Motivation:
TCP Fast Open allows data to be carried in the SYN and SYN-ACK packets and consumed by the receiving end during the initial connection handshake, and saves up to one full round-trip time (RTT) compared to the standard TCP, which requires a three-way handshake (3WHS) to complete before data can be exchanged. This commit enables support for TFO on server sockets.
Modifications:
Added new Integer Option TCP_FASTOPEN in EpollChannelOption.
Added getters/setters in EpollServerChannelConfig for TCP_FASTOPEN.
Added way to check if TCP_FASTOPEN is supported on server in Native.
Added setting on socket opt TCP_FASTOPEN if value is set on channel options in doBind in EpollServerSocketChannel.
Enhanced EpollSocketTestPermutation to contain a permutation for server socket containing fast open.
Result:
Users of native-epoll can set TCP_FASTOPEN on server sockets and thus leverage fast connect features of RFC7413 if client is capable of it.
Conflicts:
transport-native-epoll/src/main/java/io/netty/channel/epoll/EpollChannelOption.java
Motivation:
There are protocols (BGP, SXP), which are typically deployed with TCP
MD5 authentication to protect sessions from being hijacked/torn down by
third parties. This facility is not available on most operating systems,
but is typically present on Linux.
Modifications:
- add a new EpollChannelOption, which is write-only
- teach Epoll(Server)SocketChannel to track which addresses have keys
associated
- teach Native how to set the MD5 signature keys for a socket
Result:
Users of the native-epoll transport can set MD5 signature keys and thus
leverage RFC-2385 protection on TCP connections.
Motivation:
See #4174.
Modifications:
Modify transport-native-epoll to allow setting TCP_USER_TIMEOUT.
Result:
Hanging connections that are written into will get timeouted.
Conflicts:
transport-native-epoll/src/main/java/io/netty/channel/epoll/EpollChannelOption.java
Motivation:
In NIO and OIO we throw a ChannelException if a ChannelConfig operation fails. We should do the same with epoll to be consistent.
Modifications:
Use ChannelException
Result:
Consistent behaviour across different transport implementations.
Motivation:
When try to get SO_LINGER from a fd that is closed an Exception is thrown. We should only try to get SO_LINGER if the fd is still open otherwise an Exception is thrown that can be ignored anyway.
Modifications:
First check if the fd is still open before try to obtain SO_LINGER setting when get the closeExecutor. This is also the same that we do in the NIO transport.
Result:
No more exception when calling unsafe.close() on a channel that has a closed file descriptor.
Motivation:
The method implementions for setSoLinger(...) and setTrafficClass(...) were swapped by mistake.
Modifications:
Use the correct implementation for setSoLinger(...) and setTrafficClass(...)
Result:
Correct behaviour when setSoLinger(...) and setTrafficClass(...) are used with the epoll transport.
Motivation:
Commit cf171ff525 changed the way read operations were done. This change introduced a feedback loop between fireException and epollInReady.
Modifications:
- All EPOLL*Channel* classes should not call fireException and also continue to read. Instead a read operation should be executed on the eventloop (if the channel's input is not closed, and other conditions are satisfied)
Result:
Exception processing and channelRead will not be in a feedback loop.
Fixes https://github.com/netty/netty/issues/4091
Motivation:
Because of java custom UTF encoding, it was previously impossible to use
nul-bytes in domain socket names, which is required for abstract domain
sockets.
Modifications:
- Pass the encoded string byte array to the native code
- Modify native code accordingly to work with nul-bytes in the the
array.
- Move the string encoding to UTF-8 in java code.
Result:
Unix domain socket addresses will work properly if they contain nul-
bytes. Address encoding for these addresses changes from UTF-8-like to
real UTF-8.
Motivation:
If is enabled and a channel is half closed it is possible for the EPOLL event loop to get into an infinite loop by continuously being woken up on the EPOLLRDHUP event.
Modifications:
- Ensure that the EPOLLRDHUP event is unregistered for to prevent infinite loop.
Result:
1 less infinite loop.
Motivation:
We not set any optimization flag when compile native transport
Modification:
Add -O3 to CFLAGS to have GCC do optimizations
Result:
Ship optimized native code
Motiviation:
The current read loops don't fascilitate reading a maximum amount of bytes. This capability is useful to have more fine grain control over how much data is injested.
Modifications:
- Add a setMaxBytesPerRead(int) and getMaxBytesPerRead() to ChannelConfig
- Add a setMaxBytesPerIndividualRead(int) and getMaxBytesPerIndividualRead to ChannelConfig
- Add methods to RecvByteBufAllocator so that a pluggable scheme can be used to control the behavior of the read loop.
- Modify read loop for all transport types to respect the new RecvByteBufAllocator API
Result:
The ability to control how many bytes are read for each read operation/loop, and a more extensible read loop.
Motivation:
IP_FREEBIND allows to bind to addresses without the address up yet or even the interface configured yet.
Modifications:
Add support for IP_FREEBIND.
Result:
It's now possible to use IP_FREEBIND when using the native epoll transport.
Motivation:
It would be useful to support the Java `Map` interface in our primitive maps.
Modifications:
Renamed current methods to "pXXX", where p is short for "primitive". Made the template for all primitive maps extend the appropriate Map interface.
Result:
Fixes#3970
Motivation:
We missed to register for EPOLLRDHUP events when construct the EpollSocketChannel from an existing FileDescriptor. This could cause to miss connection-resets.
Modifications:
Add Native.EPOLLRDHUP to the events we are interested in.
