gszadovszky commented on a change in pull request #742:
URL: https://github.com/apache/parquet-mr/pull/742#discussion_r605519876
##########
File path:
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/InternalParquetRecordReader.java
##########
@@ -111,18 +111,18 @@ private void checkRead() throws IOException {
if (current == totalCountLoadedSoFar) {
if (current != 0) {
totalTimeSpentProcessingRecords += (System.currentTimeMillis() -
startedAssemblingCurrentBlockAt);
- if (LOG.isInfoEnabled()) {
- LOG.info("Assembled and processed " + totalCountLoadedSoFar + "
records from " + columnCount + " columns in " + totalTimeSpentProcessingRecords
+ " ms: "+((float)totalCountLoadedSoFar / totalTimeSpentProcessingRecords) + "
rec/ms, " + ((float)totalCountLoadedSoFar * columnCount /
totalTimeSpentProcessingRecords) + " cell/ms");
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("Assembled and processed " + totalCountLoadedSoFar + "
records from " + columnCount + " columns in " + totalTimeSpentProcessingRecords
+ " ms: "+((float)totalCountLoadedSoFar / totalTimeSpentProcessingRecords) + "
rec/ms, " + ((float)totalCountLoadedSoFar * columnCount /
totalTimeSpentProcessingRecords) + " cell/ms");
Review comment:
I agree with @Fokko. Could you update this?
##########
File path:
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/InternalParquetRecordReader.java
##########
@@ -111,18 +111,18 @@ private void checkRead() throws IOException {
if (current == totalCountLoadedSoFar) {
if (current != 0) {
totalTimeSpentProcessingRecords += (System.currentTimeMillis() -
startedAssemblingCurrentBlockAt);
- if (LOG.isInfoEnabled()) {
- LOG.info("Assembled and processed " + totalCountLoadedSoFar + "
records from " + columnCount + " columns in " + totalTimeSpentProcessingRecords
+ " ms: "+((float)totalCountLoadedSoFar / totalTimeSpentProcessingRecords) + "
rec/ms, " + ((float)totalCountLoadedSoFar * columnCount /
totalTimeSpentProcessingRecords) + " cell/ms");
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("Assembled and processed " + totalCountLoadedSoFar + "
records from " + columnCount + " columns in " + totalTimeSpentProcessingRecords
+ " ms: "+((float)totalCountLoadedSoFar / totalTimeSpentProcessingRecords) + "
rec/ms, " + ((float)totalCountLoadedSoFar * columnCount /
totalTimeSpentProcessingRecords) + " cell/ms");
final long totalTime = totalTimeSpentProcessingRecords +
totalTimeSpentReadingBytes;
if (totalTime != 0) {
final long percentReading = 100 * totalTimeSpentReadingBytes /
totalTime;
final long percentProcessing = 100 *
totalTimeSpentProcessingRecords / totalTime;
- LOG.info("time spent so far " + percentReading + "% reading
("+totalTimeSpentReadingBytes+" ms) and " + percentProcessing + "% processing
("+totalTimeSpentProcessingRecords+" ms)");
+ LOG.debug("time spent so far " + percentReading + "% reading
("+totalTimeSpentReadingBytes+" ms) and " + percentProcessing + "% processing
("+totalTimeSpentProcessingRecords+" ms)");
Review comment:
I agree with @Fokko. Could you update this?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]