IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
Whenever the current git hash changes, we recompile ctdb.c and
ctdb_daemon.c. As both have quite a few warnings with -Wall, this
makes it quite difficult to see the real warnings that pop up during
development. Centralize the ctdb_version_string to just a single file
without warnings.
Signed-off-by: Volker Lendecke <vl@samba.org>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
This sets up boilerplate required for a client code connecting to a
server over unix domain socket. The communication between client
and server is "request" from client to server and "reply" from
server to client.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Tools like ctdb_killtcp can't route packets to IPv4-mapped IPv6
addresses so this works around that.
Add a test case to confirm that this works.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Autobuild-User(master): Martin Schwenke <martins@samba.org>
Autobuild-Date(master): Fri Sep 1 04:06:32 CEST 2017 on sn-devel-144
Only create PID file when actually starting the daemon, rather than
when setting up the context. This will facilitate future changes.
Tweak test to confirm that PID file is no longer created during setup.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Volker Lendecke <vl@samba.org>
Autobuild-User(master): Martin Schwenke <martins@samba.org>
Autobuild-Date(master): Wed Aug 2 07:28:44 CEST 2017 on sn-devel-144
Otherwise, for example, the file descriptor for the main PID file will
leak all the way down to event scripts.
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12898
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
This allows to differentiate between the two database models.
ctdb_db_persistent() - replicated and permanent
ctdb_db_volatile() - distributed and temporary
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
The non-blocking logging variants can currently silently drop messages
when the socket queue fills.
In this case, count the number of dropped messages and attempt to log
a message about dropped log messages when the next message is logged.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Setting CTDB_LOGGING to syslog:nonblocking or syslog:udp will cause
ctdbd to crash at startup due to NULL pointer dereference.
Refactoring in commit c9124a001f
introduced this regression.
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12814
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Autobuild-User(master): Amitay Isaacs <amitay@samba.org>
Autobuild-Date(master): Thu Jun 1 15:26:19 CEST 2017 on sn-devel-144
This allows to pass data to a child process via stdin.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
This allows to mix CTDB major versions in a single cluster.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Autobuild-User(master): Amitay Isaacs <amitay@samba.org>
Autobuild-Date(master): Wed May 24 21:06:28 CEST 2017 on sn-devel-144
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12770
DEBUGLEVEL is defined as a const array reference at compile time.
debug_init() converts that to an allocated array reference at run time.
Since debug_init() is a static function, initialize DEBUGLEVEL via
setup_logging().
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Volker Lendecke <vl@samba.org>
Autobuild-User(master): Volker Lendecke <vl@samba.org>
Autobuild-Date(master): Mon May 8 00:12:25 CEST 2017 on sn-devel-144
Signed-off-by: Chris Lamb <chris@chris-lamb.co.uk>
Reviewed-by: Andrew Bartlett <abartlet@samba.org>
Reviewed-by: Garming Sam <garming@catalyst.net.nz>
Signed-off-by: Chris Lamb <chris@chris-lamb.co.uk>
Reviewed-by: Andrew Bartlett <abartlet@samba.org>
Reviewed-by: Garming Sam <garming@catalyst.net.nz>
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12580
comm_write_send() creates a new tevent_req and adds it to the queue
of requests to be processed. If this tevent_req is freed, then the
queue entry is not removed causing use-after-free error.
If the tevent_req returned by comm_write_send() is freed, then that
request should be removed from the queue and any pending actions based
on that request should also be removed.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12510
To be able to terminate the daemon from within the implementation,
create a subreq using wait_send() provided by the implementation.
When the subreq is finished, it signals the sock_daemon code to terminate
the daemon.
This avoids the need to keep track of the top level tevent_req causing
layer violation and keeps the code flow straighforward.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Stefan Metzmacher <metze@samba.org>
Autobuild-User(master): Stefan Metzmacher <metze@samba.org>
Autobuild-Date(master): Mon Jan 16 21:16:51 CET 2017 on sn-devel-144
queue->offset currently points to the end of available data. However,
after processing one packet the beginning of the next packet is not
marked explicitly and caused the same packet to be processed again.
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12500
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
This is now just a wrapper around comm_write_send/recv. This avoids the
extra tevent_req and fixes a bug in the termination of sock_socket_write
computation.
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12500
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Introduce a single new tunable IPAllocAlgorithm to set the IP
allocation algorithm. This defaults to 2 for LCP2 IP address
allocation.
