Commit Graph

476 Commits

Author SHA1 Message Date
Norman Maurer
a32652197b Avoid redundant reads of head in peakNode
Motivation:

There is not need todo redunant reads of head in peakNode as we can just spin on next() until it becomes visible.

Modifications:

Remove redundant reads of head in peakNode. This is based on @nitsanw's patch for akka.
See https://github.com/akka/akka/pull/15596

Result:

Less volatile access.
2014-08-21 09:01:34 +02:00
Norman Maurer
16a8f8b5aa Code-inspection fixes
Motivation:

Saw some code-inspection warnings

Modifications:

Fix warnings

Result:

Less code-inspection warnings
2014-08-21 07:20:00 +02:00
Norman Maurer
ceaab70153 [#2800] Fix NPE in SingleThreadEventExecutor on Android
Motivation:

The recent changes f8bee2e94c to use a FJP introduced a regression on Android that cause a NPE.

Modifications:

- Use AtomicReferenceFieldUpdater so it works also on Android
- Fix inspection warnings

Result:

Netty works again on Android too.
2014-08-21 06:31:56 +02:00
Norman Maurer
d150ee7886 Document the correct default value of SOMAXCONN
Motivation:

Recently we changed the default value of SOMAXCONN that is used when we can not determine it by reading /proc/sys/net/core/somaxconn. While doing this we missed to update the javadocs to reflect the new default value that is used.

Modifications:

List correct default value in the javadocs of SOMAXCONN.

Result:

Correct javadocs.
2014-08-18 05:57:35 +02:00
Trustin Lee
951ff902bd Reduce the fallback SOMAXCONN value
Related issue: #2407

Motivation:

The current fallback SOMAXCONN value is 3072.  It is way too large
comparing to the default SOMAXCONN value of popular OSes.

Modifications:

Decrease the fallback SOMAXCONN value to 128 or 200 depending on the
current OS

Result:

Saner fallback value
2014-08-14 15:40:18 -07:00
Jakob Buchgraber
220660e351 Deregistration of a Channel from an EventLoop
Motivation:

After a channel is created it's usually assigned to an
EventLoop. During the lifetime of a Channel the
EventLoop is then responsible for processing all I/O
and compute tasks of the Channel.

For various reasons (e.g. load balancing) a user might
require the ability for a Channel to be assigned to
another EventLoop during its lifetime.

Modifications:

Introduce under the hood changes that ensure that Netty's
thread model is obeyed during and after the deregistration
of a channel.

Ensure that tasks (one time and periodic) are executed by
the right EventLoop at all times.

Result:

A Channel can be deregistered from one and re-registered with
another EventLoop.
2014-08-11 15:28:46 -07:00
Jakob Buchgraber
f8bee2e94c Make Nio/EpollEventLoop run on a ForkJoinPool
Related issue: #2250

Motivation:

Prior to this commit, Netty's non blocking EventLoops
were each assigned a fixed thread by which all of the
EventLoop's I/O and handler logic would be performed.

While this is a fine approach for most users of Netty,
some advanced users require more flexibility in
scheduling the EventLoops.

Modifications:

Remove all direct usages of threads in MultithreadEventExecutorGroup,
SingleThreadEventExecutor et al., and introduce an Executor
abstraction instead.

The way to think about this change is, that each
iteration of an eventloop is now a task that gets scheduled
in a ForkJoinPool.

While the ForkJoinPool is the default, one also has the
ability to plug in his/her own Executor (aka thread pool)
into a EventLoop(Group).

Result:

Netty hands off thread management to a ForkJoinPool by default.
Users can also provide their own thread pool implementation and
get some control over scheduling Netty's EventLoops
2014-08-11 15:28:46 -07:00
Norman Maurer
7022dcd4a1 [#2744] Fix flakey HashedWheelTimerTest.testExecutionOnTime()
Motivation:

The calculation of the max wait time for HashedWheelTimerTest.testExecutionOnTime() was wrong and so the test sometimes failed.

Modifications:

Fix the max wait time.

