foundationdb/flow
Evan Tschannen f17f00fdd5 Merge branch 'release-6.2'
# Conflicts:
#	documentation/sphinx/source/release-notes.rst
2020-05-10 22:33:38 -07:00
..
actorcompiler Generate rvalue reference overloads with actor compiler 2020-04-21 15:18:59 -07:00
coveragetool Delete old build system 2020-04-07 11:03:45 -07:00
stacktrace_internal Import //base/debugging:stacktrace from abseil. 2017-10-16 16:05:02 -07:00
ActorCollection.actor.cpp remove memory-hungry benchmark 2019-05-17 14:12:44 -07:00
ActorCollection.h Merge branch 'release-5.2' of github.com:apple/foundationdb into feature-redwood 2018-04-06 16:29:37 -07:00
Arena.cpp Fix condition to check whether allocation tracing is enabled 2020-03-16 15:12:50 -07:00
Arena.h Merge branch 'master' into transaction-tagging 2020-05-09 07:50:29 -07:00
AsioReactor.h Separate AsioReactor sleep and react into two different functions. Track slow tasks and time spent in react, track time spent in launch. Don't track react time at priority 0. 2019-08-28 14:35:48 -07:00
CMakeLists.txt simple benchmarks of IndexedSet, VersionedMap and std::map 2020-05-07 12:08:00 -07:00
CompressedInt.actor.cpp Replace g_random and g_nondeterministic_random with functions deterministicRandom() and nondeterministicRandom() that return thread_local random number generators. Delete g_debug_random and trace_random. Allow only deterministicRandom() to be seeded, and require it to be seeded from each thread on which it is used. 2019-05-10 14:01:52 -07:00
CompressedInt.h Missing include, doesn't cause a compile error but IDE complains when viewing the file. 2020-04-01 02:41:16 -07:00
Deque.cpp Replace g_random and g_nondeterministic_random with functions deterministicRandom() and nondeterministicRandom() that return thread_local random number generators. Delete g_debug_random and trace_random. Allow only deterministicRandom() to be seeded, and require it to be seeded from each thread on which it is used. 2019-05-10 14:01:52 -07:00
Deque.h Request alignment that's at least sizeof(void*) 2019-12-02 12:51:33 -08:00
DeterministicRandom.cpp Apply A.J.'s suggestion to randomInt as well 2019-12-05 11:01:41 -08:00
DeterministicRandom.h Move DeterministicRandom impl to its own translation unit 2019-12-04 16:45:32 -08:00
Error.cpp Extend RebootRequest API to include time to suspend the process before reboot. This is intended to be used for testing purposes to simulate failures. 2019-06-14 11:35:38 -07:00
Error.h Remove unused parameter. Don't put check for g_network presence in ASSERT_WE_THINK. 2020-02-21 16:28:03 -08:00
EventTypes.actor.h Adjust all includes to be relative to the root. 2018-10-19 17:35:33 +00:00
FastAlloc.cpp flow: update headers and includes 2020-04-30 18:11:23 +00:00
FastAlloc.h Merge remote-tracking branch 'upstream/master' into features/icc 2020-02-04 10:26:18 -08:00
FastRef.h Remove obsolete function 2019-05-13 14:15:23 -07:00
FaultInjection.cpp Adjust all includes to be relative to the root. 2018-10-19 17:35:33 +00:00
FaultInjection.h remove trailing whitespace from our copyright headers ; fixed formatting of python setup.py 2018-02-21 10:25:11 -08:00
FileIdentifier.h Disallow scalars from being root types 2019-08-28 14:40:06 -07:00
FileTraceLogWriter.cpp Added back the changes that report trace log flush failures and fix the random crash 2020-03-12 14:34:19 -07:00
FileTraceLogWriter.h Added back the changes that report trace log flush failures and fix the random crash 2020-03-12 14:34:19 -07:00
Hash3.c Fixed headers and some whitespace 2018-02-23 04:50:23 -08:00
Hash3.h Add includes for missing definitions of size_t and uint32_t. 2018-08-14 15:50:26 -07:00
