Ronnie Sahlberg [Sat, 14 Jul 2007 00:27:34 +0000 (10:27 +1000)]
add an initial system_aix.c to manage raw sockets under aix
Ronnie Sahlberg [Fri, 13 Jul 2007 07:10:09 +0000 (17:10 +1000)]
update the comment at the top of file to reflect the purpose of the file
Ronnie Sahlberg [Fri, 13 Jul 2007 07:07:10 +0000 (17:07 +1000)]
add a private_data field to the killtcp structure and let the system
specific routines populate it as it see fit when creating a
capture socket.
pass this structure to read_tcp and close capture socket as parameter
Ronnie Sahlberg [Fri, 13 Jul 2007 01:30:19 +0000 (11:30 +1000)]
merge from tridge
Andrew Tridgell [Fri, 13 Jul 2007 01:31:18 +0000 (11:31 +1000)]
- merge from ronnie
- cleaner handling of system capture socket
Andrew Tridgell [Thu, 12 Jul 2007 23:35:46 +0000 (09:35 +1000)]
fully save/restore scheduler parameters
Andrew Tridgell [Thu, 12 Jul 2007 23:14:31 +0000 (09:14 +1000)]
fixed the sense of do_setsched
Andrew Tridgell [Thu, 12 Jul 2007 23:14:15 +0000 (09:14 +1000)]
allow extra option override in /etc/sysconfig/ctdb
Andrew Tridgell [Thu, 12 Jul 2007 22:47:02 +0000 (08:47 +1000)]
added --nosetsched option to ctdbd
Ronnie Sahlberg [Thu, 12 Jul 2007 01:43:30 +0000 (11:43 +1000)]
netinet/if_ether.h is more portable than net/ethernet.h
Ronnie Sahlberg [Thu, 12 Jul 2007 01:31:20 +0000 (11:31 +1000)]
the posix.4 name for the priority field is sched_priority
not __sched_priority
Ronnie Sahlberg [Wed, 11 Jul 2007 23:22:06 +0000 (09:22 +1000)]
as an optimization for when we want to send multiple tickles at a time
let the caller create the sending socket and use a single socket instead
of one new one for each tickle.
pass a sending socket to ctdb_sys_send_tcp()
ctdb_sys_kill_tcp is not longer used so remove it
set the socketflags for close on exec and nonblocking in the helper that
creates the sockets instead of in the caller
add a helper to create a sending socket to send tickles from
Ronnie Sahlberg [Wed, 11 Jul 2007 22:52:24 +0000 (08:52 +1000)]
rename killtcp->fd to killtcp->capture_fd
we might want to have two sockets attached to the killtcp structure
one for capturing and a second one for sending so we dont have to
create a new socket for each tickle we want to send
Ronnie Sahlberg [Wed, 11 Jul 2007 22:31:56 +0000 (08:31 +1000)]
ctdb killtcp no longer takes a <numrst> argument to control how many
times to try the reset.
the reset retry attempt is now handled inside the daemon
update the 60.nfs script and remove this parameter that is no longer
used
Ronnie Sahlberg [Wed, 11 Jul 2007 22:30:04 +0000 (08:30 +1000)]
make the ctdb tool use the killtcp control in the daemon instead of
calling killtcp directly
Ronnie Sahlberg [Wed, 11 Jul 2007 08:24:25 +0000 (18:24 +1000)]
add daemon code for the new kill_tcp control
Ronnie Sahlberg [Wed, 11 Jul 2007 08:13:03 +0000 (18:13 +1000)]
add a ctdb_ prefix to two public functions
Ronnie Sahlberg [Wed, 11 Jul 2007 07:43:51 +0000 (17:43 +1000)]
first cut at a better and more scalable socketkiller
that can kill multiple connections asynchronously using one listening
socket
Ronnie Sahlberg [Wed, 11 Jul 2007 02:33:14 +0000 (12:33 +1000)]
add a ctdb_kill_tcp_callback() that will perform a kill tcp using a
background process
Ronnie Sahlberg [Tue, 10 Jul 2007 23:44:52 +0000 (09:44 +1000)]
pass the header to ctdb_become_dmaster instead of just the reqid
this allows us to print from which node Invalid or Dropped orphan become
dmaster packets came from
Ronnie Sahlberg [Tue, 10 Jul 2007 22:41:29 +0000 (08:41 +1000)]
print the operation code in the debug message when we discard a packet
due to incorrect generation number
Ronnie Sahlberg [Tue, 10 Jul 2007 22:27:22 +0000 (08:27 +1000)]
regenerated ctdbd manpage
Ronnie Sahlberg [Tue, 10 Jul 2007 09:07:23 +0000 (19:07 +1000)]
merge from tridge
Andrew Tridgell [Tue, 10 Jul 2007 08:13:47 +0000 (18:13 +1000)]
minor back-merge from samba4
Ronnie Sahlberg [Tue, 10 Jul 2007 07:45:04 +0000 (17:45 +1000)]
merge from tridge
Andrew Tridgell [Tue, 10 Jul 2007 05:46:05 +0000 (15:46 +1000)]
more merges for GPLv3 update
Andrew Tridgell [Tue, 10 Jul 2007 05:34:00 +0000 (15:34 +1000)]
update lib/events from samba4 (If->if)
Andrew Tridgell [Tue, 10 Jul 2007 05:32:27 +0000 (15:32 +1000)]
update lib/tdb from samba4
Andrew Tridgell [Tue, 10 Jul 2007 05:29:31 +0000 (15:29 +1000)]
update lib/replace from samba4
Andrew Tridgell [Tue, 10 Jul 2007 04:59:23 +0000 (14:59 +1000)]
merge from ronnie
Ronnie Sahlberg [Tue, 10 Jul 2007 03:09:35 +0000 (13:09 +1000)]
use the socketkiller to kill off all lock manager sessions as well
Ronnie Sahlberg [Tue, 10 Jul 2007 02:43:46 +0000 (12:43 +1000)]
update the documentation for NFS to mention that the lock manager must
run on the same port on all nodes.
