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.
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
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
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
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
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.
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:
Allow to make use of our new FastThreadLocal whereever possible
Modification:
Make use of an array to store FastThreadLocals and so allow to also use it in PooledByteBufAllocator that is instanced by users.
The maximal size of the array is configurable per system property to allow to tune it if needed. As default we use 64 entries which should be good enough.
Result:
More flexible usage of FastThreadLocal
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:
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.
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)
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
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:
The current DefaultAttributeMap cause an infinite-loop when the user removes an attribute and create the same attribute again. This regression was introduced by c3bd7a8ff1.
Modification:
Correctly break out loop
Result:
No infinite-loop anymore.
Motivation:
When (listeners == null && lateListeners == null) and (stackDepth >= MAX_LISTENER_STACK_DEPTH), the listener is not notified at all. The discard client does not work.
Modification:
Make sure to submit the notification task.
Result:
The discard client works again and all listeners are notified.
Motivation:
During a large memory copy, safepoint polling is diabled, hindering
accurate profiling.
Modifications:
Only copy up to 1 MiB per Unsafe.copyMemory()
Result:
Potentially more reliable performance
Motivation:
Some users already use an SSLEngine implementation in finagle-native. It
wraps OpenSSL to get higher SSL performance. However, to take advantage
of it, finagle-native must be compiled manually, and it means we cannot
pull it in as a dependency and thus we cannot test our SslHandler
against the OpenSSL-based SSLEngine. For an instance, we had #2216.
Because the construction procedures of JDK SSLEngine and OpenSslEngine
are very different from each other, we also need to provide a universal
way to enable SSL in a Netty application.
Modifications:
- Pull netty-tcnative in as an optional dependency.
http://netty.io/wiki/forked-tomcat-native.html
- Backport NativeLibraryLoader from 4.0
- Move OpenSSL-based SSLEngine implementation into our code base.
- Copied from finagle-native; originally written by @jpinner et al.
- Overall cleanup by @trustin.
- Run all SslHandler tests with both default SSLEngine and OpenSslEngine
- Add a unified API for creating an SSL context
- SslContext allows you to create a new SSLEngine or a new SslHandler
with your PKCS#8 key and X.509 certificate chain.
- Add JdkSslContext and its subclasses
- Add OpenSslServerContext
- Add ApplicationProtocolSelector to ensure the future support for NPN
(NextProtoNego) and ALPN (Application Layer Protocol Negotiation) on
the client-side.
- Add SimpleTrustManagerFactory to help a user write a
TrustManagerFactory easily, which should be useful for those who need
to write an alternative verification mechanism. For example, we can
use it to implement an unsafe TrustManagerFactory that accepts
self-signed certificates for testing purposes.
- Add InsecureTrustManagerFactory and FingerprintTrustManager for quick
and dirty testing
- Add SelfSignedCertificate class which generates a self-signed X.509
certificate very easily.
- Update all our examples to use SslContext.newClient/ServerContext()
- SslHandler now logs the chosen cipher suite when handshake is
finished.
Result:
- Cleaner unified API for configuring an SSL client and an SSL server
regardless of its internal implementation.
- When native libraries are available, OpenSSL-based SSLEngine
implementation is selected automatically to take advantage of its
performance benefit.
- Examples take advantage of this modification and thus are cleaner.
Motivation:
The old DefaultAttributeMap impl did more synchronization then needed.
Modifications:
* Rewrite DefaultAttributeMap to not use IdentityHashMap and synchronization on the map directly. The new impl uses a combination of AtomicReferenceArray and synchronization per chain (linked-list). Also access the first Attribute per bucket can be done without any synchronization at all and just uses atomic operations. This should fit for most use-cases pretty weel.
Result:
Synchronization is per linked-list and the first entry can even be added via atomic operation.
Motivation:
At the moment there are two issues with HashedWheelTimer:
* the memory footprint of it is pretty heavy (250kb fon an empty instance)
* the way how added Timeouts are handled is inefficient in terms of how locks etc are used and so a lot of context-switching / condition can happen.
Modification:
Rewrite HashedWheelTimer to use an optimized bucket implementation to store the submitted Timeouts and a MPSC queue to handover the timeouts. So volatile writes are reduced to a minimum and also the memory foot-print of the buckets itself is reduced a lot as the bucket uses a double-linked-list. Beside this we use Atomic*FieldUpdater where-ever possible to improve the memory foot-print and performance.
