Willy Tarreau [Thu, 25 Feb 2021 14:31:00 +0000 (15:31 +0100)]
MINOR: ssl: mark the SSL handshake tasklet as heavy
There's a fairness issue between SSL and clear text. A full end-to-end
cleartext connection can require up to ~7.7 wakeups on average, plus 3.3
for the SSL tasklet, one of which is particularly expensive. So if we
accept to process many handshakes taking 1ms each, we significantly
increase the processing time of regular tasks just by adding an extra
delay between their calls. Ideally in order to be fair we should have a
1:18 call ratio, but this requires a bit more accounting. With very little
effort we can mark the SSL handshake tasklet as TASK_HEAVY until the
handshake completes, and remove it once done.
Doing so reduces from 14 to 3.0 ms the total response time experienced
by HTTP clients running in parallel to 1000 SSL clients doing full
handshakes in loops. Better, when tune.sched.low-latency is set to "on",
the latency further drops to 1.8 ms.
The tasks latency distribution explain pretty well what is happening:
=> process_stream() is divided by 100 while ssl_sock_io_cb() is
multipled by 4
Interestingly, the total HTTPS response time doesn't increase and even very
slightly decreases, with an overall ~1% higher request rate. The net effect
here is a redistribution of the CPU resources between internal tasks, and
in the case of SSL, handshakes wait bit more but everything after completes
faster.
This was made simple enough to be backportable if it helps some users
suffering from high latencies in mixed traffic.
Willy Tarreau [Thu, 25 Feb 2021 23:25:51 +0000 (00:25 +0100)]
MINOR: task: limit the number of subsequent heavy tasks with flag TASK_HEAVY
While the scheduler is priority-aware and class-aware, and consistently
tries to maintain fairness between all classes, it doesn't make use of a
fine execution budget to compensate for high-latency tasks such as TLS
handshakes. This can result in many subsequent calls adding multiple
milliseconds of latency between the various steps of other tasklets that
don't even depend on this.
An ideal solution would be to add a 4th queue, have all tasks announce
their estimated cost upfront and let the scheduler maintain an auto-
refilling budget to pick from the most suitable queue.
But it turns out that a very simplified version of this already provides
impressive gains with very tiny changes and could easily be backported.
The principle is to reserve a new task flag "TASK_HEAVY" that indicates
that a task is expected to take a lot of time without yielding (e.g. an
SSL handshake typically takes 700 microseconds of crypto computation).
When the scheduler sees this flag when queuing a tasklet, it will place
it into the bulk queue. And during dequeuing, we accept only one of
these in a full round. This means that the first one will be accepted,
will not prevent other lower priority tasks from running, but if a new
one arrives, then the queue stops here and goes back to the polling.
This will allow to collect more important updates for other tasks that
will be batched before the next call of a heavy task.
Preliminary tests consisting in placing this flag on the SSL handshake
tasklet show that response times under SSL stress fell from 14 ms
before the patch to 3.0 ms with the patch, and even 1.8 ms if
tune.sched.low-latency is set to "on".
Amaury Denoyelle [Thu, 25 Feb 2021 13:46:08 +0000 (14:46 +0100)]
BUG/MINOR: stats: fix compare of no-maint url suffix
Only the first 3 characters are compared for ';no-maint' suffix in
http_handle_stats. Fix it by doing a full match over the entire suffix.
As a side effect, the ';norefresh' suffix matched the inaccurate
comparison, so the maintenance servers were always hidden on the stats
page in this case.
REORG: server: Export and rename some functions updating server info
Some static functions are now exported and renamed to follow the same
pattern of other exported functions. Here is the list :
* update_server_fqdn: Renamed to srv_update_fqdn and exported
* update_server_check_addr_port: renamed to srv_update_check_addr_port and exported
* update_server_agent_addr_port: renamed to srv_update_agent_addr_port and exported
* update_server_addr: renamed to srv_update_addr
* update_server_addr_potr: renamed to srv_update_addr_port
* srv_prepare_for_resolution: exported
This change is mandatory to move all functions dealing with the server-state
files in a separate file.
MEDIUM: server: Don't load server-state file if a line is corrupted
This change is not huge but may have a visible impact for users. Now, if a
line of a server-state file is corrupted, the whole file is ignored. A
warning is emitted with the corrupted line number.
In fact, there is no way to recover from a corrupted line. A line is
considered as corrupted if it is too long (truncated line) or if it contains
the wrong number of arguments. In both cases, it means the file was forged
(or at least manually edited). It is safer to ignore it.
Note for now, memory allocation errors are not reported and the
corresponding line is silently ignored.
MINOR: server: Parse and store server-state lines in a dedicated function
Now, srv_state_parse_and_store_line() function is used to parse and store a
line in a tree. It is used for global and local server-state files. This
significatly simplies the apply_server_state() function.
MEDIUM: server: Use a tree to store local server-state lines
Just like for the global server-state file, the line of a local server-state
file are now stored in a tree. This way, the file is fully parsed before
loading the servers state. And with this change, global and local
server-state files are now handled the same way. This will be the
opportunity to factorize the code. It is also a good way to validate the
file before loading any server state.
MINOR: server: Move loading state of servers in a dedicated function
The loop on the servers of a proxy to load the server states was moved in
the function srv_state_px_update(). This simplify a bit the
apply_server_state() function. It is aslo mandatory to simplify the loading
of local server-state file.
MINOR: server: Remove cached line from global server-state tree when found
When a server for a given backend is found in the tree containing all lines
of the global server-state file, the node is removed from the tree. It is
useless to keep it longer. It is a small improvement, but it may also be
usefull to track the orphan lines (not used for now).
MEDIUM: server: Store parsed params of a server-state line in the tree
Parsed parameters are now stored in the tree of server-state lines. This
way, a line from the global server-state file is only parsed once. Before,
it was parsed a first time to store it in the tree and one more time to load
the server state. To do so, the server-state line object must be allocated
before parsing a line. This means its size must no longer depend on the
length of first parsed parameters (backend and server names). Thus the node
type was changed to use a hashed key instead of a string.
MINOR: server: Be more strict when reading the version of a server-state file
Now, we read a full line and expects to found an integer only on it. And if
the line is empty or truncated, an error is returned. If the version is not
valid, an error is also returned. This way, the first line is no longer
partially read.
