|
Any help would great ... I still cannot figure out why LVS just
arbitrarily drains the web traffic to zero and then a restart
fixes the problem.
LDB
LDB wrote:
> I hope the community can help me ...
>
> My problem is that if the resources are on either server, over a period
> of 6 to 9 hours the web traffic begins to drain to zero while I am monitoring
> it using the command:
>
> ipvsadm -L --rate
>
> I do not get an errors in /var/log/ha-debug or /var/log/ha-log. Something is
> wrong with the configuration, but I cannot determine what is wrong with it.
>
> Also, failover works sometimes and the for some reason LVS has an affinity
> with
> LVS2 and not LVS1.
>
>
> Any help would be much appreciated ...
>
>
>
>
>
>
>
> uname -a = Linux lvs1.example.org 2.4.21-27.0.2.EL.um.1smp #1 SMP Wed Jan 19
> 17:21:01 JST 2005 i686 i686 i386 GNU/Linux
>
> uname -a = Linux lvs2.example.org 2.4.21-27.0.2.EL.um.1smp #1 SMP Wed Jan 19
> 17:21:01 JST 2005 i686 i686 i386 GNU/Linux
>
>
>
>
>
>
>
> ls -al /etc/ha.d/resource.d:
>
> drwxr-xr-x 2 root root 2048 Feb 22 17:27 .
> drwxr-xr-x 8 root root 2048 Mar 4 08:22 ..
> -rwxr-xr-x 1 root root 8301 Jan 26 2004 apache
> -rwxr-xr-x 1 root root 2094 Jan 26 2004 AudibleAlarm
> -rwxr-xr-x 1 root root 5661 Jan 26 2004 db2
> -rwxr-xr-x 1 root root 1379 Jan 26 2004 Delay
> -rwxr-xr-x 1 root root 7347 Jan 26 2004 Filesystem
> -rwxr-xr-x 1 root root 4131 Jan 26 2004 ICP
> -rwxr-xr-x 1 root root 22077 Jan 26 2004 IPaddr
> -rwxr-xr-x 1 root root 5258 Jan 26 2004 IPsrcaddr
> lrwxrwxrwx 1 root root 20 Aug 22 2006 ldirectord ->
> /usr/sbin/ldirectord
> -rwxr-xr-x 1 root root 5401 Jan 26 2004 LinuxSCSI
> -rwxr-xr-x 1 root root 3512 Jan 26 2004 LVM
> -rwxr-xr-x 1 root root 1841 Jan 26 2004 MailTo
> -rwxr-xr-x 1 root root 6849 Jan 26 2004 Raid1
> -rwxr-xr-x 1 root root 9002 Jan 26 2004 ServeRAID
> -rwxr-xr-x 1 root root 9620 Jan 26 2004 WAS
> -rwxr-xr-x 1 root root 1901 Jan 26 2004 WinPopup
>
>
>
>
>
>
>
>
> lvs1:/etc/ha.d/ha.cf:
> lvs2:/etc/ha.d/ha.cf:
>
> #
> # There are lots of options in this file. All you have to have is a set
> # of nodes listed {"node ...}
> # and one of {serial, bcast, mcast, or ucast}
> #
> # ATTENTION: As the configuration file is read line by line,
> # THE ORDER OF DIRECTIVE MATTERS!
> #
> # In particular, make sure that the timings and udpport
> # et al are set before the heartbeat media are defined!
> # All will be fine if you keep them ordered as in this
> # example.
> #
> #
> # Note on logging:
> # If any of debugfile, logfile and logfacility are defined then they
> # will be used. If debugfile and/or logfile are not defined and
> # logfacility is defined then the respective logging and debug
> # messages will be loged to syslog. If logfacility is not defined
> # then debugfile and logfile will be used to log messges. If
> # logfacility is not defined and debugfile and/or logfile are not
> # defined then defaults will be used for debugfile and logfile as
> # required and messages will be sent there.
> #
> # File to write debug messages to
> debugfile /var/log/ha-debug
> #
> #
> # File to write other messages to
> #
> logfile /var/log/ha-log
> #
> #
> # Facility to use for syslog()/logger
> #
> logfacility local0
> #
> #
> # A note on specifying "how long" times below...
> #
> # The default time unit is seconds
> # 10 means ten seconds
> #
> # You can also specify them in milliseconds
> # 1500ms means 1.5 seconds
> #
> #
> # keepalive: how long between heartbeats?
> #
> keepalive 1
> #
> # deadtime: how long-to-declare-host-dead?
> #
> deadtime 15
> #
> # warntime: how long before issuing "late heartbeat" warning?
> # See the FAQ for how to use warntime to tune deadtime.
