CONTAP-494779: ONTAP cluster node reboots unexpectedly
Issue
One node goes down with error below:[node-01: nodewatchdog: nodewatchdog.monitor.history:debug]: large_mbuf_flowcontrol stranded capacity S0 0,1,1? -30,1,1? -61,1,1? -91,1,1? -120,1,1? -150,1,1? -180,1,1? -210,1,1? -240,1,1? -270,1,1? -300,1,1? -330,1,1? -360,1,1? -390,1,1? -420,1,1? -451,1,1? -480,1,1? -510,1,1? -540,1,1? -570,1,1? -600,1,1? -630,1,1? -660,1,1? -690,1,1? -720,0,1 -751,0,1 -780,0,1 -811,0,1 -840,0,1 -871,0,1
[node-01: nodewatchdog: nodewatchdog.node.panic:alert]: Data ONTAP has experienced a serious internal error: Resource large_mbuf_flowcontrol had 100% stranded capacity for 720 seconds. This might cause the node experiencing the problem to become unresponsive to data access. The node has been panicked to prevent this condition from continuing.
[node-01: nodewatchdog: sk.panic:alert]: Panic String: Resource large_mbuf_flowcontrol had 100% stranded capacity for 720 seconds in process nodewatchdog on release 9.14.1P7 (C)