By: Lora Johnson
Hardware serves as the foundation for your IT stack, and if your hardware devices aren’t performing at optimal levels, your networks, applications and storage ultimately suffers. For your Dell EMC PowerEdge servers, extending your monitoring to see more metrics can give you the visibility that you need to clearly understand issues, simplifying troubleshooting and eliminating mean-time-to-innocence (MTTI) hunts.
In this blog post, I’ll highlight the top metrics we recommend monitoring in order to optimize your Dell EMC PowerEdge performance.
Monitoring server temperatures gives you important insight into one of the most important baseline metrics for server performance. Taking it one step further and integrating this monitoring into alerts and recommendations gives you actionable information.
Figure 1: Example of an Analysis Badge with insight into capacity issues in the Blue Medora Management Pack for Dell EMC PowerEdge
Within Blue Medora’s Dell EMC PowerEdge Management Pack for vRealize Operations, you can extend your server temperature monitoring to include capacity definitions. As a result, you can set specific thresholds to indicate when you receive alerts and notifications.
For Dell EMC PowerEdge, this is commonly used for server temperatures. Set your threshold for a temperature just below one that causes performance issues — when temperatures rise, you receive a notification so you can quickly troubleshoot before the temperature change triggers other alerts or issues within your servers, or even other layers of the IT stack.
Hardware issues trickle down to other layers of the IT stack and can quickly wreak havoc on performance. Understanding how your devices are interacting with each other can simplify the troubleshooting process — making it easier to pinpoint issues faster, before they impact the rest of the IT stack.
Within your Dell EMC PowerEdge servers, there are a number of relationships that you can monitor and track, including:
When issues do arise, teams often spend a great deal of time tracking down the cause of the issue. MTTI hunts can lead to finger pointing and significant delays in actually figuring out what may be causing the performance issue. Is it network traffic is too high? Are there I/O bottlenecks?
Figure 2: Dell EMC PowerEdge Server Performance Dashboard
Insight into key performance indicators around device performance for your Dell EMC PowerEdge workloads can eliminate MTTI hunts and give you immediate indication if there are issues occurring among these resources.
Some key metrics to monitor include:
Drilling down into the disk and memory usage across your Dell EMC PowerEdge servers serves as one of the best ways to determine what may be causing performance issues. Bottlenecks are often the most common cause for concern, which generate when too much disk and memory space are leveraged for other processes. As a result, your CPU lags — resulting in slow input/output operations and a negative impact on your end-user experience.
Not all alerts are created equal and when it comes to managing your servers, you can get inundated with notifications when issues arise. Within vRealize Operations and Blue Medora’s Management Pack for Dell EMC PowerEdge, you can set thresholds so that you are only notified when the highest priority alerts occur.
Figure 3: Example of an alert in the Dell EMC PowerEdge Management Pack
The alert count gives you insight into key trends that may be occurring with your servers. For instance, if you frequently receive notifications that your device status is unavailable, it may indicate that your device may be faltering. With the ability to track alert counts, you can track the frequency and any increases that may indicate a larger issue with your specific device.
To learn more about the Dell EMC PowerEdge Management Pack from Blue Medora or to download a free trial, please visit the True Visibility Suite for VMware vRealize Operations page on Blue Medora’s website.
This blog post first appeared on the VMware Cloud Management Blog. Read the full post here.