Hi, I pushed the RA to the repository. Just changed the meta-data a bit to mention the default for the name parameter and removed the check for probe before check_binary (it is not necessary in this case).
Many thanks for the contribution! Cheers, Dejan On Thu, Jun 16, 2011 at 04:34:54PM +0200, alexander.kra...@basf.com wrote: > Dejan Muhamedagic schrieb am 15.06.2011 15:40:21: > > On Tue, Jun 14, 2011 at 07:15:21PM +0200, alexander.kra...@basf.com > wrote: > > > Dejan Muhamedagic schrieb am 08.06.2011 18:32:16: > > > > Hi Alexander, > > > > On Mon, Jun 06, 2011 at 05:42:30PM +0200, alexander.kra...@basf.com > > > wrote: > > > > > Dejan Muhamedagic schrieb am 04.04.2011 14:35:34: > > > > > > On Fri, Mar 18, 2011 at 04:15:16PM +0100, > alexander.kra...@basf.com > > > > > wrote: > > > > > > > Hi, > > > > > > > > > > > > > > Dejan Muhamedagic schrieb am 18.03.2011 14:31:08: > > > > > > > > Hi, > > > > > > > > > > > > > > > > On Wed, Mar 16, 2011 at 04:58:25PM +0100, Corvus Corax > wrote: > > > > > > > > > > > > > > > > > > IPAddr2 puts the interface up on start and down on stop. > > > > > > > > > But its not able to detect an UP or DOWN change in status > or > > > > > monitor. > > > > > > > > > > > > > > > > > > Therefore an "ifconfig <interface> down" from a thrird > program > > > or > > > > > a > > > > > > > > > careless administrator would drop the link without > pacemaker > > > > > noticing! > > > > > > > > > > > > > > > > Hmm, careless administrator is somewhat of a paradox, right? > > > > > > > > > > > > > > > > Really, what was your motivation for this? It makes me > wonder, > > > > > > > > since this RA has existed for many years and so far nobody > > > > > > > > bothered to test this. > > > > > > > > > > > > > > Hm, maybe the idea behind is not totally new. Remember this > > > thread: > > > > > > > > > > > > > > > > http://lists.community.tummy.com/pipermail/linux-ha-dev/2011-February/018184.html > > > > > > > > > > > > > > > > > > > > > > > I would go with the remarks of LMB, that this is something > closer > > > to > > > > > > > the pingd than to Ipaddr2. Isn't the real intention of both > post, > > > that > > > > > you > > > > > > > want to know, if your network interface is vital ? > > > > > > > > > > > > Yes. > > > > > > > > > > > > > You may use pingd for that, but someone may be concerned to > ping > > > the > > > > > right > > > > > > > remote device (also a default-gateway might not be a very > static > > > thing > > > > > in > > > > > > > a modern network). > > > > > > > > > > > > > > My imagination is currently an agent (let's call it > ethmonitor) > > > that > > > > > > > monitors > > > > > > > a network interface with a combination of the fine methods > that > > > Robert > > > > > > > > > > > > Euhus > > > > > > > has posted in his patch. Than you could define some rules in > CIB > > > how > > > > > to > > > > > > > react on the event of a failed network interface. Sure this > > > assumes > > > > > that > > > > > > > you > > > > > > > do your heartbeats over more than one interface. > > > > > > > > > > > > > > It would check: > > > > > > > 1. interface link up ? > > > > > > > 2. does the RX counter of the interface increase during a > certain > > > > > > > > amout > > > > > > > of time ? > > > > > > > 3. do I have some other nodes in my arp-cache which I could > > > arping ? > > > > > > > 4. maybe retry all checks to overcome short outages > > > > > > > If all questions are answered with NO - the interface is dead. > > > > > > > > > > > > > > I would add my vote for such a feature. > > > > > > > > > > > > Just took a look at the thread you referenced above. > > > > > > Unfortunately, the author didn't get back with the new code > > > > > > after review and short discussion. > > > > > > > > > > > > > > > > Now I took the code from Robert in the above referenced thread and > put > > > it > > > > > into a complete new RA. > > > > > It is based very much on the existing pind agent, but