eG Help

The XtremIO Storage Array is an all-flash system, based on a scale-out architecture. The system uses building blocks, called X-Bricks, which can be clustered together to grow performance and capacity as required. An X-Brick is the basic building block of an XtremIO array. An X-Brick comprises of 25 SSDs. A data protection group is a set of SSDs that form a redundancy group. Each data protection group has a name, health state, and defined usable SSD space. Each X-Brick contains one data protection group, which is created during the initial configuration. The data protection group cannot be removed. Whenever multiple SSDs fail, administrators are required to assign a new SSD in the data protection group so that the space within the data protection group is maintained and the data loss is kept to a minimum. To achieve superior data protection, enhanced performance of the XtremIO storage array along with a minimal data loss due to SSD failure, it is necessary to continuously monitor the bandwidth utilization and IOPS of the data protection group. The XIOXDPGTest test helps administrators in this regard!

This test auto-discovers the Data Protection Group of an X-Brick and reports the bandwidth utilization for read/write operations, the rate at which read/write operations are performed and the percentage of free space within the SSDs of the Data Protection Group.

Outputs of the test : One set of results for each Data Protection Group on the EMC XtremIO Storage array that is to be monitored

Measurement	Description	Measurement Unit	Interpretation
bandwidth	Indicates the amount of data handled while performing I/O operations per second on this data protection group.	MB/Sec	Compare the value of this measure across the data protection groups to identify the group that is consuming the maximum bandwidth.
readBandwidth	Indicates the rate at which data is read from this data protection group.	MB/Sec	Comparing the value of these measures across the data protection groups will clearly indicate which data protection group is the slowest in I/O processing, and when exactly the slowdown occurred - when reading data? or when writing data?
writeBandwidth	Indicates the rate at which data is written to this data protection group.	MB/Sec
IOPS	Indicates the rate at which I/O operations were performed on this data protection group.	IOPS	A high value is desired for this measure. Compare the value of this measure across the data protection groups to identify the group that is handling the maximum number of I/O operations.
readIOPS	Indicates the rate at which read operations were performed on this data protection group.	IOPS	Ideally, the value of this measure should be high. A steady dip in this measure value could indicate a potential reading bottleneck.
writeIOPS	Indicates the rate at which write operations were performed on this data protection group.	IOPS	Ideally, the value of this measure should be high. A steady dip in this measure value could indicate a potential writing bottleneck.
udSSDFreeSpacePCT	Indicates the percentage of free space available for use in the SSDs of this data protection group.	Percent	A high value is desired for this measure. When an SSD in a data protection group fails, the cluster rebuilds it to restore redundancy. A rebuild reconstructs the data from the failed SSD onto the remaining SSDs in the data protection group, thus restoring redundancy and protection level. A rebuild requires sufficient available space in the remaining SSDs to handle the data protection group's demands. If sufficient free space is not available, a rebuild cannot be performed and the data protection group's performance and resiliency may be degraded.