Tunables LCP2PublicIPs and DeterministicIPs are obsolete.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
This is a generic socket read/write to be used in the ctdb daemon.
It is based on ctdb_io.c and comm.c.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
This extracts the code from following files:
- server/ctdb_logging.c
- server/ctdb_logging_file.c
- server/ctdb_logging_syslog.c
This is in preparation for each daemon (and some processes) doing
their own loging instead of relying on CTDB.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Persistent databases are now always recovered by sequence number, so
there is no need for this tunable.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Autobuild-User(master): Martin Schwenke <martins@samba.org>
Autobuild-Date(master): Fri Nov 25 08:13:59 CET 2016 on sn-devel-144
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12392
Feature SCHED_RESET_ON_FORK is completely broken on RHEL6 and RHEL7
distributions. So do not rely on SCHED_RESET_ON_FORK for now.
This reverts commit 1be8564e55.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Autobuild-User(master): Martin Schwenke <martins@samba.org>
Autobuild-Date(master): Tue Oct 25 11:28:28 CEST 2016 on sn-devel-144
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12157
In the AIX case, also add the close of the file.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Drop setting socket non-blocking and close-on-exec. The socket is
closed soon after. Only a single packet is sent, making it almost
impossible for it to block. Also, note that sockets aren't setup this
way for IPv6.
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12157
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Occurs on an invalid line that isn't the first. Isn't really a leak
because it is allocated off mem_ctx, which should be freed by the
caller.
BUG: https://bugzilla.samba.org/show_bug.cgi?id=12110
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
This avoids CTDB spending too much time processing multiple packets and
return to the event loop sooner.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Andrew Bartlett <abartlet@samba.org>
Reviewed-by: Martin Schwenke <martin@meltin.net>
This controls the maximum size of data ctdb will read from sockets at
a time.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Andrew Bartlett <abartlet@samba.org>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Both of these expand to 1. However, AF_LOCAL is a Unix domain socket,
which makes no sense when reading the code.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Autobuild-User(master): Martin Schwenke <martins@samba.org>
Autobuild-Date(master): Thu May 26 11:42:46 CEST 2016 on sn-devel-144
If this fails, we want to know which states it wanted to move to. Don't do the
return before the debug.
Signed-off-by: Volker Lendecke <vl@samba.org>
Reviewed-by: Jeremy Allison <jra@samba.org>
These controls have never been used and also they do not use the server_id
structure defined in samba. In future, similar controls can be added to
register/unregister using proper server_id structure.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
BUG: https://bugzilla.samba.org/show_bug.cgi?id=11770
From man page of packet(7):
protocol is the IEEE 802.3
protocol number in network byte order. See the <linux/if_ether.h>
include file for a list of allowed protocols. When protocol is set to
htons(ETH_P_ALL), then all protocols are received.
Protocol argument was changed from network order to host order wrongly
in commit 9f8395cb7d.
Specifying "protocol" field to socket(AF_PACKET, ...) call only affects
the packets that are recevied. So use protocol = 0 when sending raw
packets.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Autobuild-User(master): Martin Schwenke <martins@samba.org>
Autobuild-Date(master): Fri Mar 4 12:58:50 CET 2016 on sn-devel-144
This pattern is used quite a few times in the CTDB code. Many
instances use ctdb_kill() but for signal 0 this just calls kill(2)
anyway.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Since this code does not need any private structures defined in
ctdb_private.h, protocol/protocol.h should suffice.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Jeremy Allison <jra@samba.org>
This makes the function compatible with parse_debug().
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Michael Adam <obnox@samba.org>
This allows for backward compatibility with the current code where
DEBUG_ERR corresponds to "ERR".
Fix the test that relies on "ERR" instead of "ERROR".
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Michael Adam <obnox@samba.org>
This variable is used for adding a prefix to log entries from various
child processes.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Michael Adam <obnox@samba.org>
These functions are only used in the ctdb daemon code.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Michael Adam <obnox@samba.org>
Reviewed-by: Andrew Bartlett <abartlet@samba.org>
Reviewed-by: Michael Adam <obnox@samba.org>
Autobuild-User(master): Andrew Bartlett <abartlet@samba.org>
Autobuild-Date(master): Fri Nov 6 13:43:45 CET 2015 on sn-devel-104
This groups function prototypes for common client/server functions in
common/common.h and removes them from ctdb_private.h.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Instead of includes.h, include the required header files explicitly.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
This groups function prototypes for system specific functions in
common/system.h and removes them from ctdb_private.h.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Attempt to make common code independent and free from ctdb_context.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Signed-off-by: Michael Adam <obnox at samba.org>
Reviewed-by: Volker Lendecke <vl@samba.org>
Autobuild-User(master): Volker Lendecke <vl@samba.org>
Autobuild-Date(master): Sat Jun 27 13:20:18 CEST 2015 on sn-devel-104
Every time a nodemap is contructed the node IP addresses all need to
be parsed. This isn't very productive use of CPU.