implements > the > > > > > monitoring like discussed above. > > > > > > > > Great! > > > > > > > > > Please let me know, what you think about it. > > > > > > > > Does it work? :) > > > > > > Yes, it does. For me in my test environment. :-) > > > I did review your comments and attached a new version of the agent (as > it > > > is not in the repository for diffs). > > > Some comments of your comments below. > > > > > > Regards > > > Alex > > > > > > > > > > > See below for a few comments. > > > > > > > > Cheers, > > > > > > > > Dejan > > > > > > > > > > > > > > Cheers, > > > > > Alex > > > > > > > > > #!/bin/sh > > > > > # > > > > > # OCF Resource Agent compliant script. > > > > > # Monitor the vitality of a local network interface. > > > > > # > > > > > # Based on the work by Robert Euhus and Lars Marowsky-Brée. > > > > > # > > > > > # Transfered from Ipaddr2 into ethmonitor by Alexander Krauth > > > > > # > > > > > # Copyright (c) 2011 Robert Euhus, Alexander Krauth, Lars > > > Marowsky-Brée > > > > > # All Rights Reserved. > > > > > # > > > > > # This program is free software; you can redistribute it and/or > modify > > > > > # it under the terms of version 2 of the GNU General Public > License as > > > > > # published by the Free Software Foundation. > > > > > # > > > > > # This program is distributed in the hope that it would be useful, > but > > > > > # WITHOUT ANY WARRANTY; without even the implied warranty of > > > > > # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. > > > > > # > > > > > # Further, this software is distributed without any warranty that > it > > > is > > > > > # free of the rightful claim of any third person regarding > > > infringement > > > > > # or the like. Any license provided herein, whether implied or > > > > > # otherwise, applies only to this software file. Patent licenses, > if > > > > > # any, provided herein do not apply to combinations of this > program > > > with > > > > > # other software, or any other product whatsoever. > > > > > # > > > > > # You should have received a copy of the GNU General Public > License > > > > > # along with this program; if not, write the Free Software > Foundation, > > > > > # Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. > > > > > # > > > > > # OCF parameters are as below > > > > > # > > > > > # OCF_RESKEY_interface > > > > > # OCF_RESKEY_multiplicator > > > > > # OCF_RESKEY_name > > > > > # OCF_RESKEY_repeat_count > > > > > # OCF_RESKEY_repeat_interval > > > > > # OCF_RESKEY_pktcnt_timeout > > > > > # OCF_RESKEY_arping_count > > > > > # OCF_RESKEY_arping_timeout > > > > > # OCF_RESKEY_arping_cache_entries > > > > > # > > > > > # TODO: Check against IPv6 > > > > > # > > > > > > > > > ####################################################################### > > > > > # Initialization: > > > > > > > > > > : ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/resource.d/heartbeat} > > > > > . ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs > > > > > > > > > > > > > > ####################################################################### > > > > > > > > > > meta_data() { > > > > > cat <<END > > > > > <?xml version="1.0"?> > > > > > <!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd"> > > > > > <resource-agent name="ethmonitor"> > > > > > <version>1.2</version> > > > > > > > > > > <LONGdesc lang="en"> > > > > > Monitor the vitality of a local network interface. > > > > > > > > > > You may setup this RA as a clone resource to monitor the network > > > interfaces on different nodes, with the same interface name. > > > > > This is not related to the IP adress or the network on which a > > > interface is configured. > > > > > You may use this RA to move resources away from a node, which has > a > > > faulty interface or prevent moving resources to such a node. > > > > > This gives you independend control of the resources, without > involving > > > cluster intercommunication. But it requires your nodes to have