The previous fix da95fd90 ("BUILD/MINOR: ssl: fix build with non-alpn/
non-npn libssl") does fix the build in old OpenSSL release, but I
overlooked that the ctx is only freed when NPN is supported.
Fix this by moving the #endif to the proper place (this was broken in
c7566001 ("MINOR: server: Add "alpn" and "npn" keywords")).
Having a thread_local for the pool cache is messy as we need to
initialize all elements upon startup, but we can't until the threads
are created, and once created it's too late. For this reason, the
allocation code used to check for the pool's initialization, and
it was the release code which used to detect the first call and to
initialize the cache on the fly, which is not exactly optimal.
Now that we have initcalls, let's turn this into a per-thread array.
This array is initialized very early in the boot process (STG_PREPARE)
so that pools are always safe to use. This allows to remove the tests
from the alloc/free calls.
Doing just this has removed 2.5 kB of code on all cumulated pool_alloc()
and pool_free() paths.
signal_init(), init_log(), init_stream(), and init_task() all used to
only preset some values and lists. This needs to be done very early to
provide a reliable interface to all other users. The calls used to be
explicit in haproxy.c:init(). Now they're placed in initcalls at the
STG_PREPARE stage. The functions are not exported anymore.
Instead of exporting a number of pools and having to manually delete
them in deinit() or to have dedicated destructors to remove them, let's
simply kill all pools on deinit().
For this a new function pool_destroy_all() was introduced. As its name
implies, it destroys and frees all pools (provided they don't have any
user anymore of course).
This allowed to remove 4 implicit destructors, 2 explicit ones, and 11
individual calls to pool_destroy(). In addition it properly removes
the mux_pt_ctx pool which was not cleared on exit (no backport needed
here since it's 1.9 only). The sig_handler pool doesn't need to be
exported anymore and became static now.
This commit replaces the explicit pool creation that are made in
constructors with a pool registration. Not only this simplifies the
pools declaration (it can be done on a single line after the head is
declared), but it also removes references to pools from within
constructors. The only remaining create_pool() calls are those
performed in init functions after the config is parsed, so there
is no more user of potentially uninitialized pool now.
It has been the opportunity to remove no less than 12 constructors
and 6 init functions.
The new function create_pool_callback() takes 3 args including the
return pointer, and creates a pool with the specified name and size.
In case of allocation error, it emits an error message and returns.
The new macro REGISTER_POOL() registers a callback using this function
and will be usable to request some pools creation and guarantee that
the allocation will be checked. An even simpler approach is to use
DECLARE_POOL() and DECLARE_STATIC_POOL() which declare and register
the pool.
Most calls to hap_register_post_check(), hap_register_post_deinit(),
hap_register_per_thread_init(), hap_register_per_thread_deinit() can
be done using initcalls and will not require a constructor anymore.
Let's create a set of simplified macros for this, called respectively
REGISTER_POST_CHECK, REGISTER_POST_DEINIT, REGISTER_PER_THREAD_INIT,
and REGISTER_PER_THREAD_DEINIT.
Some files were not modified because they wouldn't benefit from this
or because they conditionally register (e.g. the pollers).
Most register_build_opts() calls use static strings. These ones were
replaced with a trivial REGISTER_BUILD_OPTS() statement adding the string
and its call to the STG_REGISTER section. A dedicated section could be
made for this if needed, but there are very few such calls for this to
be worth it. The calls made with computed strings however, like those
which retrieve OpenSSL's version or zlib's version, were moved to a
dedicated function to guarantee they are called late in the process.
For example, the SSL call probably requires that SSL_library_init()
has been called first.
This patch replaces a number of __decl_hathread() followed by HA_SPIN_INIT
or HA_RWLOCK_INIT by the new __decl_spinlock() or __decl_rwlock() which
automatically registers the lock for initialization in during the STG_LOCK
init stage. A few static modifiers were lost in the process, but since they
were not essential at all it was not worth extending the API to provide such
a variant.
This patch adds ha_spin_init() and ha_rwlock_init() which are used as
a callback to initialise locks at boot time. They perform exactly the
same as HA_SPIN_INIT() or HA_RWLOCK_INIT() but from within a real
function.