CLEANUP: server: Use a local eb-tree to store lines of the global server-state file
There is no reason to use a global variable to store the lines of the global
server-state file. This tree is only used during the file parsing, as a line
cache. Now the eb-tree is declared as a local variable in the
apply_server_state() function.
CLEANUP: server: Rename state_line structure into server_state_line
The structure used to store a server-state line in an eb-tree has a too
generic name. Instead of state_line, the structure is renamed as
server_state_line.
CLEANUP: server: Rename state_line node to node instead of name_name
<state_line.name_name> field is a node in an eb-tree. Thus, instead of
"name_name", we now use "node" to name this field. If is a more explicit
name and not too strange.
MEDIUM: server: Refactor apply_server_state() to make it more readable
The apply_server_state() function is really hard to read. Thus it was
refactored to be more maintainable. First, an helper function is used to get
the server-state file path. Some useless variables were removed and most of
other variables were renamed to be more readable. The error messages are now
prefixed to know the context (global vs per-proxy). Finally, the loop on the
proxies list was simplified.
This patch may seem a bit huge, but the changes are not so important.
MINOR: server: Only fill one array when parsing a server-state line
There is no reason to fill two parameter arrays in srv_state_parse_line()
function. Now, only one array is used. The 4th first entries are just
skipped when srv_update_state() is called.
MINOR: server: Be more strict on the server-state line parsing
The srv_state_parse_line() function was rewritten to be more strict. First
of all, it is possible to make the difference between an ignored line and an
malformed one. Then, only blank characters (spaces and tabs) are now allowed
as field separator. An error is reported for truncated lines or for lines
with an unexpected number of arguments regarding the provided version.
However, for now, errors are ignored by the caller, invalid lines are just
skipped.
Willy Tarreau [Thu, 25 Feb 2021 08:32:58 +0000 (09:32 +0100)]
MINOR: task: make tasklet wakeup latency measurements more accurate
First, we don't want to measure wakeup times if the call date had not
been set before profiling was enabled at run time. And second, we may
only collect the value before clearing the TASK_IN_LIST bit, otherwise
another wakeup might happen on another thread and replace the call date
we're about to use, hence artificially lower the wakeup times.
Willy Tarreau [Thu, 25 Feb 2021 07:39:07 +0000 (08:39 +0100)]
MINOR: tasks: also compute the tasklet latency when DEBUG_TASK is set
It is extremely useful to be able to observe the wakeup latency of some
important I/O operations, so let's accept to inflate the tasklet struct
by 8 extra bytes when DEBUG_TASK is set. With just this we have enough
to get live reports like this:
Willy Tarreau [Thu, 25 Feb 2021 06:51:18 +0000 (07:51 +0100)]
MINOR: task: make grq_total atomic to move it outside of the grq_lock
Instead of decrementing grq_total once per task picked from the global
run queue, let's do it at once after the loop like we do for other
counters. This simplifies the code everywhere. It is not expected to
bring noticeable improvements however, since global tasks tend to be
less common nowadays.
Willy Tarreau [Thu, 25 Feb 2021 06:19:45 +0000 (07:19 +0100)]
MINOR: task: don't decrement then increment the local run queue
Now we don't need to decrement rq_total when we pick a tack in the tree
to immediately increment it again after installing it into the local
list. Instead, we simply add to the local queue count the number of
globally picked tasks. Avoiding this shows ~0.5% performance gains at
1Mreq/s (2M task switches/s).
Willy Tarreau [Thu, 25 Feb 2021 06:14:58 +0000 (07:14 +0100)]
MINOR: task: do not use __task_unlink_rq() from process_runnable_tasks()
As indicated in previous commit, this function tries to guess which tree
the task is in to figure what counters to update, while we already have
that info in the caller. Let's just pick the relevant parts to place them
in the caller.
Willy Tarreau [Thu, 25 Feb 2021 06:09:08 +0000 (07:09 +0100)]
MINOR: task: split the counts of local and global tasks picked
In process_runnable_tasks() we're still calling __task_unlink_rq() to
pick a task, and this function tries to guess where to pick the task
from and which counter to update while the caller's context already
has everything. Worse, the number of local tasks is decremented then
recredited, doubling the operations. In order to avoid this we first
need to keep separate counters for local and global tasks that were
picked. This is what this patch does.
William Dauchy [Wed, 24 Feb 2021 23:53:13 +0000 (00:53 +0100)]
BUG/MEDIUM: contrib/prometheus-exporter: fix segfault in listener name dump
We need to check whether listener is empty before doing anything; in
that case, we were trying to dump listerner name while name is null. So
simply move the counters check above, which validate all possible cases
when the listener is empty. This is very similar to what is done in
stats.c
see also the trace:
Thread 1 "haproxy" received signal SIGSEGV, Segmentation fault.
__strlen_sse2 () at ../sysdeps/x86_64/multiarch/../strlen.S:120
120 ../sysdeps/x86_64/multiarch/../strlen.S: No such file or directory.
(gdb) bt
#0 __strlen_sse2 () at ../sysdeps/x86_64/multiarch/../strlen.S:120
#1 0x00005555555b716b in promex_dump_listener_metrics (htx=0x5555558fadf0, appctx=0x555555926070) at contrib/prometheus-exporter/service-prometheus.c:722
#2 promex_dump_metrics (htx=0x5555558fadf0, si=0x555555925920, appctx=0x555555926070) at contrib/prometheus-exporter/service-prometheus.c:1200
#3 promex_appctx_handle_io (appctx=0x555555926070) at contrib/prometheus-exporter/service-prometheus.c:1477
#4 0x00005555556f0c94 in task_run_applet (t=0x555555926180, context=0x555555926070, state=<optimized out>) at src/applet.c:88
#5 0x00005555556bc6d8 in run_tasks_from_lists (budgets=budgets@entry=0x7fffffffe374) at src/task.c:548
#6 0x00005555556bd1a0 in process_runnable_tasks () at src/task.c:750
#7 0x0000555555696cdd in run_poll_loop () at src/haproxy.c:2870
#8 0x0000555555697025 in run_thread_poll_loop (data=data@entry=0x0) at src/haproxy.c:3035
#9 0x0000555555596c90 in main (argc=<optimized out>, argv=0x7fffffffe818) at src/haproxy.c:3723
quit)
this bug was introduced by commit e3f7bd5ae9e969cbfe87e4130d06bff7a3e814c6 ("MEDIUM:
contrib/prometheus-exporter: add listen stats"), which is present for
2.4 only, so no backport needed.