more > than > > > one network interface. > > > > > > > > > > The resource configuration requires a monitor operation, because > the > > > monitor does the main part of the work. > > > > > In addition to the resource configuration, you need to configure > some > > > location contraints, based on a CIB attribute value. > > > > > The name of the attribute value is configured in the 'name' option > of > > > this RA. > > > > > > > > > > Example constraint configuration: > > > > > location loc_connected_node my_resource_grp \ > > > > > rule $id="rule_loc_connected_node" -INF: ethmonitor eq 0 > > > > > > > > > > The ethmonitor works in 3 different modes to test the interface > > > vitality. > > > > > 1. call ip to see if the link status is up (if link is down -> > error) > > > > > 2. call ip an watch the RX counter (if packages come around in a > > > certain time -> success) > > > > > 3. call arping to check wether any of the IPs found in the lokal > ARP > > > cache answers an ARP REQUEST (one answer -> success) > > > > > 4. return error > > > > > > > > I think that some parts of this long description should go to > > > www.linux-ha.org/wiki/ethmonitor_(resource_agent) > > > > > > > > > </longdesc> > > > > > <shortdesc lang="en">Monitors network interfaces</shortdesc> > > > > > > > > > > <parameters> > > > > > <parameter name="interface" unique="0" required="1"> > > > > > > > > shouldn't this be unique? > > > > > > Hm, I never really understand the unique flag (see also current > > > mailinglist discussion). > > > If, I clone this resource, because I want to monitor eth0 on two > nodes. > > > May it then be set to unique ? > > > > Yes. > > > > unique: > > > > Two resources of the same kind in the cluster may not have the > > same value for a "unique" parameter. > > done. > > > > > > > > > <longdesc lang="en"> > > > > > The name of the network interface which should be monitored (e.g. > > > eth0). > > > > > </longdesc> > > > > > <shortdesc lang="en">Network interface name</shortdesc> > > > > > <content type="string" default=""/> > > > > > </parameter> > > > > > > > > > > <parameter name="name" unique="0"> > > > > > > > > and this too? > > > > > > Didn't "unique=1" also require "required=1" ? So then it is not, > because > > > it has a default. > > > > Well, not entirely true. The user still can set the parameter. > > However, if the parameter is unset in two resources, then that > > would effectively make the parameter non-unique. Currently, the > > crm shell won't notice that. But ultimately it is up to the user > > to keep the configuration sane. Imagine what would happen if the > > two resources used the same attribute to write the interface > > status. > > > > One option would be to name the attribute after the interface by > > default, say eth0mon, br0mon or perhaps mon-eth0, mon-br0. That > > way just by setting the interface we make sure that the > > attribute is unique as well. > > > > OK. No more comments here. > > > > Cheers, > > > > Dejan > > done, like you proposed. > > > > > > > > > <longdesc lang="en"> > > > > > The name of the CIB attribute to set. This is the name to be used > in > > > the constraints. > > > > > </longdesc> > > > > > <shortdesc lang="en">Attribute name</shortdesc> > > > > > <content type="integer" default="ethmonitor"/> > > > > > </parameter> > > > > > > > > > > <parameter name="multiplier" unique="0" > > > > > > <longdesc lang="en"> > > > > > Multiplier for the value of the CIB attriobute specified in > parameter > > > name. > > > > > </longdesc> > > > > > <shortdesc lang="en">Multiplier for result variable</shortdesc> > > > > > <content type="integer" default="1"/> > > > > > </parameter> > > > > > > > > > > <parameter name="repeat_count"> > > > > > <longdesc lang="en"> > > > > > Specify how often the interface will be monitored, before the > status > > > is set to failed. You need to set the timeout of the monitoring > operation > > > to at least repeat_count * repeat_interval > > > > > </longdesc> > > > > > <shortdesc lang="en">Monitor repeat count</shortdesc> > > > > > <content type="integer" default="5"/> > > > > > </parameter> > > > > > > > > > > <parameter name="repeat_interval"> > > > > > <longdesc lang="en"> > > > > > Specify how long to wait in seconds between the repeat_counts. > > > > > </longdesc> > > > > > <shortdesc lang="en">Monitor repeat interval in > seconds</shortdesc> > > > > > <content type="integer" default="10"/> > > > > > </parameter> > > > > > > > > > > <parameter name="pktcnt_timeout"> > > > > > <longdesc lang="en"> > > > > > Timeout for the RX packet counter. Stop listening for packet > counter > > > changes after the given number of seconds. > > > > > </longdesc> > > > > > <shortdesc lang="en">packet counter timeout</shortdesc> > > > > > <content type="integer" default="5"/> > > > > > </parameter> > > > > > > > > > > <parameter name="arping_count"> > > > > > <longdesc lang="en"> > > > > > Number of ARP REQUEST packets to send for every IP. > > > > > Usually one ARP REQUEST (arping) is send > > > > > </longdesc> > > > > > <shortdesc lang="en">Number of arpings per IP</shortdesc> > > > > > <content type="integer" default="1"/> > > > > > </parameter> > > > > > > > > > > <parameter name="arping_timeout"> > > > > > <longdesc lang="en"> > > > > > Time in seconds to wait for ARP REQUESTs (all packets of > > > arping_count). > > > > > This is to limit the time for arp requests, to be able to send > > > requests to more than one node, without running in the monitor > operation > > > timeout. > > > > > </longdesc> > > > > > <shortdesc lang="en">Timeout for arpings per IP</shortdesc> > > > > > <content type="integer" default="1"/> > > > > > </parameter> > > > > > > > > > > <parameter name="arping_cache_entries"> > > > > > <longdesc lang="en"> > > > > > Maximum number of IPs from ARP cache list to check for ARP REQUEST > > > > (arping) answers. Newest entries are tried first. > > > > > </longdesc> > > > > > <shortdesc lang="en">Number of ARP cache entries to > try</shortdesc> > > > > > <content type="integer" default="5"/> > > > > > </parameter> > > > > > > > > > > </parameters> > > > > > <actions> > > > > > <action name="start" timeout="20s" /> > > > > > <action name="stop" timeout="20s" /> > > > > > <action name="status" depth="0" timeout="20s" interval="10s" /> > > > > > <action name="monitor" depth="0" timeout="20s" interval="10s" /> > > > > > <action name="meta-data" timeout="5s" /> > > > > > <action name="validate-all" timeout="20s" /> > > > > > </actions> > > > > > </resource-agent> > > > > > END > > > > > > > > > > exit $OCF_SUCCESS > > > > > } > > > > > > > > > > # > > > > > # Return true, if the interface exists > > > > > # > > > > > is_interface() { > > > > > # > > > > > # List interfaces but exclude FreeS/WAN ipsecN virtual > interfaces > > > > > # > > > > > local iface=`$IP2UTIL -o -f inet addr show | grep " $1 " \ > > > > > | cut -d ' ' -f2 | sort -u | grep -v '^ipsec[0-9][0-9]*$'` > > > > > if [ "$iface" != "" ]; then return 0; fi > > > > > return 1 > > > > > > > > [ "$iface" != "" ] is enough instead of the previous two lines > > > done. > > > > > > > > > > > > } > > > > > > > > > > if_init() { > > > > > local rc > > > > > > > > > > if [ X"$OCF_RESKEY_interface" = "X" ]; then > > > > > ocf_log err "Interface name (the interface parameter) is > > > mandatory" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > > > > > > NIC="$OCF_RESKEY_interface" > > > > > > > > > > if is_interface $NIC > > > > > then > > > > > case "$NIC" in > > > > > *:*) ocf_log err "Do not specify a virtual interface : > > > $OCF_RESKEY_interface" > > > > > exit $OCF_ERR_CONFIGURED;; > > > > > *) ;; > > > > > esac > > > > > else > > > > > case $__OCF_ACTION in > > > > > validate-all) ocf_log err "Interface $OCF_RESKEY_interface > does > > > not exist" > > > > > exit $OCF_ERR_CONFIGURED;; > > > > > *) ocf_log warn "Interface $OCF_RESKEY_interface > does > > > not