Result:

No more test-failures
2014-08-06 07:01:24 +02:00
Trustin Lee
e59ec5384d Fix a bug where ChannelFuture.setFailure(null) doesn't fail
Motivation:

We forgot to do a null check on the cause parameter of
ChannelFuture.setFailure(cause)

Modifications:

Add a null check

Result:

Fixed issue: #2728
2014-08-05 11:23:52 -07:00
Norman Maurer
4a3ef90381 Port ChannelOutboundBuffer and related changes from 4.0
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
2014-08-05 15:00:56 +02:00
Trustin Lee
2b12640960 More brief somaxconn logging
- Consistent log message format
- Avoid unnecessary autoboxing when debug level is off
- Remove the duplication of somaxconn path
2014-08-04 10:27:22 -07:00
Norman Maurer
bc92ac6ba3 Remove duplicated code 2014-07-31 18:27:26 -07:00
Norman Maurer
045f9ff0ed [#2720] Check if /proc/sys/net/core/somaxconn exists before try to parse it
Motivation:

As /proc/sys/net/core/somaxconn does not exists on non-linux platforms you see a noisy stacktrace when debug level is enabled while the static method of NetUtil is executed.

Modifications:

Check if the file exists before try to parse it.

Result:

Less noisy logging on non-linux platforms.
2014-07-31 18:09:08 -07:00
Trustin Lee
c5ae3e3dcb Use our own URL shortener wherever possible 2014-07-31 17:06:30 -07:00
Trustin Lee
1c9cb90655 Fix a ConstantPoolTest failure 2014-07-29 15:45:50 -07:00
Trustin Lee
e64644b21c Fix a bug where AbstractConstant.compareTo() returns 0 for different constants
Related issue: #2354

Motivation:

AbstractConstant.compareTo() can return 0 even if the specified constant
object is not the same instance with 'this'.

Modifications:

- Compare the identityHashCode of constant first. If that fails,
  allocate a small direct buffer and use its memory address as a unique
  value.  If the platform does not provide a way to get the memory
  address of a direct buffer, use a thread-local random value.
- Signal cannot extend AbstractConstant. Use delegation.

Result:

It is practically impossible for AbstractConstant.compareTo() to return
0 for different constant objects.
2014-07-29 14:56:28 -07:00
Norman Maurer
ca0571cc9d Optimize native transport for gathering writes
Motivation:

While benchmarking the native transport with gathering writes I noticed that it is quite slow. This is due the fact that we need to do a lot of array copies to get the buffers into the iov array.

Modification:

Introduce a new class calles IovArray which allows to fill buffers directly in a iov array that can be passed over to JNI without any array copies. This gives a nice optimization in terms of speed when doing gathering writes.

Result:

Big performance improvement when doing gathering writes. See the included benchmark...

Before:
[nmaurer@xxx]~% wrk/wrk -H 'Host: localhost' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' -H 'Connection: keep-alive' -d 120 -c 256 -t 16 --pipeline 256  http://xxx:8080/plaintext
Running 2m test @ http://xxx:8080/plaintext
  16 threads and 256 connections
  Thread Stats   Avg      Stdev     Max   +/- Stdev
    Latency    23.44ms   16.37ms 259.57ms   91.77%
    Req/Sec   181.99k    31.69k  304.60k    78.12%
  346544071 requests in 2.00m, 46.48GB read
Requests/sec: 2887885.09
Transfer/sec:    396.59MB

With this change:
[nmaurer@xxx]~% wrk/wrk -H 'Host: localhost' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' -H 'Connection: keep-alive' -d 120 -c 256 -t 16 --pipeline 256  http://xxx:8080/plaintext
Running 2m test @ http://xxx:8080/plaintext
  16 threads and 256 connections
  Thread Stats   Avg      Stdev     Max   +/- Stdev
    Latency    21.93ms   16.33ms 305.73ms   92.34%
    Req/Sec   194.56k    33.75k  309.33k    77.04%
  369617503 requests in 2.00m, 49.57GB read
Requests/sec: 3080169.65
Transfer/sec:    423.00MB
2014-07-25 09:54:41 +02:00
Norman Maurer
44ea769f53 [#2662] Fix race in cancellation of TimerTasks which could let to NPE
Motivation:

Due some race-condition while handling canellation of TimerTasks it was possibleto corrupt the linked-list structure that is represent by HashedWheelBucket and so produce a NPE.