Result:
Connection-resets are detected correctly.
Motivation:
Some glibc/kernel versions will trigger an EPOLLERR event to notify
about failed connect and not an EPOLLOUT. Also EPOLLERR may be triggered
when a connection is broke.
Modification:
React on EPOLLERR like if an EPOLLOUT / EPOLLIN was received, this will work in
all cases as we handle errors in EPOLLOUT / EPOLLIN anyway.
Result:
Correctly detect errors.
Motivation:
The unit tests should not fail due to using a channel option which is not supported by the underlying kernel.
Modifications:
- Ignore RuntimeExceptions which are thrown by JNI code when setsockopt or getsockopt fails.
Result:
Unit tests pass if socket option is not supported by kernel.
Motiviation:
TCP_NOTSENT_LOWAT is only supported in linux kernel 3.12 or newer. The addition of this socket option prevents older kernels from building.
Modifications:
- Conditionally define TCP_NOTSENT_LOWAT if it is not defined
Result:
Kernels older than 3.12 can still compile the EPOLL module.
Motiviation:
Linux provides the TCP_NOTSENT_LOWAT socket option. This can be used to control how much unsent data is queued in the tcp kernel buffers. This can be important when application level protocols (SPDY, HTTP/2) have their own priority mechanism and don't want data queued in the kernel.
Modifications:
- The epoll module will have an additional socket option TCP_NOTSENT_LOWAT
- There will be JNI methods to control the underlying linux socket option mechanism
Result:
Linux EPOLL module exposes the TCP_NOTSENT_LOWAT socket option.
Motivation:
the JNI function ThrowNew won't release any allocated memory.
The method exceptionMessage is allocating a new string concatenating 2 constant strings
What is creating a small leak in case of these exceptions are happening.
Modifications:
Added new methods that will use exceptionMessage and free resources accordingly.
I am also removing the inline definition on these methods as they could be reused by
other added modules (e.g. libaio which should be coming soon)
Result:
No more leaks in case of failures.
Motivation:
Due a bug we not correctly handled connection refused errors and so failed the connect promise with the wrong exception.
Beside this we some times even triggered fireChannelActive() which is not correct.
Modifications:
- Add testcase
- correctly detect connect errors
Result:
Correct and consistent handling.
Motivation:
When trying to write more then Integer.MAX_VALUE / SSIZE_MAX via writev(...) the OS may return EINVAL depending on the kernel or the actual OS (bsd / osx always return EINVAL). This will trigger an IOException.
Modifications:
Never try to write more then Integer.MAX_VALUE / SSIZE_MAX when using writev.
Result:
No more IOException when write more data then Integer.MAX_VALUE / SSIZE_MAX via writev.
Motivation:
When EPOLLRDHUP is received we need to try to read at least one time to ensure
that we read all pending data from the socket. Otherwise we may loose data.
Modifications:
- Ensure we read all data from socket
- Ensure file descriptor is closed on doClose() even if doDeregister() throws an Exception.
- Only handle either EPOLLRDHUP or EPOLLIN as only one is needed to detect connection reset.
Result:
No more data loss on connection reset.
Motivation:
When using epoll_ctl we should respect the return value and do the right thing depending on it.
Modifications:
Adjust java and native code to respect epoll_ctl return values.
Result:
Correct and cleaner code.
Motivation:
Linux supports splice(...) to transfer data from one filedescriptor to another without
pass data through the user-space. This allows to write high-performant proxy code or to stream
stuff from the socket directly the the filesystem.
Modification:
Add AbstractEpollStreamChannel.spliceTo(...) method to support splice(...) system call
Result:
Splice is now supported when using the native linux transport.
Conflicts:
transport-native-epoll/src/main/java/io/netty/channel/epoll/AbstractEpollStreamChannel.java
Motivation:
Because of a bug we missed to fail the connect future when doClose() is called. This can lead to a future which is never notified and so may lead to deadlocks in user-programs.
Modifications:
Correctly fail the connect future when doClose() is called and the connection was not established yet.
Result:
Connect future is always notified.
Motivation:
Each different *ChannelOption did extend ChannelOption in 4.0, which we changed in 4.1. This is a breaking change in terms of the API so we need to ensure we keep the old hierarchy.
Modifications:
- Let all *ChannelOption extend ChannelOption
- Add back constructor and mark it as @deprecated
Result:
No API breakage between 4.0 and 4.1
Motivation:
As we missed to correctly handle EPOLLRDHUP we produce an IOException which is unnessary. This leads
to have exceptionCaught(...) methods called.
Modifications:
When EPOLLRDHUP was received just close the socket and fail all pending writes.
Result:
Correctly handle of EPOLLRDHUP and so not miss-leading exceptions.
Motivation:
When an error happens during loading the native library it may try to generate a new RuntimeException before the RuntimeException is loaded.
Modifications:
- Load RuntimeException as first
Result:
No more segfaults possible
Motivation:
On a system where ipv4 and ipv6 are supported a user may want to use -Djava.net.preferIPv4Stack=true to restrict it to use ipv4 only.
This is currently ignored with the epoll transport.
Modifications:
Respect java.net.preferIPv4Stack system property.
Result:
-Djava.net.preferIPv4Stack=true will have the effect the user is looking for.
Motivation:
Due a a regression that was introduced by b898bdd we failed to set the localAddress if the connect did not success directly.
Modifications:
Correct set localAddress in doConnect(...)
Result:
Be able to get the localAddress in all cases.