This switches explicit calls to various trivial registration methods for
keywords, muxes or protocols from constructors to INITCALL1 at stage
STG_REGISTER. All these calls have in common to consume a single pointer
and return void. Doing this removes 26 constructors. The following calls
were addressed :
- acl_register_keywords
- bind_register_keywords
- cfg_register_keywords
- cli_register_kw
- flt_register_keywords
- http_req_keywords_register
- http_res_keywords_register
- protocol_register
- register_mux_proto
- sample_register_convs
- sample_register_fetches
- srv_register_keywords
- tcp_req_conn_keywords_register
- tcp_req_cont_keywords_register
- tcp_req_sess_keywords_register
- tcp_res_cont_keywords_register
- flt_register_keywords
We reintroduced some FDs leaking by using a poller and some listeners in
the master.
The master proxy needs to be stopped to avoid leaking its listeners, the
polling loop needs to be deinit, and the thread waker pipe need to be
closed too.
No backport needed.
Surprisingly, the compression pool was created at runtime on first use,
which is not very convenient, has performance and reliability impacts,
and even makes monitoring less easy. Let's move the pool creation at
startup time instead. This even removes the need for the spinlock in
case USE_ZLIB is not defined.
The tune.maxzlibmem setting was moved with commit 368780334 ("MEDIUM:
compression: move the zlib-specific stuff from global.h to compression.c")
but the preset value using DEFAULT_MAXZLIBMEM was incorrectly moved :
- the field is in "global" and not "global.tune"
- the trailing comma instead of semi-colon will make it either zero
(threads enabled), break (threads enabled with debugging), or cast
the memprintf's return pointer to int (threads disabled)
It simply proves that nobody ever used DEFAULT_MAXZLIBMEM since 1.8!
This needs to be backported to 1.8.
Valgrind reports:
==3389== Warning: invalid file descriptor -1 in syscall close()
Check for >= 0 before closing.
This bug was introduced in commit ce83b4a5dd
and is specific to 1.9. No backport needed.
In commit c7566001 ("MINOR: server: Add "alpn" and "npn" keywords") and
commit 201b9f4e ("MAJOR: connections: Defer mux creation for outgoing
connection if alpn is set"), the build was broken on older OpenSSL
releases.
Move the #ifdef's around so that we build again with older OpenSSL
releases (0.9.8 was tested).
Since the connection changes in 1.9, some breakage happened to the H2 mux
whose initial design was heavily relying on the fact that connection-level
functions were woken up after data were transferred to the stream layer.
We need to wake the demux up after receiving such data if the demux is
blocked. This at least allows to receive POSTs again. One issue remains,
it looks like the end of the uploaded data is silently discarded if the
server responds before the end of the transfer (H2 in half-closed(local)
state), which doesn't happen with 1.8.14 and nghttp as the client.
No backport is needed.
After the changes to the connection layer in 1.9, some wake up calls
need to be introduced to re-activate reading from the connection. One
such place is at the end of h2_process_demux(), otherwise processing
of input data stops after a few frames.
No backport is needed.
When we create a connection, if we have to defer the conn_stream and the
mux creation until we can decide it (ie until the SSL handshake is done, and
the ALPN is decided), store the connection in the stream_interface, so that
we're sure we can destroy it if needed.
When ending a stream, if the origin is an appctx, the appctx will have been
destroyed already, but it does not destroy the session. So later, when we
try to destroy the session, we try to dereference sess->origin and die
trying.
Fix this by explicitely setting sess->origin to NULL before calling
session_free().
The creation of the conn_stream for an outgoing connection has been delayed
a bit, and when using dispatch, a check was made to see if a conn_stream
was attached before the conn_stream was created, so remove the test, as
it's done later anyway, and create and install the conn_stream right away
when we don't have a server, as is done when we don't have an alpn/npn
defined.
In the various connect_server() functions, don't reset the connection flags,
as some may have been set before. The flags are initialized in conn_init(),
anyway.
If an ALPN (or a NPN) was chosen for a server, defer choosing the mux until
after the SSL handshake is done, and the ALPN/NPN has been negociated, so
that we know which mux to pick.