The filters guide was totally outdated. Callbacks to filter payload were
changed, especially the HTTP one because of the HTX. All the HTTP legacy
part is removed. This new guide now reflects the reality.
Missing functions have been added. And because the EOM block was removed,
some parts have been adapted to better explain how the end of the message
may be detected.
MINOR: htx: Add function to reserve the max possible size for an HTX DATA block
The function htx_reserve_max_data() should be used to get an HTX DATA block
with the max possible size. A current block may be extended or a new one
created, depending on the HTX message state. But the idea is to let the
caller to copy a bunch of data without requesting many new blocks. It is its
responsibility to resize the block at the end, to set the final block size.
This function will be used to parse messages with small chunks. Indeed, we
can have more than 2700 1-byte chunks in a 16Kb of input data. So it is easy
to understand how this function may help to improve the parsing of chunk
messages.
Some missing modules have been added and some others have been updated. The
list is now sorted. It is a bit easier to find something. In addition the
path of files have been updated to reflect recent changes.
BUG/MEDIUM: resolvers: Reset address for unresolved servers
If the DNS resolution failed for a server, its ip address must be
removed. Otherwise, the server is stopped but keeps its ip. This may be
confusing when the servers state are retrieved on the CLI and it may lead to
undefined behavior if HAproxy is configured to load its servers state from a
file.
BUG/MEDIUM: resolvers: Reset server address and port for obselete SRV records
When a SRV record expires, the ip/port assigned to the associated server are
now removed. Otherwise, the server is stopped but keeps its ip/port while
the server hostname is removed. It is confusing when the servers state are
retrieve on the CLI and may be a problem if saved in a server-state
file. Because the reload may fail because of this inconsistency.
Here is an example:
* Declare a server template in a backend, using the resolver <dns>
server-template test 2 _http._tcp.example.com resolvers dns check
* 2 SRV records are announced with the corresponding additional
records. Thus, 2 servers are filled. Here is the "show servers state"
output :
Baptiste Assmann [Thu, 19 Nov 2020 21:38:33 +0000 (22:38 +0100)]
BUG/MINOR: resolvers: new callback to properly handle SRV record errors
When a SRV record was created, it used to register the regular server name
resolution callbacks. That said, SRV records and regular server name
resolution don't work the same way, furthermore on error management.
This patch introduces a new call back to manage DNS errors related to
the SRV queries.
BUG/MINOR: resolvers: Only renew TTL for SRV records with an additional record
If no additional record is associated to a SRV record, its TTL must not be
renewed. Otherwise the entry never expires. Thus once announced a first
time, the entry remains blocked on the same IP/port except if a new announce
replaces the old one.
Now, the TTL is updated if a SRV record is received while a matching
existing one is found with an additional record or when an new additional
record is assigned to an existing SRV record.
BUG/MINOR: resolvers: Fix condition to release received ARs if not assigned
At the end of resolv_validate_dns_response(), if a received additionnal
record is not assigned to an existing server record, it is released. But the
condition to do so is buggy. If "answer_record" (the received AR) is not
assigned, "tmp_record" is not a valid record object. It is just a dummy
record "representing" the head of the record list.
Now, the condition is far cleaner. This patch must be backported as far as
2.2.
Willy Tarreau [Wed, 24 Feb 2021 18:40:49 +0000 (19:40 +0100)]
BUG/MINOR: fd: properly wait for !running_mask in fd_set_running_excl()
In fd_set_running_excl() we don't reset the old mask in the CAS loop,
so if we fail on the first round, we'll forcefully take the FD on the
next one.
In practice it's used bu fd_insert() and fd_delete() only, none of which
is supposed to be passed an FD which is still in use since in practice,
given that for now only listeners may be enabled on multiple threads at
once.
This can be backported to 2.2 but shouldn't result in fixing any user
visible bug for now.
Willy Tarreau [Wed, 24 Feb 2021 16:51:38 +0000 (17:51 +0100)]
CLEANUP: task: split the large tasklet_wakeup_on() function in two
This function has become large with the multi-queue scheduler. We need
to keep the fast path and the debugging parts inlined, but the rest now
moves to task.c just like was done for task_wakeup(). This has reduced
the code size by 6kB due to less inlining of large parts that are always
context-dependent, and as a side effect, has increased the overall
performance by 1%.
Willy Tarreau [Wed, 24 Feb 2021 16:03:30 +0000 (17:03 +0100)]
MINOR: task: move the allocated tasks counter to the per-thread struct
The nb_tasks counter was still global and gets incremented and decremented
for each task_new()/task_free(), and was read in process_runnable_tasks().
But it's only used for stats reporting, so doing this this often is
pointless and expensive. Let's move it to the task_per_thread struct and
have the stats sum it when needed.
Willy Tarreau [Wed, 24 Feb 2021 15:44:51 +0000 (16:44 +0100)]
MINOR: task: limit the remote thread wakeup to the global runqueue only
The test in __task_wakeup() to figure if the remote threads are sleeping
doesn't make sense outside of the global runqueue test, since there are
only two possibilities here: local runqueue or global runqueue, hence a
sleeping thread is another one and can only happen when sending to the
global run queue. Let's move the test inside the "if" block.
Willy Tarreau [Wed, 24 Feb 2021 15:41:11 +0000 (16:41 +0100)]
CLEANUP: task: move the tree root detection from __task_wakeup() to task_wakeup()
Historically we used to call __task_wakeup() with a known tree root but
this is not the case and the code has remained needlessly complicated
with the root calculation in task_wakeup() passed in argument to
__task_wakeup() which compares it again.
Let's get rid of this and just move the detection code there. This
eliminates some ifdefs and allows to simplify the test conditions quite
a bit.
Willy Tarreau [Wed, 24 Feb 2021 13:13:40 +0000 (14:13 +0100)]
CLEANUP: tasks: use a less confusing name for task_list_size
This one is systematically misunderstood due to its unclear name. It
is in fact the number of tasks in the local tasklet list. Let's call
it "tasks_in_list" to remove some of the confusion.
Willy Tarreau [Wed, 24 Feb 2021 15:13:03 +0000 (16:13 +0100)]
MINOR: tasks: do not maintain the rqueue_size counter anymore
This one is exclusively used as a boolean nowadays and is non-zero only
when the thread-local run queue is not empty. Better check the root tree's
pointer and avoid updating this counter all the time.
