[ https://issues.apache.org/jira/browse/MAPREDUCE-6468?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14736364#comment-14736364 ]
Tsuyoshi Ozawa commented on MAPREDUCE-6468: ------------------------------------------- [~jagadesh.kiran] Could you double check that the patch you uploaded is correct? It seems old one. {code} +++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/ha/BootstrapStandby.java @@ -374,9 +374,7 @@ private boolean checkLogsAvailableForRead(FSImage image, long imageTxId, "or call saveNamespace on the active node.\n" + "Error: " + e.getLocalizedMessage(); if (LOG.isDebugEnabled()) { - LOG.fatal(msg, e); - } else { - LOG.fatal(msg); + LOG.debug("", e); } return false; } {code} Also, in BackupImage, the log level looks wrong. Please fix it. {code} if (LOG.isDebugEnabled()) { - LOG.debug("State transition " + bnState + " -> " + newState); + LOG.trace("State transition " + bnState + " -> " + newState); } {code} > Consistent log severity level guards and statements in MapReduce project > ------------------------------------------------------------------------ > > Key: MAPREDUCE-6468 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-6468 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Reporter: Jackie Chang > Assignee: Jagadesh Kiran N > Priority: Minor > Labels: BB2015-05-TBR > Attachments: HADOOP-9995-00.patch, HADOOP-9995.patch, > MAPREDUCE-6468-01.patch, MAPREDUCE-6468-02.patch, MAPREDUCE-6468-03.patch > > > Developers use logs to do in-house debugging. These log statements are later > demoted to less severe levels and usually are guarded by their matching > severity levels. However, we do see inconsistencies in trunk. A log statement > like > {code} > if (LOG.isDebugEnabled()) { > LOG.info("Assigned container (" + allocated + ") " > {code} > doesn't make much sense because the log message is actually only printed out > in DEBUG-level. We do see previous issues tried to correct this > inconsistency. I am proposing a comprehensive correction over trunk. > Doug Cutting pointed it out in HADOOP-312: > https://issues.apache.org/jira/browse/HADOOP-312?focusedCommentId=12429498&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-12429498 > HDFS-1611 also corrected this inconsistency. > This could have been avoided by switching from log4j to slf4j's {} format > like CASSANDRA-625 (2010/3) and ZOOKEEPER-850 (2012/1), which gives cleaner > code and slightly higher performance. -- This message was sent by Atlassian JIRA (v6.3.4#6332)