IDispatched.h remove trailing whitespace from our copyright headers ; fixed formatting of python setup.py 2018-02-21 10:25:11 -08:00
IKeyValueContainer.h replace double invocations of operator<() with three way compare(). 2020-05-07 12:08:29 -07:00
IRandom.h fix two correctness bugs in the comparison logic 2020-05-07 15:50:40 -07:00
IThreadPool.cpp When one of the sqlite reader or writer thread pools fail, fail the other with the same error. 2020-02-24 12:39:04 -08:00
IThreadPool.h Use DefaultOnMainThread if not on the main thread 2020-05-07 23:22:22 +00:00
IndexedSet.actor.h Add [[flow_allow_discard]] 2019-08-16 09:24:57 -07:00
IndexedSet.cpp fix MacOS + Windows build (std::random_shuffle has been deprecated + removed in newer versions of C++) 2020-05-07 12:09:40 -07:00
IndexedSet.h pr comment 2020-05-07 17:22:04 -07:00
JsonTraceLogFormatter.cpp Emit valid json for unprintable characters 2018-12-20 11:43:18 -08:00
JsonTraceLogFormatter.h Integrate JsonTraceLogFormatter into build system + more. 2018-12-13 22:07:16 -08:00
Knobs.cpp Merge branch 'master' into feature-proxy-load-balance 2020-05-01 09:19:39 -07:00
Knobs.h Merge branch 'master' into feature-proxy-load-balance 2020-05-01 09:19:39 -07:00
MetricSample.h Replace g_random and g_nondeterministic_random with functions deterministicRandom() and nondeterministicRandom() that return thread_local random number generators. Delete g_debug_random and trace_random. Allow only deterministicRandom() to be seeded, and require it to be seeded from each thread on which it is used. 2019-05-10 14:01:52 -07:00
Net2.actor.cpp Linux aarch64 port 2020-05-09 22:14:03 +00:00
Net2Packet.cpp Eliminate unnecessary memcpy 2019-07-11 23:03:31 -07:00
Net2Packet.h Support PacketBuffer's of arbitrary size 2019-07-11 23:03:31 -07:00
ObjectSerializer.h Add logging when file identifiers don't match 2020-03-12 11:06:53 -07:00
ObjectSerializerTraits.h Remove several nonsensical const uses 2019-10-26 14:30:34 -07:00
Platform.cpp Linux aarch64 port 2020-05-09 22:14:03 +00:00
Platform.h Linux aarch64 port 2020-05-09 22:14:03 +00:00
Profiler.actor.cpp Fix build with glibc 2.30 2020-01-23 09:28:18 +01:00
Profiler.h remove trailing whitespace from our copyright headers ; fixed formatting of python setup.py 2018-02-21 10:25:11 -08:00
ProtocolVersion.h shrink the serialized size of StorageServerInterface 2020-05-01 21:37:19 -07:00
README.md Add suggested nodiscards, and mention UNCANCELLABLE actors 2019-08-16 09:24:57 -07:00
RadixTree.h change getKey() interface, pass in uint8_t * only 2020-01-15 13:49:45 -08:00
SignalSafeUnwind.cpp Support compiling/running with thread sanitizer 2020-04-25 00:26:50 +00:00
SignalSafeUnwind.h Remove dl_iterate_phdr results caching that is used by slow task profiler, instead favoring disabling and reenabling profiling around the call. Add a mechanism to handle deferred profile requests. 2019-07-03 12:48:36 -07:00
SimpleOpt.h Adjust all includes to be relative to the root. 2018-10-19 17:35:33 +00:00
SourceVersion.h.cmake Rename hgVersion to sourceVersion. 2019-11-15 12:26:51 -08:00
Stats.actor.cpp Merge pull request #2741 from ajbeamon/roughness-cleanup 2020-03-17 15:45:35 -07:00
Stats.h Change a special case return to -1. Update comments to clarify and correct some things. 2020-02-26 16:39:13 -08:00
SystemMonitor.cpp Merge branch 'master' into per-priority-busy-logging 2020-04-15 08:31:30 -07:00
SystemMonitor.h Merge commit 'cf01233f28a2c42908656a39f458a4475c1d44a3' into run-loop-busy-profiler 2020-04-14 14:02:24 -07:00
TDMetric.actor.h replace double invocations of operator<() with three way compare(). 2020-05-07 12:08:29 -07:00
