- Documentation: describe lsquic internals ("guts").
- Two more fixes to compliance issues found by h3spec.
- Truncate, don't abort, SCIDs larger than 16 bytes (PR #244).
- Several small internal improvements and space optimizations.
- [API] lsquic_ssl_sess_to_resume_info() is the new way to get
session info.
- [API] Add user pointer to ea_generate_scid callback.
- [API] Add lsquic_dcid_from_packet() -- a fast function to parse
out DCID.
- [API] Add es_max_batch_size to control outgoing packet batch size.
- [BUGFIX] Disallow sending of header while promise is being written.
- [BUGFIX] Flush stream when buffered bytes exhaust stream cap.
- [BUGFIX] Deactivate HQ frame if writing push promise fails.
- Perform sanity check on peer transport parameters and fail the
handshake if some flow control limits are too low. This can be
turned off, see es_check_tp_sanity.
- http_server: fix how requests are read in "hq" mode.
- [API] New knob to set outgoing packet batch size.
- Aborted connection now become tickable immediately.
- Abort connection when HTTP/3 frame cannot be opened (can only happen
when malloc fails).
- Add QPACK stats collection and experimentation mode, see the new
es_qpack_experiment setting.
- Log busy connection stats every second using the new "conn-stats"
log module.
- Log about skipping only once.
- Update HTTP/3 greased frame type formula.
- Use ls-qpack v2.2.1.
- [FEATURE] Extensible HTTP Priorities (HTTP/3 only).
- [FEATURE] Add conn context to packet-out memory interface (PR #175).
- [BUGFIX] gQUIC proof generation: allocate buffer big enough for
signature (issue #173).
- [BUGFIX] Make library thread-safe: drop use of global variables
(issue #133, issue #167).
- [BUGFIX] Deactivate only *recent* HQ frame, not any HQ frame.
- [BUGFIX] gQUIC server: associate compressed cert with SSL_CTX,
instead of keeping them in a separate hash, potentially leading
to mismatches.
- [BUGFIX] Stream data discard infinite loop: break on FIN.
- cmake: add install target via -DCMAKE_INSTALL_PREFIX (PR #171).
- Support randomized packet number to begin a connection.
- Mini and full IETF connection size optimization.
- http_client: specify HTTP priorities based on stream conditions.
- [FEATURE] QUIC and HTTP/3 Internet Draft 31 support.
- [API] Let user generate Souce Connection IDs.
- [FEATURE] Allow building lsquic as shared library.
- [OPTIMIZATION] Receive history: use a single contiguous memory
block for everything.
- Deprecate QUIC versions ID-27 and ID-30.
- [FEATURE] QUIC and HTTP/3 Internet Draft 30 support.
- [FEATURE] Unreliable Datagram Extension support.
- [FEATURE] Adaptive congestion controller.
- [BUGFIX] Do not send MAX_STREAM_DATA frames on crypto streams.
- [BUGFIX] Fail with CRYPTO_BUFFER_EXCEEDED when too much CRYPTO
data comes in.
- [BUFFIX] Spin bit is now strictly per path; value is reset on
DCID change.
- [BUGFIX] Check that max value of max_streams_uni and
max_streams_bidi TPs is 2^60.
- [BUGFIX] Close IETF mini conn immediately if crypto session
cannot be initialized.
- Deprecate ID-28 (no browser uses it): it's no longer in the
default versions list.
- New programs duck_server and duck_client that implement the
experimental siduck-00 protocol. They quack!
- IETF crypto streams: don't limit ourselves from sending.
- Command-line programs: turn off QL loss bits if -G is used, as
Wireshark cannot decrypt QUIC packets when this extension is used.
- Turn all h3 framing unit tests back on.
- Fix malo initialization when compiled in no-pool mode.
- [FEATURE] DPLPMTUD support. IETF connections now search for the
maximum packet size, improving throughput.
- [DEBUG] Record event in stream history when on_close() is called
in dtor.
- [BUGFIX] Initial packet size check for IETF mini conn applies to
UDP payload, not QUIC packet.
- Support old and new school loss_bits transport parameter.