Instead, parse each string once when the nodes file is loaded. This
results in much simpler code.
This code also removes the use of ctdb_address. Duplicating the port
is pointless without an abstraction layer around ctdb_address. If
CTDB gets an incompatible transport in the future then add an
abstraction layer.
Note that the infiniband code is not updated. Compilation of the
infiniband code is already broken. Fixing it will be a separate,
properly tested effort.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
Having it require a CTDB context stops ctdb_parse_address() from being
used in more generic code. Just use the existing talloc context for
memory allocations.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
When sending messages to clients, ctdb checks for EAGAIN error code and
schedules next write in the subsequent event loop. Using sys_write in
these places causes ctdb to loop hard till a client is able to read from
the socket. With real time scheduling, ctdb daemon spins consuming 100%
of CPU trying to write to the client sockets. This can be quite harmful
when running under VMs or machines with single CPU.
This regression was introduced when all read/write calls were replaced to
use sys_read/sys_write wrappers (c1558adeaa).
The existing code backs off in case of EAGAIN failures and waits for an
event loop to process the write again. This should give ctdb clients
a chance to get scheduled and to process the ctdb socket.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Autobuild-User(master): Martin Schwenke <martins@samba.org>
Autobuild-Date(master): Tue Feb 24 12:29:30 CET 2015 on sn-devel-104
This was true for the daemon until commit
b4589b954e.
Defaulting to ERR in the ctdb CLI tool encourages logging notices at
ERR level, so default to NOTICE instead.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Before storing node IP address, convert into the correct abbreviated
string form for IPv6 addresses.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Put declarations into ctdb_logging.h, factor out some common code,
clean up #includes.
Remove the check so see if the 1st character of the debug level is
'-'. This is wrong, since it is trying to check for a negative
numeric debug level (which is no longer supported) and would need to
be handled in the else anyway.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Internally map them to DEBUG_ERR to limit code churn.
This reduces the unwieldy number of debug levels used by CTDB. ALERT
and CRIT aren't of much use as separate errors, since everything from
ERR up should always be logged. In future just ERR can be used.
This also improves compatibility with Samba's debug.c system priority
mapping.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
It isn't used and shouldn't be. CTDB can't make the system unusable.
Update associated test to ensure that EMERG isn't attempted. Actually
test all remaining debug levels and modernise the test a bit.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Samba's debug subsystem has changed a lot, so CTDB's logging needs
to be rewritten to be compatible.
The new debug.h/debug.c can't just be pulled in because it has some
extra dependencies into Samba's lib/util. For now, to support the
smallest possible patch, implement a minimal subset of Samba's
debug.[ch] that just supports the DEBUG_CALLBACK logtype.
Define a callback for each logging method.
Check later to see if debug_extra (or similar) can somehow be
implemented using debug classes.
The timestamp on CTDB CLI tool and test program DEBUG() output goes
away, so update the unit test code to cope.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Volker Lendecke <vl@samba.org>
As far as we know, nobody uses this and it just complicates the
logging subsystem.
Remove all ringbuffer code and documentation. Update the local
daemons startup code correspondingly.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Volker Lendecke <vl@samba.org>
Although configure should catch this, logging a run-time error is
better than being mystified when ctdbd silently exits.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
This makes it consistent with Samba, to ease transition.
Update unit test code to link to with tdb_wrap instead of including
db_wrap.c.
There are some potential whitespace fixes in this commit that have
been ignored. CTDB's lib/tdb_wrap will be deleted after the
transition to Samba's lib/tdb_wrap, so there's no point polishing it
too much.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
debug_extra is CTDB-specific. Moving it will help with the
transitions to Samba's updated debug.[ch].
