On server connection migration from one thread to another, the wrong
idle thread-specific counter is decremented. This bug was introduced
since commit 3d52f0f1f8 due to the
factorization with srv_use_idle_conn. However, this statement is only
executed from conn_backend_get. Extract the decrement from
srv_use_idle_conn in conn_backend_get and use the correct
thread-specific counter.
Rename the function to srv_use_conn to better reflect its purpose as it
is also used with a newly initialized connection not in the idle list.
As a side change, the connection insertion to available list has also
been extracted to conn_backend_get. This will be useful to be able to
specify an alternative list for protocol subject to HOL risk that should
not be shared between several clients.
This bug is only present in this release and thus do not need a backport.
Reported github issue #759 shows there is no name resolving
on server lines for ring and peers sections.
This patch introduce the resolving for those lines.
This patch adds boolean a parameter to parse_server function to specify
if we want the function to perform an initial name resolving using libc.
This boolean is forced to true in case of peers or ring section.
The boolean is kept to false in case of classic servers (from
backend/listen)
This patch should be backported in branches where peers sections
support 'server' lines.
The srv_del_conn_from_list() function is now responsible to update the server
counters and the connection flags when a connection is removed from an idle list
(safe, idle or available). It is called when a connection is released or when a
connection is set as private. This function also removes the connection from the
idle list if necessary.
The srv_use_idle_conn() function is now responsible to update the server
counters and the connection flags when an idle connection is reused. The same
function is called when a new connection is created. This simplifies a bit the
connect_server() function.
When a connection is added to an idle list, it's already detached and
cannot be seen by two threads at once, so there's no point using
TRY_ADDQ, there will never be any conflict. Let's just use the cheaper
ADDQ.
Initially when mt_lists were added, their purpose was to be used with
the scheduler, where anyone may concurrently add the same tasklet, so
it sounded natural to implement a check in MT_LIST_ADD{,Q}. Later their
usage was extended and MT_LIST_ADD{,Q} started to be used on situations
where the element to be added was exclusively owned by the one performing
the operation so a conflict was impossible. This became more obvious with
the idle connections and the new macro was called MT_LIST_ADDQ_NOCHECK.
But this remains confusing and at many places it's not expected that
an MT_LIST_ADD could possibly fail, and worse, at some places we start
by initializing it before adding (and the test is superflous) so let's
rename them to something more conventional to denote the presence of the
check or not:
MT_LIST_ADD{,Q} : inconditional operation, the caller owns the
element, and doesn't care about the element's
current state (exactly like LIST_ADD)
MT_LIST_TRY_ADD{,Q}: only perform the operation if the element is not
already added or in the process of being added.
This means that the previously "safe" MT_LIST_ADD{,Q} are not "safe"
anymore. This also means that in case of backport mistakes in the
future causing this to be overlooked, the slower and safer functions
will still be used by default.
Note that the missing unchecked MT_LIST_ADD macro was added.
The rest of the code will have to be reviewed so that a number of
callers of MT_LIST_TRY_ADDQ are changed to MT_LIST_ADDQ to remove
the unneeded test.
The problem with the way idle connections currently work is that it's
easy for a thread to steal all of its siblings' connections, then release
them, then it's done by another one, etc. This happens even more easily
due to scheduling latencies, or merged events inside the same pool loop,
which, when dealing with a fast server responding in sub-millisecond
delays, can really result in one thread being fully at work at a time.
In such a case, we perform a huge amount of takeover() which consumes
CPU and requires quite some locking, sometimes resulting in lower
performance than expected.
In order to fight against this problem, this patch introduces a new server
setting "pool-low-conn", whose purpose is to dictate when it is allowed to
steal connections from a sibling. As long as the number of idle connections
remains at least as high as this value, it is permitted to take over another
connection. When the idle connection count becomes lower, a thread may only
use its own connections or create a new one. By proceeding like this even
with a low number (typically 2*nbthreads), we quickly end up in a situation
where all active threads have a few connections. It then becomes possible
to connect to a server without bothering other threads the vast majority
of the time, while still being able to use these connections when the
number of available FDs becomes low.
We also use this threshold instead of global.nbthread in the connection
release logic, allowing to keep more extra connections if needed.