Willy Tarreau [Wed, 24 Feb 2021 14:10:07 +0000 (15:10 +0100)]
MEDIUM: task: remove the tasks_run_queue counter and have one per thread
This counter is solely used for reporting in the stats and is the hottest
thread contention point to date. Moving it to the scheduler and having a
separate one for the global run queue dramatically improves the performance,
showing a 12% boost on the request rate on 16 threads!
In addition, the thread debugging output which used to rely on rqueue_size
was not totally accurate as it would only report task counts. Now we can
return the exact thread's run queue length.
It is also interesting to note that there are still a few other task/tasklet
counters in the scheduler that are not efficiently updated because some cover
a single area and others cover multiple areas. It looks like having a distinct
counter for each of the following entries would help and would keep the code
a bit cleaner:
- global run queue (tree)
- per-thread run queue (tree)
- per-thread shared tasklets list
- per-thread local lists
Maybe even splitting the shared tasklets lists between pure tasklets and
tasks instead of having the whole and tasks would simplify the code because
there remain a number of places where several counters have to be updated.
Willy Tarreau [Wed, 24 Feb 2021 16:38:46 +0000 (17:38 +0100)]
BUILD: dns: avoid a build warning when threads are disabled (dss unused)
dns_session_release() only uses its struct dns_stream_server to access
the lock, so a warning is emitted when threads are disabled. Let's mark
it __maybe_unused.
Willy Tarreau [Wed, 24 Feb 2021 12:46:12 +0000 (13:46 +0100)]
MEDIUM: streams: do not use the streams lock anymore
The lock was still used exclusively to deal with the concurrency between
the "show sess" release handler and a stream_new() or stream_free() on
another thread. All other accesses made by "show sess" are already done
under thread isolation. The release handler only requires to unlink its
node when stopping in the middle of a dump (error, timeout etc). Let's
just isolate the thread to deal with this case so that it's compatible
with the dump conditions, and remove all remaining locking on the streams.
This effectively kills the streams lock. The measured gain here is around
1.6% with 4 threads (374krps -> 380k).
Willy Tarreau [Wed, 24 Feb 2021 09:37:01 +0000 (10:37 +0100)]
MINOR: streams: use one list per stream instead of a global one
The global streams list is exclusively used for "show sess", to look up
a stream to shut down, and for the hard-stop. Having all of them in a
single list is extremely expensive in terms of locking when using threads,
with performance losses as high as 7% having been observed just due to
this.
This patch makes the list per-thread, since there's no need to have a
global one in this situation. All call places just iterate over all
threads. The most "invasive" changes was in "show sess" where the end
of list needs to go back to the beginning of next thread's list until
the last thread is seen. For now the lock was maintained to keep the
code auditable but a next commit should get rid of it.
The observed performance gain here with only 4 threads is already 7%
(350krps -> 374krps).
Willy Tarreau [Wed, 24 Feb 2021 10:53:17 +0000 (11:53 +0100)]
MINOR: cli/streams: make "show sess" dump all streams till the new epoch
Instead of placing the current stream at the end of the stream list when
issuing a "show sess" on the CLI as was done in 2.2 with commit c6e7a1b8e
("MINOR: cli: make "show sess" stop at the last known session"), now we
compare the listed stream's epoch with the dumping stream's and stop on
more recent ones.
This way we're certain to always only dump known streams at the moment we
issue the dump command without having to modify the list. In theory we
could miss some streams if more than 2^31 "show sess" requests are issued
while an old stream remains present, but that's 68 years at 1 "show sess"
per second and it's unlikely we'll keep a process, let alone a stream, that
long.
It could be verified that the count of dumped streams still matches the
one before this change.
Willy Tarreau [Wed, 24 Feb 2021 10:29:51 +0000 (11:29 +0100)]
MINOR: stream: add an "epoch" to figure which streams appeared when
The "show sess" CLI command currently lists all streams and needs to
stop at a given position to avoid dumping forever. Since 2.2 with
commit c6e7a1b8e ("MINOR: cli: make "show sess" stop at the last known
session"), a hack consists in unlinking the stream running the applet
and linking it again at the current end of the list, in order to serve
as a delimiter. But this forces the stream list to be global, which
affects scalability.
This patch introduces an epoch, which is a global 32-bit counter that
is incremented by the "show sess" command, and which is copied by newly
created streams. This way any stream can know whether any other one is
newer or older than itself.
Willy Tarreau [Wed, 24 Feb 2021 10:13:59 +0000 (11:13 +0100)]
BUG/MINOR: proxy: wake up all threads when sending the hard-stop signal
The hard-stop event didn't wake threads up. In the past it wasn't an issue
as the poll timeout was limited to 1 second, but since commit 4f59d3861
("MINOR: time: increase the minimum wakeup interval to 60s") it has become
a problem because old processes can remain live for up to one minute after
the hard-stop-after delay. Let's just wake them up.
This may be backported to older releases, though before 2.4 the extra
delay was only one second.
Willy Tarreau [Wed, 24 Feb 2021 10:11:06 +0000 (11:11 +0100)]
BUG/MEDIUM: cli/shutdown sessions: make it thread-safe
There's no locking around the lookup of a stream nor its shutdown
when issuing "shutdown sessions" over the CLI so the risk of crashing
the process is particularly high.
Let's use a thread_isolate() there which is suitable for this task, and
there are not that many alternatives.
Willy Tarreau [Wed, 24 Feb 2021 10:08:56 +0000 (11:08 +0100)]
BUG/MEDIUM: proxy: use thread-safe stream killing on hard-stop
When setting hard-stop-after, hard_stop() is called at the end to kill
last pending streams. Unfortunately there's no locking there while
walking over the streams list nor when shutting them down, so it's
very likely that some old processes have been crashing or gone wild
due to this. Let's use a thread_isolate() call for this as we don't
have much other choice (and it happens once in the process' life,
that's OK).
Willy Tarreau [Wed, 24 Feb 2021 08:07:52 +0000 (09:07 +0100)]
DOC: muxes: add a diagram of the exchanges between muxes and outer world
Since the muxes API is far from being obvious, let's show a stream being
forwarded between two sides through muxes with their buffers and the
transport layers. The diagram is provided in .fig, .svg, .png, and .pdf.
