Summary:
Becuase when we clone an existing packet, the logic inside the current
writetStreamFrameHeader is no longer correct.
Reviewed By: mjoras
Differential Revision: D21383828
fbshipit-source-id: 8e6bbb048eefd97ca7cf17b89edc2f395f274a73
Summary:
Currently the packet builder contructor will encode the packet
builder. This is fine when the builder creates its own output buffer. If later
on we decides not to use this builder, or it fails to build packet, the buffer
will be thrown away. But once the builder uses a buffer provided by caller, and
will be reused, we can no longer just throw it away if we decide not to use
this builder. So we have to delay the header encoding until we know we will use
the builder.
This is still not enough to solve the case where we want to use this builder,
it builds, then it fails . For that, we will need to retreat the tail position
of the IOBuf.
Reviewed By: mjoras
Differential Revision: D21000658
fbshipit-source-id: 4d758b3e260463b17c870618ba68bd4b898a7d4c
Summary:
As it turns out, the extra indirection from storing a unique_ptr is not worse than the gain from using an `F14ValueMap` versus an `F14VectorMap`.
This reduces the `find` cost measurably in profiles, and doesn't appear to have any real negative effects otherwise.
Reviewed By: yangchi
Differential Revision: D20923854
fbshipit-source-id: a75c4649ea3dbf0e6c89ebfe0d31d082bbdc31fd
Summary:
Previously we stored an `IntervalSet` in each `WriteAckFrame`. We don't need to do this, as by the time we are writing an `ACK` the `IntervalSet` is complete. Instead of bothering with the `IntervalSet` operations, we can simply serialize it to a reverse-sorted `vector.`
Additionally this has some micro-optimizations for filling the ACK frame, with a new function for getting varint size.
Reviewed By: yangchi
Differential Revision: D19397728
fbshipit-source-id: ba6958fb36a4681edaa8394b1bcbbec3472e177d
Summary:
Previously we track them since we thought we can get some additional
RTT samples. But these are bad RTT samples since peer can delays the acking of
pure acks. Now we no longer trust such RTT samples, there is no reason to keep
tracking pure ack packets.
Reviewed By: mjoras
Differential Revision: D18946081
fbshipit-source-id: 0a92d88e709edf8475d67791ba064c3e8b7f627a
Summary: By modifying `IntervalSet` a bit we can make it so it takes a `folly::small_vector` as the container. We expect that for real traffic there will not generally be a lot of ACK blocks per frame, so optimize for that.
Reviewed By: siyengar
Differential Revision: D18919975
fbshipit-source-id: 199a2ea9ba5003382e2d7d99fc7a6de7e8aafdca
Summary: As a part of Draft 17, application close frame has been removed, we use connection close frame to represent both application close and connection close.
Reviewed By: mjoras
Differential Revision: D18580856
fbshipit-source-id: d274fa2d3dbc59b926bca5a2b8a20328ae582703
Summary:
Get rid of IObufQueue usage in the PacketBuilder and replace it with a vanilla IOBuf.
This requires replacing QueueAppender with something else as well, so this diff adds a new class call BufAppender which does exactly the same things as a QueueAppender.
Having a BufAppender will allow us to avoid cloning the stream buffer in the future and avoid a clone during the write path.
Reviewed By: mjoras
Differential Revision: D18673517
fbshipit-source-id: 31fd7758688686371d038111514eb62d6b21672c
Summary:
The retransmission buffer tracks stream frame data we have sent that is currently unacked. We keep this as a sorted `deque`. This isn't so bad for performance, but we can do better if we break ourselves of the requirement that it be sorted (removing a binary search on ACK).
To do this we make the buffer a map of offset -> `StreamBuffer`.
There were two places that were dependent on the sorted nature of the list.
1. For partial reliablity we call `shrinkBuffers` to remove all unacked buffers less than an offset. For this we now have to do it with a full traversal of the retransmission buffer instead of only having to do an O(offset) search. In the future we could make this better by only lazily deleting from the retransmission buffer on ACK or packet loss.
2. We used the start of the retransmission buffer to determine if a delivery callback could be fired for a given offset. We need some new state to track this. Instead of tracking unacked buffers, we now track acked ranges using the existing `IntervalSet`. This set should be small for the typical case, as we think most ACKs will come in order and just cause existing ranges to merge.
Reviewed By: yangchi
Differential Revision: D18609467
fbshipit-source-id: 13cd2164352f1183362be9f675c1bdc686426698
Summary: The state machine logic is quite abstruse, this modifies it to make it more readable.
Reviewed By: siyengar
Differential Revision: D18488301
fbshipit-source-id: c6fd52973880931e34904713e8b147f56d0c4629
Summary:
Use the custom variant type for write frames as well, now that
we use them for read frames.
Reviewed By: mjoras
Differential Revision: D17776862
fbshipit-source-id: 47093146d0f1565c22e5393ed012c70e2e23d279
Summary:
Make a custom variant type for PacketHeader. By not relying on boost::variant
this reduces the code size of the implementation.
This uses a combination of a union type as well as a enum type to emulate a variant
Reviewed By: yangchi
Differential Revision: D17187589
fbshipit-source-id: 00c2b9b8dd3f3e73af766d84888b13b9d867165a
Summary:
Implement sending stream limit updates in a windowed fashion, so that as a peer exhausts its streams we will grant it additional credit. This is implemented by having the stream manager check if an update is needed on removing streams, and the api layer potentially sending an update after it initiates the check for closed streams.
This also makes some driveby changes to use `std::lower_bound` instead of `std::find` for the sorted collections in the stream manager.
Reviewed By: yangchi
Differential Revision: D16808229
fbshipit-source-id: f6e3460d43e4d165e362164be00c0cec27cf1e79
Summary:
Prior to this diff we would clone out an entire flow control's worth of data from the writebuffer and then clone out a smaller portion of that to write into the packet builder. This is extremely wasteful when we have a large flow control window.
Additionally we would always write the stream data length field even when we are going to fill the remainder of the packet with the current stream frame. By first calculating the amount of data that needs to can be written and writing the header, we can now omit the data length field when we can fill the whole packet.
Reviewed By: yangchi
Differential Revision: D15769514
fbshipit-source-id: 95ac74eebcde87dd06de54405d7f69c42362e29c
Summary: post draft-17 it is interpreted as count not the max stream id
Reviewed By: mjoras
Differential Revision: D15523021
fbshipit-source-id: 779a1c5269eb8dbcdcd169303caa7a65e467339c
Summary: This is step 1 for removing reset on reset, since the send side may need to transition to waiting for a reset ack while the read side is an any state.
Reviewed By: lnicco
Differential Revision: D15075849
fbshipit-source-id: 1e094942a8a1ca9a01d4161cd6309b4136a9cfbf