A test performed with 10000 concurrent HTTP/1 connections, 16 threads
and 210 servers with 1 millisecond of server response time showed the
following numbers:
haproxy 2.1.7: 185000 requests per second
haproxy 2.2: 314000 requests per second
haproxy 2.2 lowconn 32: 352000 requests per second
The takeover rate goes down from 300k/s to 13k/s. The difference is
further amplified as the response time shrinks.
There was a logic bug in commit ddfe0743d ("MEDIUM: server: use the two
thresholds for the connection release algorithm"): instead of keeping
only our first idle connection when FDs become scarce, the condition was
inverted resulting in enforcing this constraint unless FDs are scarce.
This results in less idle connections than permitted to be kept under
normal condition.
No backport needed.
The algorithm improvement in bdb86bd ("MEDIUM: server: improve estimate
of the need for idle connections") is still not enough because there's
a hard limit between below and above the FD count, so it continues to
end up with many killed connections.
Here we're proceeding differently. Given that there are two configured
limits, a low and a high one, what we do is that we drop connections
when the high limit is reached (what's already done by the killing task
anyway), when we're between the low and the high threshold, we only keep
the connection if our idle entries are empty (with a preference for safe
ones), and below the low threshold, we keep any connection so as to give
them a chance of being reused or taken over by another thread.
Proceeding like this results in much less dropped connections, we
typically see a 99.3% reuse rate (76k conns for 10M requests over 200
servers and 4 threads, with 335k takeovers or 3%), and much less CPU
usage variations because there are no more bursts to try to kill extra
connections.
It should be possible to further improve this by counting the number
of threads exploiting a server and trying to optimize the amount of
per-thread idle connections so that it is approximately balanced among
the threads.
The idle server connection estimates brought in commit bdb86bd ("MEDIUM:
server: improve estimate of the need for idle connections") were committed
without the minimum of 1 idle conn needed for the current thread. The net
effect is that there are bursts of dropped connections when the load varies
because there's no provision for the last connection.
No backport needed, this is 2.2-dev.
Starting with commit 079cb9a ("MEDIUM: connections: Revamp the way idle
connections are killed") we started to improve the way to compute the
need for idle connections. But the condition to keep a connection idle
or drop it when releasing it was not updated. This often results in
storms of close when certain thresholds are met, and long series of
takeover() when there aren't enough connections left for a thread on
a server.
This patch tries to improve the situation this way:
- it keeps an estimate of the number of connections needed for a server.
This estimate is a copy of the max over previous purge period, or is a
max of what is seen over current period; it differs from max_used_conns
in that this one is a counter that's reset on each purge period ;
- when releasing, if the number of current idle+used connections is
lower than this last estimate, then we'll keep the connection;
- when releasing, if the current thread's idle conns head is empty,
and we don't exceed the estimate by the number of threads, then
we'll keep the connection.
- when cleaning up connections, we consider the max of the last two
periods to avoid killing too many idle conns when facing bursty
traffic.
Thanks to this we can better converge towards a situation where, provided
there are enough FDs, each active server keeps at least one idle connection
per thread all the time, with a total number close to what was needed over
the previous measurement period (as defined by pool-purge-delay).
On tests with large numbers of concurrent connections (30k) and many
servers (200), this has quite smoothed the CPU usage pattern, increased
the reuse rate and roughly halved the takeover rate.
We used to have 3 thread-based arrays for toremove_lock, idle_cleanup,
and toremove_connections. The problem is that these items are small,
and that this creates false sharing between threads since it's possible
to pack up to 8-16 of these values into a single cache line. This can
cause real damage where there is contention on the lock.
This patch creates a new array of struct "idle_conns" that is aligned
on a cache line and which contains all three members above. This way
each thread has access to its variables without hindering the other
ones. Just doing this increased the HTTP/1 request rate by 5% on a
16-thread machine.
The definition was moved to connection.{c,h} since it appeared a more
natural evolution of the ongoing changes given that there was already
one of them declared in connection.h previously.
This patch fixes all the leftovers from the include cleanup campaign. There
were not that many (~400 entries in ~150 files) but it was definitely worth
doing it as it revealed a few duplicates.
extern struct dict server_name_dict was moved from the type file to the
main file. A handful of inlined functions were moved at the bottom of
the file. Call places were updated to use server-t.h when relevant, or
to simply drop the entry when not needed.