Dragan Dosen [Mon, 22 Feb 2021 16:20:01 +0000 (17:20 +0100)]
BUG/MEDIUM: vars: make functions vars_get_by_{name,desc} thread-safe
This patch adds a lock to functions vars_get_by_name() and
vars_get_by_desc() to protect accesses to the list of variables.
After the variable is fetched, a sample data is duplicated by using
smp_dup() because the variable may be modified by another thread.
This should be backported to all versions supporting vars along with
"BUG/MINOR: sample: secure convs that accept base64 string and var name
as args" which this patch depends on.
Dragan Dosen [Mon, 22 Feb 2021 09:03:53 +0000 (10:03 +0100)]
BUG/MINOR: sample: secure convs that accept base64 string and var name as args
This patch adds a few improvements in order to secure the use of
converters that accept base64 string and variable name as arguments.
The first change is within related function sample_conv_var2smp_str()
which now flags the sample as SMP_F_CONST if the argument is of type
ARGT_STR. This makes the sample more safe for later use.
A new function sample_check_arg_base64() is added. It checks an argument
and fills it with a variable type if the argument string contains a
valid variable name. If failed, it tries to perform a base64 decode
operation on a non-empty string, and fills the argument with the decoded
content which can be used later, without any additional base64dec()
function calls during runtime. This means that haproxy configuration
check may fail if variable lookup fails and an invalid base64 encoded
string is specified as an argument for such converters.
Both converters, "aes_gcm_dec" and "hmac", now use alloc_trash_chunk()
in order to allocate additional buffers for various conversions, and
avoid the use of a pre-allocated trash chunks directly (usually returned
by get_trash_chunk()). The function sample_check_arg_base64() is used
for both converters in order to check their arguments specified within
the haproxy configuration.
This patch should be backported as far as 2.0. However, it is important
to keep in mind a few things. The "hmac" converter is only available
starting with 2.2. In versions prior to 2.2, the "aes_gcm_dec" converter
and sample_conv_var2smp_str() are implemented in src/ssl_sock.c. Thus
the patch will have to be adapted on these versions.
Note that this patch is required for a subsequent, more important fix.
Ilya Shipitsin [Fri, 19 Feb 2021 18:42:53 +0000 (23:42 +0500)]
BUILD: SSL: introduce fine guard for RAND_keep_random_devices_open
RAND_keep_random_devices_open is OpenSSL specific function, not
implemented in LibreSSL and BoringSSL. Let us define guard
HAVE_SSL_RAND_KEEP_RANDOM_DEVICES_OPEN in include/haproxy/openssl-compat.h
That guard does not depend anymore on HA_OPENSSL_VERSION
Willy Tarreau [Sat, 20 Feb 2021 12:30:31 +0000 (13:30 +0100)]
[RELEASE] Released version 2.4-dev9
Released version 2.4-dev9 with the following main changes :
- BUG/MINOR: server: Remove RMAINT from admin state when loading server state
- CLEANUP: check: fix get_check_status_info declaration
- CLEANUP: contrib/prometheus-exporter: align for with srv status case
- MEDIUM: stats: allow to select one field in `stats_fill_li_stats`
- MINOR: stats: add helper to get status string
- MEDIUM: contrib/prometheus-exporter: add listen stats
- BUG/MINOR: dns: add test on result getting value from buffer into ring.
- BUG/MINOR: dns: dns_connect_server must return -1 unsupported nameserver's type
- BUG/MINOR: dns: missing test writing in output channel in session handler
- BUG/MINOR: dns: fix ring attach control on dns_session_new
- BUG/MEDIUM: dns: fix multiple double close on fd in dns.c
- BUG/MAJOR: connection: prevent double free if conn selected for removal
- BUG/MINOR: session: atomically increment the tracked sessions counter
- REGTESTS: fix http_reuse_conn_hash proxy test
- BUG/MINOR: backend: do not call smp_make_safe for sni conn hash
- MINOR: connection: remove pointers for prehash in conn_hash_params
- BUG/MINOR: checks: properly handle wrapping time in __health_adjust()
- BUG/MEDIUM: checks: don't needlessly take the server lock in health_adjust()
- DEBUG: thread: add 5 extra lock labels for statistics and debugging
- OPTIM: server: switch the actconn list to an mt-list
- Revert "MINOR: threads: change lock_t to an unsigned int"
- MINOR: lb/api: let callers of take_conn/drop_conn tell if they have the lock
- OPTIM: lb-first: do not take the server lock on take_conn/drop_conn
- OPTIM: lb-leastconn: do not take the server lock on take_conn/drop_conn
- OPTIM: lb-leastconn: do not unlink the server if it did not change
- MINOR: tasks: add DEBUG_TASK to report caller info in a task
- MINOR: tasks/debug: add some extra controls of use-after-free in DEBUG_TASK
- BUG/MINOR: sample: Always consider zero size string samples as unsafe
- MINOR: cli: add missing agent commands for set server
- BUILD/MEDIUM: da Adding pcre2 support.
- BUILD: ssl: introduce fine guard for OpenSSL specific SCTL functions
- REGTESTS: reorder reuse conn proxy protocol test
- DOC: explain the relation between pool-low-conn and tune.idle-pool.shared
- MINOR: tasks: refine the default run queue depth
- MINOR: listener: refine the default MAX_ACCEPT from 64 to 4
- MINOR: mux_h2: do not try to remove front conn from idle trees
- REGTESTS: workaround for a crash with recent libressl on http-reuse sni
- BUG/MEDIUM: lists: Avoid an infinite loop in MT_LIST_TRY_ADDQ().
- MINOR: connection: allocate dynamically hash node for backend conns
- DOC: DeviceAtlas documentation typo fix.
- BUG/MEDIUM: spoe: Resolve the sink if a SPOE logs in a ring buffer
- BUG/MINOR: http-rules: Always replace the response status on a return action
- BUG/MINOR: server: Init params before parsing a new server-state line
- BUG/MINOR: server: Be sure to cut the last parsed field of a server-state line
- MEDIUM: server: Don't introduce a new server-state file version
- DOC: contrib/prometheus-exporter: remove htx reference
- REGTESTS: contrib/prometheus-exporter: test NaN values
- REGTESTS: contrib/prometheus-exporter: test well known labels
- CI: github actions: switch to stable LibreSSL release
- BUG/MINOR: server: Fix test on number of fields allowed in a server-state line
- MINOR: dynbuf: make the buffer wait queue per thread
- MINOR: dynbuf: use regular lists instead of mt_lists for buffer_wait
- MINOR: dynbuf: pass offer_buffers() the number of buffers instead of a threshold
- MINOR: sched: have one runqueue ticks counter per thread
Willy Tarreau [Sat, 20 Feb 2021 11:49:54 +0000 (12:49 +0100)]
MINOR: sched: have one runqueue ticks counter per thread
The runqueue_ticks counts the number of task wakeups and is used to
position new tasks in the run queue, but since we've had per-thread
run queues, the values there are not very relevant anymore and the
nice value doesn't apply well if some threads are more loaded than
others. In addition, letting all threads compete over a shared counter
is not smart as this may cause some excessive contention.
