Commit Graph

5970 Commits

Author SHA1 Message Date
Trustin Lee
824662c6ef Rename fromByte() to valueOf()
Motivation:

Persuit the consistency in method naming

Modifications:

Rename fromByte(byte) to valueOf(byte)

Result:

Consistency
2014-06-24 16:36:21 +09:00
Trustin Lee
0ef87697d5 Fix potential buffer leak in AbstractBinaryMemcacheDecoder
If a connection is closed unexpectedly while
AbstractBinaryMemcacheDecoder decodes a message, the half-constructed
message's content might not be released.
2014-06-24 16:24:48 +09:00
Trustin Lee
ca212c2162 Adhere to our getter/setter naming rules
Motivation:

Persuit for consistent method naming across all classes

Modifications:

Remove 'get' prefix for the getter methods in codec-memcache

Result:

More consistent method naming
2014-06-24 16:08:46 +09:00
Trustin Lee
2f650fdab7 Fix buffer leak in DefaultFullBinaryMemcacheRequest/Response
Motivation:

DefaultFullBinaryMemcacheRequest/Response overrides release(), retain(),
and touch() methods without calling its super, resulting in a leak of
the extras.

Modifications:

When overriding release(), retain(), and touch(), ensure to call super.

Result:

Fixes #2533 by fixing the buffer leak
2014-06-24 15:04:50 +09:00
Idel Pivnitskiy
daa58f74e7 Implement a Bzip2Decoder
Motivation:

Bzip2Decoder provides receiving data compressed in bzip2 format.

Modifications:

Added classes:
- Bzip2Decoder
- Bzip2Constants
- Bzip2BlockDecompressor
- Bzip2HuffmanStageDecoder
- Bzip2MoveToFrontTable
- Bzip2Rand
- Crc32
- Bzip2DecoderTest

Result:

Implemented and tested new decoder which can uncompress incoming data in bzip2 format.
2014-06-24 14:49:49 +09:00
Norman Maurer
35c7f66c48 MessageToByteEncoder always starts with ByteBuf that use initalCapacity == 0
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.
2014-06-24 13:55:34 +09:00
Norman Maurer
9fb6fb3236 Make use of HttpChunkedInput as this will also work when compression is used 2014-06-23 09:39:50 +02:00
Trustin Lee
d25ed3f0e7 Revert "Improve the allocation algorithm in PoolChunk"
This reverts commit 36305d7dce, which
seems to cause an assertion failure on our CI machine.
2014-06-21 19:18:45 +09:00
Trustin Lee
38de4d81ed Make sure OpenSslEngine is tested against transport-native-epoll 2014-06-21 18:28:07 +09:00
Trustin Lee
a874062434 Remove padding utility classes
- It's not used anywhere
2014-06-21 18:00:01 +09:00
Trustin Lee
5409b560e3 Add missing last padding / Comment 2014-06-21 17:55:38 +09:00
Trustin Lee
a2400d9eb2 Checkstyle / Overall clean-up / Fix serialization 2014-06-21 17:54:22 +09:00
nitsanw
0925bc3e79 Fix false sharing between head and tail reference in MpscLinkedQueue
Motivation:

The tail node reference writes (by producer threads) are very likely to
invalidate the cache line holding the headRef which is read by the
consumer threads in order to access the padded reference to the head
node. This is because the resulting layout for the object is:

- header
- Object AtomicReference.value -> Tail node
- Object MpscLinkedQueue.headRef -> PaddedRef -> Head node

This is 'passive' false sharing where one thread reads and the other
writes.  The current implementation suffers from further passive false
sharing potential from any and all neighbours to the queue object as no
pre/post padding is provided for the class fields.

Modifications:

Fix the memory layout by adding pre-post padding for the head node and
putting the tail node reference in the same object.