Modification:

Fix the problem by adding another MpscLinkedQueue which holds the cancellation tasks and process them on each tick. This allows to use no synchronization / locking at all while introduce a latency of max 1 tick before the TimerTask can be GC'ed.

Result:

No more NPE
2014-07-25 06:29:28 +02:00
Osvaldo Doederlein
8fc58a4a91 Fixes and improvements to IntObjectHashMap. Related to [#2659]
- Rewrite with linear probing, no state array, compaction at cleanup
- Optimize keys() and values() to not use reflection
- Optimize hashCode() and equals() for efficient iteration
- Fixed equals() to not return true for equals(null)
- Optimize iterator to not allocate new Entry at each next()
- Added toString()
- Added some new unit tests
2014-07-21 16:15:18 +02:00
Idel Pivnitskiy
6860019f41 Fix NPE problems
Motivation:

Now Netty has a few problems with null values.

Modifications:

- Check HAProxyProxiedProtocol in HAProxyMessage constructor and throw NPE if it is null.
If HAProxyProxiedProtocol is null we will set AddressFamily as null. So we will get NPE inside checkAddress(String, AddressFamily) and it won't be easy to understand why addrFamily is null.
- Check File in DiskFileUpload.toString().
If File is null we will get NPE when calling toString() method.
- Check Result<String> in MqttDecoder.decodeConnectionPayload(...).
If !mqttConnectVariableHeader.isWillFlag() || !mqttConnectVariableHeader.hasUserName() || !mqttConnectVariableHeader.hasPassword() we will get NPE when we will try to create new instance of MqttConnectPayload.
- Check Unsafe before calling unsafe.getClass() in PlatformDependent0 static block.
- Removed unnecessary null check in WebSocket08FrameEncoder.encode(...).
Because msg.content() can not return null.
- Removed unnecessary null check in DefaultStompFrame(StompCommand) constructor.
Because we have this check in the super class.
- Removed unnecessary null checks in ConcurrentHashMapV8.removeTreeNode(TreeNode<K,V>).
- Removed unnecessary null check in OioDatagramChannel.doReadMessages(List<Object>).
Because tmpPacket.getSocketAddress() always returns new SocketAddress instance.
- Removed unnecessary null check in OioServerSocketChannel.doReadMessages(List<Object>).
Because socket.accept() always returns new Socket instance.
- Pass Unpooled.buffer(0) instead of null inside CloseWebSocketFrame(boolean, int) constructor.
If we will pass null we will get NPE in super class constructor.
- Added throw new IllegalStateException in GlobalEventExecutor.awaitInactivity(long, TimeUnit) if it will be called before GlobalEventExecutor.execute(Runnable).
Because now we will get NPE. IllegalStateException will be better in this case.
- Fixed null check in OpenSslServerContext.setTicketKeys(byte[]).
Now we throw new NPE if byte[] is not null.

Result:

Added new null checks when it is necessary, removed unnecessary null checks and fixed some NPE problems.
2014-07-20 12:55:08 +02:00
Idel Pivnitskiy
a5095c5616 Small fixes and improvements
Motivation:

Fix some typos in Netty.

Modifications:

- Fix potentially dangerous use of non-short-circuit logic in Recycler.transfer(Stack<?>).
- Removed double 'the the' in javadoc of EmbeddedChannel.
- Write to log an exception message if we can not get SOMAXCONN in the NetUtil's static block.
2014-07-20 09:37:36 +02:00
Idel Pivnitskiy
dd26d47adc Small performance improvements
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.
2014-07-20 09:24:56 +02:00
Norman Maurer
0eb64b5a5d Fix over-sensible testcase 2014-07-13 17:19:47 +02:00
Norman Maurer
1cdbbe0f9b [#2651] Fix possible infinite-loop when cancel tasks
Motivations:
In our new version of HWT we used some kind of lazy cancelation of timeouts by put them back in the queue and let them pick up on the next tick. This  multiple problems:
 - we may corrupt the MpscLinkedQueue if the task is used as tombstone
 - this sometimes lead to an uncessary delay especially when someone did executed some "heavy" logic in the TimeTask

Modifications:
Use a Lock per HashedWheelBucket for save and fast removal.