- Use Q run length of 64 as suggested in the loss bits Draft.
- Undo square wave count when packet is delayed.
- Code cleanup; minor fixes.
- [BUGFIX] Send controller: update scheduled bytes when DCID length
changes (IETF client).
- [BUGFIX] Drop alarm check from sanity test. It no longer works now
that we use loss chains.
- [PORTABILITY] Fix build on Alpine Linux.
- [PORTABILITY] Fix build using XCode.
- Client initial DCID length: use RAND_bytes() instead of rand(3).
- Add unit tests for connection min heap.
- [DEBUG] Log CID in gQUIC handshake module
- [DEBUG] Turn on extra checks for IETF client send controller.
- [DEBUG] Dedup next advisory tick messages when reason is IDLE timer.
- [DEBUG] QPACK decoder handler: log header error code.
- [FEATURE, API Change] 0-RTT support. Add function to export 0-RTT
information; it can be supplied to a subsequent connect() call.
- [FEATURE] Add -0 flag to http_client to exercise 0-RTT support.
- [BUGFIX] Resuscitate the Windows build.
- [BUGFIX] Send HTTP settings (max header list size) if necessary.
- [BUGFIX] Buffered packets can contain ACK frames.
- [BUGFIX] Make packet writeable once all STREAM frames are elided.
- [BUGFIX] Fix potential null dereference when realloc fails.
- cmake: simplify build configuration.
- [API Change] Sendfile-like functionality is gone. The stream no
longer opens files and deals with file descriptors. (Among other
things, this makes the code more portable.) Three writing functions
are provided:
lsquic_stream_write
lsquic_stream_writev
lsquic_stream_writef (NEW)
lsquic_stream_writef() is given an abstract reader that has function
pointers for size() and read() functions which the user can implement.
This is the most flexible way. lsquic_stream_write() and
lsquic_stream_writev() are now both implemented as wrappers around
lsquic_stream_writef().
- [OPTIMIZATION] When writing to stream, be it within or without the
on_write() callback, place data directly into packet buffer,
bypassing auxiliary data structures. This reduces amount of memory
required, for the amount of data that can be written is limited
by the congestion window.
To support writes outside the on_write() callback, we keep N
outgoing packet buffers per connection which can be written to
by any stream. One half of these are reserved for the highest
priority stream(s), the other half for all other streams. This way,
low-priority streams cannot write instead of high-priority streams
and, on the other hand, low-priority streams get a chance to send
their packets out.
The algorithm is as follows:
- When user writes to stream outside of the callback:
- If this is the highest priority stream, place it onto the
reserved N/2 queue or fail.
(The actual size of this queue is dynamic -- MAX(N/2, CWND) --
rather than N/2, allowing high-priority streams to write as
much as can be sent.)
- If the stream is not the highest priority, try to place the
data onto the reserved N/2 queue or fail.
- When tick occurs *and* more packets can be scheduled:
- Transfer packets from the high N/2 queue to the scheduled
queue.
- If more scheduling is allowed:
- Call on_write callbacks for highest-priority streams,
placing resulting packets directly onto the scheduled queue.
- If more scheduling is allowed:
- Transfer packets from the low N/2 queue to the scheduled
queue.
- If more scheduling is allowed:
- Call on_write callbacks for non-highest-priority streams,
placing resulting packets directly onto the scheduled queue
The number N is currently 20, but it could be varied based on
resource usage.
- If stream is created due to incoming headers, make headers readable
from on_new.
- Outgoing packets are no longer marked non-writeable to prevent placing
more than one STREAM frame from the same stream into a single packet.
This property is maintained via code flow and an explicit check.
Packets for stream data are allocated using a special function.
- STREAM frame elision is cheaper, as we only perform it if a reset
stream has outgoing packets referencing it.
- lsquic_packet_out_t is smaller, as stream_rec elements are now
inside a union.
- Hide handshake implementation behind a set of function pointers
- Use monotonically increasing clock
- Make sure that retx delay is not larger than the max of 60 seconds
George Wang
Dmitri Tikhonov
Victor Stewart
LiteSpeed Tech