Motivation:
During 6b941e9bdb I introduced a regression that could cause an IllegalStateException.
A non-proper fix was commited as part of #3443. This commit add a proper fix.
Modifications:
Remove FileDescriptor.INVALID and add FileDescriptor.isOpen() as replacement. Once FileDescriptor.close() is called isOpen() will return false.
Result:
No more IllegalStateException caused by a close channel.
Motivation:
EpollDragramChannel never calls fireChannelActive after connect() which is a bug.
Modifications:
Correctly call fireChannelActive if needed
Result:
Correct behaviour
Motivation:
Before struct's were passed per value and not pointer. This did enforce a memory copy which is not needed.
Modifications:
- Use "const struct....*" as replacement
Result:
No more unnecessary memory copies
Motivation:
When create address from filedescriptor we may use incorrect byte order and so end up with an incorrect InetAddress.
Modification:
Not manually shift bytes
Result:
Correct address in all cases.
Motivation:
Because of a regression sometimes accept could produce an IllegalArgumentException
Modifications:
Correctly respect offset when decode port and scope id.
Result:
No more IllegalArgumentException
Motivation:
This is a regression that was introduced as part of 6b941e9bdb. The regression could produce an "infinity" triggering of IllegalStateException if a channel goes inactive while process the events for it.
Modifications:
Correctly check if the channel is still active before trigger the callbacks.
Result:
No more IllegalStateException
Motivation:
There is a small race in the native transport where an accept(...) may success but a later try to obtain the remote address from the fd may fail is the fd is already closed.
Modifications:
Let accept(...) directly set the remote address.
Result:
No more race possible.
Motivation:
When epoll LT is used and autoRead == false when entering epollIn() we need to return without reading any data.
Modifications:
Correctly respect autoRead == false if using epoll LT.
Result:
Consistent and correct behaviour.
Motivation:
In the native transport we should throw a pre-instanced IOException on connection reset while reading.
Modifications:
Correctly throw pre-instanced IOException when ECONNRESET is received
Result:
Less overhead on connection reset
Motivation:
As we plan to have other native transports soon (like a kqueue transport) we should move unix classes/interfaces out of the epoll package so we
introduce other implementations without breaking stuff before the next stable release.
Modifications:
Create a new io.netty.channel.unix package and move stuff over there.
Result:
Possible to introduce other native impls beside epoll.
Motivation:
Sometimes it's useful to be able to create a Epoll*Channel from an existing file descriptor. This is especially helpful if you integrade some c/jni code.
Modifications:
- Add extra constructor to Epoll*Channel implementations that take a FileDescriptor as an argument
- Make Rename EpollFileDescriptor to NativeFileDescriptor and make it public
- Also ensure we obtain the correct remote/local address when create a Channel from a FileDescriptor
Result:
It's now possible to create a FileDescriptor and instance a Epoll*Channel via it.
Motivation:
If SO_LINGER is used shutdownOutput() and close() syscalls will block until either all data was send or until the timeout exceed. This is a problem when we try to execute them on the EventLoop as this means the EventLoop may be blocked and so can not process any other I/O.
Modifications:
- Add AbstractUnsafe.closeExecutor() which returns null by default and use this Executor for close if not null.
- Override the closeExecutor() in NioSocketChannel and EpollSocketChannel and return GlobalEventExecutor.INSTANCE if getSoLinger() > 0
- use closeExecutor() in shutdownInput(...) in NioSocketChannel and EpollSocketChannel
Result:
No more blocking of the EventLoop if SO_LINGER is used and shutdownOutput() or close() is called.
Motivation:
Some of the methods are frequently called and so should be inlined if possible.
Modifications:
Give the compiler a hint that we want to inline these methods.
Result:
Better performance if inlined.
Motivation:
Older linux kernels have problems handling a large value for epoll_wait(...) and so wait for ever.
Modifications:
Adjust timeout on the fly if a too big value is passed in.
Result:
Correctly works also on older kernels.
Motivation:
The writeSpinCount was ignored in the epoll transport and it just kept on trying writing. This could cause unnessary cpu spinning if a slow remote peer was reading the data very very slow.
Modification:
- Correctly take writeSpinCount into account when writing.
Result:
Less cpu spinning when writing to a slow remote peer.
Motivation:
Fix regression introduced by 585ce1593f, which missed to set EPOLLRDHUP for all stream channels.
Modifications:
Correctly set EPOLLRDHUP for all stream channels in the AbstractEpollStreamChannel constructor.
Result:
No more test failures in EpollDomain*Channel tests.
Motivation:
Before we used a long[] to store the ready events, this had a few problems and limitations:
- An extra loop was needed to translate between epoll_event and our long
- JNI may need to do extra memory copy if the JVM not supports pinning
- More branches
Modifications:
- Introduce a EpollEventArray which allows to directly write in a struct epoll_event* and pass it to epoll_wait.
Result:
Better speed when using native transport, as shown in the benchmark.
