f209310719
(This PR addresses https://issues.apache.org/jira/browse/SPARK-17231) ## What changes were proposed in this pull request? While debugging the performance of a large GraphX connected components computation, we found several places in the `network-common` and `network-shuffle` code bases where trace or debug log messages are constructed even if the respective log level is disabled. According to YourKit, these constructions were creating substantial churn in the eden region. Refactoring the respective code to avoid these unnecessary constructions except where necessary led to a modest but measurable reduction in our job's task time, GC time and the ratio thereof. ## How was this patch tested? We computed the connected components of a graph with about 2.6 billion vertices and 1.7 billion edges four times. We used four different EC2 clusters each with 8 r3.8xl worker nodes. Two test runs used Spark master. Two used Spark master + this PR. The results from the first test run, master and master+PR:   The results from the second test run, master and master+PR:   Though modest, I believe these results are significant. Author: Michael Allman <michael@videoamp.com> Closes #14798 from mallman/spark-17231-logging_perf_improvements. |
||
|---|---|---|
| .. | ||
| network-common | ||
| network-shuffle | ||
| network-yarn | ||
| sketch | ||
| tags | ||
| unsafe | ||