Modifications:
Cancellation of tasks can be done fast and so stuff can be GC'ed and no more infinite-loop possible
2014-07-11 15:41:44 +02:00
nmittler
67159e7119 Upgrade to HTTP/2 draft 13
Motivation:

Need to upgrade HTTP/2 implementation to latest draft.

Modifications:

Various changes to support draft 13.

Result:

Support for HTTP/2 draft 13.
2014-07-08 21:10:46 +02:00
Trustin Lee
3921f7c88a Reduce the perceived time taken to retrieve initialSeedUniquifier
Motivation:

When system is in short of entrophy, the initialization of
ThreadLocalRandom can take at most 3 seconds.  The initialization occurs
when ThreadLocalRandom.current() is invoked first time, which might be
much later than the moment when the application has started.  If we
start the initialization of ThreadLocalRandom as early as possible, we
can reduce the perceived time taken for the retrieval.

Modification:

Begin the initialization of ThreadLocalRandom in InternalLoggerFactory,
potentially one of the firstly initialized class in a Netty application.

Make DefaultChannelId retrieve the current process ID before retrieving
the current machine ID, because retrieval of a machine ID is more likely
to use ThreadLocalRandom.current().

Use a dummy channel ID for EmbeddedChannel, which prevents many unit
tests from creating a ThreadLocalRandom instance.

Result:

We gain extra 100ms at minimum for initialSeedUniquifier generation.  If
an application has its own initialization that takes long enough time
and generates good amount of entrophy, it is very likely that we will
gain a lot more.
2014-07-04 16:04:37 +09:00
Trustin Lee
b4c2ae5e59 Log the time taken for generating the initialSeedUniquifier
- Sometimes useful to know it how long it takes from the log, to make
  sure it's not something else that is blocking.
2014-07-04 13:25:26 +09:00
Trustin Lee
ba81831e0a Fix the cruft produced from the refactoring
.. in 330404da07
2014-07-02 20:30:45 +09:00
Trustin Lee
330404da07 Fix most inspector warnings
Motivation:

It's good to minimize potentially broken windows.

Modifications:

Fix most inspector warnings from our profile

Result:

Cleaner code
2014-07-02 19:04:11 +09:00
Norman Maurer
887838a06b Correctly return from selector loop one a scheduled task is ready for processing
Motivation:

We use the nanoTime of the scheduledTasks to calculate the milli-seconds to wait for a select operation to select something. Once these elapsed we check if there was something selected or some task is ready for processing. Unfortunally we not take into account scheduled tasks here so the selection loop will continue if only scheduled tasks are ready for processing. This will delay the execution of these tasks.

Modification:

- Check if a scheduled task is ready after selecting
- also make a tiny change in NioEventLoop to not trigger a rebuild if nothing was selected because the timeout was reached a few times in a row.

Result:

Execute scheduled tasks on time.
2014-07-02 09:10:49 +02:00
Norman Maurer
20adbb325e [#2604] Not try to use sun.misc.Cleaner when on android
Motivation:

When a user tries to use netty on android it currently fails with "Could not find class 'sun.misc.Cleaner'"

Modification:

Encapsulate sun.misc.Cleaner usage in extra class to workaround this isssue.

Result:
Netty can be used on android again
2014-06-27 08:25:56 +02:00
Norman Maurer
d4d27248b4 [#2599] Not use sun.nio.ch.DirectBuffer as it not exists on android
Motivation:

During some refactoring we changed PlatformDependend0 to use sun.nio.ch.DirectBuffer for release direct buffers. This broke support for android as the class does not exist there and so an exception is thrown.

Modification:

Use again the fieldoffset to get access to Cleaner for release direct buffers.

Result:
Netty can be used on android again
2014-06-25 15:07:16 +02:00
Norman Maurer
580965f775 Improve performance of Recycler
Motivation:

Recycler is used in many places to reduce GC-pressure but is still not as fast as possible because of the internal datastructures used.

Modification:

 - Rewrite Recycler to use a WeakOrderQueue which makes minimal guaranteer about order and visibility for max performance.
 - Recycling of the same object multiple times without acquire it will fail.
 - Introduce a RecyclableMpscLinkedQueueNode which can be used for MpscLinkedQueueNodes that use Recycler

These changes are based on @belliottsmith 's work that was part of #2504.