Before:
[xxx@xxx wrk]$ ./wrk -H 'Connection: keep-alive' -d 120 -c 256 -t 16 -s scripts/pipeline-many.lua http://xxx:8080/plaintext
Running 2m test @ http://xxx:8080/plaintext
16 threads and 256 connections
Thread Stats Avg Stdev Max +/- Stdev
Latency 14.56ms 8.64ms 117.15ms 80.58%
Req/Sec 286.17k 38.71k 421.48k 68.17%
546324329 requests in 2.00m, 73.78GB read
Requests/sec: 4553438.39
Transfer/sec: 629.66MB
After:
[xxx@xxx wrk]$ ./wrk -H 'Connection: keep-alive' -d 120 -c 256 -t 16 -s scripts/pipeline-many.lua http://xxx:8080/plaintext
Running 2m test @ http://xxx:8080/plaintext
16 threads and 256 connections
Thread Stats Avg Stdev Max +/- Stdev
Latency 14.12ms 8.69ms 100.40ms 83.08%
Req/Sec 294.79k 40.23k 472.70k 66.75%
555997226 requests in 2.00m, 75.08GB read
Requests/sec: 4634343.40
Transfer/sec: 640.85MB
Motivation:
Netty uses edge-triggered epoll by default for performance reasons. The downside here is that a messagesPerRead limit can not be enforced correctly, as we need to consume everything from the channel when notified.
Modification:
- Allow to switch epoll modes before channel is registered
- Some refactoring to share more code
Result:
It's now possible to switch epoll mode.
Motiviation:
When using domain sockets on linux it is supported to recv and send file descriptors. This can be used to pass around for example sockets.
Modifications:
- Add support for recv and send file descriptors when using EpollDomainSocketChannel.
- Allow to obtain the file descriptor for an Epoll*Channel so it can be send via domain sockets.
Result:
recv and send of file descriptors is supported now.
Motivation:
Using Unix Domain Sockets can be very useful when communication should take place on the same host and has less overhead then using loopback. We should support this with the native epoll transport.
Modifications:
- Add support for Unix Domain Sockets.
- Adjust testsuite to be able to reuse tests.
Result:
Unix Domain Sockets are now support when using native epoll transport.
Motivation:
At the moment the max number of events that can be handled per epoll wakup was set during construction.
Modifications:
- Automatically increase the max number of events to handle
Result:
Better performance when a lot of events need to be handled without adjusting the code.
Motivation:
The current way how the guard against overflow when generating the nextId() is pretty slow once an overflow happened.
Modifications:
Once a possible overflow is detected all ids used by the EpollEventLoop are scrubed and re-assigned to the registered Channels. This way we only need to do extra work each time an overflow is detected.
Result:
More consistent performance even after the first overflow was detected.
Motivation:
On Linux, you can gather various metrics using getsockopt(..., TCP_INFO,
...).
Modifications:
Add EpollSocketChannel.tcpInfo() which returns EpollTcpInfo that exposes
all metrics exposed via getsockopt(..., TCP_INFO, ...)
Result:
TCP_INFO support implemented
Motivation:
In the native transport we use getpeername to obtain the remote address from the file descriptor. This may fail for various reasons in which case NULL is returned.
Modifications:
- Check for null when try to obtain remote / local address
Result:
No more NPE
Related: #3274
Motivation:
channelReadComplete() event is not triggered after reading successfully
in EpollDatagramChannel.
Modifications:
- Trigger exceptionCaught() event for read failure only once for less
noise
- Trigger channelReadComplete() event at the end of the read.
Result:
Fix#3274
Rebased and cleaned-up based on the work by @normanmaurer
Motivation:
Currently, IOExceptions and ClosedChannelExceptions are thrown from
inside the JNI methods. Instantiation of Java objects inside JNI code is
an expensive operation, needless to say about filling stack trace for
every instantiation of an exception.
Modifications:
Change most JNI methods to return a negative value on failure so that
the exceptions are instantiated outside the native code.
Also, pre-instantiate some commonly-thrown exceptions for better
performance.
Result:
Performance gain
Motivation:
So far, we generated and deployed test JARs to Maven repositories. The
deployed JAR had the classifier 'test-jar'. The test JAR is consumed by
transport-native-epoll as a test dependency.
The problem is, when netty-transport-native-epoll pulls the test JAR as
a dependency, that Maven resolves its transitive dependencies at
'compile' and 'runtime' scope only, which is incorrect.
I was bitten by this problem recently while trying to add a new
dependency to netty-testsuite. Because I added a new dependency at the
'test' scope, the new dependency was not pulled transitively by
transport-native-epoll and caused an unexpected build failure.
- d6160208c3
- bf77bb4c3a
Modifications:
- Move all classes in netty-testsuite from src/test to src/main
- Update the 'compile' scope dependencies of netty-testsuite
- Override the test directory configuration properties of the surefire
plugin
- Do not generate the test JAR anymore
- Update the dependency of netty-transport-native-epoll
Result:
It is less error-prone to add a new dependency to netty-testsuite.
Motivation:
Everytime a new connection is accepted via EpollSocketServerChannel it will create a new EpollSocketChannel that needs to get the remote and local addresses in the constructor. The current implementation uses new InetSocketAddress(String, int) to create these. This is quite slow due the implementation in oracle and openjdk.
Modifications:
Encode all needed informations into a byte array before return from jni layer and then use new InetSocketAddress(InetAddress, int) to create the socket addresses. This allows to create the InetAddress via a byte[] and so reduce the overhead, this is done either by using InetAddress.getByteAddress(byte[]) or by Inet6Address.getByteAddress(String, byte[], int).
Result:
Reduce performance overhead while accept new connections with native transport
Motivation:
So far, our TLS renegotiation test did not test changing cipher suite
during renegotiation explicitly.
Modifications:
- Switch the cipher suite during renegotiation
Result:
We are now sure the cipher suite change works.
Motivation:
We only provided a constructor in DefaultFileRegion that takes a FileChannel which means the File itself needs to get opened on construction. This has the problem that if you want to write a lot of Files very fast you may end up with may open FD's even if they are not needed yet. This can lead to hit the open FD limit of the OS.
