Hey everyone, I'm a sysadmin who's been assigned to deploy an HCI cluster using an HPE DL380 11th gen setup. The installation process has been a real headache, taking months just to get to the point of installing VMs. The cluster is experiencing random packet drops—about 5-10% overall loss over an hour. Packets drop for several consecutive pings, then stabilize, causing issues for some of our applications that aren't resilient to packet loss. We've verified switch configurations with HPE and checked the OS settings, but we're stuck in a back-and-forth between HPE and Microsoft support, with little progress. Has anyone faced similar issues or have any suggestions?
3 Answers
I totally get your frustration! Have you checked the specific switches you're using for the cluster? It’s crucial whether they’re dedicated or shared with other systems. In some setups, shared switches can cause unpredictable behavior. Try to ensure your data and storage networks are physically separate if possible. Let me know what you're working with and we can troubleshoot from there!
I believe there's an Azure local community on Slack where you might get quicker insights. It could be worth joining to ask around. Sometimes, real-world experiences shared in those groups can shed light on tricky issues like yours!
Just curious, what switches are you using? It seems like packet loss could be tied to network configuration. Dedicated switches often reduce interference compared to shared setups. If you have Mellanox SN2010Ms dedicated to your cluster, you should be in good shape. Have you tested them for firmware updates or known issues?
Related Questions
Can't Load PhpMyadmin On After Server Update
Redirect www to non-www in Apache Conf
How To Check If Your SSL Cert Is SHA 1
Windows TrackPad Gestures