As we now will no longer try tro subscribe to recv/send events before the
connection is established, there's no need to reactivate polling on the fd
when retrying connection. It will be activated later on subscribe.
In some situations, especially when dealing with low latency on processors
supporting a variable frequency or when running inside virtual machines,
each time the process waits for an I/O using the poller, the processor
goes back to sleep or is offered to another VM for a long time, and it
causes excessively high latencies.
A solution to this provided by this patch is to enable busy polling using
a global option. When busy polling is enabled, the pollers never sleep and
loop over themselves waiting for an I/O event to happen or for a timeout
to occur. On multi-processor machines it can significantly overheat the
processor but it usually results in much lower latencies.
A typical test consisting in injecting traffic over a single connection at
a time over the loopback shows a bump from 4640 to 8540 connections per
second on forwarded connections, indicating a latency reduction of 98
microseconds for each connection, and a bump from 12500 to 21250 for
locally terminated connections (redirects), indicating a reduction of
33 microseconds.
It is only usable with epoll and kqueue because select() and poll()'s
API is not convenient for such usages, and the level of performance they
are used in doesn't benefit from this anyway.
The option, which obviously remains disabled by default, can be turned
on using "busy-polling" in the global section, and turned off later
using "no busy-polling". Its status is reported in "show info" to help
troubleshooting suspicious CPU spikes.
Fix some memory leak and a FD leak in the error path of the master proxy
initialisation. It's a really minor issue since the process is exiting
when taking those error paths.
Valgrind's memcheck reports memory leaks in cli.c, because
the out parameter of memprintf is not properly freed:
==31035== 11 bytes in 1 blocks are definitely lost in loss record 16 of 101
==31035== at 0x4C2DB8F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==31035== by 0x4C2FDEF: realloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==31035== by 0x4A3C72: my_realloc2 (standard.h:1364)
==31035== by 0x4A3C72: memvprintf (standard.c:3459)
==31035== by 0x4A3D93: memprintf (standard.c:3482)
==31035== by 0x4AF77E: mworker_cli_sockpair_new (cli.c:2324)
==31035== by 0x48E826: init (haproxy.c:1749)
==31035== by 0x408BBC: main (haproxy.c:2725)
==31035==
==31035== 11 bytes in 1 blocks are definitely lost in loss record 17 of 101
==31035== at 0x4C2DB8F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==31035== by 0x4C2FDEF: realloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==31035== by 0x4A3C72: my_realloc2 (standard.h:1364)
==31035== by 0x4A3C72: memvprintf (standard.c:3459)
==31035== by 0x4A3D93: memprintf (standard.c:3482)
==31035== by 0x4AF071: mworker_cli_proxy_create (cli.c:2172)
==31035== by 0x48EC89: init (haproxy.c:1760)
==31035== by 0x408BBC: main (haproxy.c:2725)
These leaks were introduced in commits
ce83b4a5dd and
8a02257d88
which are specific to haproxy 1.9 dev.
The "cpust_{tot,1s,15s}" fields used to report milliseconds but nothing
in the value's title made this explicit. Let's rename the field to report
"cpust_ms_{tot,1s,15s}" to more easily remind that the unit represents
milliseconds.
These sample fetch keywords report performance metrics about the task calling
them. They are useful to report in logs which requests consume too much CPU
time and what negative performane impact it has on other requests. Typically
logging cpu_ns_avg and lat_ns_avg will show culprits and victims.
Right now we measure for each task the cumulated time spent waiting for
the CPU and using it. The timestamp uses a 64-bit integer to report a
nanosecond-level date. This is only enabled when "profiling.tasks" is
enabled, and consumes less than 1% extra CPU on x86_64 when enabled.
The cumulated processing time and wait time are reported in "show sess".
The task's counters are also reset when an HTTP transaction is reset
since the HTTP part pretends to restart on a fresh new stream. This
will make sure we always report correct numbers for each request in
the logs.
This is a new global setting which enables or disables CPU profiling
per task. For now it only sets/resets the variable based on the global
option "profiling.tasks" and supports showing it as well as setting it
from the CLI using "show profiling" and "set profiling". The option will
be used by a future commit. It was done in a way which should ease future
addition of profiling options.
