Made some ByteBuf implementations public so that those who implements a new allocator can make use of them.
* Added ByteBufAllocator.compositeBuffer() and its variants.
* ByteBufAllocator.ioBuffer() creates a buffer with 0 capacity.
* UnsafeByteBuf is gone. I added ByteBuf.unsafe() back.
* To avoid extra instantiation, all ByteBuf implementations implement the ByteBuf.Unsafe interface.
* To hide this implementation detail, all ByteBuf implementations are package-private.
* AbstractByteBuf and SwappedByteBuf are public and they do not implement ByteBuf.Unsafe because they don't need to.
* unwrap() is not an unsafe operation anymore.
* ChannelBuf also has unsafe() and Unsafe. ByteBuf.Unsafe extends ChannelBuf.unsafe(). ChannelBuf.unsafe() provides free() operation so that a user does not need to down-cast the buffer in freeInbound/OutboundBuffer().
To perform writes in AioSocketChannel, we get a ByteBuffer view of the
outbound buffer and specify it as a parameter when we call
AsynchronousSocketChannel.write().
In most cases, the write() operation is finished immediately. However,
sometimes, it is scheduled for later execution. In such a case, there's
a chance for a user's handler to append more data to the outbound
buffer.
When more data is appended to the outbound buffer, the outbound buffer
can expand its capacity by itself. Changing the capacity of a buffer is
basically made of the following steps:
1. Allocate a larger new internal memory region.
2. Copy the current content of the buffer to the new memory region.
3. Rewire the buffer so that it refers to the new region.
4. Deallocate the old memory region.
Because the old memory region is deallocated at the step 4, the write
operation scheduled later will access the deallocated region, leading
all sort of data corruption or even segfaults.
To prevent this situation, I added suspendIntermediaryDeallocations()
and resumeIntermediaryDeallocations() to UnsafeByteBuf.
AioSocketChannel.doFlushByteBuf() now calls suspendIntermediaryDealloc()
to defer the deallocation of the old memory regions until the completion
handler is notified.
An AssertionError is triggered by a ByteBuf when beginRead() attempts to
access the buffer which has been freed already. This commit ensures the
buffer is not freed before performing an I/O operation.
To determine if the buffer has been freed, UnsafeByteBuf.isFreed() has
been added.
This commit introduces a new API for ByteBuf allocation which fixes
issue #643 along with refactoring of ByteBuf for simplicity and better
performance. (see #62)
A user can configure the ByteBufAllocator of a Channel via
ChannelOption.ALLOCATOR or ChannelConfig.get/setAllocator(). The
default allocator is currently UnpooledByteBufAllocator.HEAP_BY_DEFAULT.
To allocate a buffer, do not use Unpooled anymore. do the following:
ctx.alloc().buffer(...); // allocator chooses the buffer type.
ctx.alloc().heapBuffer(...);
ctx.alloc().directBuffer(...);
To deallocate a buffer, use the unsafe free() operation:
((UnsafeByteBuf) buf).free();
The following is the list of the relevant changes:
- Add ChannelInboundHandler.freeInboundBuffer() and
ChannelOutboundHandler.freeOutboundBuffer() to let a user free the
buffer he or she allocated. ChannelHandler adapter classes implement
is already, so most users won't need to call free() by themselves.
freeIn/OutboundBuffer() methods are invoked when a Channel is closed
and deregistered.
- All ByteBuf by contract must implement UnsafeByteBuf. To access an
unsafe operation: ((UnsafeByteBuf) buf).internalNioBuffer()
- Replace WrappedByteBuf and ByteBuf.Unsafe with UnsafeByteBuf to
simplify overall class hierarchy and to avoid unnecesary instantiation
of Unsafe instances on an unsafe operation.
- Remove buffer reference counting which is confusing
- Instantiate SwappedByteBuf lazily to avoid instantiation cost
- Rename ChannelFutureFactory to ChannelPropertyAccess and move common
methods between Channel and ChannelHandlerContext there. Also made it
package-private to hide it from a user.
- Remove unused unsafe operations such as newBuffer()
- Add DetectionUtil.canFreeDirectBuffer() so that an allocator decides
which buffer type to use safely
o Add ByteBuf.hasNioBuffers() method
o Promote CompositeByteBuf.nioBuffers() methods to ByteBuf
o Use ByteBuf.nioBuffers() methods from AioSocketChannel
- Replace ByteBufferBackedByteBuf with DirectByteBuf
- Make DirectByteBuf and HeapByteBuf dynamic
- Remove DynamicByteBuf
- Replace Unpooled.dynamicBuffer() with Unpooled.buffer() and
directBuffer()
- Remove ByteBufFactory (will be replaced with ByteBufPool later)
- Add ByteBuf.Unsafe (might change in the future)
- Removed all methods that requires ByteOrder as a parameter
from Unpooled (formerly ByteBufs/ChannelBuffers)
- Instead, a user calls order(ByteOrder) to get a little endian
version of the user's buffer
- This gives less overwhelming number of methods in Unpooled.
- ChannelInboundHandler and ChannelOutboundHandler does not have a type
parameter anymore.
- User should implement ChannelInboundMessageHandler or
ChannelOutboundMessageHandler.
- Add MessageBuf which replaces java.util.Queue
- Add ChannelBuf which is common type of ByteBuf and ChannelBuf
- ChannelBuffers was renamed to ByteBufs
- Add MessageBufs
- All these changes are going to replace ChannelBufferHolder.
- ChannelBuffer gives a perception that it's a buffer of a
channel, but channel's buffer is now a byte buffer or a message
buffer. Therefore letting it be as is is going to be confusing.
... just like we do with byte arrays. toByteBuffer() and
toByteBuffers() had an indeterministic behavior and thus it could not
tell when the returned NIO buffer is shared or not. nioBuffer() always
returns a view buffer of the Netty buffer. The only case where
hasNioBuffer() returns false and nioBuffer() fails is the
CompositeChannelBuffer, which is not very commonly used and *slow*.