Result:

Huge increase in performance.

4.0 branch without this commit:

Benchmark                                                (size)   Mode   Samples        Score  Score error    Units
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    00000  thrpt        20 116026994.130  2763381.305    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    00256  thrpt        20 110823170.627  3007221.464    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    01024  thrpt        20 118290272.413  7143962.304    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    04096  thrpt        20 120560396.523  6483323.228    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    16384  thrpt        20 114726607.428  2960013.108    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    65536  thrpt        20 119385917.899  3172913.684    ops/s
Tests run: 1, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 297.617 sec - in io.netty.microbench.internal.RecyclableArrayListBenchmark

4.0 branch with this commit:

Benchmark                                                (size)   Mode   Samples        Score  Score error    Units
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    00000  thrpt        20 204158855.315  5031432.145    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    00256  thrpt        20 205179685.861  1934137.841    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    01024  thrpt        20 209906801.437  8007811.254    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    04096  thrpt        20 214288320.053  6413126.689    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    16384  thrpt        20 215940902.649  7837706.133    ops/s
i.n.m.i.RecyclableArrayListBenchmark.recycleSameThread    65536  thrpt        20 211141994.206  5017868.542    ops/s
Tests run: 1, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 297.648 sec - in io.netty.microbench.internal.RecyclableArrayListBenchmark
2014-06-24 10:57:35 +02:00
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
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
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
Trustin Lee
9a169f5865 Fix incorrect method signature of awaitInactivity()
- Related: #2084
2014-06-17 15:59:11 +09:00
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
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
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
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
Trustin Lee
d0640a6686 Clean up MpscLinkedQueue, fix its leak, and make it work without Unsafe
Motivation:

MpscLinkedQueue has various issues:
- It does not work without sun.misc.Unsafe.
- Some field names are confusing.
  - Node.tail does not refer to the tail node really.
  - The tail node is the starting point of iteration. I think the tail
    node should be the head node and vice versa to reduce confusion.
- Some important methods are not implemented (e.g. iterator())
- Not serializable
- Potential false cache sharing problem due to lack of padding
- MpscLinkedQueue extends AtomicReference and thus exposes various
  operations that mutates the internal state of the queue directly.

Modifications:

- Use AtomicReferenceFieldUpdater wherever possible so that we do not
  use Unsafe directly. (e.g. use lazySet() instead of putOrderedObject)
- Extend AbstractQueue to implement most operations
- Implement serialization and iterator()
- Rename tail to head and head to tail to reduce confusion.
- Rename Node.tail to Node.next.
- Fix a leak where the references in the removed head are not cleared
  properly.
- Add Node.clearMaybe() method so that the value of the new head node
  is cleared if possible.
- Add some comments for my own educational purposes
- Add padding to the head node
  - Add FullyPaddedReference and RightPaddedReference for future reuse
- Make MpscLinkedQueue package-local so that a user cannot access the
  dangerous yet public operations exposed by the superclass.
  - MpscLinkedQueue.Node becomes MpscLinkedQueueNode, a top level class

Result:

- It's more like a drop-in replacement of ConcurrentLinkedQueue for the
  MPSC case.
- Works without sun.misc.Unsafe
- Code potentially easier to understand
- Fixed leak (related: #2372)
2014-06-04 03:23:44 +09:00
Trustin Lee
fc45635af3 Fix checkstyle 2014-06-02 19:27:26 +09:00
Trustin Lee
c827c6da37 Add awaitInactivity() to GlobalEventExecutor and ThreadDeathWatcher
Motivation:

When running Netty on a container environment, the container will often
complain about the lingering threads such as the worker threads of
ThreadDeathWatcher and GlobalEventExecutor.  We should provide an
operation that allows a use to wait until such threads are terminated.

Modifications:

- Add awaitInactivity()
- (misc) Fix typo in GlobalEventExecutorTest
- (misc) Port ThreadDeathWatch's CAS-based thread life cycle management
  to GlobalEventExecutor

Result:

- Fixes #2084
- Less overhead on task submission of GlobalEventExecutor
2014-06-02 19:23:50 +09:00