Details
-
Bug
-
Resolution: Fixed
-
Minor
-
None
-
None
-
3
-
9223372036854775807
Description
sles15s01 config:
sles15s01:~ # start.sh debug=+net sles15s01:~ # lctl list_nids 192.168.2.30@tcp1 sles15s01:~ # lctl show_route net tcp2 hops 4294967295 gw 192.168.2.20@tcp1 up pri 0 sles15s01:~ #
sles15c01 config:
sles15c01:~ # start.sh debug=+net sles15c01:~ # lctl list_nids 192.168.2.38@tcp2 sles15c01:~ # lctl show_route net tcp1 hops 4294967295 gw 192.168.2.50@tcp2 up pri 0 sles15c01:~ #
sles15build01 config:
sles15build01:~ # start.sh debug=+net sles15build01:~ # lctl list_nids 192.168.2.20@tcp1 192.168.2.50@tcp2 sles15build01:~ #
sles15c01:~ # date; lnetctl peer show; lctl show_route; ssh sles15build01 'lnetctl net del --net tcp1 --if eth0'; sleep 1; lnetctl peer show; lctl show_route
Assert was tripped after the lnetctl net del command was executed on sles15build01.
I think the bug is probably in the initial router discovery. When we create the lpni for the primary nid, 192.168.2.20@tcp1, and attach it to peer it is at the end of the list, but I think primary nid is expected to be the first one.