remove the CTDB_MANAGES_NFSLOCK variable that is no longer used
Ronnie Sahlberg [Tue, 10 Jul 2007 00:24:20 +0000 (10:24 +1000)]
make it possible to specify how many times ctdb killtcp will try to RST
the tcp connection
change the 60.nfs script to run ctdb killtcp in the foreground so we
dont get lots of these running in parallel when there are a lot of tcp
connections to rst
Ronnie Sahlberg [Tue, 10 Jul 2007 00:07:26 +0000 (10:07 +1000)]
run the ctdb killtcp in the background
Ronnie Sahlberg [Mon, 9 Jul 2007 23:45:14 +0000 (09:45 +1000)]
dont restart the tcp service after a ip takeover, it is more efficient
to just kill off the tcp connections
Ronnie Sahlberg [Mon, 9 Jul 2007 07:40:15 +0000 (17:40 +1000)]
nicer handling of DISCONNECTED flag when we update the node flags from
a remote message
Ronnie Sahlberg [Mon, 9 Jul 2007 03:21:17 +0000 (13:21 +1000)]
when a remote node has sent us a message to update the flags for a node,
dont let those messages modify the DISCONNECTED flag.
the DISCONNECTED flag must be managed locally since it describes whether
the local node can communicate with the remote node or not
Ronnie Sahlberg [Mon, 9 Jul 2007 02:55:15 +0000 (12:55 +1000)]
a better way to fix the DISCONNECT|BANNED vs DISCONNECT bug
Ronnie Sahlberg [Mon, 9 Jul 2007 02:33:00 +0000 (12:33 +1000)]
when checking the nodemap flags for consitency while monitoring the
cluster, we cant check that both the BANNED and the DISCONNECTED flags
are both set at the same time since if a node becomes banned just
before it is DISCONNECTED there is no guarantee that all other nodes
will have seen the BANNED flag.
So we must first check the DISCONNECTED flag only and only if the
DISCONNECTED flag is not set should we check the BANNED flag.
othervise this can cause a recovery loop while some nodes thing the
disconnected node is DISCONNECTED|BANNED and other think it is just
DISCONNECTED
Ronnie Sahlberg [Sun, 8 Jul 2007 22:38:01 +0000 (08:38 +1000)]
merge from tridge
Andrew Tridgell [Sun, 8 Jul 2007 11:09:09 +0000 (21:09 +1000)]
fixed sense of inet_aton test
Andrew Tridgell [Sun, 8 Jul 2007 10:45:12 +0000 (20:45 +1000)]
call kill_clients when releasing all IPs, as well as for individual IPs
Andrew Tridgell [Sun, 8 Jul 2007 10:24:03 +0000 (20:24 +1000)]
we do tell banned nodes to release IPs
Andrew Tridgell [Sun, 8 Jul 2007 09:36:55 +0000 (19:36 +1000)]
log the generation numbers to give a hint about this bug
Andrew Tridgell [Sun, 8 Jul 2007 00:41:30 +0000 (10:41 +1000)]
increment rpm release number
Andrew Tridgell [Fri, 6 Jul 2007 06:17:31 +0000 (16:17 +1000)]
merge from ronnie - we have an official port number, yay!