TDMetric.cpp Separate AsioReactor sleep and react into two different functions. Track slow tasks and time spent in react, track time spent in launch. Don't track react time at priority 0. 2019-08-28 14:35:48 -07:00
TLSConfig.actor.cpp Fix clients crashing in TLS code on exit. 2020-04-18 15:48:02 -07:00
TLSConfig.actor.h Fix clients crashing in TLS code on exit. 2020-04-18 15:48:02 -07:00
ThreadHelper.actor.h Fix some data races 2020-04-25 00:26:54 +00:00
ThreadHelper.cpp Adjust all includes to be relative to the root. 2018-10-19 17:35:33 +00:00
ThreadPrimitives.cpp flow: update headers and includes 2020-04-30 18:11:23 +00:00
ThreadPrimitives.h Linux aarch64 port 2020-05-09 22:14:03 +00:00
ThreadSafeQueue.h Consistent use of #if VALGRIND 2019-05-13 12:44:13 -10:00
Trace.cpp Fix invalid trace event detail named "Type" 2020-05-07 11:22:32 -07:00
Trace.h Merge pull request #2897 from tclinken/fix-trace-batch-loggroup-and-role 2020-04-13 11:22:51 -07:00
TreeBenchmark.h fix MacOS + Windows build (std::random_shuffle has been deprecated + removed in newer versions of C++) 2020-05-07 12:09:40 -07:00
UnitTest.cpp Adjust all includes to be relative to the root. 2018-10-19 17:35:33 +00:00
UnitTest.h Replace g_random and g_nondeterministic_random with functions deterministicRandom() and nondeterministicRandom() that return thread_local random number generators. Delete g_debug_random and trace_random. Allow only deterministicRandom() to be seeded, and require it to be seeded from each thread on which it is used. 2019-05-10 14:01:52 -07:00
Util.h Add a missing #include <algorithm> to flow/Util.h 2018-08-14 15:50:26 -07:00
XmlTraceLogFormatter.cpp Adjust all includes to be relative to the root. 2018-10-19 17:35:33 +00:00
XmlTraceLogFormatter.h Adjust all includes to be relative to the root. 2018-10-19 17:35:33 +00:00
actorcompiler.h Moved THIS and THIS_ADDR to actorcompiler.h 2019-02-19 15:16:59 -08:00
crc32c-generated-constants.cpp Move crc32c from fdbrpc to flow 2020-01-13 18:19:30 -08:00
crc32c.cpp Linux aarch64 port 2020-05-09 22:14:03 +00:00
crc32c.h Move crc32c from fdbrpc to flow 2020-01-13 18:19:30 -08:00
error_definitions.h Merge branch 'master' into atn34/special-key-versioning 2020-05-09 15:34:20 -07:00
flat_buffers.cpp Use VecSerStrategy::String 2020-05-02 01:05:58 +00:00
flat_buffers.h Merge branch 'master' into transaction-tagging 2020-05-07 14:52:22 -07:00
flow.cpp Checkpointing a bunch of work on throttles. Rudimentary implementation of auto-throttling. Support for manual throttling via fdbcli. Throttles are stored in the system keyspace. 2020-04-03 15:24:14 -07:00
flow.h Merge branch 'master' into transaction-tagging 2020-05-07 14:50:25 -07:00
genericactors.actor.cpp Avoid some unnecessary copies 2020-04-24 12:21:35 -07:00
genericactors.actor.h Avoid some unnecessary copies 2020-04-24 12:21:35 -07:00
network.cpp Update flow/network.cpp 2020-04-14 17:12:07 -07:00
network.h Merge branch 'release-6.2' 2020-05-10 22:33:38 -07:00
no_intellisense.opt Initial repository commit 2017-05-25 13:48:44 -07:00
serialize.cpp Revert "Revert "Make protocol version a type"" 2019-06-18 14:49:04 -07:00
serialize.h Remove offending overload? 2020-03-10 10:18:14 -07:00
sse2neon.h Linux aarch64 port 2020-05-09 22:14:03 +00:00
stacktrace.amalgamation.cpp Support compiling/running with thread sanitizer 2020-04-25 00:26:50 +00:00
stacktrace.h Import //base/debugging:stacktrace from abseil. 2017-10-16 16:05:02 -07:00
unactorcompiler.h Moved THIS and THIS_ADDR to actorcompiler.h 2019-02-19 15:16:59 -08:00
version.cpp Rename hgVersion to sourceVersion. 2019-11-15 12:26:51 -08:00