Result:

Fixed false sharing
2014-06-21 17:54:22 +09:00
Trustin Lee
db53e67ab7 Mqtt -> MQTT 2014-06-21 17:14:20 +09:00
Trustin Lee
3ad96d647c Fix test failures due to incorrect validation 2014-06-21 17:11:08 +09:00
Trustin Lee
365b3f5e11 Rename io.netty.util.collection.Collections to PrimitiveCollections
Motivation:

An IDE's auto-completion often confuses between java.util.Collections
and io.netty.util.collection.Collections, and it's annoying to me. :-)

Modifications:

Use a different class name.

Result:

When I type Collections, it's always 'the' Collections.
2014-06-21 16:57:06 +09:00
Trustin Lee
a49c4518c0 Overall clean-up on codec-mqtt
- Use simple string concatenation instead of String.format()
- Rewrite exception messages so that it follows our style
- Merge MqttCommonUtil and MqttValidationUtil into MqttCodecUtil
- Hide MqttCodecUtil from users
- Rename MqttConnectReturnCode.value to byteValue
- Rename MqttMessageFactory.create*() to new*()
- Rename QoS to MqttQoS
- Make MqttSubAckPayload.grantedQoSLevels immutable and add more useful
  constructor
2014-06-21 16:51:37 +09:00
Mousom Dhar Gupta
9325b9121c Add MQTT protocol codec
MQTT is a open source protocol on top of TCP which is widely used in
mobile communication and also for IoT (Internet of Things) today. This
will add an open source implementation of MQTT so that it becomes easier
for Netty users to implement an MQTT application.

For more information about the MQTT protocol, read this:

http://public.dhe.ibm.com/software/dw/webservices/ws-mqtt/mqtt-v3r1.html
2014-06-21 16:51:37 +09:00
Trustin Lee
5859933de0 Checkstyle 2014-06-21 16:03:57 +09:00
Trustin Lee
75152ea864 Overall refactoring of the haproxy codec
- Convert constant classes to enum
- Rename HAProxyProtocolMessage to HAProxyMessage for simpilicity
- Rename HAProxyProtocolDecoder to HAProxyMessageDecoder
- Rename HAProxyProtocolCommand to HAProxyCommand
- Merge ProxiedProtocolAndFamity, ProxiedAddressFamily, and
  ProxiedTransportProtocol into HAProxiProxiedProtocol and its inner
  enums
- Overall clean-up
2014-06-21 15:58:53 +09:00
Trustin Lee
f4d6970e87 Move haproxy codec to a separate module 2014-06-21 15:58:53 +09:00
Jon Keys
bea5d0321a Add HAProxy protocol decoder
Motivation:

The proxy protocol provides client connection information for proxied
network services. Several implementations exist (e.g. Haproxy, Stunnel,
Stud, Postfix), but the primary motivation for this implementation is to
support the proxy protocol feature of Amazon Web Services Elastic Load
Balancing.

Modifications:

This commit adds a proxy protocol decoder for proxy protocol version 1
as specified at:

  http://haproxy.1wt.eu/download/1.5/doc/proxy-protocol.txt

The foundation for version 2 support is also in this commit but it is
explicitly NOT supported due to a lack of external implementations to
test against.

Result:

The proxy protocol decoder can be used to send client connection
information to inbound handlers in a channel pipeline from services
which support the proxy protocol.
2014-06-21 15:58:53 +09:00
Trustin Lee
87346d14a8 Fix the inconsistencies between performance tests in ByteBufAllocatorBenchmark
Motivation:

default*() tests are performing a test in a different way, and they must be same with other tests.

Modification:

Make sure default*() tests are same with the others

Result:

Easier to compare default and non-default allocators
2014-06-21 13:27:28 +09:00
Pavan Kumar
36305d7dce Improve the allocation algorithm in PoolChunk
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
2014-06-21 13:20:03 +09:00
Norman Maurer
fa5e602238 [#2589] LocalServerChannel.doClose() throws NPE when localAddress == null
Motivation:

LocalServerChannel.doClose() calls LocalChannelRegistry.unregister(localAddress); without check if localAddress is null and so produce a NPE when pass null the used ConcurrentHashMapV8

Modification:
Check for localAddress != null before try to remove it from Map. Also added a unit test which showed the stacktrace of the error.

