Monitoring Pure Storage FlashArray

eG Enterprise provides a specialized monitoring model (see Figure 1) to monitor the target Pure Storage FlashArray inside-out and sheds light on current or probable performance dips that the FlashAppray suffers.

Figure 1 : The layer model of the Pure Storage FlashArray

Every layer of the layer model is mapped to a variety of tests that monitor critical performance parameters such as processing ability, load, and operational state, of the core components of the FlashArray’s architecture. To pull out such useful performance data from the storage system, the eG agent needs to be deployed on a remote Windows host in the environment and connect to the REST API of the Pure Storage FlashArray to collect critical statistics pertaining to its performance. The metrics reported by these tests enable administrators to answer the following questions:

• What is the current status of each drive on the target FlashArray?
• What is the current state of each array controller?
• What is the rate at which read and write operations were performed on the target FlashAray?
• What is the I/O latency of the FlashArray?
• What is the rate at which read and write I/O operations were performed on the target FlashArray?
• What is the rate at which read and write operations were performed on each volume of the target FlashArray?
• What is the space utilization of each array? Are any arrays running out of space?
• What is the connection state of each replicated array?
• What is the I/O latency of each volume?
• What is the rate at which read and write I/O operations were performed on each volume of the target FlashArray?
• What is the total capacity of each volume?
• What is the space utilization of each volume? Is space contention noticed in any of the volumes?
• How much of space is allocated to the volume, volume snapshot etc from the total capacity of each volume?
• How well the read and write operations were performed on the each host connected to the target FlashArray?
• What is the rate at which read and write I/O operations were performed on each host?
• What is the I/O latency of each host?
• What is the space utilization of each host?
• What is the rate at which read and write I/O operations were performed on each host group?
• What is the I/O latency of each host group?
• What is the space utilization of each host group?

The sections that will follow discusses each of the layers of Figure 1 in great detail.