Hello, I am trying to get the performance counters (cache reference, cache misses) using the counting mode for hadoop which is running on a physical machine. The various processes of hadoop is contained inside a cgroup. I am trying to get information using the following script
perf stat -B -a -e cache-references,cache-misses -G cgroup_hadoop sleep 1 But, I am getting cache misses to be 197.478 (percent) of all cache refs My question is how can I have cache-misses which is greater than the cache-reference? I have multiple occurrences where the cache-misses is more that the cache reference. Is there something wrong with the way I am measuring the performance counters. Regards, Vivek Nair -- To unsubscribe from this list: send the line "unsubscribe linux-perf-users" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