README.md

Flow Tutorial

Using Flow

Flow introduces some new keywords and flow controls. Combining these into workable units also introduces some new design patterns to C++ programmers.

Keywords/primitives

The essence of Flow is the capability of passing messages asynchronously between components. The basic data types that connect asynchronous senders and receivers are Promise<> and Future<>. The sender holds a Promise<X> to, sometime in the future, deliver a value of type X to the holder of the Future<X>. A receiver, holding a Future<X>, at some point needs the X to continue computation, and invokes the wait(Future<> f) statement to pause until the value is delivered. To use the wait() statement, a function needs to be declared as an ACTOR function, a special flow keyword which directs the flow compiler to create the necessary internal callbacks, etc. Similarly, When a component wants to deal not with one asynchronously delivered value, but with a series, there are PromiseStream<> and FutureStream<>. These two constructs allow for “reliable delivery” of messages, and play an important role in the design patterns.

Promise, Future

Promise<T> and Future<T> are intrinsically linked (they go in pairs) and are two wrappers around a construct called SingleAssignmentVar, a variable that can be set only once. A Promise is a handle to a SingleAssignmentVar that allows for a one-time set of the value; a Future is a read-only handle to the variable that only allows reading of the value.

The following example uses these two simple types:

Promise<int> p;
Future<int> f = p.getFuture();
p.send( 4 );
printf( "%d\n", f.get() ); // f is already set

Network traversal

Promises and futures can be used within a single process, but their real strength in a distributed system is that they can traverse the network. For example, one computer could create a promise/future pair, then send the promise to another computer over the network. The promise and future will still be connected, and when the promise is fulfilled by the remote computer, the original holder of the future will see the value appear.

[TODO: network delivery guarantees]

wait()

Wait allows for the calling code to pause execution while the value of a Future is set. This statement is called with a Future<T> as its parameter and returns a T; the eventual value of the Future. Errors that are generated in the code that is setting the Future, will be thrown from the location of the wait(), so Errors must be caught at this location.

The following example shows a snippet (from an ACTOR) of waiting on a Future:

Future<int> f = asyncCalculation(); // defined elsewhere
int count = wait( f );
printf( "%d\n", count );

It is worth nothing that, although the function wait() is declared in actorcompiler.h, this “function” is compiled by the Actor Compiler into a complex set of integrated statements and callbacks. It is therefore never present in generated code or at link time. Note : because of the way that the actor compiler is built, wait() must always assign the resulting value to a newly declared variable.

From 6.1, wait() on Void actors shouldn't assign the resulting value. So, the following code

Future<Void> asyncTask(); //defined elsewhere
Void _ = _wait(asyncTask());

becomes

Future<Void> asyncTask(); //defined elsewhere
wait(asyncTask());

ACTOR

The only code that can call the wait() function are functions that are themselves labeled with the “ACTOR” tag. This is the essential unit of asynchronous work that can be chained together to create complex message-passing systems. An actor, although declared as returning a Future<T>, simply returns a T. Because an actor may wait on the results of other actors, an actor must return either a Future or void. In most cases returning void is less advantageous than returning a Future, since there are implications for actor cancellation. See the Actor Cancellation section for details.