exist" > > > > > ## It might be a bond interface which > is > > > temporarily not available, therefore we want to continue here > > > > > ;; > > > > > > > > Why not use NIC instead of OCF_RESKEY_interface when you already set > > > > that? > > > done. > > > > > > > > > > > > esac > > > > > fi > > > > > > > > > > : ${OCF_RESKEY_multiplier:="1"} > > > > > if ! ocf_is_decimal "$OCF_RESKEY_multiplier"; then > > > > > ocf_log err "Invalid OCF_RESKEY_multiplier > > > [$OCF_RESKEY_multiplier]" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > > > > > > ATTRNAME=${OCF_RESKEY_name:-ethmonitor} > > > > > > > > > > REP_COUNT=${OCF_RESKEY_repeat_count:-5} > > > > > if ! ocf_is_decimal "$REP_COUNT" -o [ $REP_COUNT -lt 1 ]; then > > > > > ocf_log err "Invalid OCF_RESKEY_repeat_count [$REP_COUNT]" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > REP_INTERVAL_S=${OCF_RESKEY_repeat_interval:-10} > > > > > if ! ocf_is_decimal "$REP_INTERVAL_S"; then > > > > > ocf_log err "Invalid OCF_RESKEY_repeat_interval > > > [$REP_INTERVAL_S]" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > : ${OCF_RESKEY_pktcnt_timeout:="5"} > > > > > if ! ocf_is_decimal "$OCF_RESKEY_pktcnt_timeout"; then > > > > > ocf_log err "Invalid OCF_RESKEY_pktcnt_timeout > > > [$OCF_RESKEY_pktcnt_timeout]" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > : ${OCF_RESKEY_arping_count:="1"} > > > > > if ! ocf_is_decimal "$OCF_RESKEY_arping_count"; then > > > > > ocf_log err "Invalid OCF_RESKEY_arping_count > > > [$OCF_RESKEY_arping_count]" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > : ${OCF_RESKEY_arping_timeout:="1"} > > > > > if ! ocf_is_decimal "$OCF_RESKEY_arping_timeout"; then > > > > > ocf_log err "Invalid OCF_RESKEY_arping_timeout > > > [$OCF_RESKEY_arping_count]" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > : ${OCF_RESKEY_arping_cache_entries:="5"} > > > > > if ! ocf_is_decimal "$OCF_RESKEY_arping_cache_entries"; then > > > > > ocf_log err "Invalid OCF_RESKEY_arping_cache_entries > > > [$OCF_RESKEY_arping_cache_entries]" > > > > > exit $OCF_ERR_CONFIGURED > > > > > fi > > > > > return $OCF_SUCCESS > > > > > } > > > > > > > > > > # get the link status on $NIC > > > > > # returns UP or DOWN or whatever ip reports (UNKNOWN?) > > > > > get_link_status () { > > > > > $IP2UTIL -o link show dev "$NIC" \ > > > > > | sed 's/.* state \([^ ]*\) .*/\1/' > > > > > > > > This prints "UNKNOWN" for my bridge (brn) interfaces which are up: > > > > [0]hex-12:~ > ip -o link show dev br0 > > > > 6: br0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue > state > > > UNKNOWN \ > > > > link/ether 00:23:7d:a7:29:96 brd ff:ff:ff:ff:ff:ff > > > > > > Hm, yes. Didn't feel well with this function all the time. Changed it, > to > > > let ip decide what is up or down. > > > I think this is much more up- and downward compatible. > > > > > > get_link_status () { > > > $IP2UTIL -o link show up dev "$NIC" | grep -c "$NIC" > > > } > > > > > > > > > > > > } > > > > > > > > > > # returns the number of received rx packets on $NIC > > > > > get_rx_packets () { > > > > > ocf_log debug "$IP2UTIL -o -s link show dev $NIC" > > > > > $IP2UTIL -o -s link show dev "$NIC" \ > > > > > | sed 's/.* RX: [^0-9]*[0-9]* *\([0-9]*\) .*/\1/' > > > > > # the first number after RX: ist the # of bytes , > > > > > # the second is the # of packets received > > > > > } > > > > > > > > > > # watch for packet counter changes for max. > OCF_RESKEY_pktcnt_timeout > > > seconds > > > > > # returns immedeately with return code 0 if any packets were > received > > > > > # otherwise 1 is returned > > > > > watch_pkt_counter () { > > > > > local RX_PACKETS_NEW > > > > > local RX_PACKETS_OLD > > > > > RX_PACKETS_OLD="`get_rx_packets`" > > > > > for n in `seq $(( $OCF_RESKEY_pktcnt_timeout * 10 ))`; do > > > > > sleep 0.1 > > > > > RX_PACKETS_NEW="`get_rx_packets`" > > > > > ocf_log debug "RX_PACKETS_OLD: $RX_PACKETS_OLD > RX_PACKETS_NEW: > > > $RX_PACKETS_NEW" > > > > > if [ "$RX_PACKETS_OLD" -ne "$RX_PACKETS_NEW" ]; then > > > > > ocf_log debug "we received some packets." > > > > > return 0 > > > > > fi > > > > > done > > > > > return 1 > > > > > } > > > > > > > > > > # returns list of cached ARP entries for $NIC > > > > > # sorted by age ("last confirmed") > > > > > # max. OCF_RESKEY_arping_cache_entries entries > > > > > get_arp_list () { > > > > > $IP2UTIL -s neighbour show dev $NIC \ > > > > > | sort -t/ -k2,2n | cut -d' ' -f1 \ > > > > > | head -n $OCF_RESKEY_arping_cache_entries > > > > > # the "used" entries in `ip -s neighbour show` are: > > > > > # "last used"/"last confirmed"/"last updated" > > > > > } > > > > > > > > > > # arping the IP given as argument $1 on $NIC > > > > > # until OCF_RESKEY_arping_count answers are received > > > > > do_arping () { > > > > > # TODO: add the source IP > > > > > # TODO: check for diffenrent arping versions out there > > > > > arping -q -c $OCF_RESKEY_arping_count -w > $OCF_RESKEY_arping_timeout > > > -I $NIC $1 > > > > > # return with the exit code of the arping command > > > > > return $? > > > > > } > > > > > > > > > > # > > > > > # Check the interface depending on the level given as > parameter: > > > $OCF_RESKEY_check_level > > > > > # > > > > > # 09: check for nonempty ARP cache > > > > > # 10: watch for packet counter changes > > > > > # > > > > > # 19: check arping_ip_list > > > > > # 20: check arping ARP cache entries > > > > > # > > > > > # 30: watch for packet counter changes in promiscios mode > > > > > # > > > > > # If unsuccessfull in levels 18 and above, > > > > > # the tests for higher check levels are run. > > > > > # > > > > > if_check () { > > > > > # always check link status first > > > > > link_status="`get_link_status`" > > > > > ocf_log debug "link_status: $link_status" > > > > > case $link_status in > > > > > UP) > > > > > ;; > > > > > DOWN) > > > > > # remove address from NIC > > > > > return $OCF_NOT_RUNNING > > > > > ;; > > > > > *) # this should not happen. > > > > > return $OCF_ERR_GENERIC > > > > > ;; > > > > > esac > > > > > > > > > > # watch for packet counter changes > > > > > ocf_log debug "watch for packet counter changes" > > > > > watch_pkt_counter && return $OCF_SUCCESS > > > > > > > > > > # check arping ARP cache entries > > > > > ocf_log debug "check arping ARP cache entries" > > > > > for ip in `get_arp_list`; do > > > > > do_arping $ip && return $OCF_SUCCESS > > > > > done > > > > > > > > > > # watch for packet counter changes in promiscios mode > > > > > # ocf_log debug "watch for packet counter changes in promiscios > > > mode" > > > > > # be sure switch off promiscios mode in any case > > > > > # TODO: check first, wether promisc is already on and leave it > > > untouched. > > > > > # trap "$IP2UTIL link set dev $NIC promisc off; exit" INT TERM > EXIT > > > > > # $IP2UTIL link set dev $NIC promisc on > > > > > # watch_pkt_counter && return $OCF_SUCCESS > > > > > # $IP2UTIL link set dev $NIC promisc off > > > > > # trap - INT TERM EXIT > > > > > > > > > > # looks like it's not working (for whatever reason) > > > > > return $OCF_NOT_RUNNING > > > > > } > > > > > > > > > > > > > > ####################################################################### > > > > > > > > > > if_usage() { > > > > > cat <<END > > > > > usage: $0 {start|stop|status|monitor|validate-all|meta-data} > > > > > > > > > > Expects to have a fully populated OCF RA-compliant environment > set. > > > > > END > > > > > } > > > > > > > > > > set_cib_value() { > > > > > local score=`expr $1 \* $OCF_RESKEY_multiplier` > > > > > attrd_updater -n $ATTRNAME -v $score -q > > > > > local rc=$? > > > > > case $rc in > > > > > 0) ocf_log debug "attrd_updater: Updated $ATTRNAME = > $score" > > > ;; > > > > > *) ocf_log warn "attrd_updater: Could not update $ATTRNAME > = > > > $score: rc=$rc";; > > > > > esac > > > > > return $rc > > > > > } > > > > > > > > > > if_monitor() { > > > > > ha_pseudo_resource $OCF_RESOURCE_INSTANCE monitor > > > > > local pseudo_status=$? > > > > > if [ $pseudo_status -ne $OCF_SUCCESS ]; then > > > > > exit $pseudo_status > > > > > fi > > > > > > > > > > local mon_rc=$OCF_NOT_RUNNING > > > > > local attr_rc=$OCF_NOT_RUNNING > > > > > local runs=0 > > > > > local start_time > > > > > local end_time > > > > > local sleep_time > > > > > while [ $mon_rc -ne $OCF_SUCCESS -a $REP_COUNT -gt 0 ] > > > > > do > > > > > start_time=`date +%s%N` > > > > > if_check > > > > > mon_rc=$? > > > > > REP_COUNT=$(( $REP_COUNT - 1 )) > > > > > if [ $mon_rc -ne $OCF_SUCCESS -a $REP_COUNT -gt 0 ]; then > > > > > ocf_log warn "Monitoring of $OCF_RESOURCE_INSTANCE failed, > > > > $REP_COUNT retries left." > > > > > end_time=`date +%s%N` > > > > > sleep_time=`echo "scale=9; ( $start_time + ( $REP_INTERVAL_S * > > > 1000000000 ) - $end_time ) / 1000000000" | bc -q 2> /dev/null` > > > > > sleep $sleep_time 2> /dev/null > > > > > runs=$(($runs + 1)) > > > > > fi > > > > > > > > > > if [ $mon_rc -eq $OCF_SUCCESS -a $runs -ne 0 ]; then > > > > > ocf_log info "Monitoring of $OCF_RESOURCE_INSTANCE > recovered > > > from error" > > > > > fi > > > > > done > > > > > > > > > > ocf_log debug "Monitoring return code: $mon_rc" > > > > > if [ $mon_rc -eq $OCF_SUCCESS ]; then > > > > > set_cib_value 1 > > > > > attr_rc=$? > > > > > else > > > > > ocf_log err "Monitoring of $OCF_RESOURCE_INSTANCE failed." > > > > > set_cib_value 0 > > > > > attr_rc=$? > > > > > fi > > > > > > > > > > ## The resource should not fail, if the interface is down. It > > > should fail, if the update of the CIB variable has errors. > > > > > ## To react on the interface failure you must use constraints > > > based on the CIB variable value, not on the recourse itself. > > > > > > > > recourse -> resource > > > done. > > > > > > > > > > > > exit $attr_rc > > > > > } > > > > > > > > > > if_validate() { > > Added: > > if ! ocf_is_probe ; then > > > > > check_binary $IP2UTIL > > > > check_binary arping > fi > > to be ocf-tester compliant in case of OCF_TESTER_FAIL_HAVE_BINARY. > > New version of the agent attached. > > Cheers, > Alex > > > > > > > > > > > > > > if_init > > > > > return $? > > > > > > > > this line is superfluous > > > done. > > > > > > > > > > > > } > > > > > > > > > > case $__OCF_ACTION in > > > > > meta-data) meta_data > > > > > ;; > > > > > usage|help) if_usage > > > > > exit $OCF_SUCCESS > > > > > ;; > > > > > esac > > > > > > > > > > if_validate > > > > > > > > > > case $__OCF_ACTION in > > > > > start) ha_pseudo_resource $OCF_RESOURCE_INSTANCE start > > > > > exit $? > > > > > ;; > > > > > stop) attrd_updater -D -n $ATTRNAME > > > > > ha_pseudo_resource $OCF_RESOURCE_INSTANCE stop > > > > > exit $? > > > > > ;; > > > > > monitor|status) if_monitor > > > > > exit $? > > > > > ;; > > > > > validate-all) exit $? > > > > > ;; > > > > > *) if_usage > > > > > exit $OCF_ERR_UNIMPLEMENTED > > > > > ;; > > > > > esac > > > > _______________________________________________________ > > > > Linux-HA-Dev: Linux-HA-Dev@lists.linux-ha.org > > > > http://lists.linux-ha.org/mailman/listinfo/linux-ha-dev > > > > Home Page: http://linux-ha.org/ > > > > > > > > > > > > > > > > _______________________________________________________ > > > Linux-HA-Dev: Linux-HA-Dev@lists.linux-ha.org > > > http://lists.linux-ha.org/mailman/listinfo/linux-ha-dev > > > Home Page: http://linux-ha.org/ > > > > _______________________________________________________ > > Linux-HA-Dev: Linux-HA-Dev@lists.linux-ha.org > > http://lists.linux-ha.org/mailman/listinfo/linux-ha-dev > > Home Page: http://linux-ha.org/ > > _______________________________________________________ > Linux-HA-Dev: Linux-HA-Dev@lists.linux-ha.org > http://lists.linux-ha.org/mailman/listinfo/linux-ha-dev > Home Page: http://linux-ha.org/ _______________________________________________________ Linux-HA-Dev: Linux-HA-Dev@lists.linux-ha.org http://lists.linux-ha.org/mailman/listinfo/linux-ha-dev Home Page: http://linux-ha.org/