Ronnie Sahlberg [Fri, 6 Jul 2007 05:29:03 +0000 (15:29 +1000)]
use the official iana number for ctdb and not 9001
Ronnie Sahlberg [Fri, 6 Jul 2007 01:51:34 +0000 (11:51 +1000)]
use 'ctdb tickle' instead of sendip to tickle nfs clients.
Ronnie Sahlberg [Fri, 6 Jul 2007 00:54:42 +0000 (10:54 +1000)]
remove 59.nfslock and fold this into 60.nfs
add a 61.nfstickle script to make nfs failover faster
Ronnie Sahlberg [Fri, 6 Jul 2007 00:48:46 +0000 (10:48 +1000)]
merge from tridge
Andrew Tridgell [Thu, 5 Jul 2007 05:06:42 +0000 (15:06 +1000)]
merge from ronnie (with spelling fixes)
Ronnie Sahlberg [Thu, 5 Jul 2007 00:17:46 +0000 (10:17 +1000)]
break the tickle description into two paragraphs
Ronnie Sahlberg [Thu, 5 Jul 2007 00:16:11 +0000 (10:16 +1000)]
update the manpage for ctdb to describe killtcp and tickle
Ronnie Sahlberg [Thu, 5 Jul 2007 00:01:35 +0000 (10:01 +1000)]
merge from tridge
Andrew Tridgell [Thu, 5 Jul 2007 00:00:51 +0000 (10:00 +1000)]
fixed help layout
Andrew Tridgell [Wed, 4 Jul 2007 23:59:45 +0000 (09:59 +1000)]
fixed error message on bad IP/port
Andrew Tridgell [Wed, 4 Jul 2007 23:59:11 +0000 (09:59 +1000)]
merge from ronnie
Ronnie Sahlberg [Wed, 4 Jul 2007 22:56:02 +0000 (08:56 +1000)]
add a command to ctdb to send tickle-ack's
Ronnie Sahlberg [Wed, 4 Jul 2007 07:53:16 +0000 (17:53 +1000)]
merge from tridge
Andrew Tridgell [Wed, 4 Jul 2007 07:45:46 +0000 (17:45 +1000)]
forgot to add this
Ronnie Sahlberg [Wed, 4 Jul 2007 07:37:26 +0000 (17:37 +1000)]
merge from tridge
Ronnie Sahlberg [Wed, 4 Jul 2007 07:35:16 +0000 (17:35 +1000)]
merge from tridge
Andrew Tridgell [Wed, 4 Jul 2007 06:52:38 +0000 (16:52 +1000)]
removed unused makefile var
Andrew Tridgell [Wed, 4 Jul 2007 06:51:13 +0000 (16:51 +1000)]
- neaten up the command line for killtcp
- split out the event script code into a separate module
- get rid of the separate takeover directory
Andrew Tridgell [Wed, 4 Jul 2007 06:22:09 +0000 (16:22 +1000)]
more careful checking of lengths
Andrew Tridgell [Wed, 4 Jul 2007 04:51:33 +0000 (14:51 +1000)]
merge from ronnie
Ronnie Sahlberg [Wed, 4 Jul 2007 04:16:28 +0000 (14:16 +1000)]
we dont need socketkiller anymore now that the
kill-tcp-connection code is available from the ctdb tool
Ronnie Sahlberg [Wed, 4 Jul 2007 04:14:48 +0000 (14:14 +1000)]
add a killtcp command to the ctdb tool
Ronnie Sahlberg [Wed, 4 Jul 2007 03:53:22 +0000 (13:53 +1000)]
add a new ctdb_sys_kill_tcp() function that kills (RST) the specified
connection
Ronnie Sahlberg [Wed, 4 Jul 2007 03:32:38 +0000 (13:32 +1000)]
change the signature for ctdb_sys_send_ack() to ctdb_sys_send_tcp()
to make it possible to provide which seq/ack numbers to use and also
whether the RST flag should be set.