Let's move this index close to the run queues themselves, i.e. one per
thread and a global one. In addition to improving fairness, this has
increased global performance by 2% on 16 threads thanks to the lower
contention on rqueue_ticks.
Fairness issues were not observed, but if any were to be, this patch
could be backported as far as 2.0 to address them.
Willy Tarreau [Sat, 20 Feb 2021 11:02:46 +0000 (12:02 +0100)]
MINOR: dynbuf: pass offer_buffers() the number of buffers instead of a threshold
Historically this function would try to wake the most accurate number of
process_stream() waiters. But since the introduction of filters which could
also require buffers (e.g. for compression), things started not to be as
accurate anymore. Nowadays muxes and transport layers also use buffers, so
the runqueue size has nothing to do anymore with the number of supposed
users to come.
In addition to this, the threshold was compared to the number of free buffer
calculated as allocated minus used, but this didn't work anymore with local
pools since these counts are not updated upon alloc/free!
Let's clean this up and pass the number of released buffers instead, and
consider that each waiter successfully called counts as one buffer. This
is not rocket science and will not suddenly fix everything, but at least
it cannot be as wrong as it is today.
This could have been marked as a bug given that the current situation is
totally broken regarding this, but this probably doesn't completely fix
it, it only goes in a better direction. It is possible however that it
makes sense in the future to backport this as part of a larger series if
the situation significantly improves.
Willy Tarreau [Sat, 20 Feb 2021 10:38:56 +0000 (11:38 +0100)]
MINOR: dynbuf: make the buffer wait queue per thread
The buffer wait queue used to be global historically but this doest not
make any sense anymore given that the most common use case is to have
thread-local pools. Thus there's no point waking up waiters of other
threads after releasing an entry, as they won't benefit from it.
Let's move the queue head to the thread_info structure and use
ti->buffer_wq from now on.
BUG/MINOR: server: Fix test on number of fields allowed in a server-state line
When a server-state line is parsed, a test is performed to be sure there is
enough but not too much fields. However the test is buggy. The bug was
introduced in the commit ea2cdf55e ("MEDIUM: server: Don't introduce a new
server-state file version").
William Dauchy [Thu, 18 Feb 2021 22:05:34 +0000 (23:05 +0100)]
REGTESTS: contrib/prometheus-exporter: test well known labels
as we previously briefly broke labels handling, test them to make sure
we don't introduce regressions in the future.
see also commit 040b1195f70d6a24204ede081451fd1dd71e6a34 ("BUG/MINOR:
contrib/prometheus-exporter: Restart labels dump at the right pos") for
reference
MEDIUM: server: Don't introduce a new server-state file version
This revert the commit 63e6cba12 ("MEDIUM: server: add server-states version
2"), but keeping all recent features added to the server-sate file. Instead
of adding a 2nd version for the server-state file format to handle the 5 new
fields added during the 2.4 development, these fields are considered as
optionnal during the parsing. So it is possible to load a server-state file
from HAProxy 2.3. However, from 2.4, these new fields are always dumped in
the server-state file. But it should not be a problem to load it on the 2.3.
This patch seems a bit huge but the diff ignoring the space is much smaller.
The version 2 of the server-state file format is reserved for a real
refactoring to address all issues of the current format.
BUG/MINOR: server: Be sure to cut the last parsed field of a server-state line
If a line of a server-state file has too many fields, the last one is not
cut on the first following space, as all other fileds. It contains all the
end of the line. It is not the expected behavior. So, now, we cut it on the
next following space, if any. The parsing loop was slighly rewritten.
Note that for now there is no error reported if the line is too long.
This patch may be backported at least as far as 2.1. On 2.0 and prior the
code is not the same. The line parsing is inlined in apply_server_state()
function.
BUG/MINOR: server: Init params before parsing a new server-state line
Same static arrays of parameters are used to parse all server-state
lines. Thus it is important to reinit them to be sure to not get params from
the previous line, eventually from the previous loaded file.
This patch should be backported to all stable branches. However, in 2.0 and
prior, the parsing of server-state lines are inlined in apply_server_state()
function. Thus the patch will have to be adapted on these versions.
BUG/MINOR: http-rules: Always replace the response status on a return action
When a HTTP return action is triggered, HAProxy is responsible to return the
response, based on the configured status code. On the request side, there is
no problem because there is no server response to replace. But on the
response side, we must take care to override the server response status
code, if any, to be sure to use the rigth status code to get the http reply
message.
In short, we must always set the configured status code of the HTTP return
action before returning the http reply to be sure to get the right reply,
the one base on the http return action status code and not a reply based on
the server response status code..
This patch should fix the issue #1139. It must be backported as far as 2.2.
BUG/MEDIUM: spoe: Resolve the sink if a SPOE logs in a ring buffer
If a SPOE filter is configured to send its logs to a ring buffer, the
corresponding sink must be resolved during the configuration post
parsing. Otherwise, the sink is undefined when a log message is emitted,
crashing HAProxy.
Amaury Denoyelle [Fri, 19 Feb 2021 14:29:16 +0000 (15:29 +0100)]
MINOR: connection: allocate dynamically hash node for backend conns
Remove ebmb_node entry from struct connection and create a dedicated
struct conn_hash_node. struct connection contains now only a pointer to
a conn_hash_node, allocated only for connections where target is of type
OBJ_TYPE_SERVER. This will reduce memory footprints for every
connections that does not need http-reuse such as frontend connections.
Olivier Houchard [Thu, 18 Feb 2021 22:55:30 +0000 (23:55 +0100)]
BUG/MEDIUM: lists: Avoid an infinite loop in MT_LIST_TRY_ADDQ().
In MT_LIST_TRY_ADDQ(), deal with the "prev" field of the element before the
"next". If the element is the first in the list, then its next will
already have been locked when we locked list->prev->next, so locking it
again will fail, and we'll start over and over.