Modifications:
Add a new constructor to DefaultFileRegion which allows to construct it from a File. The FileChannel will only be obtained when transferTo(...) is called or the DefaultFileRegion is explicit open'ed via open() (this is needed for the native epoll transport)
Result:
Less resource usage when writing a lot of DefaultFileRegion.
Related: #3125
Motivation:
We did not expose a way to initiate TLS renegotiation and to get
notified when the renegotiation is done.
Modifications:
- Add SslHandler.renegotiate() so that a user can initiate TLS
renegotiation and get the future that's notified on completion
- Make SslHandler.handshakeFuture() return the future for the most
recent handshake so that a user can get the future of the last
renegotiation
- Add the test for renegotiation to SocketSslEchoTest
Result:
Both client-initiated and server-initiated renegotiations are now
supported properly.
Motivation:
So far, we relied on the domain name resolution mechanism provided by
JDK. It served its purpose very well, but had the following
shortcomings:
- Domain name resolution is performed in a blocking manner.
This becomes a problem when a user has to connect to thousands of
different hosts. e.g. web crawlers
- It is impossible to employ an alternative cache/retry policy.
e.g. lower/upper bound in TTL, round-robin
- It is impossible to employ an alternative name resolution mechanism.
e.g. Zookeeper-based name resolver
Modification:
- Add the resolver API in the new module: netty-resolver
- Implement the DNS-based resolver: netty-resolver-dns
.. which uses netty-codec-dns
- Make ChannelFactory reusable because it's now used by
io.netty.bootstrap, io.netty.resolver.dns, and potentially by other
modules in the future
- Move ChannelFactory from io.netty.bootstrap to io.netty.channel
- Deprecate the old ChannelFactory
- Add ReflectiveChannelFactory
Result:
It is trivial to resolve a large number of domain names asynchronously.
Motivation:
JDK's exception messages triggered by a connection attempt failure do
not contain the related remote address in its message. We currently
append the remote address to ConnectException's message, but I found
that we need to cover more exception types such as SocketException.
Modifications:
- Add AbstractUnsafe.annotateConnectException() to de-duplicate the
code that appends the remote address
Result:
- Less duplication
- A transport implementor can annotate connection attempt failure
message more easily
Motivation:
We use malloc(1) in the on JNI_OnLoad method but never free the allocated memory. This means we have a tiny memory leak of 1 byte.
Modifications:
Call free(...) on previous allocated memory.
Result:
Fix memory leak
Motiviation:
If sendmmsg is already defined then the native epoll module failed to build because of conflicting definitions.
The mmsghdr type was also redefined on systems that already supported this structure.
Modifications:
Provide a way so that systems which already define sendmmsg and mmsghdr can build
Provide a way so that systems which don't define sendmmsg and mmsghdr can build
Result:
The native EPOLL module can build in more environments
Motivation:
In linux it is possible to write more then one buffer withone syscall when sending datagram messages.
Modifications:
Not copy CompositeByteBuf if it only contains direct buffers.
Result:
More performance due less overhead for copy.
Motivation:
On linux with glibc >= 2.14 it is possible to send multiple DatagramPackets with one syscall. This can be a huge performance win and so we should support it in our native transport.
Modification:
- Add support for sendmmsg by reuse IovArray
- Factor out ThreadLocal support of IovArray to IovArrayThreadLocal for better separation as we use IovArray also without ThreadLocal in NativeDatagramPacketArray now
- Introduce NativeDatagramPacketArray which is used for sendmmsg(...)
- Implement sendmmsg(...) via jni
- Expand DatagramUnicastTest to test also sendmmsg(...)
Result:
Netty now automatically use sendmmsg(...) if it is supported and we have more then 1 DatagramPacket in the ChannelOutboundBuffer and flush() is called.
Motivation:
On linux it is possible to use the sendMsg(...) system call to write multiple buffers with one system call when using datagram/udp.
Modifications:
- Implement the needed changes and make use of sendMsg(...) if possible for max performance
- Add tests that test sending datagram packets with all kind of different ByteBuf implementations.
Result:
Performance improvement when using CompoisteByteBuf and EpollDatagramChannel.
Motivation:
InetAddress.getByName(...) uses exceptions for control flow when try to parse IPv4-mapped-on-IPv6 addresses. This is quite expensive.
Modifications:
Detect IPv4-mapped-on-IPv6 addresses in the JNI level and convert to IPv4 addresses before pass to InetAddress.getByName(...) (via InetSocketAddress constructor).
Result:
Eliminate performance problem causes by exception creation when parsing IPv4-mapped-on-IPv6 addresses.
Motivation:
In EpollSocketchannel.doWriteFileRegion(...) we need to make sure we write until sendFile(...) returns either 0 or all is written. Otherwise we may not get notified once the Channel is writable again.
This is the case as we use EPOLL_ET.
Modifications:
Always write until either sendFile returns 0 or all is written.
Result:
No more hangs when writing DefaultFileRegion can happen.
Motivation:
There were no way to efficient write a CompositeByteBuf as we always did a memory copy to a direct buffer in this case. This is not needed as we can just write a CompositeByteBuf as long as all the components are buffers with a memory address.
Modifications:
- Write CompositeByteBuf which contains only direct buffers without memory copy
- Also handle CompositeByteBuf that have more components then 1024.
Result:
More efficient writing of CompositeByteBuf.
