Measures reported by VnxMetaVolTest
Metavolumes can be created from a disk volume, stripe volume, slice volume, or another metavolume. A file system is created on the metavolume. All information stored within a metavolume is arranged in addressable logical blocks and is organized in a sequential, end-to-end fashion. A metavolume is required to create a file system because metavolumes provide the expandable storage capacity needed to dynamically expand file systems. A metavolume also provides a way to form a logical volume larger than a single disk.
Where metavolumes are in use, a slowdown or space-crunch experienced by a single metavolume, can ripple and affect the overall performance of the VNX storage system. This is why, it is imperative that metavolumes are continuously monitored for performance faults, and faults detected in the process are corrected in time to ensure uninterrupted functioning of the storage system as a whole. For this purpose, administrators can use the VnxMetaVolTest test.
This test auto-discovers the metavolumes configured on the EMC VNX Storage system, monitors the processing ability of each metavolume, and reports the following:
- Is I/O load uniformly balanced across all metavolumes, or is any metavolume overloaded?
- Are the metavolumes able to process the I/O requests quickly? Is any metavolume experiencing processing bottlenecks?
The measures made by this test are as follows:
| Measurement |
Description |
Measurement Unit |
Interpretation |
| Read_operations |
Indicates the rate at which the read operations were performed on this metavolume. |
Ops/sec |
A high value is desired for this measure. A consistent decrease in this value could indicate a processing bottleneck. |
| Write_operations |
Indicates the rate at which the write operations were performed on this metavolume. |
Ops/sec |
| Read_req |
Indicates the rate at which the read requests were processed on this metavolume. |
Requests/Sec |
A consistent decrease in the value of these measures for a metavolume indicates an I/O processing bottleneck. |
| Write_req |
Indicates the rate at which the write requests were processed by this metavolume. |
Requests/sec |
| Read_data |
Indicates the rate at which data is read from this metavolume. |
KiB/sec |
A consistent decrease in the value of these measures for a metavolume indicates an I/O processing bottleneck. |
| Write_data |
Indicates the rate at which data is written to this metavolume. |
KiB/sec |
| Avg_read_data |
Indicates the amount of data read from this metavolume per request. |
KB/Request |
A consistent decrease in the value of these measures for a metavolume indicates an I/O processing bottleneck. |
| Avg_write_data |
Indicates the amount of data written to this disk volume per request. |
KB/Request |
| Reads_percentage |
Indicates the percentage of total I/O operations on this metavolume that were read operations |
Percent |
In the event of an overload, you can compare the value of these measures for a metavolume to figure out what caused the overload - i.e., what type of operations were too many on the metavolume - read operations or write operations? |
| Write_percentage |
Indicates the percentage of total I/O operations on this metavolume that were write operations. |
Percent |
|