The following simple actor function waits on the Future to be ready, when it is ready adds offset and returns the result:

ACTOR Future<int> asyncAdd(Future<int> f, int offset) {
    int value = wait( f );
    return value + offset;
}

State Variables

Since ACTOR-labeled functions are compiled into a c++ class and numerous supporting functions, the variable scoping rules that normally apply are altered. The differences arise out of the fact that control flow is broken at wait() statements. Generally the compiled code is broken into chunks at wait statements, so scoping variables so that they can be seen in multiple “chunks” requires the state keyword. The following function waits on two inputs and outputs the sum with an offset attached:

ACTOR Future<int> asyncCalculation(Future<int> f1, Future<int> f2, int offset ) {
    state int value1 = wait( f1 );
    int value2 = wait( f2 );
    return value1 + value2 + offset;
}

Void

The Void type is used as a signalling-only type for coordination of asynchronous processes. The following function waits on an input, send an output to a Promise, and signals completion:

ACTOR Future<Void> asyncCalculation(Future<int> f, Promise<int> p, int offset ) {
    int value = wait( f );
    p.send( value + offset );
    return Void();
}

PromiseStream<>, FutureStream<>

PromiseStream and FutureStream are groupings of a series of asynchronous messages.

These allow for two important features: multiplexing and network reliability, discussed later. They can be waited on with the waitNext() function.

waitNext()

Like wait(), waitNext() pauses program execution and awaits the next value in a FutureStream. If there is a value ready in the stream, execution continues without delay. The following “server” waits on input, send an output to a PromiseStream:

ACTOR void asyncCalculation(FutureStream<int> f, PromiseStream<int> p, int offset ) {
    while( true ) {
        int value = waitNext( f );
        p.send( value + offset );
    }
}

choose / when

The choose / when construct allows an Actor to wait for multiple Future events at once in a ordered and predictable way. Only the when associated with the first future to become ready will be executed. The following shows the general use of choose and when:

choose {
    when( int number = waitNext( futureStreamA ) ) {
        // clause A
    }
    when( std::string text = wait( futureB ) ) {
        // clause B
    }
}

You can put this construct in a loop if you need multiple when clauses to execute.

Future composition

Futures can be chained together with the result of one depending on the output of another.

ACTOR Future<int> asyncAddition(Future<int> f, int offset ) {
    int value = wait( f );
    return value + offset;
}

ACTOR Future<int> asyncDivision(Future<int> f, int divisor ) {
    int value = wait( f );
    return value / divisor;
}

ACTOR Future<int> asyncCalculation( Future<int> f ) {
    int value = wait( asyncDivision(
    asyncAddition( f, 10 ), 2 ) );
    return value;
}

Design Patterns

RPC

Many of the “servers” in FoundationDB that communicate over the network expose their interfaces as a struct of PromiseStreams--one for each request type. For instance, a logical server that keeps a count could look like this:

struct CountingServerInterface {
    PromiseStream<int> addCount;
    PromiseStream<int> subtractCount;
    PromiseStream<Promise<int>> getCount;

    // serialization code required for use on a network
    template <class Ar>
    void serialize( Ar& ar ) {
        serializer(ar, addCount, subtractCount, getCount);
    }
};

Clients can then pass messages to the server with calls such as this:

CountingServerInterface csi = ...; // comes from somewhere
csi.addCount.send(5);
csi.subtractCount.send(2);
Promise<int> finalCount;
csi.getCount.send(finalCount);
int value = wait( finalCount.getFuture() );

There is even a utility function to take the place of the last three lines: [TODO: And is necessary when sending requests over a real network to ensure delivery]