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
To avoid warnings when using --enable-developer, which uses
-Wmissing-prototypes.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Seeing these with -Wall:
../server/ctdb_call.c:1117:3: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
record_flags = *(uint32_t *)&c->data[c->keylen + c->datalen];
^
memcpy() seems to be the easiest way to get fix these. The
alternative would be to use unmarshalling functions.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
We really should extricate these from source3 and into some common
code. However, just copy them for now to help get rid of a lot of
warnings.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
If we have already partly written a packet, "data" and thus "pkt->data"
does not point to the start of the packet anymore. Assign "hdr" while
it still points at the start of the header.
Signed-off-by: Volker Lendecke <vl@samba.org>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Autobuild-User(master): Amitay Isaacs <amitay@samba.org>
Autobuild-Date(master): Tue Jul 22 06:09:50 CEST 2014 on sn-devel-104
This makes the scheduler reset code a no-op.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Autobuild-User(master): Amitay Isaacs <amitay@samba.org>
Autobuild-Date(master): Mon Jul 7 13:28:25 CEST 2014 on sn-devel-104
If something unexpectedly uses fork() then an exiting child will
remove the PID file while the main daemon is still running. The real
test is whether the current process has the PID of the main CTDB
daemon, which is the process that calls setsid().
This could be done using getpgrp() instead. At the moment the
eventscript handler harmlessly calls setpgid() - harmless because the
atexit() handlers are cleared upon exec(). However, it is possible
that process groups will be used more in future so it is probably
better to rely on the session ID.
Thanks to Sumit Bose <sbose@redhat.com> for the idea.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Routines in system_common and system_<os> are supposed to be ctdb
functions with OS specific implementations.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Allocate an array of size PATH_MAX on the stack instead. To stop
unnecessary recursion, try to create the desired directory before
creating ancestors and only create ancestors on ENOENT.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
Copy these values onto the stack instead. INET6_ADDRSTRLEN is 46, so
64 is plenty for an IP address and a port number.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
This code is only executed in child processes, so aborting does not
really achieve much.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
When calling sched_setscheduler() with SCHED_OTHER, the only valid
priority is 0. Nice value is "restored" anyway.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Martin Schwenke <martin@meltin.net>
This code can then be used to track child processes created with vfork().
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Michael Adam <obnox@samba.org>
Behaves like mkdir -p.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit afe2145d91725daf1399f0a24f1cddcf65f0ec31)
Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit c700dd0c7b6b43b61b3e231643b5d7cbe2f9592a)
Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit c0bb147ca09e82019b05ec22995623cffc3184e2)
If we process all the data available in a socket buffer, CTDB can stay busy
processing lots of packets via immediate event mechanism in tevent. After
processing an immediate event, tevent returns without epoll_wait. So as long
as there are immediate events, tevent will never poll other FDs. CTDB will
report this as "Event handling took xx seconds" warning. This is misleading
since CTDB is very busy processing packets, but never gets to the point of
polling FDs.
The improvement in socket handling made it worse when handling traverse
control. There were lots of packets filled in the socket buffer quickly and
CTDB stayed busy processing those packets and not polling other FDs and timer
events. This can lead to controls timing out and in worse case other nodes
marking busy node as disconnected.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 92939c1178d04116d842708bc2d6a9c2950e36cc)
This reverts commit 5e9b1a7e24d058ff88aaa0563db36a804e866fa9.
This is not the best approach. Allowing queue buffer size to grow
indefinitely causes large number of CTDB packets to be queued up very
quickly which when processed via immediate events will block CTDB from
processing events from other FDs. If there are immediate events queued
up, tevent will never process any of the FDs till all immediate events
are processed.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit d8b094e804efc53fae9f44c6ef961b7b5797d290)
This reverts commit 035c0d981bde8c0eee8b3f24ba8e2dc817e5b504.
This is a premature optimization. Record can bounce between nodes
very quickly if it is a contended record. There is no need to hold a
record on a node unnecessarily. In case record contention becomes bad,
enabling sticky records on a database is a better idea.
Conflicts:
include/ctdb_private.h
server/ctdb_tunables.c
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit ac417b0003f0116f116834ad2ac51482d25cfa0d)
Empty record with rsn=0 should not be written on any other node other than
dmaster. This is however not true for persistent databases. So currently
apply the check only for volatile databases.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit df83ae7a047dab4803e0d94b1c11df48ae17ca96)
Currently queue buffer size is realloc'd every time we need to extend the
buffer. Small increments can cause memory fragmentation. Instead always
extend buffer in multiples of 4K. This should reduce multiple talloc_realloc
calls when there are lots of packets in the socket buffer.