Amaury Denoyelle [Fri, 19 Feb 2021 14:37:40 +0000 (15:37 +0100)]
REGTESTS: workaround for a crash with recent libressl on http-reuse sni
Disable the ssl-reuse for the sni test on http_reuse_conn_hash vtc. This
seems to be the origin of a crash with libressl environment from 3.2.2
up to 3.3.1 included.
For now, it is not determined if the root cause is in haproxy or
libressl.
Please look for the github issue #1115 for all the details.
Amaury Denoyelle [Fri, 19 Feb 2021 14:37:38 +0000 (15:37 +0100)]
MINOR: mux_h2: do not try to remove front conn from idle trees
In h2_process there was two parts where the connection was removed from
the idle trees, without first checking if the connection is a backend
side.
This should not produce a crash as the node is properly zeroed on
conn_init. However, it is better to explicit the test as it is done on
all other places. Besides it will be mandatory if the node part is
dynamically allocated only for backend connections.
Willy Tarreau [Fri, 19 Feb 2021 14:50:27 +0000 (15:50 +0100)]
MINOR: listener: refine the default MAX_ACCEPT from 64 to 4
The maximum number of connections accepted at once by a thread for a single
listener used to default to 64 divided by the number of processes but the
tasklet-based model is much more scalable and benefits from smaller values.
Experimentation has shown that 4 gives the highest accept rate for all
thread values, and that 3 and 5 come very close, as shown below (HTTP/1
connections forwarded per second at multi-accept 4 and 64):
Willy Tarreau [Fri, 19 Feb 2021 14:11:55 +0000 (15:11 +0100)]
MINOR: tasks: refine the default run queue depth
Since a lot of internal callbacks were turned to tasklets, the runqueue
depth had not been readjusted from the default 200 which was initially
used to favor batched processing. But nowadays it appears too large
already based on the following tests conducted on a 8c16t machine with
a simple config involving "balance leastconn" and one server. The setup
always involved the two threads of a same CPU core except for 1 thread,
and the client was running over 1000 concurrent H1 connections. The
number of requests per second is reported for each (runqueue-depth,
nbthread) couple:
It's possible to save up to about 18% performance by lowering the
default value to 40. One possible explanation to this is that checking
I/Os more frequently allows to flush buffers faster and to smooth the
I/O wait time over multiple operations instead of alternating phases
of processing, waiting for locks and waiting for new I/Os.
The total round trip time also fell from 1.62ms to 1.40ms on average,
among which at least 0.5ms is attributed to the testing tools since
this is the minimum attainable on the loopback.
After some observation it would be nice to backport this to 2.3 and
2.2 which observe similar improvements, since some users have already
observed some perf regressions between 1.6 and 2.2.
Willy Tarreau [Fri, 19 Feb 2021 10:45:22 +0000 (11:45 +0100)]
DOC: explain the relation between pool-low-conn and tune.idle-pool.shared
Disabling idle-pool sharing can result in awful performance in presence
of a not so high number of threads, because the number of available idle
connections will be shared among threads, resulting in most of them
abandonning their connections after a request is done if there are already
enough total available. This is a case where pool-low-conn ought to be
used to preserve a number of connections for each thread, but this relation
isn't obvious as is. Let's add mentions about this with both keywords.
Amaury Denoyelle [Thu, 18 Feb 2021 15:03:37 +0000 (16:03 +0100)]
REGTESTS: reorder reuse conn proxy protocol test
Try to fix http_reuse_conn_hash proxy protocol for both single and
multi-thread environment. Schedule a new set of requests to be sure that
takeover will be functional even with pool-low-count set to 2.
Ilya Shipitsin [Sat, 13 Feb 2021 06:45:33 +0000 (11:45 +0500)]
BUILD: ssl: introduce fine guard for OpenSSL specific SCTL functions
SCTL (signed certificate timestamp list) specified in RFC6962
was implemented in c74ce24cd22e8c683ba0e5353c0762f8616e597d, let
us introduce macro HAVE_SSL_SCTL for the HAVE_SSL_SCTL sake,
which in turn is based on SN_ct_cert_scts, which comes in the same commit
David Carlier [Tue, 16 Feb 2021 11:37:45 +0000 (11:37 +0000)]
BUILD/MEDIUM: da Adding pcre2 support.
The DeviceAtlas Detection API now supports also the pcre2 library,
and some users wish to have exclusively this version in their
environment.
Also, there is no longer new development happening in the legacy
pcre(1) counterpart.
Simple check in the build process as the mutual exclusivity check between the
two are already taking care of early on. Moving the check to the part
only when we build haproxy + the API from source as the other case the API is
already built with the chosen regex library separately.
William Dauchy [Mon, 15 Feb 2021 16:22:16 +0000 (17:22 +0100)]
MINOR: cli: add missing agent commands for set server
we previously forgot to add `agent-*` commands.
Take this opportunity to rewrite the help string in a simpler way for
readability (mainly removing simple quotes)
BUG/MINOR: sample: Always consider zero size string samples as unsafe
smp_is_safe() function is used to be sure a sample may be safely
modified. For string samples, a test is performed to verify if there is a
null-terminated byte. If not, one is added, if possible. It means if the
sample is not const and if there is some free space in the buffer, after
data. However, we must not try to read the null-terminated byte if the
string sample is too long (data >= size) or if the size is equal to
zero. This last test was not performed. Thus it was possible to consider a
string sample as safe by testing a byte outside the buffer.
Now, a zero size string sample is always considered as unsafe and is
duplicated when smp_make_safe() is called.
This patch must be backported in all stable versions.
Willy Tarreau [Thu, 18 Feb 2021 13:38:49 +0000 (14:38 +0100)]
MINOR: tasks/debug: add some extra controls of use-after-free in DEBUG_TASK
It's pretty easy to pre-initialize the index, change it on free() and check
it during the wakeup, so let's do this to ease detection of any accidental
task_wakeup() after a task_free() or tasklet_wakeup() after a tasklet_free().
If this would ever happen we'd then get a backtrace and a core now. The
index's parity is respected so that the call history remains exploitable.
Willy Tarreau [Tue, 16 Feb 2021 17:44:00 +0000 (18:44 +0100)]
MINOR: tasks: add DEBUG_TASK to report caller info in a task
The idea is to know who woke a task up, by recording the last two
callers in a rotating mode. For now it's trivial with task_wakeup()
but tasklet_wakeup_on() will require quite some more changes.