Related issue: #2764
Motivation:
EpollSocketChannel.writeFileRegion() does not handle the case where the
position of a FileRegion is non-zero properly.
Modifications:
- Improve SocketFileRegionTest so that it tests the cases where the file
transfer begins from the middle of the file
- Add another jlong parameter named 'base_off' so that we can take the
position of a FileRegion into account
Result:
Improved test passes. Corruption is gone.
Motivation:
At the moment it's only possible for a user to set the RecvByteBufAllocator for a Channel but not access the Handle once it is assigned. This makes it hard to write more flexible implementations.
Modifications:
Add a new method to the Channel.Unsafe to allow access the the used Handle for the Channel. The RecvByteBufAllocator.Handle is created lazily.
Result:
It's possible to write more flexible implementatons that allow to adjust stuff on the fly for a Handle that is used by a Channel
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
Related issue: #2733
Motivation:
Unlike OpenSsl, Epoll lacks a couple useful availability checker
methods:
- ensureAvailability()
- unavailabilityCause()
Modifications:
Add missing methods
Result:
More ways to check the availability and to get the cause of
unavailability programatically.
Motivation:
We sometimes not use the correct exception message when throw it from the native code.
Modifications:
Fixed the message.
Result:
Correct message in exception
Motivation:
We have some inconsistency when handling writes. Sometimes we call ChannelOutboundBuffer.progress(...) also for complete writes and sometimes not. We should call it always.
Modifications:
Correctly call ChannelOuboundBuffer.progress(...) for complete and incomplete writes.
Result:
Consistent behavior
Motivation:
While optimize gathering writes I introduced a bug when writing single ByteBuf that have a memoryAddress. This regression was introduced by 88bd6e7a93.
Modifications:
Correctly use the writerIndex as argument when call Native.writeAddress(...)
Result:
No more corruption while write single buffers.
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
Motivation:
At the moment we use Get*ArrayElement all the time in the epoll transport which may be wasteful as the JVM may do a memory copy for this. For code-path that will get executed fast (without blocking) we should better make use of GetPrimitiveArrayCritical and ReleasePrimitiveArrayCritical as this signal the JVM that we not want to do any memory copy if not really needed. It is important to only do this on non-blocking code-path as this may even suspend the GC to disallow the JVM to move the arrays around.
See also http://docs.oracle.com/javase/7/docs/technotes/guides/jni/spec/functions.html#GetPrimitiveArrayCritical
Modification:
Make use of GetPrimitiveArrayCritical / ReleasePrimitiveArrayCritical as replacement for Get*ArrayElement / Release*ArrayElement where possible.
Result:
Better performance due less memory copies.
Motivation:
In EpollSocketchannel.writeBytesMultiple(...) we loop over all buffers to see if we need to adjust the readerIndex for incomplete writes. We can skip this if we know that everything was written (a.k.a complete write).
Modification:
Use fast-path if all bytes are written and so no need to loop over buffers
Result:
Fast write path for the average use.
Motivation:
At the moment NioSocketChannelOutboundBuffer.nioBuffers() / EpollSocketChannelOutboundBuffer.memoryAddresses() returns null if something is contained in the ChannelOutboundBuffer which is not a ByteBuf. This is a problem for two reasons:
1 - In the javadocs we state that it will never return null
2 - We may do a not optimal write as there may be things that could be written via gathering writes
Modifications:
Change NioSocketChannelOutboundBuffer.nioBuffers() / EpollSocketChannelOutboundBuffer.memoryAddresses() to never return null but have it contain all ByteBuffer that were found before the non ByteBuf. This way we can do a gathering write and also conform to the javadocs.
Result:
Better speed and also correct implementation in terms of the api.
Motivation:
In the previous fix for #2667 I did introduce a bit overhead by calling setEpollOut() too often.
Modification:
Only call setEpollOut() if really needed and remove unused code.
Result:
Less overhead when saturate network.
Motivation:
As a DatagramChannel supports to write to multiple remote peers we must not close the Channel once a IOException accours as this error may be only valid for one remote peer.
Modification:
Continue writing on IOException.
Result:
DatagramChannel can be used even after an IOException accours during writing.
Motivation:
We need to continue write until we hit EAGAIN to make sure we not see an starvation
Modification:
Write until EAGAIN is returned
Result:
No starvation when using native transport with ET.
Motivation:
Because of a missing return statement we may produce a NPE when try to fullfill the connect ChannelPromise when it was fullfilled before.
Modification:
Add missing return statement.
Result:
No more NPE.
Motivation:
The handling of IOV_MAX was done in JNI code base which makes stuff really complicated to maintain etc.
Modifications:
Move handling of IOV_MAX to java code to simplify stuff
Result:
Cleaner code.
Motivation:
In our nio implementation we use write-spinning for maximize throughput, but in the native implementation this is not used.
Modification:
Respect writeSpinCount in native transport.
Result:
Better throughput
Motivation:
Currently when Native.writev(...) is used it is possible to see a JVM segfault because the offset is updated to early.
Modification:
Only update the offset once it is safe to do so.
Result:
No more segfault
Motivation:
epoll transport fails on gathering write of more then 1024 buffers. As linux supports max. 1024 iov entries when calling writev(...) the epoll transport throws an exception.
Thanks again to @blucas to provide me with a reproducer and so helped me to understand what the issue is.
Modifications:
Make sure we break down the writes if to many buffers are uses for gathering writes.
Result:
Gathering writes work with any number of buffers
Motivation:
Currently it is impossible to build netty on linux system that not define SO_REUSEPORT even if it is supported.
