Em Fri, May 22, 2020 at 02:55:46PM +0530, kajoljain escreveu:
On 5/20/20 11:50 PM, Ian Rogers wrote:
quoted
Metric groups contain metrics. Metrics create groups of events to
ideally be scheduled together. Often metrics refer to the same events,
for example, a cache hit and cache miss rate. Using separate event
groups means these metrics are multiplexed at different times and the
counts don't sum to 100%. More multiplexing also decreases the
accuracy of the measurement.
<SNIP>
quoted
Ian Rogers (7):
perf metricgroup: Always place duration_time last
perf metricgroup: Use early return in add_metric
perf metricgroup: Delay events string creation
perf metricgroup: Order event groups by size
perf metricgroup: Remove duped metric group events
perf metricgroup: Add options to not group or merge
perf metricgroup: Remove unnecessary ',' from events
Reviewd-By: Kajol Jain [off-list ref]
Tested-By: Kajol Jain <redacted> ( Tested it to see behavior with some metric groups in both x86 and Power machine)
Thanks, added to the patches,
- Arnaldo