Result:

No more NPE during doClose().
2014-06-20 20:13:50 +02:00
Norman Maurer
c44b5f54fb Remove System.out.println(...) debug messages 2014-06-20 19:42:47 +02:00
Norman Maurer
4e36c0ae96 [#2580] [#2587] Fix buffer corruption regression when ByteBuf.order(LITTLE_ENDIAN) is used
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.
2014-06-20 18:19:45 +02:00
Norman Maurer
f341562b91 [#2586] Use correct EventLoop to notify delayed successful registration
Motivation:

At the moment AbstractBoostrap.bind(...) will always use the GlobalEventExecutor to notify the returned ChannelFuture if the registration is not done yet. This should only be done if the registration fails later. If it completes successful we should just notify with the EventLoop of the Channel.

Modification:

Use EventLoop of the Channel if possible to use the correct Thread to notify and so guaranteer the right order of events.

Result:

Use the correct EventLoop for notification
2014-06-20 17:05:54 +02:00
nmittler
217a666b1f Grab-bag of minor changes to HTTP/2
Motivation:

Various small fixes/improvements to the interface to the HTTP/2 classes,
as well as some minor performance improvements.

Modifications:

- Added fix for IntObjectHashMap to ensure that capacity is always odd.
Even capacity can cause probing to fail.
- Cleaned the access to GOAWAY information in Http2Connection interface.
Endpoints now manage their own state for GOAWAY. Also added a goingAway
event handler.
- Added Endpoint methods for checking MAX_CONCURRENT_STREAMS or if the
number of streams for the endpoint have been exhausted. See
Endpoint.nextStreamId()/acceptingNewStreams().
- Changed DefaultHttp2Connection to use IntObjectHashMap. This should be
a slight memory improvement.
- Fixed check for MAX_CONCURRENT_STREAMS to correctly use the number of
active streams for the endpoint (not total active). See
DefaultHttp2Connection.checkNewStreamAllowed.
- Exposing a few methods to subclasses of AbstractHttp2ConnectionHandler
(e.g. exception handling).
- Cleaning up GOAWAY and RST_STREAM handling in
AbstractHttp2ConnectionHandler.

Result:

HTTP/2 code should provide more information to subclasses and will have
a reduced memory footprint.
2014-06-19 20:00:26 +02:00
Trustin Lee
760bbc7ea6 Refactor FastThreadLocal to simplify TLV management
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.
2014-06-19 21:17:46 +09:00
Norman Maurer
55b6f7129c Small improvement in SimpleChannelInboundHandlerAdapter javadoc 2014-06-18 14:49:50 +02:00
Norman Maurer
9160ceb921 Make use of AtomicLongFieldUpdater.addAndGet(...) for cleaner code
Motivation:

The code in ChannelOutboundBuffer can be simplified by using AtomicLongFieldUpdater.addAndGet(...)

Modification:

Replace our manual looping with AtomicLongFieldUpdater.addAndGet(...)

Result:

Cleaner code
2014-06-17 20:15:44 +02:00
Norman Maurer
2c7ecb444d Move calculateNewCapacity(...) to ByteBufAllocator
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.
2014-06-17 09:32:46 +02:00
Norman Maurer
fe91aea655 [#2577] ChannelOutboundBuffer.addFlush() unnecessary loop through all entries on multiple calls
Motivation:

If ChannelOutboundBuffer.addFlush() is called multiple times and flushed != unflushed it will still loop through all entries that are not flushed yet even if it is not needed anymore as these were marked uncancellable before.

Modifications:

Check if new messages were added since addFlush() was called and only if this was the case loop through all entries and try to mark the uncancellable.

Result:

Less overhead when ChannelOuboundBuffer.addFlush() is called multiple times without new messages been added.
2014-06-17 09:32:14 +02:00
Trustin Lee
9a169f5865 Fix incorrect method signature of awaitInactivity()
- Related: #2084
2014-06-17 15:59:11 +09:00
Norman Maurer
a2ec2a1e3a [#2573] UnpooledUnsafeDirectByteBuf.setBytes(int,ByteBuf,int,int) fails to use fast-path when src has array
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.
2014-06-16 11:11:17 +02:00
nmittler
376f4b2516 Adding int-to-object map implementation.
Motivation:

Maps with integer keys are used in several places (HTTP/2 code, for
example). To reduce the memory footprint of these structures, we need a
specialized map class that uses ints as keys.

