eG Monitoring
 

Measures reported by XIOInfiSwTest

Multiple X-Brick clusters may consist of:

  • Two, four, six or eight X -Bricks

  • Two InfiniBand Switches

From the hardware perspective of the X-Brick cluster, no component is a single point of failure. Each Storage Controller, DAE and InfiniBand Switch in the system is equipped with dual power supplies. The system also has dual Battery Backup Units and dual network and data ports (in each of the Storage Controllers). The two InfiniBand Switches are cross connected and create a dual data fabric. Failure of any component may trigger a recovery attempt or a failover. For the failover process to be smooth enough, it is necessary that all the components are functioning well. Failure of the Infiniband switch may lead to connection loss to the storage controller and in due course may lead to data loss during failover. Therefore, it is necessary to monitor the Infiniband Switchess round the clock! The XIOInfiSwTest test helps administrators in this regard!

This test reports whether/not each Infiniband Switch is enabled. This test also helps administrators to determine the availability of each Infiniband Switch, the current health of the switches and the state of the ports on the Infiniband Switches. Using this test, administrators can easily identify the infiniband switch that is wrongly connected to the storage controllers.

Outputs of the test : One set of results for the InfiniBand Switches of the target EMC XtremIO being monitored.

The measures made by this test are as follows:

Measurement Description Measurement Unit Interpretation
enableState Indicates whether/not this InfiniBand Switch is enabled.   The values reported by this measure and its numeric equivalents are mentioned in the table below:

Measure value Numeric Value
Yes 0
No 1

Note:

By default, this measure reports the Measure Values listed in the table above to indicate whether/not this InfiniBand Switch is enabled. The graph of this measure however is represented using the numeric equivalents only - 0 or 1.
fruLCState Indicates the current health of this InfiniBand Switch.   The values reported by this measure and its numeric equivalents are mentioned in the table below:

Measure value Numeric Value
Healthy 0
Initializing 1
Uninitialized 2
Failed 3
Disconnected 4

Note:

By default, this measure reports the Measure Values listed in the table above to indicate the current health of this InfiniBand Switch. The graph of this measure however is represented using the numeric equivalents only - 0 to 4.
fanDrawerStatus Indicates the current state of the fan drawer in this InfiniBand Switch.   The values reported by this measure and its numeric equivalents are mentioned in the table below:

Measure Value Numeric Value
Healthy 0
One_fan_failed 1
Failed 1

Note:

By default, this measure reports the Measure Values listed in the table above to indicate the current state of the fan drawer in this InfiniBand Switch. The graph of this measure however is represented using the numeric equivalents only - 0 or 2.
ib1PortState Indicates the current state of the Inter-switch port 1 of this InfiniBand Switch.   The values reported by this measure and its numeric equivalents are mentioned in the table below:

Measure Value Numeric Value
Active 0

Note:

By default, this measure reports the Measure Values listed in the table above to indicate the current state of the Inter-switch port 1 of this InfiniBand Switch. The graph of this measure however is represented using the numeric equivalents only i.e., 0.
ib2PortState Indicates the current state of the Inter-switch port 2 of this InfiniBand Switch.   The values reported by this measure and its numeric equivalents are mentioned in the table below:

Measure Value Numeric Value
Active 0

Note:

By default, this measure reports the Measure Values listed in the table above to indicate the current state of the Inter-switch port 2 of this InfiniBand Switch. The graph of this measure however is represented using the numeric equivalents only i.e., 0.
isAvailable Indicates whether/not this InfiniBand Switch is available.   The values reported by this measure and its numeric equivalents are mentioned in the table below:

Measure Value Numeric Value
Available 0

Note:

By default, this measure reports the Measure Values listed in the table above to indicate whether/not this InfiniBand Switch is available. The graph of this measure however is represented using the numeric equivalents only i.e., 0.
isWrongScConnDetected Indicates whether any storage controller was not connected to the corresponding InfiniBand Switch.   The values reported by this measure and its numeric equivalents are mentioned in the table below:

Measure Value Numeric Value
None 0
Wrong connection detected 1

Note:

By default, this measure reports the Measure Values listed in the table above to indicate whether any storage controller was not connected to the corresponding InfiniBand Switch. The graph of this measure however is represented using the numeric equivalents only - 0 or 1.