Also, if queue buffer has grown larger than 64K, throw away the buffer once
all the requests in the queue have been processed. That way queue does not
hold on to large buffers.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 5e9b1a7e24d058ff88aaa0563db36a804e866fa9)
This helps distinguish processes in process list in top, perf, etc.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 2493f57ce268d6fe7e4c40a87852c347fd60d29e)
This is like ctdb_fatal() but exits cleanly without dumping core or
generating a backtrace.
Signed-off-by: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit c0a9456692c88a7a5542cd893d8f326524d3f94e)
This adds more serialisation to the startup, ensuring that the
"startup" event runs after everything to do with the first recovery
(including the "recovered" event).
Given that it now takes longer to get to the "startup" state, the
initscript needs to wait until ctdbd gets to "first_recovery".
Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit ed6814ff0a59ddbb1c1b3128b505380f60d7aeb7)
This allows states, including startup and shutdown states, to be
clearly tracked. This doesn't include regular runtime "states", which
are handled by node flags.
Introduce new functions ctdb_set_runstate(), runstate_to_string() and
runstate_from_string().
Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 8076773a9924dcf8aff16f7d96b2b9ac383ecc28)
When ringbuffer is full, it does not return any entries. Simplify
ringbuffer logic by keeping track of number of log entries rather than
last entry.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Pair-Programmed-With: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit 939d12b96a0cbebbe6269fa2b14f584058dd6174)
For now we pass NULL as the child name. Later we'll give ctdb_fork()
and friends an extra argument and pass that through.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Michael Adam <obnox@samba.org>
(This used to be ctdb commit ba8866d40125bab06391a17d48ff06a4a9f9da89)
Must be called by all child processes.
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Michael Adam <obnox@samba.org>
(This used to be ctdb commit 59b019a97aad9a731f9080ea5be14d0dbdfe03d6)
This simplifies the use of message indexdb API and abstracts tdb related code
inside the API.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit bf7296ce9b98563bcb8426cd035dbeab6d884f59)
This fixes a memory leak in the messaging code.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 20be1f991dd75c2333c9ec9db226432a819f57ba)
This makes sure that even if the srvids are not deregistered, the header
structure is freed when the last message handler has been freed as a result of
client going away.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 4e1ec7412866f2d31c41de1bec0fbf788c03051b)
tevent_schedule_immediate() is much more efficient at handling events that need
to be processed immediately rather than creating timed events with
timeval_zero().
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 11734be353a1e246163eda631d35dfe55d1d6fb1)
When CTDB is busy with lots of smbd, CTDB was spending too much time in
daemon_check_srvids() which searches a list of srvids in the registered
message handlers. Using a hash based index significantly improves the
performance of search in a linked list.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 3e09f25d419635f6dd679b48fa65370f7860be7d)
This improves the processing of packets considerably. It has been
observed that there can be as many as 10 packets in the socket buffer and
the current code of reading a single packet from a socket at a time is
not very optimal. This change reads all the bytes from socket buffer and
then parses to extract multiple packets. If there are multiple packets,
set up a timed event to process next packet.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit d788bc8f7212b7dc1587ae592242dc8c876f4053)
Commit a82d3ec12f0fda16d6bfa8442a07595de897c10e broke fetching from
the log ringbuffer. The solution there is still generally good: there
is no need to keep the ringbuffer in children created by
ctdb_fork()... except for those special children that are created to
fetch data from the ringbuffer!
Introduce a new function ctdb_fork_no_free_ringbuffer() that does
everything ctdb_fork() needs to do except free the ringbuffer (i.e. it
is the old ctdb_fork() function). The new ctdb_fork() function just
calls that function and then frees the ringbuffer in the child.
This means all callers of ctdb_fork() have the convenience of having
the ringbuffer freed. There are 3 special cases:
* Forking the recovery daemon. We want to be able to fetch from the
ringbuffer there.
* The ringbuffer fetching code. Change the 2 calls in this code (main
daemon, recovery daemon) to call ctdb_fork_no_free_ringbuffer()
instead.
While we're here, clear the log ringbuffer when the recovery deamon is
forked, since it will contain a copy of the messages from the main
daemon.
Note to self: always test... even the most obvious patches... ;-)
Signed-off-by: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit 00db5fa00474f8a83f1aa3b603fd756cc9b49ff4)
At the moment the log ringbuffer is duplicated in every child process.
Althought it is copy-on-write we want to see if it is contributing to
out-of-memory situations when there are a lot of children.
