i'm using 2 F5 DNS units in a sync group . (version 12.1.2)
we have 2 datacenters (DC1 & DC2) . In each datacenter we deployed an F5 DNS .
hereunder is the config like it was created (I changed DNS names & IP's but nothing else) :
gtm datacenter /Common/DC1 {
description "Datacenter DC1"
}
gtm datacenter /Common/DC2 {
description "Datacenter DC2"
}
gtm prober-pool /Common/GTM-Probers-DC1 {
members {
/Common/unit-dc1 {
order 0
}
/Common/unit-dc2 {
order 1
}
}
}
gtm prober-pool /Common/GTM-Probers-DC2 {
members {
/Common/unit-dc1{
order 1
}
/Common/unit-dc2 {
order 0
}
}
}
gtm server /Common/DC1-Openshift-virtual-ip {
addresses {
10.100.100.100 {
device-name /Common/DC1-Openshift-virtual-ip
}
}
datacenter /Common/DC1
prober-pool /Common/GTM-Probers-DC1
product generic-host
virtual-servers {
testname.domain {
destination 10.100.100.100:443
monitor /Common/Test
}
}
}
gtm monitor external /Common/Test {
defaults-from /Common/external
destination *:*
interval 30
probe-timeout 5
run /Common/https-sni-monitor-v1
timeout 120
user-defined HOST testname.domain
user-defined RECV 200
user-defined URI /checkService
}
so we are creating a generic host without monitor . ANd than define a virtual server on F5 DNS based on that host on port 443 .Monitor "Test" is associated with this vs , and this is an EAV monitior pointing to file "https-sni-monitor-v1" . Which is the file with script mentioned earlier here .
This script was uploaded as a file , via "System" - "File management" - "external monitor" as is normal procedure described by F5.
When monitor is enabled on host , we see host being put "down" after the monitoring interval .
however when doing an tcpdump , we do not see anything going out to IP address of the host where monitor is defined .