update all callers to the new signature
Ronnie Sahlberg [Wed, 4 Jul 2007 03:27:08 +0000 (13:27 +1000)]
ETH_P_IP does not work on my ubuntu system so changing it back to the
slightly less efficient ETH_P_ALL
Andrew Tridgell [Wed, 4 Jul 2007 03:14:45 +0000 (13:14 +1000)]
merge from ronnie
Ronnie Sahlberg [Wed, 4 Jul 2007 03:13:54 +0000 (13:13 +1000)]
merge from tridge
Ronnie Sahlberg [Wed, 4 Jul 2007 02:52:07 +0000 (12:52 +1000)]
initial version of a socketkiller tool
checked in so it is not lost
this tool takes a socketpair as arguments and will reset the tcp
connection
Ronnie Sahlberg [Tue, 3 Jul 2007 22:36:59 +0000 (08:36 +1000)]
add a tuneable to control how long we wait after a successful recovery
before we alow another recovery to be initiated
Ronnie Sahlberg [Tue, 3 Jul 2007 02:25:49 +0000 (12:25 +1000)]
add more command line parsing
add the PREEMPT service action for persistent reservation out so we
can delete someone elses registration from the lun and thus disable that
someone else from reading/writing the lun completely
Ronnie Sahlberg [Mon, 2 Jul 2007 08:41:37 +0000 (18:41 +1000)]
merge from tridge
Andrew Tridgell [Mon, 2 Jul 2007 08:30:17 +0000 (18:30 +1000)]
merge from ronnie
Ronnie Sahlberg [Mon, 2 Jul 2007 08:25:13 +0000 (18:25 +1000)]
add GPL comment to scsi_io.c
Andrew Tridgell [Mon, 2 Jul 2007 08:24:43 +0000 (18:24 +1000)]
merge from ronnie
Ronnie Sahlberg [Mon, 2 Jul 2007 07:52:57 +0000 (17:52 +1000)]
start implementing command line parsing to scsi_io to make it take
parameters that control what operations to perform
Ronnie Sahlberg [Mon, 2 Jul 2007 06:13:31 +0000 (16:13 +1000)]
get rid of some compiler warnings for the scsi tool
Ronnie Sahlberg [Mon, 2 Jul 2007 05:51:38 +0000 (15:51 +1000)]
add incomplete code fragments to perform SCSI PERSISTENT RESERVATION
calls to a scsi device.
added to bzr so it will not be lost
we need access to an array that supports this optional cdb before we
can proceed and toolify it properly
(the idea is that ctdb should have a mechanism where it can shut out
nodes from accessing the LUNs when it has deemed a node as disconnected)
Ronnie Sahlberg [Mon, 2 Jul 2007 04:26:50 +0000 (14:26 +1000)]
rename tnode->queue to tnode->out_queue to indicate this queue is for
sending data out to the other node
Ronnie Sahlberg [Mon, 2 Jul 2007 04:10:20 +0000 (14:10 +1000)]
when accepting an incoming connection, verify that the source address is
from one of the configured nodes and reject the connection othervise
Ronnie Sahlberg [Tue, 26 Jun 2007 22:44:42 +0000 (08:44 +1000)]
merge from tridge
Andrew Tridgell [Mon, 25 Jun 2007 21:40:37 +0000 (07:40 +1000)]
script version of install needs spaces after -m
Ronnie Sahlberg [Mon, 25 Jun 2007 18:04:00 +0000 (04:04 +1000)]
merge from tridge
Andrew Tridgell [Mon, 18 Jun 2007 17:54:06 +0000 (03:54 +1000)]
added code to kill registered clients on a IP release
Ronnie Sahlberg [Sun, 17 Jun 2007 17:15:28 +0000 (03:15 +1000)]
merge from tridge
Andrew Tridgell [Sun, 17 Jun 2007 17:15:08 +0000 (03:15 +1000)]
run smbstatus every 10 minutes to scrub databases
Ronnie Sahlberg [Sun, 17 Jun 2007 17:14:06 +0000 (03:14 +1000)]
merge from tridge
Andrew Tridgell [Sun, 17 Jun 2007 17:10:50 +0000 (03:10 +1000)]
merge from ronnie
Ronnie Sahlberg [Sun, 17 Jun 2007 16:34:29 +0000 (02:34 +1000)]
add a mechanism to the samba event script to do periodic cleanup of the
databases once every 60 minutes
Andrew Tridgell [Sun, 17 Jun 2007 13:31:44 +0000 (23:31 +1000)]
- merged ctdb_store test from ronnie
- added DatabaseHashSize tunable
- added logging of events inside recovery (for timing)
Andrew Tridgell [Sun, 17 Jun 2007 02:05:29 +0000 (12:05 +1000)]
check winbind in monitoring event too
Andrew Tridgell [Sun, 17 Jun 2007 01:57:42 +0000 (11:57 +1000)]
- wait for winbind on samba start
- use $PATH for ctdb status
Ronnie Sahlberg [Sun, 17 Jun 2007 01:13:42 +0000 (11:13 +1000)]
add a small test tool that can be used to create a massive amount of
records in the test database.
the tool first creates the number of records requested, then it will
loop infinitely reading the records out again.
Ronnie Sahlberg [Thu, 14 Jun 2007 07:26:42 +0000 (17:26 +1000)]
note that there is no link on the PUBLIC interface
Ronnie Sahlberg [Wed, 13 Jun 2007 03:32:19 +0000 (13:32 +1000)]
merge from tridge