CountingServerInterface csi = ...; // comes from somewhere
csi.addCount.send(5);
csi.subtractCount.send(2);
int value = wait( csi.getCount.getReply<int>() );

Canonically, a single server ACTOR that implements the interface is a loop with a choose statement between all of the request types:

ACTOR void serveCountingServerInterface(CountingServerInterface csi) {
    state int count = 0;
    loop {
        choose {
            when (int x = waitNext(csi.addCount.getFuture())){
                count += x;
            }
            when (int x = waitNext(csi.subtractCount.getFuture())){
                count -= x;
            }
            when (Promise<int> r = waitNext(csi.getCount.getFuture())){
                r.send( count ); // goes to client
            }
        }
    }
}

In this example, the add and subtract interfaces modify the count itself, stored with a state variable. The get interface is a bit more complicated, taking a Promise<int> instead of just an int. In the interface class, you can see a PromiseStream<Promise<int>>. This is a common construct that is analogous to sending someone a self-addressed envelope. You send a promise to a someone else, who then unpacks it and send the answer back to you, because you are holding the corresponding future.

Flatbuffers/ObjectSerializer

  1. Introduction

    The goal is to have a more robust serialization protocol. One feature of flatbuffers is that you can add a new field to a network message without requiring a protocol-incompatible upgrade. In order for this to work, correctness must not depend on that field always being present. This can be tested in simulation by randomly (use buggify) default-initializing that field when deserializing. Once you make a protocol-incompatible upgrade you can rely on the field always being present in the new protocol, just like before. Currently we are using a custom flatbuffers implementation so to that we can present (roughly) the same serialization api as before. Currently the ObjectSerializer is only used for network messages, but that may change. Flatbuffers was selected because it is (relatively) simple among protocols providing forwards/backwards compatibility, and its binary format is well documented

  2. Correspondence to flatbuffers IDL

    • Tables
    // Flow type
    struct A {
        constexpr static FileIdentifier file_identifier = 12345;
        int a;
        template <class Ar>
        void serialize(Ar& ar) {
            serializer(ar, a);
        }
    }
    
    // IDL equivalent
    table A {
        a:int;
    }
    
    • Unions
    // Flow type
    using T = boost::variant<A, B, C>;
    
    // IDL equivalent
    union T { A, B, C}
    
    • Strings (there's a string type in the idl that guarantees null termination, but flow does not, so it's comparable to a vector of bytes)
    // Flow type
    StringRef, std::string
    
    // IDL equivalent
    [ubyte]
    
    • Vectors
    // Flow type
    VectorRef<T>, std::vector<T>
    
    // IDL equivalent
    [T]
    
  3. Flatbuffers Traits

    In order to serialize a type as a flatbuffers vector, struct, or union, you can implement the appropriate trait for your type.

    • scalar_traits corresponds to a flatbuffers struct. See UID for an example.
    • vector_like_traits corresponds to a flatbuffers vector. See VectorRef for an example.
    • dynamic_size_traits corresponds to a flatbuffers vector of uint8_t. See StringRef for an example.
    • union_like_traits corresponds to a flatbuffers union. See boost::variant for an example.
  4. Potential Gotchas

    • Flatbuffers 'vtables' are collected from default-constructed instances of each type. Consequently types serialized by flatbuffers should have cheap default constructors. Future work: we may be able to collect vtables without an instance of a type using declval.

    • T::serialize may get called multiple times when serializing T. It is guaranteed to be called only once for deserialization though, and thus the Ar::isDeserializing idiom is appropriate. Future work: in theory we don't need to call T::serialize multiple times when serializing, but this would complicate the implementation.

    • In a call to serializer, arenas must come after any members whose memory the arena owns. It's safe to reorder an arena in a serializer call because arenas are ignored for the flatbuffers schema. (Future work) Enforce that no fields appear after an arena at compile time.

  5. File identifiers

    File identifiers are used to sanity check that the message you're deserializing is of the schema you expect. You can give a type T a file identifier by making T::file_identifier a static member of type FileIdentifier. If you don't control T, you can specialize the FileIdentifierFor template. See flow/FileIdentifier.h for examples. You don't need to change the file identifier for a type when evolving its schema.