Since we know the time it takes to process everything between two poll()
calls, we can use this as the max latency measurement any task will
experience and average it.
This code does this, and reports in "show activity" the average of this
loop time over the last 1024 poll() loops, for each thread. It will vary
quickly at high loads and slowly under low to moderate loads, depending
on the rate at which poll() is called. The latency a task experiences
is expected to be half of this on average.
At the moment the situation with activity measurement is quite tricky
because the struct activity is defined in global.h and declared in
haproxy.c, with operations made in time.h and relying on freq_ctr
which are defined in freq_ctr.h which itself includes time.h. It's
barely possible to touch any of these files without breaking all the
circular dependency.
Let's move all this stuff to activity.{c,h} and be done with it. The
measurement of active and stolen time is now done in a dedicated
function called just after tv_before_poll() instead of mixing the two,
which used to be a lazy (but convenient) decision.
No code was changed, stuff was just moved around.
The signal_register_fct() does not remove the handlers assigned to a
signal, but add a new handler to a list.
We accidentality inherited the handlers of the main() function in the
master process which is a problem because they act on the proxies.
The side effect was to stop the MASTER proxy which handle the master CLI
on a SIGUSR1, and to display some debug info when doing a SIGHUP and a
SIGQUIT.
The new function signal_unregister() removes every handlers assigned to
a signal. Once the handler list of the signal is empty, the signal is
ignored with SIG_IGN.
In the output of 'show fd', the worker CLI's socketpair was still
handled by an "unknown" function. That can be really confusing during
debug. Fixed it by showing "mworker_accept_wrapper" instead.
The mworker waitpid mode (which is used when a reload failed to apply
the new configuration) was still using a specific initialisation path.
That's a problem since we use a polling loop in the master now, the
master proxy is not initialized and the master CLI is not activated.
This patch removes the initialisation code of the wait mode and
introduce the MODE_MWORKER_WAIT in order to use the same init path as
the MODE_MWORKER with some exceptions. It allows to use the master proxy
and the master CLI during the waitpid mode.
Because the HTX is still experimental, we must add special cases during the
configuration check to be sure it is not enabled on a proxy with incompatible
options. Here, for HTX proxies, when a mux protocol is specified on a bind line
or a server line, we must force the HTX mode (PROTO_MODE_HTX).
Concretely, H2 is the only mux protocol that can be forced. And it doesn't yet
support the HTX. So forcing the H2 on an HTX proxy will always fail.
In si_cs_send(), some checks are done the CS flags en the connection flags
before calling snd_buf(). But these checks are useless because they have already
been done earlier in the function. The harder to figure out is the flag
CO_FL_SOCK_WR_SH. So it is now tested with CF_SHUTW at the beginning.
In si_cs_send, as said in comments, snd_buf() should only be called if there is
no data in the pipe anymore. But actually, this condition was not respected.
For the same reason than for the commit b46784b1c ("MINOR: stream-int: Notify
caller when an error is reported after a rcv_pipe()"), we return 1 after the
call to rcv_buf() in si_cs_send() to notify the caller some processing may be
triggered.
This patch is not flagged as a bug because no strange behaviour was yet observed
without it. It is just a proactive fix to be consistent.
In si_cs_send(), when an error is found on the CS or the connection at the
beginning of the function, we return 1 to notify the caller some processing may
be triggered. So, it seems logical to do the same after the call to rcv_pipe().
This patch is not flagged as a bug because no strange behaviour was yet observed
without it. It is just a proactive fix to be consistent.
The request is eaten when the stats applet have finished to send its
response. It was removed from the channel's buffer, removing all HTX blocks till
the EOM. But the channel's output was not reset, leaving the request channel in
an undefined state.
When we start to parse a new message, if all headers have not been received,
nothing is copied in the channel's buffer. In this situation, we must not set
the flag CS_FL_RCV_MORE on the conn-stream. If we do so, the connection freezes
because there is no data to send that can reenable the reads
First of all, we need to be sure to keep the flag H1S_F_BUF_FLUSH on the H1S
reading data until all data was flushed from the buffer. Then we need to know
when the kernel splicing is in use and when it ends. This is handled with the
new flag H1S_F_SPLICED_DATA.
