6.3.8.3.5 Monitoring IORM Utilization
You can use metrics to monitor IORM utilization.
When OLTP and DSS workloads share Oracle Exadata Storage Servers, IORM determines whether to optimize for low latency or high throughput. To optimize for low latency, the concurrency of large I/O requests is reduced to ensure that I/O bandwidth is not saturated. To optimize for high throughput, each Oracle Exadata Storage Server must handle many concurrent large I/O requests, allowing the storage to be fully utilized while applying optimization algorithms. However, when a cell has many concurrent large I/O requests, average latency may increase because each I/O is queued behind other I/Os.
The utilization metrics for I/O requests from a database, pluggable database (PDB), or consumer group corresponds to the amount of time that the database, PDB, or consumer group utilized the storage server. Large I/O requests utilize the storage server more than small I/O requests. The following are the utilization metrics for determining IORM optimization:
CG_IO_UTIL_LGCG_IO_UTIL_SMPDB_IO_UTIL_LGPDB_IO_UTIL_SMCT_IO_UTIL_LGCT_IO_UTIL_SMDB_IO_UTIL_LGDB_IO_UTIL_SM
By comparing the I/O resource consumption with the I/O resource allocations, the
database administrator can determine if IORM should be
tuned for latency or throughput, or if a balanced approach is optimal. The IORM metric, IORM_MODE, shows the mode for
IORM. The metric value ranges between 1 and 3. The
following are the definitions for the values:
Note:
If the current plan has the IORM attributeobjective set to BASIC, then IORM_MODE has no meaning and should be ignored.
- 1 means the cell IORM objective is set to
low_latency. - 2 means the cell IORM objective is set to
balanced. - 3 means the cell IORM objective is set to
high_throughput.
A value in between 1 and 2, or between 2 and 3, indicates that the IORM objective changed in the metric period, and the precise value indicates proximity to a given objective. It is also indicative of a constantly-changing mix of workloads.