Modifications:

Added IntObjectHashMap, which is uses open addressing and double hashing
for collision resolution.

Result:

A new int-based map class that can be shared across Netty.
2014-06-16 10:32:16 +02:00
Norman Maurer
9f1999b81d [#2572] Correctly calculate length of output buffer before inflate to fix IndexOutOfBoundException
Motivation:

JdkZlibDecoder fails to decode because the length of the output buffer is not calculated correctly.
This can cause an IndexOutOfBoundsException or data-corruption when the PooledByteBuffAllocator is used.

Modifications:

Correctly calculate the length

Result:

No more IndexOutOfBoundsException or data-corruption.
2014-06-16 10:20:39 +02:00
Phil.Baxter
b7f591c38a export sun security packages as optional 2014-06-15 21:01:20 +02:00
Trustin Lee
fb5464a544 Use FastThreadLocal in more places 2014-06-14 17:45:43 +09:00
Trustin Lee
de2872f7f7 Introduce TextHeaders and AsciiString
Motivation:

We have quite a bit of code duplication between HTTP/1, HTTP/2, SPDY,
and STOMP codec, because they all have a notion of 'headers', which is a
multimap of string names and values.

Modifications:

- Add TextHeaders and its default implementation
- Add AsciiString to replace HttpHeaderEntity
  - Borrowed some portion from Apache Harmony's java.lang.String.
- Reimplement HttpHeaders, SpdyHeaders, and StompHeaders using
  TextHeaders
- Add AsciiHeadersEncoder to reuse the encoding a TextHeaders
  - Used a dedicated encoder for HTTP headers for better performance
    though
- Remove shortcut methods in SpdyHeaders
- Remove shortcut methods in SpdyHttpHeaders
- Replace SpdyHeaders.getStatus() with HttpResponseStatus.parseLine()

Result:

- Removed quite a bit of code duplication in the header implementations.
- Slightly better performance thanks to improved header validation and
  hash code calculation
2014-06-14 17:14:30 +09:00
belliottsmith
7d37af5dfb Introduce FastThreadLocal which uses an EnumMap and a predefined fixed set of possible thread locals
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
2014-06-13 11:02:16 +02:00
nmittler
1d8c7ff52e Addings helper methods to HTTP/2 handler
Motivation:

Subclasses of AbstractHttp2ConnectionHandler have to implement all frame
handler methods, many of which can be ignored in many cases.  Also there
is no easy way to access the connection object.

Modifications:

Added default implementations for frame handler methods to
AbstractHttp2ConnectionHandler, and added an accessor for the
connection.

Also fixed example test for HTTP/2 with cleartext upgrade. It must have
been broken by recent commits.

Result:

AbstractHttp2ConnectionHandler is more subclass-friendly.
2014-06-12 20:52:55 +02:00
Norman Maurer
c4d585420f Make sure cancelled Timeouts are able to be GC'ed fast.
Motivation:
At the moment the HashedWheelTimer will only remove the cancelled Timeouts once the HashedWheelBucket is processed again. Until this the instance will not be able to be GC'ed as there are still strong referenced to it even if the user not reference it by himself/herself. This can cause to waste a lot of memory even if the Timeout was cancelled before.

Modification:
Add a new queue which holds CancelTasks that will be processed on each tick to remove cancelled Timeouts. Because all of this is done only by the WorkerThread there is no need for synchronization and only one extra object creation is needed when cancel() is executed. For addTimeout(...) no new overhead is introduced.

Result:
Less memory usage for cancelled Timeouts.
2014-06-10 12:49:56 +02:00
Norman Maurer
6b17aaad71 Optimize DefaultChannelPipeline in terms of memory usage and initialization time
Motivation:
Each of DefaultChannelPipeline instance creates an head and tail that wraps a handler. These are used to chain together other DefaultChannelHandlerContext that are created once a new ChannelHandler is added. There are a few things here that can be improved in terms of memory usage and initialization time.