But it also provides a trivial macro allowing to simply place a call in
a task/tasklet handler that needs to be observed:
DEBUG_TASK_PRINT_CALLER(t);
Then starting haproxy this way would trivially yield such info:
$ ./haproxy -db -f test.cfg | sort | uniq -c | sort -nr
199992 h1_io_cb woken up from src/sock.c:797
51764 h1_io_cb woken up from src/mux_h1.c:3634
65 h1_io_cb woken up from src/connection.c:169
45 h1_io_cb woken up from src/sock.c:777
Willy Tarreau [Wed, 17 Feb 2021 15:26:55 +0000 (16:26 +0100)]
OPTIM: lb-leastconn: do not unlink the server if it did not change
Due to the two-phase server reservation, there are 3 calls to
fwlc_srv_reposition() per request, one during assign_server() to reserve
the slot, one in connect_server() to commit it, and one in process_stream()
to release it. However only one of the first two will change the key, so
it's needlessly costly to take the lock, remove a server and insert it
again at the same place when we can already figure we ought not to even
have taken the lock.
Furthermore, even when the server needs to move, there can be quite some
contention on the lbprm lock forcing the thread to wait. During this time
the served and nbpend server values might have changed, just like the
lb_node.key itself. Thus we measure the values again under the lock
before updating the tree. Measurements have shown that under contention
with 16 servers and 16 threads, 50% of the updates can be avoided there.
This patch makes the function compute the new key and compare it to
the current one before deciding to move the entry (and does it again
under the lock forthe second test).
This removes between 40 and 50% of the tree updates depending on the
thread contention and the number of servers. The performance gain due
to this (on 16 threads) was:
One point worth thinking about is that it's not logic to update the
tree 2-3 times per request while it's only read once. half to 2/3 of
these updates are not needed. An experiment consisting in subscribing
the server to a list and letting the readers reinsert them on the fly
showed further degradation instead of an improvement.
A better approach would probably consist in avoinding writes to shared
cache lines by having the leastconn nodes distinct from the servers,
with one node per value, and having them hold an mt-list with all the
servers having that number of connections. The connection count tree
would then be read-mostly instead of facing heavy writes, and most
write operations would be performed on 1-3 list heads which are way
cheaper to migrate than a tree node, and do not require updating the
last two updated neighbors' cache lines.
Willy Tarreau [Wed, 17 Feb 2021 15:14:00 +0000 (16:14 +0100)]
OPTIM: lb-leastconn: do not take the server lock on take_conn/drop_conn
The operations are only an insert and a delete into the LB tree, which
doesn't require the server's lock at all as the lbprm lock is already
held. Let's drop it. Just for the sake of cleanness, given that the
served and nbpend values used to be atomically updated, we'll use an
atomic load to read them.
Willy Tarreau [Wed, 17 Feb 2021 15:15:23 +0000 (16:15 +0100)]
OPTIM: lb-first: do not take the server lock on take_conn/drop_conn
The operations are only an insert and a delete into the LB tree, which
doesn't require the server's lock at all as the lbprm lock is already
held. Let's drop it.
Willy Tarreau [Wed, 17 Feb 2021 15:01:37 +0000 (16:01 +0100)]
MINOR: lb/api: let callers of take_conn/drop_conn tell if they have the lock
The two algos defining these functions (first and leastconn) do not need the
server's lock. However it's already present in pendconn_process_next_strm()
so the API must be updated so that the functions may take it if needed and
that the callers indicate whether they already own it.
As such, the call places (backend.c and stream.c) now do not take it
anymore, queue.c was unchanged since it's already held, and both "first"
and "leastconn" were updated to take it if not already held.
A quick test on the "first" algo showed a jump from 432 to 565k rps by
just dropping the lock in stream.c!
Repeated tests have shown a small perforamnce degradation of ~1.8%
caused by this patch at high request rates on 16 threads. The exact
cause is not yet perfectly known but it probably stems in slower
accesses for non-64-bit aligned atomic accesses.
Willy Tarreau [Wed, 17 Feb 2021 12:33:24 +0000 (13:33 +0100)]
OPTIM: server: switch the actconn list to an mt-list
The remaining contention on the server lock solely comes from
sess_change_server() which takes the lock to add and remove a
stream from the server's actconn list. This is both expensive
and pointless since we have mt-lists, and this list is only
used by the CLI's "shutdown server sessions" command!
Let's migrate to an mt-list and remove the need for this costly
lock. By doing so, the request rate increased by ~1.8%.
Willy Tarreau [Wed, 17 Feb 2021 13:33:58 +0000 (14:33 +0100)]
DEBUG: thread: add 5 extra lock labels for statistics and debugging
Since OTHER_LOCK is commonly used it's become much more difficult to
profile lock contention by temporarily changing a lock label. Let's
add DEBUG1..5 to serve only for debugging. These ones must not be
used in committed code. We could decide to only define them when
DEBUG_THREAD is set but that would complicate attempts at measuring
performance with debugging turned off.
Willy Tarreau [Wed, 17 Feb 2021 14:20:19 +0000 (15:20 +0100)]
BUG/MEDIUM: checks: don't needlessly take the server lock in health_adjust()
The server lock was taken preventively for anything in health_adjust(),
including the static config checks needed to detect that the lock was not
needed, while the function is always called on the response path to update
a server's status. This was responsible for huge contention causing a
performance drop of about 17% on 16 threads. Let's move the lock only
where it should be, i.e. inside the function around the critical sections
only. By doing this, a 16-thread process jumped back from 575 to 675 krps.
This should be backported to 2.3 as the situation degraded there, and
maybe later to 2.2.
Willy Tarreau [Wed, 17 Feb 2021 14:15:15 +0000 (15:15 +0100)]
BUG/MINOR: checks: properly handle wrapping time in __health_adjust()
There's an issue when a server state changes, we use an integer comparison
to decide whether or not to reschedule a test instead of using a wrapping
timer comparison. This will cause some health-checks not to be immediately
triggered half of the time, and some unneeded calls to task_queue() to be
performed in other cases.
This bug has always been there as it was introduced with the commit that
added the feature, 97f07b832 ("[MEDIUM] Decrease server health based on
http responses / events, version 3"). This may be backported everywhere.
projects / thirdparty / haproxy.git / log