> #
> warntime 10
> #
> #
> # Very first dead time (initdead)
> #
> # On some machines/OSes, etc. the network takes a while to come up
> # and start working right after you've been rebooted. As a result
> # we have a separate dead time for when things first come up.
> # It should be at least twice the normal dead time.
> #
> initdead 30
> #
> #
> # nice_failback: determines whether a resource will
> # automatically fail back to its "primary" node, or remain
> # on whatever node is serving it until that node fails.
> #
> # The default is "off", which means that it WILL fail
> # back to the node which is declared as primary in haresources
> #
> # "on" means that resources only move to new nodes when
> # the nodes they are served on die. This is deemed as a
> # "nice" behavior (unless you want to do active-active).
> #
> nice_failback off
> #
> # hopfudge maximum hop count minus number of nodes in config
> #hopfudge 1
> #
> #
> # Baud rate for serial ports...
> # (must precede "serial" directives)
> #
> #baud 19200
> #
> # serial serialportname ...
> #serial /dev/ttyS0 # Linux
> #serial /dev/cuaa0 # FreeBSD
> #serial /dev/cua/a # Solaris
> #
> # What UDP port to use for communication?
> # [used by bcast and ucast]
> #
> udpport 694
> #
> # What interfaces to broadcast heartbeats over?
> #
> #bcast eth0 # Linux
> #bcast eth1 eth2 # Linux
> #bcast le0 # Solaris
> #bcast le1 le2 # Solaris
> #
> # Set up a multicast heartbeat medium
> # mcast [dev] [mcast group] [port] [ttl] [loop]
> #
> # [dev] device to send/rcv heartbeats on
> # [mcast group] multicast group to join (class D multicast address
> # 224.0.0.0 - 239.255.255.255)
> # [port] udp port to sendto/rcvfrom (no reason to differ
> # from the port used for broadcast heartbeats)
> # [ttl] the ttl value for outbound heartbeats. This affects
> # how far the multicast packet will propagate. (1-255)
> # [loop] toggles loopback for outbound multicast heartbeats.
> # if enabled, an outbound packet will be looped back and
> # received by the interface it was sent on. (0 or 1)
> # This field should always be set to 0.
> #
> #
> #mcast eth0 225.0.0.1 694 1 0
> #
> # Set up a unicast / udp heartbeat medium
> # ucast [dev] [peer-ip-addr]
> #
> # [dev] device to send/rcv heartbeats on
> # [peer-ip-addr] IP address of peer to send packets to
> #
> #ucast eth0 192.168.1.2
>
> # DNC Specific (to LVS2)
> #ucast eth1 192.168.10.16
> #ucast eth2 192.168.20.16 # 100MB Ethernet Port
>
> bcast eth1 eth2
>
> #
> #
> # Watchdog is the watchdog timer. If our own heart doesn't beat for
> # a minute, then our machine will reboot.
> #
> #watchdog /dev/watchdog
> #
> # "Legacy" STONITH support
> # Using this directive assumes that there is one stonith
> # device in the cluster. Parameters to this device are
> # read from a configuration file. The format of this line is:
> #
> # stonith <stonith_type> <configfile>
> #
> # NOTE: it is up to you to maintain this file on each node in the
> # cluster!
> #
> #stonith baytech /etc/ha.d/conf/stonith.baytech
> #
> # STONITH support
> # You can configure multiple stonith devices using this directive.
> # The format of the line is:
> # stonith_host <hostfrom> <stonith_type> <params...>
> # <hostfrom> is the machine the stonith device is attached
> # to or * to mean it is accessible from any host.
> # <stonith_type> is the type of stonith device (a list of
> # supported drives is in /usr/lib/stonith.)