Modification:
- Only generate the name for the tail and head one time as it will never change anyway
- Only compute the skipFlags for the tail and head one time as it will never change
- Rename DefaultChannelHandlerContext to AbstractChannelHandlerContext and make it abstract
- Create a new DefaultChannelHandlerContext that is used when a ChannelHandler is added to the DefaultChannelPipeline
- Rename TailHandler to TailContext and HeadHandler to HeadContext and let them extend AbstractChannelHandlerContext. This way we can save 2 object creations per DefaultChannelPipeline

Result:
- Less memory usage because we have 2 less objects per DefaultChannelPipeline
- Faster creation of DefaultChannelPipeline as we not need to compute the skipFlags and not need to generate the name for the head and tail
2014-06-10 10:01:40 +02:00
Norman Maurer
805ba157e4 DNS codec for Netty which is based on the work of [#1622].
Motivation:
As part of GSOC 2013 we had @mbakkar working on a DNS codec but did not integrate it yet as it needs some cleanup. This commit is based on @mbakkar's work and provide the codec for DNS.

Modifications:
Add DNS codec

Result:
Reusable DNS codec will be included in netty.

This PR also includes a AsynchronousDnsResolver which allows to resolve DNS entries in a non blocking way by make use
of the dns codec and netty transport itself.
2014-06-10 09:47:25 +02:00
Frederic Bregier
89ed1517f5 [#2542] HTTP post request decoder does not support quoted boundaries
Motivation:
According to RFC2616 section 19, boundary string could be quoted, but
currently the PostRequestDecoder does not support it while it should.

Modifications:
Once the boundary is found, one check is made to verify if the boundary
is "quoted", and if so, it is "unqoted".

Note: in following usage of this boundary (as delimiter), quote seems no
more allowed according to the same RFC, so the reason that only the
boundary definition is corrected.

Result:
Now the boundary could be whatever quoted or not. A Junit test case
checks it.
2014-06-08 12:07:44 +02:00
Frederic Bregier
c16de8fcbc [#2544] Correctly parse Multipart-mixed POST HTTP request in case of entity ends with odd number of 0x0D
Motivation:
When an attribute is ending with an odd number of CR (0x0D), the decoder
add an extra CR in the decoded attribute and should not.

Modifications:
Each time a CR is detected, the next byte was tested to be LF or not. If
not, in a number of places, the CR byte was lost while it should not be.
When a CR is detected, if the next byte is not LF, the CR byte should be
saved as the position point to the next byte (not LF). When a CR is
detected, if there is not yet other available bytes, the position is
reset to the position of CR (since a LF could follow).

A new Junit test case is added, using DECODER and variable number of CR
in the final attribute (testMultipartCodecWithCRasEndOfAttribute).

Result:
The attribute is now correctly decoded with the right number of CR
ending bytes.
2014-06-08 11:22:51 +02:00
nmittler
bcb180b08d Reducing memory usage for HTTP/2
Motivation:

The connection, priority tree, and inbound/outbound flow controllers
each maintain a separate map for stream information. This is wasteful
and complicates the design since as streams are added/removed, multiple
structures have to be updated.

Modifications:

- Merging the priority tree into Http2Connection. Then we can use
Http2Connection as the central stream repository.

- Adding observer pattern to Http2Connection so flow controllers can be
told when a new stream is created, closed, etc.

- Adding properties for inboundFlow/outboundFlow state to Http2Stream.
This allows the controller to access flow control state directly from
the stream without requiring additional structures.

- Separate out the StreamRemovalPolicy and created a "default"
implementation that runs periodic garbage collection.  This used to be
internal to the outbound flow controller, but I think it is more general
than that.

Result:

HTTP/2 classes will require less storage for new streams.
2014-06-06 20:52:51 +02:00
Norman Maurer
405d573715 [#2436] Unsafe*ByteBuf implementation should only invert bytes if ByteOrder differ from native ByteOrder
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.
2014-06-05 10:59:03 +02:00