Then, we must subscribe to send when some data remain in the pipe after a
snd_pipe(). It is mandatory to wakeup the stream and avoid a freeze.
Finally, we must be sure to update the message state when we restart to use the
channel's buffer. Among other things, it is mandatory to swith the message from
DATA to DONE state when all data were sent using the kernel splicing.
Don't force the close on server side anymore. Since commit 7c6f8b146 ("MAJOR:
connections: Detach connections from streams"), it is possible to release a
stream without the underlying connection.
Because of this change, we must be sure to create a new stream to handle the
next HTTP transaction only on the client side. And we must be sure to correctly
handle the read0 event in h1_recv, to be sure to call h1_process().
It avoids a copy between the rxbuf and the channel's buffer. It means the
parsing is done in h1_rcv_buf(). So we need to have a stream to start the
parsing. This change should improve the overall performances. It also implies a
better split between the connection layer and the applicative layer. Now, on the
connection layer, only raw data are manipulated. Raw data received from the
socket are stored in ibuf and those sent are get from obuf. On the applicative
layer, data in ibuf are parsed and copied into the channel's buffer. And on the
other side, those structured data are formatted and copied into obuf.
James Brown reported that when an "accept-ranges" header field is sent
through haproxy and converted from HTTP/1.1 to H2, it's mis-encoded as
"accept-language". It happens that it's one of the few very common header
fields encoded using its index value and that this index value was misread
in the spec as 17 instead of 18, resulting in the wrong name being sent.
Thanks to Lukas for spotting the issue in the HPACK encoder itself.
This fix must be backported to 1.8.
This was the largest function of the whole file, taking a rough second
to build alone. Let's move it to a distinct file along with a few
dependencies. Doing so saved about 2 seconds on the total build time.
The config parser is the largest file to build and its build dominates
the total project's build time. Let's start to split it into multiple
smaller pieces by extracting the "global" section parser into a new
file called "cfgparse-global.c". This removes 1/4th of the file's build
time.
For now, the lua scripts are not compatible with the new HTX internal
representation of HTTP messages. Thus, for a given proxy, when the option
"http-use-htx" is enabled, an error is triggered if any lua's
action/service/sample-fetch/converter is also configured.
For now, the filters are not compatible with the new HTX internal representation
of HTTP messages. Thus, for a given proxy, when the option "http-use-htx" is
enabled, an error is triggered if any filter is also configured.
To do so, the stream is created as earlier as possible. It means, during the mux
creation for the first request, and for others, just at the end of the previous
transaction. Because all timeouts are handled by the strream, the mux's task is
now useless, so it is removed. Finally, to report errors, flags are set on the
HTX message. The HTX message is passed to the stream if there is some content to
analyse or if there is some error to handle.
All of this will probably be reworked later to handle errors and timeouts
directly in the mux. For now, it is the simpler way to handle all of this.
When a server is down, the channel's data must not be consumed. This is
required to allow redispatch and connection retry. So now, we wait for
the connection to be marked as connected, with the flag CO_FL_CONNECTED,
before starting to consume channel's data. In the mux, this event is
tracked with the flag H1C_F_CS_WAIT_CONN.
It does the same than smp_prefetch_http but for HTX messages. It can be called
from an HTTP proxy or a TCP proxy. For HTTP proxies, the parsing is handled by
the mux, so it does nothing but wait. For TCP proxies, it tries to parse an HTTP
message and to convert it in a temporary HTX message. Sample fetches will use
this temporary variable to do their job.
This version is simpler than the legacy one because the parsing is no more
handled by the analyzer. So now we just need to wait to have more data to move
on.
For now, the call to the stats applet is disabled for HTX messages. But HTX
versions of the function to check the request URI against the stats URI and the
fnuction to prepare the call to the stats applet have been added.
It is more or less the same than legacy version but adapted to be called from
HTX analyzers. In the legacy version of this function, we switch on the HTX code
when applicable.
It is more or less the same than legacy version but adapted to be called from
HTX analyzers. In the legacy version of this function, we switch on the HTX code
when applicable.
It is more or less the same than legacy versions but adapted to be called from
HTX analyzers. In the legacy versions of these functions, we switch on the HTX
code when applicable.