> # <params...> are driver specific parameters. To see the
> # format for a particular device, run:
> # stonith -l -t <stonith_type>
> #
> #
> # Note that if you put your stonith device access information in
> # here, and you make this file publically readable, you're asking
> # for a denial of service attack ;-)
> #
> #
> #stonith_host * baytech 10.0.0.3 mylogin mysecretpassword
> #stonith_host ken3 rps10 /dev/ttyS1 kathy 0
> #stonith_host kathy rps10 /dev/ttyS1 ken3 0
> #
> # Tell what machines are in the cluster
> # node nodename ... -- must match uname -n
> node lvs1.example.org
> node lvs2.example.org
>
>
>
>
>
>
>
>
>
>
>
>
>
> lvs1:/etc/ha.d/ldirectord.cf:
> lvs2:/etc/ha.d/ldirectord.cf:
>
> # Global Directives
> checktimeout=10
> checkinterval=5
> # fallback=192.168.10.15:80
> autoreload=yes
> logfile="/var/log/ldirectord.log"
> #logfile="local0"
>
> # If quiescent=yes, set weight to 0 instead of removing from lvs
> # quiescent + persistent = bad mojo
> quiescent=no
>
> # Virtual Server for Rediretors redir.democrats.org
> virtual=192.168.10.90:80
> fallback=192.168.10.91:80 gate
> real=192.168.10.92:80 gate
> real=192.168.10.93:80 gate
> service=http
> request="ultramonkey.html"
> receive="Redirector is up"
> scheduler=rr
> protocol=tcp
> checktype=negotiate
>
> # Virtual Server for proxy work in progress (rdr2,rdr3)
> virtual=192.168.10.180:80
> #fallback=192.168.10.91:80 gate
> #real=192.168.10.92:80 gate
> real=192.168.10.93:80 gate
> service=http
> request="ultramonkey.html"
> receive="Redirector is up"
> scheduler=rr
> protocol=tcp
> checktype=negotiate
>
> # Virtual Server for search.democrats.org
> virtual=192.168.10.46:80
> #fallback=192.168.10.91:80 gate
> real=192.168.10.92:80 gate
> real=192.168.10.93:80 gate
> service=http
> scheduler=rr
> protocol=tcp
> #checktype=connect
> checktype=negotiate
> request="ultramonkey.html"
> receive="Redirector is up"
>
> # Virtual Service for new website (HTTP) www.democrats.org:80
> virtual=192.168.10.70:80
> #fallback=192.168.10.79:80 gate
> real=192.168.10.71:80 gate
> real=192.168.10.72:80 gate
> real=192.168.10.73:80 gate
> real=192.168.10.75:80 gate
> #real=192.168.10.74:80 gate REBUILDER
> #real=192.168.10.76:80 gate
> #real=192.168.10.77:80 gate
> #real=192.168.10.78:80 gate
> service=http
> request="page/signup"
> receive="communication is not authorized"
> scheduler=rr
> persistent=10800
> protocol=tcp
> checktype=negotiate
>
> # # Virtual Service for new Website (HTTPS) www.democrats.org:443
> virtual=192.168.10.70:443
> #fallback=192.168.10.79:443 gate
> #real=192.168.10.21:443 gate
> real=192.168.10.71:443 gate
> real=192.168.10.72:443 gate
> real=192.168.10.73:443 gate
> #real=192.168.10.23:443 gate
> real=192.168.10.75:443 gate
> #real=192.168.10.24:443 gate
> service=https
> request="page/signup"
> receive="communication is not authorized"
> scheduler=rr
> persistent=10800
> protocol=tcp
> checktype=negotiate
>
> # Virtual Service for DCCC site (HTTP) www.dccc.org
> virtual=192.168.10.80:80
> fallback=192.168.10.143:80 gate
> real=192.168.10.83:80 gate
> real=192.168.10.84:80 gate
> service=http
> #request="index.html"
> #receive="Democratic Congressional Campaign Committee"
> #receive=""
> scheduler=rr
> # persistent=3600
> protocol=tcp
> checktype=connect
> #checktype=negotiate
>
> # Virtual Service for DCCC site (HTTPS) www.dccc.org
> virtual=192.168.10.80:443
> fallback=192.168.10.143:443 gate
> real=192.168.10.83:443 gate
> real=192.168.10.84:443 gate
> service=https
> #request="index.html"
> #receive=""
> scheduler=rr
> # persistent=600
> protocol=tcp
> #checktype=negotiate
> checktype=connect
>
>
>
>
>
>
>
>
>
> lvs1:/etc/ha.d/haresources:
> lvs2:/etc/ha.d/haresources:
>
> lvs1.example.org IPaddr::192.168.10.46/24 ldirectord::/etc/ha.d/ldirectord.cf
> lvs1.example.org IPaddr::192.168.10.70/24 ldirectord::/etc/ha.d/ldirectord.cf
> lvs1.example.org IPaddr::192.168.10.90/24 ldirectord::/etc/ha.d/ldirectord.cf
> lvs1.example.org IPaddr::192.168.10.80/24 ldirectord::/etc/ha.d/ldirectord.cf
> lvs1.example.org IPaddr::192.168.10.180/24 ldirectord::/etc/ha.d/ldirectord.cf
>
>
>
>
>
>
> _______________________________________________
> LinuxVirtualServer.org mailing list - lvs-users@xxxxxxxxxxxxxxxxxxxxxx
> Send requests to lvs-users-request@xxxxxxxxxxxxxxxxxxxxxx
> or go to http://lists.graemef.net/mailman/listinfo/lvs-users
>
>
|