Result:
Lower memory-footprint and better performance
Motivation:
Some JDK versions of Mac OS X generates a JNI dynamic library with '.jnilib' extension rather than with '.dynlib' extension. However, System.mapLibraryName() always returns 'lib<name>.dynlib'. As a result, NativeLibraryLoader fails to load the native library whose extension is .jnilib.
Modification:
Try to find both '.jnilib' and '.dynlib' resources on OS X.
Result:
Dynamic libraries are loaded correctly in Mac OS X, and thus we can continue the OpenSslEngine work.
Motivation:
So far, we used a very simple platform string such as linux64 and
linux32. However, this is far from perfection because it does not
include anything about the CPU architecture.
Also, the current build tries to put multiple versions of .so files into
a single JAR. This doesn't work very well when we have to ship for many
different platforms. Think about shipping .so/.dynlib files for both
Linux and Mac OS X.
Modification:
- Use os-maven-plugin as an extension to determine the current OS and
CPU architecture reliable at build time
- Use Maven classifier instead of trying to put all shared libraries
into a single JAR
- NativeLibraryLoader does not guess the OS and bit mode anymore and it
always looks for the same location regardless of platform, because the
Maven classifier does the job instead.
Result:
Better scalable native library deployment and retrieval
Motivation:
It is less confusing not to spread Thread.interrupt() calls.
Modification:
- Comments
- Move generatorThread.interrupt() to where currentThread.interrupt() is
triggered
Result:
Code that is easier to read
Motivation:
ThreadLocalRandomTest reveals that ThreadLocalRandom's initial seed generation loop becomes tight if the thread is interrupted.
We currently interrupt ourselves inside the wait loop, which will raise an InterruptedException again in the next iteration, resulting in infinite (up to 3 seconds) exception construction and thread interruptions.
Modification:
- When the initial seed generator thread is interrupted, break out of the wait loop immediately.
- Log properly when the initial seed generation failed due to interruption.
- When failed to generate the initial seed, interrupt the generator thread just in case the SecureRandom implementation handles it properly.
- Make the initial seed generator thread daemon and handle potential exceptions raised due to the interruption.
Result:
No more tight loop on interruption. More robust generator thread termination. Fixes#2412
Motivation:
When using System.getProperty(...) and various methods to get a ClassLoader it will fail when a SecurityManager is in place.
Modifications:
Use a priveled block if needed. This work is based in the PR #2353 done by @anilsaldhana .
Result:
Code works also when SecurityManager is present
Motivation:
Previously, we used SecureRandom.nextLong() to generate the initialSeedUniquifier. This required more entrophy than necessary because it has to 1) generate the seed of SecureRandom first and then 2) generate a random long integer. Instead, we can use generateSeed() to skip the step (2)
Modifications:
Use generateSeed() instead of nextLong()
Result:
ThreadLocalRandom requires less amount of entrphy to start up
Motivation:
As reported in #2331, some query operations in NetworkInterface takes much longer time than we expected. For example, specifying -Djava.net.preferIPv4Stack=true option in Window increases the execution time by more than 4 times. Some Windows systems have more than 20 network interfaces, and this problem gets bigger as the number of unused (virtual) NICs increases.
Modification:
Use NetworkInterface.getInetAddresses() wherever possible.
Before iterating over all NICs reported by NetworkInterface, filter the NICs without proper InetAddresses. This reduces the number of candidates quite a lot.
NetUtil does not query hardware address of NIC in the first place but uses InetAddress.isLoopbackAddress().
Do not call unnecessary query operations on NetworkInterface. Just get hardware address and compare.
Result:
Significantly reduced class initialization time
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:
- 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:
Remove the synchronization bottleneck in startThread() which is called by each execute(..) call from outside the EventLoop.
Modifications:
Replace the synchronized block with the use of AtomicInteger and compareAndSet loops.
Result:
Less conditions during SingleThreadEventExecutor.execute(...)
Motivation:
- As reported recently [1], Recycler's thread-local object pool has unbounded capacity which is a potential problem.
- It accesses a hash table on each push and pop for debugging purposes. We don't really need it besides debugging Netty itself.
Modifications:
- Introduced the maxCapacity constructor parameter to Recycler. The default default maxCapacity is retrieved from the system property whose default is 256K, which should be plenty for most cases.
- Recycler.Stack.map is now created and accessed only when assertion is enabled for Recycler.
Result:
- Recycler does not grow infinitely anymore.
- If assertion is disabled, Recycler should be much faster.
[1] https://github.com/netty/netty/issues/1841
Previously ConcurrentHashMapV8 evaulated ((x | 1) == 0), an expression
that always returned false. This commit brings Netty closer to the
Java 8 implementation.