It is more or less the same than legacy versions but adapted to be called from
HTX analyzers. In the legacy versions of these functions, we switch on the HTX
code when applicable.
It is more or less the same than del_hdr_value but adapted to be called from HTX
analyzers. The main changes is that it takes pointers on the start and the end
of the header value.
The mux-h1 now parses and formats HTTP/1 messages using the HTX
representation. The HTX analyzers have been updated too. For now, only
htx_wait_for_{request/response} and http_{request/response}_forward_body have
been adapted. Others are disabled for now.
Now, the HTTP messages are parsed by the mux on a side and then, after analysis,
formatted on the other side. In the middle, in the stream, there is no more
parsing. Among other things, the version parsing is now handled by the
mux. During the data forwarding, depending the value of the "extra" field, we
are able to know if the body length is known or not and if yes, how many bytes
are still expected.
This file will host all functions to manipulate HTTP messages using the HTX
representation. Functions in this file will be able to be called from anywhere
and are mainly related to the HTTP semantics.
The internal representation of an HTTP message, called HTX, is a structured
representation, unlike the old one which is a raw representation of
messages. Idea is to have a version-agnostic representation of the HTTP
messages, which can be easily used by to handle HTTP/1, HTTP/2 and hopefully
QUIC messages, and communication from one of them to another.
In this patch, we add types to define the internal representation itself and the
main functions to manipulate them.
The mux relies on the flag CO_RFL_BUF_FLUSH during a call to h1_rcv_buf to know
if it needs to stop reads and to flush its internal buffers to use kernel tcp
splicing. It is the caller responsibility (here the SI) to know when it must
come back on buffered exchanges.
Now, the connection mode is detected in the mux and not in HTX analyzers
anymore. Keep-alive connections are now managed by the mux. A new stream is
created for each transaction. This removes the most important part of the
synchronization between channels and the HTTP transaction cleanup. These changes
only affect the HTX part (proto_htx.c). Legacy HTTP analyzers remain untouched
for now.
On the client-side, the mux is responsible to create new streams when a new
request starts. It is also responsible to parse and update the "Connection:"
header of the response. On the server-side, the mux is responsible to parse and
update the "Connection:" header of the request. Muxes on each side are
independent. For now, there is no connection pool on the server-side, so it
always close the server connection.
For now, it only parses and transfers data. There is no internal representation
yet. It means the stream still need to parse it too. So a message is parsed 3
times today: one time by each muxes (the client one and the server one) and
another time by the stream. This is of course inefficient. But don't worry, it
is only a transitionnal state. And this mux is optional for now.
BTW, headers and body parsing are now handled using same functions than the mux
H2. Request/Response synchronization is also handled. The mux's task is now used
to catch client/http-request timeouts. Others timeouts are still handled by the
stream. On the clien-side, the stream is created once headers are fully parsed
and body parsing starts only when heeaders are transferred to the stream (ie,
copied into channel buffer).
There is still some known limitations here and there. But, it works in the
common cases. Bad message are not captured and some logs are emitted when errors
occur, only if no stream are attached to the mux. Otherwise, data are
transferred and we let the stream handles errors itself.
For now, it is just an other kind of passthrough multiplexer, but with internal
buffers to be prepared to parse incoming messages and to format outgoing
ones. There is also a task attached to it to handle timeouts. However, because
it does not handle any timeout for now, this task is unused. And finally,
because it handles internal buffers, it also handles retries on recv/send. To
use this multiplexer, you must use the option "http-use-htx" both on the
frontend and the backend.
It does not support keep-alive and will freeze connections after the first
request/response.
For now, these analyzers are just copies of the legacy HTTP analyzers. But,
during the HTTP refactoring, it will be the main place where it will be
visible. And in legacy analyzers, the macro IS_HTX_STRM is used to know if the
HTX version should be called or not.
Note: the following commits were applied to proto_http.c after this patch
was developed and need to be studied to see if an adaptation to htx
is required :
fd9b68c BUG/MINOR: only mark connections private if NTLM is detected
The flag CS_FL_READ_PARTIAL can be set by the mux on the conn_stream to notify
the stream interface that some data were received. Is is used in si_cs_recv to
re-arm read timeout on the channel.
