You can accumulate error count information for every device on a physical disk channel including:
Analyzing the error count data of the physical disk channel diagnostics is based on the principle that the channel immediately downstream of the problematic device should see the largest number of error counts.
The analysis process obtains an error count for the selected devices on a physical disk channel, views the data, and identifies any large increases in the error counts. The table shows the typical error count information that appears in the Physical Disk Channel Diagnostics Results dialog.
|
Error Count Type |
Definition of the Error |
|
Test status |
A status code that provides general information about the outcome of the test for this device. These values are possible:
|
|
Total iterations attempted |
The total number of iterations tried. |
|
Successful iterations |
The number of iterations that completed successfully. |
|
Channel-level resets |
The number of channel-level resets that occurred. |
|
Data miscompares |
The number of iterations that failed due to data miscompares. |
|
Iteration-preparation failures |
The number of iterations that failed due to iteration-preparation failures (for example, the inability to establish the requisite device bypass state). |
|
I/O timeouts on outbound data commands |
The number of iterations that failed due to I/O timeouts on outbound-data commands. |
|
Channel-level resets on outbound data commands |
The number of iterations that failed due to channel-level resets that occurred during outbound-data commands. |
|
Other failures on outbound data commands |
The number of iterations that failed due to other command failures on outbound-data commands, such as check conditions, aborted commands, or channel-level resets. |
|
I/O timeouts on inbound-data commands |
The number of iterations that failed due to I/O timeouts on inbound-data commands. |
|
Channel-level resets on inbound data commands |
The number of iterations that failed due to channel-level resets that occurred during inbound-data commands. |
|
Other failures on inbound data commands |
The number of iterations that failed due to other command failures on inbound-data commands, such as check conditions, aborted commands, or channel-level resets. |
|
Average time for successful outbound data phases |
The Average elapsed command-processing time for the outbound-data phases of all successful iterations. The time is shown in microseconds. |
|
Statistical variance of average elapsed time |
The statistical variance of the elapsed command-processing time for the outbound-data phases of all successful iterations. |
|
Average time for successful inbound data phases |
The average elapsed command-processing time for the inbound-data phases of all successful iterations. The time is shown in microseconds. |
|
Statistical variance of average elapsed time |
The statistical variance of the elapsed command-processing time for the inbound data phases of all successful iterations. |
|
RLS errors for the device under test (Fibre Channel only) |
The RLS counters for the device under test. |
|
RLS errors for all EMM devices on channel (Fibre Channel only) |
The RLS counters for all of the EMM devices on the channel. |
|
SOC error statistics for loop switch port when relevant |
If the device under test resides in an enclosure that is based on loop switch technology, this data displays the SOC error statistics for the loop switch port to which the disk physical disk is attached. |
|
SOC error statistics for EMM and SFPs when relevant |
For each EMM that resides on the channel under test and that uses loop switch technology, this data shows the SOC error statistics for the EMM device and for its associated small form factor pluggable (SFP) devices. |
|
SAS error stats for each SAS PHY |
If you have a SAS technology configuration, then the data shows the SAS error stats for each SAS PHY. SATA means that SAS error status for each SAS PHY is not available. |
Note: When you analyze RLS data for a storage array that contains both SATA disk physical disks and a RAID controller module in a single enclosure, NA (Not Applicable) appears for each SATA disk physical disk in this enclosure. This error occurs when the SATA disk physical disks are not communicating with the RAID controller module by using the Fibre Channel (FC) protocol. However, if any SATA expansion disk expansion enclosures are in the storage array, the EMMs in those enclosures are identified as Fibre Channel devices, and they report meaningful RLS data back to the RAID controller module. The SATA disk physical disks behind the EMMs report RLS data, but this data comes from the Fibre-to-SATA translation circuitry in the EMM.
If you are unable to determine which component or storage array on your Fibre Channel loop is experiencing problems, save the RLS diagnostics results. Forward the results to a Customer and Technical Support representative for assistance.