The Input/Output Token Allocations (IOTA) columns provide the percentage of disk throughput that is used.
Column Name | Mode | Description | Data Type |
---|---|---|---|
FullPotentialIota | count | Sum of the full potential input or output token allocations from all devices attached to the node. This field is reported only to the AMP vproc rows. The input or output token allocations are not limited by the I/O_COD setting. The data source for this field is located in the all_wd_full_potential_iota field in the /proc/tdmeter/limit_stats file. This field is available on SLES 11 only.
|
FLOAT |
CodPotentialIota | count | Sum of the potential input or output token allocations from all devices attached to the node for this workload. This field is reported only to the AMP vproc rows. The input or output token allocations are accumulated only when an I/O is pending on a device and are limited by the I/O_COD setting. The data source for this field is located in the wd_potential_iota field in the /proc/tdmeter/limit_stats file. This field is available on SLES 11 only.
|
FLOAT |
UsedIota | count | Sum of the used input or output token allocations from all devices attached to the node for this workload. This field is reported only to AMP vproc rows. The data source for this field is located in the wd_used_iota field in the /proc/tdmeter/limit_stats file. This field is available on SLES 11 only.
|
FLOAT |
IoThrottleCount | count | Number of times that an I/O was in a releasable position to disk, but TDSCHED did not release the I/O because of I/O COD or Hard Limits; the cost of the I/O exceeded the number of IOTAs in possession. This field is reported only to AMP Vproc rows. An I/O may not be in a releasable position because there are higher priority I/Os. The data source for this field is: ((tdsched_io_info *)TvsaIoBuf_p->io_info)->req_pct) This field is available on SLES 11 only.
|
FLOAT |