These 2 functions are pretty naive. They only split a start-line into its 3
substrings or a header line into its name and value. Spaces before and after
each part are skipped. No CRLF at the end are expected.
By setting the flag CO_RFL_KEEP_RSV when calling mux->rcv_buf, the
stream-interface notifies the mux it must keep some space to preserve the
buffer's reserve. This flag is only useful for multiplexers handling structured
data, because in such case, the stream-interface cannot know the real amount of
free space in the channel's buffer.
This file is empty for now. But it will be used to add new versions of the HTTP
analyzers based on the internal representation of HTTP messages (not implemented
yet but called HTX).
By setting the flag CO_RFL_BUF_FLUSH when calling mux->rcv_buf, the
stream-interface notifies the mux it should flush its buffers without reading
more data. This flag is set when the SI want to use the kernel TCP splicing to
forward data. Of course, the mux can respect it or not, depending on its
state. It's just an information.
Do not destroy the connection when we're about to destroy a stream. This
prevents us from doing keepalive on server connections when the client is
using HTTP/2, as a new stream is created for each request.
Instead, the session is now responsible for destroying connections.
When reusing connections, the attach() mux method is now used to create a new
conn_stream.
Introduce a new field in session, "srv_conn", and a linked list of sessions
in the connection. It will be used later when we'll switch connections
from being managed by the stream, to being managed by the session.
Add a new method for mux, avail_streams, that returns the number of streams
still available for a mux.
For the mux_pt, it'll return 1 if the connection is in idle, or 0. For
the H2 mux, it'll return the max number of streams allowed, minus the number
of streams currently in use.
In order to make the mux_pt able to handle idle connections, give it its
own context, where it'll stores the connection, the current conn_stream if
any, and a wait_event, so that it can subscribe to I/O events.
Add a new parameter to the detach() method, that gives the mux a hint
if it should destroy the connection or not when detaching a conn_stream.
If 1, then the mux_pt immediately destroys the connecion, if 0, then it
just subscribes to any read event. If a read happens, it will call
conn_sock_drain(), and if there's a connection error, it'll free the
connection, after removing it from the idle list.
Instead of trying to receive as soon as the connection is created, and to
eventually have to transfer subscription if we move connections, wait
until the connection is established before attempting to recv.
Remaining calls to si_cant_put() were all for lack of room and were
turned to si_rx_room_blk(). A few places where SI_FL_RXBLK_ROOM was
cleared by hand were converted to si_rx_room_rdy().
The now unused si_cant_put() function was removed.
The channel can disable reading from the stream-interface using various
methods, such as :
- CF_DONT_READ
- !channel_may_recv()
- and possibly others
Till now this was done by mangling SI_FL_RX_WAIT_EP which is not
appropriate at all since it's not the stream interface which decides
whether it wants to deliver data or not. Some places were also wrongly
relying on SI_FL_RXBLK_ROOM since it was the only other alternative,
but it's not suitable for CF_DONT_READ.
Let's use the SI_FL_RXBLK_CHAN flag for this instead. It will properly
prevent the stream interface from being woken up and reads from
subscribing to more receipt without being accidently removed. It is
automatically reset if CF_DONT_READ is not set in stream_int_notify().
The code is not trivial because it splits the logic between everything
related to buffer contents (channel_is_empty(), CF_WRITE_PARTIAL, etc)
and buffer policy (CF_DONT_READ). Also it now needs to decide timeouts
based on any blocking flag and not just SI_FL_RXBLK_ROOM anymore.
It looks like this patch has caused a minor performance degradation on
connection rate, which possibly deserves being investigated deeper as
the test conditions are uncertain (e.g. slightly more subscribe calls?).
For a long time, stream_int_update() and stream_int_notify() used to only
conditionally call si_chk_rcv() based on state change detection. This
detection is not reliable and quite complex. With the new blocked flags
that si_chk_rcv() checks, it's much more reliable to always call the
function to take into account recent changes,and let it decide if it needs
to wake something up or not.
This also removes the calls to si_chk_rcv() that were performed in
si_update_both() since these ones are systematically performed in
stream_int_update() after updating the Rx flags.