Modification:
Define SO_REUSEPORT if not defined.
Result:
Possible to build on more linux dists.
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 we do a (env*)->GetObjectArrayElement(...) call we may created many local references which will only be cleaned up once we exist the native method. Thus a lot of memory can be used and so a StackOverFlow may be triggered. Beside this the JNI specification only say that an implementation must cope with 16 local references.
Modification:
Call (env*)->ReleaseLocalRef(...) to release the resource once not needed anymore.
Result:
Less memory usage and guard against StackOverflow
Motivation:
At the moment there is no simple way for a user to check if the native epoll transport can be used on the running platform. Thus the user can only try to instance it and catch any exception and fallback to nio transport.
Modification:
Add Epoll.isAvailable() which allows to check if epoll can be used.
Result:
User can easily check if epoll transport can be used or not
Motivation:
When using openjdk and oracle jdk's nio (while using the nio transport) the ServerSocketChannel uses SO_REUSEADDR by default. Our native transport should do the same to make it easier to switch between the different implementations and get the expected result.
Modification:
Change EpollServerSocketChannelConfig to set SO_REUSEADDR on the created socket.
Result:
SO_REUSEADDR is used by default on servers.
Motivation:
We need to map from ints to AbstractEpollChannel in EpollEventLoop but there is no need for box to Integer.
Modification:
Replace Map with IntObjectMap.
Result:
No more auto-boxing needed.
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:
At the moment we sometimes use only RecvByteBufAllocator.guess() to guess the next size and the use the ByteBufAllocator.* directly to allocate the buffer. We should always use RecvByteBufAllocator.allocate(...) all the time as this makes the behavior easier to adjust.
Modifications:
Change the read() implementations to make use of RecvByteBufAllocator.
Result:
Behavior is more consistent.
Motivation:
When doing a gathering write we need to update the indices after the write partial completes. In the current code-base we use the wrong value when compare the expected written bytes and the actual written bytes.
Modifications:
Use the correct value when compare.
Result:
Indices are updated correctly and so no corruption can happen when resume writing after data was only partial written before.
Motivation:
oss.sonatype.org refuses to promote an artifact if it doesn't have the
default JAR (the JAR without classifier.)
Modifications:
- Generate both the default JAR and the native JAR to make
oss.sonatype.org happy
- Rename the profile 'release' to 'restricted-release' which reflects
what it really does better
- Remove the redundant <quickbuild>true</quickbuild> in all/pom.xml
We specify the profile 'full' that triggers that property already
in maven-release-plugin configuration.
Result:
oss.sonatype.org is happy. Simpler pom.xml
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:
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:
Remove ChannelHandlerInvoker.writeAndFlush(...) and the related
implementations.
Result:
4.1 and master got closer.
Motivation:
AbstractEpollChannel.clearEpollIn() throws an IllegalStateException if a user tries to change the autoRead configuration for the Channel and the Channel is not registered on an EventLoop yet. This makes it for example impossible to set AUTO_READ to false via the ServerBootstrap as the configuration is modifed before the Channel is registered.
Modification:
Check if the Channel is registered and if not just modify the flags directly so they are respected once the Channel is registered
Result:
It is possible now to configure AUTO_READ via the ServerBootstrap
Motivation:
We are currently try to modify the events via EpollEventLoop even when the channel was closed before and so the fd was set to -1. This fails with a RuntimeException in this case.
Modification:
Always check if the Channel is still open before try to modify the events.
Result:
No more RuntimeException because of a not open channel
Motivation:
Currently the generics used for TCP_KEEPIDLE, TCP_KEEPINTVL and TCP_KEEPCNT are incorrect.
Modifications:
Use Integer as type
Result:
User can use TCP_KEEPIDLE, TCP_KEEPINTVL and TCP_KEEPCNT as expected
Motivation:
EpollDatagramChannel produced buffer leaks when tried to read from the channel and nothing was ready to be read.
Modifications:
Correctly release buffer if nothing was read
Result:
No buffer leak
Motivation:
Allow to set TCP_KEEPIDLE, TCP_KEEPINTVL and TCP_KEEPCNT in native transport to offer the user with more flexibility.
Modifications:
Expose methods to set these options and write the JNI implementation.
Result:
User can now use TCP_KEEPIDLE, TCP_KEEPINTVL and TCP_KEEPCNT.
Motivation:
With SO_REUSEPORT it is possible to bind multiple sockets to the same port and so handle the processing of packets via multiple threads. This allows to handle DatagramPackets with more then one thread on the same port and so gives better performance.
Modifications:
Expose EpollDatagramChannelConfig.setReusePort(..) and isReusePort()
Result:
Allow to bind multiple times to the same local address and so archive better performance.
Motivation:
At the moment ChanneConfig.setAutoRead(false) only is guaranteer to not have an extra channelRead(...) triggered when used from within the channelRead(...) or channelReadComplete(...) method. This is not the correct behaviour as it should also work from other methods that are triggered from within the EventLoop. For example a valid use case is to have it called from within a ChannelFutureListener, which currently not work as expected.
Beside this there is another bug which is kind of related. Currently Channel.read() will not work as expected for OIO as we will stop try to read even if nothing could be read there after one read operation on the socket (when the SO_TIMEOUT kicks in).
Modifications:
Implement the logic the right way for the NIO/OIO/SCTP and native transport, specific to the transport implementation. Also correctly handle Channel.read() for OIO transport by trigger a new read if SO_TIMEOUT was catched.
