We have recently implemented an HNAS in our environment. We have a two-node cluster, with another 2-nodes at a secondary site which receives data through object replication. We have about 30TB of data mostly office files, pdfs and PST files. We have a annoying issue which we are trying to diagnose and need help.
At random points during the day the running bossock fibers reach 384 and all cifs connections to shares are dropped. There is no commonality in time of day, during replication or anything that we can see. We've looked through the logs and can't find anything indicating anything out of the ordinary.
If anyone with experience with these issues could point me in the right direction on what to look into. We are at a loss here.