  6. Schema evolution

    Two schemas are forward/backward compatible if they meet the following requirements. (Future work) Any fields that are not common to both schemas should be default-initialized in deserialized messages. Currently they will be uninitialized if their default constructor doesn't initialize.

    • Two tables are compatible if one table's fields are all compatible with a prefix of the other table's fields.
    • Two vectors are compatible if their element types are compatible.
    • Two unions are compatible if one union's fields are all compatible with a prefix of the other union's fields.
    • Two scalar types are only compatible if they are equal.
  7. Deprecation

    Flatbuffers allows fields to be deprecated, and a deprecated field consumes only two bytes on the wire. (Future work) Introduce Deprecated<...> template or something similar so that we can write smaller messages for deprecated fields.

ACTOR return values

An actor can have only one returned Future, so there is a case that one actor wants to perform some operation more than once:

ACTOR Future<Void> periodically(PromiseStream<Void> ps, int seconds) {
    loop {
        wait( delay( seconds ) );
        ps.send(Void());
    }
}

In this example, the PromiseStream is actually a way for the actor to return data from some operation that it ongoing.

By default it is a compiler error to discard the result of a cancellable actor. If you don't think this is appropriate for your actor you can use the [[flow_allow_discard]] attribute. This does not apply to UNCANCELLABLE actors.

“gotchas”

Actor compiler

There are some things about the actor compiler that can confuse and may change over time

Switch statements

Do not use these with wait statements inside!

try/catch with no wait()

When a try/catch block does not wait() the blocks are still decomposed into separate functions. This means that variables that you want to access both before and after such a block will need to be declared state.

ACTOR cancellation

When the reference to the returned Future of an actor is dropped, that actor will be cancelled. Cancellation of an actor means that any wait()s that were currently active (the callback was currently registered) will be delivered an exception (actor_cancelled). In almost every case this exception should not be caught, though there are cetainly exceptions!

Memory Management

Reference Counting

The FoundationDB solution uses reference counting to manage the lifetimes of many of its constituent classes. In order for a class T to be reference counted, the following two globally defined methods must be defined (see FastRef.h):

void addref(T*);
void delref(T*);

The easiest way to implement these methods is by making your class a descendant of ReferenceCounted.

NOTE: Any descendants of ReferenceCounted should either have virtual destructors or be sealed. If you fail to meet these criteria, then references to descendants of your class will never be deleted.

If you choose not to inherit from ReferenceCounted, you will have to manage the reference count yourself. One way this can be done is to define void addref() and void delref() methods on your class, which will make it compatible with the existing global addref and delref methods. Otherwise, you will need to create the global addref and delref methods for your class, as mentioned above. In either case, you will need to manage the reference count on your object and delete it when the count reaches 0. Note that the reference count should usually be initialized to 1, as the addRef(T*) function is not called when the object is created.

To create a reference counted instance of a class T, you instantiate a Reference<T> on the stack with a pointer to your T object:

Reference<T> refCountedInstance(new T());

The Reference<T> class automatically calls addref on your T instance every time it is copied (such as by argument passing or assignment), but not when the object is initially created (consequently, ReferenceCounted classes are initialized with reference count 1). It will call delref on your T instance whenever a particular Reference<T> instance gets deleted (usually by going out of scope). When no more instances of Reference<T> holding a particular T instance exist, then that T instance will be destroyed.

Potential Gotchas

Reference Cycles

You must be cautious about creating reference cycles when using reference counting. For example, if two Reference<T> objects refer to each other, then without specific intervention their reference counts will never reach 0 and the objects will never be deleted.