Result:
It is now also possible to use ChannelConfig.setAutoRead(false) from other methods that are called from within the EventLoop and have direct effect.
Conflicts:
transport-sctp/src/main/java/io/netty/channel/sctp/nio/NioSctpChannel.java
transport/src/main/java/io/netty/channel/socket/nio/NioDatagramChannel.java
transport/src/main/java/io/netty/channel/socket/nio/NioSocketChannel.java
Motivation:
There is currently no epoll based DatagramChannel. We should add one to make the set of provided channels complete and also to be able to offer better performance compared to the NioDatagramChannel once SO_REUSEPORT is implemented.
Modifications:
Add implementation of DatagramChannel which uses epoll. This implementation does currently not support multicast yet which will me implemented later on. As most users will not use multicast anyway I think it is fair to just add the EpollDatagramChannel without the support for now. We shipped NioDatagramChannel without support earlier too ...
Result:
Be able to use EpollDatagramChannel for max. performance on linux
Motivation:
In linux kernel 3.9 a new featured named SO_REUSEPORT was introduced which allows to have multiple sockets bind to the same port and so handle the accept() of new connections with multiple threads. This can greatly improve the performance when you not to accept a lot of connections.
Modifications:
Implement SO_REUSEPORT via JNI
Result:
Be able to use the SO_REUSEPORT feature when using the EpollServerSocketChannel
Motivation:
We sometimes see data corruption when writing to the EpollSocketChannel.
Modifications:
Correctly update the position of the ByteBuffer after something was written.
Result:
Fix data-corruption which could happen on partial writes
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:
EpollSocketChannel.remoteAddress0() is always null on accepted EpollSocketChannels as we not set it excplicit.
Modifications:
Correctly retrieve the local and remote address when accept new channel and store it
Result:
EpollSocketchannel.remoteAddress0() and EpollSocketChannel.localAddress0() return correct addresses
Motivation:
Native.epollCreate(...) fails on systems using a kernel < 2.6.27 / glibc < 2.9 because it uses epoll_create1(...) without checking if it is present
Modifications:
Check if epoll_create1(...) exists abd if not fall back to use epoll_create(...)
Result:
Works even on systems with kernel < 2.6.27 / glibc < 2.9
Motivation:
While the default thread model provided by Netty is reasonable enough for most applications, some users might have a special requirement for the thread model. Here are a few examples:
- A user might want to invoke handlers from the caller thread directly, assuming that his or her application is completely asynchronous and does not make any invocation from non-I/O thread. In this case, the default invoker implementation will only add the overhead of checking if the current thread is an I/O thread or not.
- A user might want to invoke handlers from different threads depending on the type of events flexibly.
Modifications:
- Backport 132af3a485 which is a fix for #1912
- Add a new interface called 'ChannelHandlerInvoker' that performs the invocation of event handler methods.
- Add pipeline manipulation methods that accept ChannelHandlerInvoker
- The differences from the original commit:
- Separated the irrelevant changes out
- Channel.eventLoop is null until the registration is complete in this branch, so Channel.Unsafe.invoker() doesn't work before registration.
- Deregistration is not gone in this branch, so the methods related with deregistration were added to ChannelHandlerInvoker
Motivation:
Make sure the remote/local InetSocketAddress can be obtained correctly
Modifications:
Set the remote/local InetSocketAddress after a bind/connect operation was performed
Result:
It is possible to still access the informations even after the fd became invalid. This mirror the behaviour of NIO.
Motivation:
The epoll testsuite tests the epoll transport only against itself (i.e. epoll x epoll only). We should test the epoll transport also against the well-tested NIO transport, too.
Modifications:
- Make SocketTestPermutation extensible and reusable so that the epoll testsuite can take advantage of it.
- Rename EpollTestUtils to EpollSocketTestPermutation and make it extend SocketTestPermutation.
- Overall clean-up of SocketTestPermutation
- Use Arrays.asList() for simplicity
- Add combo() method to remove code duplication
Result:
The epoll transport is now also tested against the NIO transport. SocketTestPermutation got cleaner.
Motivation:
Previous commit (2de65e25e9) introduced a regression that makes the epoll testsuite fail with an 'incompatible event loop' error.
Modifications:
Use the correct event loop type.
Result:
Build doesn't fail anymore.
Motivation:
We are seeing EpollSocketSslEchoTest does not finish itself while its I/O thread is busy. Jenkins should have terminated them when the global build timeout reaches, but Jenkins seems to fail to do so. What's more interesting is that Jenkins will start another job before the EpollSocketSslEchoTest is terminated, and Linux starts to oom-kill them, impacting the uptime of the CI service.
Modifications:
- Set timeout for all test cases in SocketSslEchoTest so that all SSL tests terminate themselves when they take too long.
- Fix a bug where the epoll testsuite uses non-daemon threads which can potentially prevent JVM from quitting.
- (Cleanup) Separate boss group and worker group just like we do for NIO/OIO transport testsuite.
Result:
Potentially more stable CI machine.
Motivation:
We better use UnresolveableAddressException as NIO does the same.
Modifications:
Replace usage of UnknownHostException with UnresolveableAddressException
Result:
epoll transport and nio transport behave the same way
Motivation:
At the moment when an unresolvable InetSocketAddress is passed into the epoll transport a NPE is thrown
Modifications:
Add check in place which will throw an UnknownHostException if an InetSocketAddress could not been resolved.
Result:
Proper handling of unresolvable InetSocketAddresses
