eG Monitoring
 

Measures reported by XIOVolumesTest

One of the primary capabilities of the XtremIO Storage Array is to provision volumes (LUNs) to the connected servers. Each volume is a defined quantity of disk space which is provisioned to the servers so that you can enable the servers to treat the volume as a SCSI device. Once the volumes are provisioned, you can create instantaneous copy images of volume data called snapshots so as to ensure availability of the original copy of the volume data without interruption. In an EMC XtremIO cluster, you can define various quantities of disk space as volumes. For an administrator to efficiently utilize the volumes, it is essential to provision the volumes prudently and monitor the processing ability of the volumes round the clock. If a sudden decrease in the I/O processing is noticed, administrators need to analyze what exactly has brought down the I/O processing capability of the volumes. To address the needs of the administrators and keep an eye on the volumes, eG Enterprise suite provides you with the XIO Volumes test.

This test auto discovers the volumes of the target storage array and helps administrators to figure out the volume that is busy processing I/O requests, detect irregularities in the distribution of I/O load across the volumes, analyze the space utilization of each volume and thus enables administrators to initiate pre-emptive measures when I/O processing capability decreases gradually.

Outputs of the test : One set of results for each volume of the target EMC XtremIO being monitored

The measures made by this test are as follows:

Measurement Description Measurement Unit Interpretation
bandwidth Indicates the amount of data handled while performing I/O operations per second on this volume. MB/Sec  
readBandwidth Indicates the amount of data utilized for read I/O operations per second on this volume. MB/Sec  
writeBandwidth Indicates the amount of data utilized for write I/O operations per second on this volume. MB/Sec  
iops Indicates the rate at which I/O operations were performed on this volume during the last measurement period. IOPS Compare the value of this measure across the volumes to know which volume handles the maximum number of I/O operations.
readIOPS Indicates the rate at which read operations were performed on this volume. IOPS  
writeIOPS Indicates the rate at which write operations were performed on this volume. IOPS  
readLatency Indicates the time taken to perform read operations on this volume. msec  
writeLatency Indicates the time taken to perform write operations on this volume. msec  
avgLatency Indicates the average time taken to perform I/O operations on this volume. msec  
reads Indicates the number of reads performed on this volume per second during the last measurement period. Reads/sec Compare the values of this measure across the volumes to know which volume handles the maximum number of read requests.
dataWritten Indicates the amount of data written to this volume during the last measurement period. MB/Sec Ideally, the value of this measure should be high. A steady dip in this measure value could indicate a potential writing bottleneck. By comparing the value of this measure across the volumes, you can quickly identify the volume that is the slowest to process write requests.
noOfLUNMappings Indicates the number of LUN mappings defined on this volume. Number  
noOfDestSnaps Indicates the number of snapshots that were snapshotted from this volume. Number By default, volumes are snapshotted at equal intervals and these snapshots are distributed to various clients whereas the original volume is maintained as the source copy.

If the value of this measure is high, then administrators may be required to correlate this value with that of the Bandwidth measure. The higher the value of this measure, the greater is the bandwidth utilized. Therefore, for the bandwidth to be maintained in an optimal range, the value of this measure should be maintained within the permissible limits. If too many snapshots are created within a short period of time, then the optimization of the storage array may fail leading to severe processing bottlenecks.
logicalSpaceInUse Indicates the total amount of space utilized for writing data to this volume before deduplication process. GB  
freeVolumeSize Indicates the amount of space that is available for use in this volume. GB A high value is desired for this measure. A gradual/sudden decrease in the value of this measure indicates that the volume is running out of space.
usedVolumePCT Indicates the percentage of space that is already utilized in this volume. Percent A value close to 100 % indicates that this volume is running out of space.
freeVolumePCT Indicates the percentage of space that is available for use in this volume. Percent A high value is desired for this measure.