NFS Performance Test

NFS (Network File System) is a protocol used by Unix system to access data on the storage system. When a VNX for File is configured as an NFS server, file systems are mounted on a Data Mover and a path to that file system is exported. Exported file systems are then available across the network and can be mounted by remote users.

An NFS-configured Data mover does the following:

• Provides access to the exported file system through an IP network.
• Authenticates the user if using a secure NFS.

• Performs authorization by:

  • Comparing the access rights of the NFS client by requesting information with the access rights defined for the exported file system.
  • Performing user access control on the file system object.

By continuously monitoring the NFS operations on every data mover, you can easily identify that data mover on which NFS is most ineffective/problematic. This is where, the NFS Performance test helps. This test monitors the NFS reads and writes performed on each data mover in the VNX system and reports the following:

• The number of NFS operations on the data mover;
• The number of active NFS threads;
• How well the I/O operations were performed using the NFS protocol, and whether any delays were noticed;
• The total amount of data transacted when performing NFS reads and writes

These statistics will not only enable administrators to promptly detect current or probable latencies in I/O operations when using NFS, but will also help them figure out which I/O activity was most latent – i.e., whether reading or writing – and on which data mover.

Target of the test : An EMC VNX Unified Storage system

Agent deploying the test : A remote agent

Outputs of the test : One set of results for each data mover in the DME of the EMC VNX Unified Storage system.

Configurable parameters for the test

Parameter	Description
Test Period	How often should the test be executed.
Host	The IP address of the storage device for which this test is to be configured.
Controller Station IP	The Control Station is the management station for the VNX for File system, and enables control and configuration of the system. The eG agent uses the CLI that runs on the Control Station to monitor and manage the performance of the VNX for File system. To enable the eG agent to use this CLI, specify the IP address of the Control Station in the Controller Station IP text box. By default, the IP address of the host will be displayed here.

Measurements made by the test

Measurement	Description	Measurement Unit	Interpretation
Total operations	Indicates the rate at which NFS operations were performed on this data mover.	Ops/Sec	A high value is desired for this measure. A consistent decrease in this value could indicate a processing bottleneck.
Read operations	Indicates the rate at which read operations were performed on this data mover using the NFS protocol.	Ops/Sec	If the value of the Total operations measure dips consistently, then, you may want to time-correlate that measure with the value of these two measures to know what is causing the steady decline in NFS performance – read operations or write operations? This way, you can figure out when the slowdown actually occurred – when reading or when writing?
Write operations	Indicates the rate at which write operations were performed by users through NFS protocol on this Data Mover.	Number
Data read	Indicates the rate at which the data is read using NFS protocol from this data mover.	KB/Sec	Ideally, the value of these measures should be high. A consistent decrease in their value is an indication of a processing bottleneck. When users complaint of delays when accessing the file system using NFS, you can compare the value of each of these measures across data movers to know which data mover is experiencing the slowdown. You can then compare the value of these measures for that data mover to know when the slowdown occurred – when reading from or when writing to the file system?
Data written	Indicates the rate at which the data is written to this data mover using NFS protocol.	KB/Sec
Average read data	Indicates the average amount of data read from this data mover per NFS read operation.	KiB/Operation	Compare the value of this measure across data movers to know which data mover is taking the longest to complete an NFS read operation. You can then begin to focus on that data mover and closely track how this measure is behaving for that data mover. A consistent decrease in the value of this measure could indicate problems when reading from the file systems in that data mover.
Average write data	Indicates the average amount of data written to this data mover per NFS write operation.	KiB/Operation	Compare the value of this measure across data movers to know which data mover is taking the longest to complete an NFS write operation. You can then begin to focus on that data mover and closely track how this measure is behaving for that data mover. A consistent decrease in the value of this measure could indicate problems when writing into the file systems in that data mover.
Active threads	Indicates the number of NFS threads that are currently active on this data mover.	Number	This measure is a good indicator of the level of NFS activity on a data mover.