Arenas

In addition to using reference counting, the FoundationDB solution also uses memory pools to allocate buffers. In this scheme, buffers are allocated from a common pool, called an Arena, and remain valid for the entire lifetime of that Arena. When the Arena is destroyed, all of the memory it held for the buffers is deallocated along with it. As a general convention, types which can use these Arenas and do not manage their own memory are given the "Ref" suffix. When a *Ref object is being used, consideration should be given to how its buffers are being managed (much in the same way that you would consider memory management when you see a T*).

As an example, consider the StringRef class. A StringRef is an object which contains a pointer to a sequence of bytes, but does not actually manage that buffer. Thus, if a StringRef is deallocated, the data remains intact. Conversely, if the data is deallocated, the StringRef becomes invalid. In order for the StringRef to manage its own buffer, we need to create an instance of the Standalone<StringRef> class:

Standalone<StringRef> str("data");

A Standalone<T> object has its own arena (technically, it is an Arena), and for classes like StringRef which support the use of arenas, the memory buffers used by the class are allocated from that arena. Standalone<T> is also a subclass of T, and so for all other purposes operates just like a T.

There are a number of classes which support the use of arenas, and some which have convenience types for their Standalone versions (not a complete list):

T Standalone alias
StringRef N/A
LiteralStringRef N/A
KeyRef Key
ValueRef Value
KeyValueRef KeyValue
KeyRangeRef KeyRange
KeySelectorRef KeySelector
VectorRef N/A

The VectorRef<T> class is an std::vector-like object which is used to manage a list of these *Ref objects. A Standalone<VectorRef<T>> has its own arena which can be used to store the buffers held by its constituents. In order for that to happen, one of the two deep insertion methods (push_back_deep or append_deep) should be used when placing items in the vector. The shallow insertion methods will hold the objects only; any arena-managed memory is not copied. Thus, the Standalone<VectorRef<T>> will hold the T objects without managing their memory. Note that the arena(s) used by the VectorRef need not be its own (and cannot be unless the VectorRef is a Standalone object), and are determined by arguments to the functions that insert items.

VectorRef<T> can also be used with types besides the standard Ref types, in which case the deep copy methods should not be used. In this case, the VectorRef<T> object holds the items in an arena much like a normal vector would hold the items in its buffer. Again, the arena used by the VectorRef<T> need not be its own.

When a Standalone<T> is copied (e.g. by argument passing or assignment) to another Standalone<T>, they will share the same memory. The actual memory contents of the arena are stored in a reference counted structure (ArenaBlock), so the memory will persist until all instances of Arena holding that memory are destroyed. If instead a T object is copied to a Standalone<T>, then its entire contents are copied into the arena of the new Standalone<T> object using a deep copy. Thus, it is generally more efficient to consistently use *Ref objects and manage the memory with something external, or to consistently use Standalone<T> objects (where assignments just increment reference counters) to avoid memory copies.

Potential Gotchas

Function Creating and Returning a non-Standalone Ref Object

A function which creates a Ref object should generally return a Standalone version of that object. Otherwise, make certain that the Arena on which that Ref object was created still exists when the caller uses the returned Ref.

Assigning Returned Standalone Object to non Standalone Variable

A caller which receives a Standalone return value should assign that return value to a Standalone variable. Consider the following example:

Standalone<StringRef> foo() {
    return Standalone<StringRef>("string");
}

void bar() {
    StringRef val = foo();
}

When val is copy-assigned in bar, its data is stored in the Arena of the StringRef that was returned from foo. When this returned StringRef is subsequently deallocated, val will no longer be valid.

Use of Standalone Objects in ACTOR Functions

Special care needs to be taken when using using Standalone values in actor functions. Consider the following example:

ACTOR Future<void> foo(StringRef param)
{
    //Do something
    return Void();
}

ACTOR Future<Void> bar()
{
    Standalone<StringRef> str("string");
    wait(foo(str));
    return Void();
}

Although it appears at first glance that bar keeps the Arena for str alive during the call to foo, it will actually go out of scope in the class generated by the actor compiler. As a result, param in foo will become invalid. To prevent this, either declare param to be of type Standalone<StringRef> or make str a state variable.