The ringbuffer isn't accessible from any of the children anyway...
Signed-off-by: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit a82d3ec12f0fda16d6bfa8442a07595de897c10e)
These support getting and clearing logs from the ring-buffer in the
recovery daemon.
Signed-off-by: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit cbca233d1e03b2410e0bb63b936328d4a8b3c7b4)
Currently these functions are implemented only for Linux.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit be4051326b0c6a0fd301561af10fd15a0e90023b)
We've seen this function report "Unknown family, 0" and then CTDB
disappeared without a trace. If we can reproduce it then this might
help us to debug it.
The idea is that you do something like the following in /etc/sysconfig/ctdb:
export CTDB_EXTERNAL_TRACE="/etc/ctdb/config/gcore_trace.sh"
When we hit this error than we call out to gcore to get a core file so
we can do forensics. This might block CTDB for a few seconds.
Signed-off-by: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit 7895bc003f087ab2f3181df3c464386f59bfcc39)
Do some other hosuekeeping including stopping tevent.
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
Signed-off-by: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit 212298279557a2833ef0f81809b4a5cdac72ca02)
Thanks to Ronnie for highlighting the issue of memory lockdown on AIX.
Fix typo, use getuid and not getpid.
Signed-off-by: Amitay Isaacs <amitay@gmail.com>
(This used to be ctdb commit 21a5cbf9518fafc610939f14874371a52b1dc8b3)
Wrap all creation of child processes inside ctdb_fork() which is used to track all processes we have spawned.
Capture SIGCHLD to track also which child processes have terminated.
Wrap kill() inside ctdb_kill() and make sure that we never send a !0 signal to a child process pid that has already terminated (and might have been replaced with a
(This used to be ctdb commit f73a4b1495830bcdd094a93732a89dd53b3c2f78)
This can improve performance slightly on certain workloads where smbds frequently read from the same record
(This used to be ctdb commit 035c0d981bde8c0eee8b3f24ba8e2dc817e5b504)
there are some child processes where we do not create a connection to the main daemon (switch_from_server_to_client()) because it is expensive to set up and we normally might not need to talk to the daemon at all via a domainsocket.
but we might want to still call to ctdb_ltdb_store() from such chil processes.
(This used to be ctdb commit 9e372a08c40087e6b5335aa298e94d88273566a5)
When the traverse callback frees the current node, the traverse of the
rbtree can fail (the next node->right fails since node is not there any more...).
This is fixed by introducing variables to store the right (and left)
pointers before the callback is called.
(This used to be ctdb commit 8b0caaeed154d26c67a73659d3bbbdd63b21be11)
CTDB has the following limitations on GNU Hurd:
- The pid of a peer is not get from the socket [1]. As a consequence, the peer
process is not killed when releasing IP [2].
- Gratuitous arp are not yet supported [3]
- network interfaces are always considered present [4]
[1]: ctdb_get_peer_pid() in common/system_gnu.c
[2]: release_kill_clients() in server/ctdb_takeover.c
[3]: ctdb_sys_send_arp() in common/system_gnu.c
[4]: ctdb_sys_check_iface_exists() in common/system_gnu.c
(This used to be ctdb commit 00212e5c7dd229e7f8975a165d5ab8875d4917cc)
Move identical copies of ctdb_null_func(), ctdb_fetch_func(),
ctdb_fetch_with_header_func() from ctdb_client.c and
ctdb_ltdb_server.c to somewhere common.
This is in the context of wanting to run CCAN-style tests where most
of the ctdbd code is just included in the test program.
Signed-off-by: Martin Schwenke <martin@meltin.net>
(This used to be ctdb commit 126cb0d369b2b1aed63801dc4ba0554399e8b7e4)
This patch changes the callback signature for traversal
functions to allow a client to abort a traverse before it finishes.
Updates to all callers and examples as well as rb-test tool.
(This used to be ctdb commit 8ab0c63ad36cfbbb1e5fed46a1f4c47b1fdb581f)
Following connection to the local ctdbd, ctdb_cmdline_client() currently
issues a CTDB_CONTROL_GET_PNN request with a fixed 3 second timeout.
The ctdb cmd line client accepts a --timelimit argument for specifying
a per request timeout, pass this value through to ctdb_cmdline_client()
for use as a CTDB_CONTROL_GET_PNN request timeout.
(This used to be ctdb commit 0634d0305f42f17048b6830733767e8dc300e11c)
