// if we don't have enough files to compact, just wait
if (end - start < this.compactionThreshold) {
if (LOG.isDebugEnabled()) {
LOG.debug("Skipped compaction of " + this.storeNameStr
+ " because only " + (end - start) + " file(s) of size "
+ StringUtils.humanReadableInt(totalSize)
+ " meet compaction criteria.");
}
return checkSplit(forceSplit);
}
if (0 == start && end == countOfFiles) {
// we decided all the files were candidates! major compact
majorcompaction = true;
} else {
// 从待compaction的store file list中先切除一批满足条件的store file去做min compaction
filesToCompact = new ArrayList<StoreFile>(filesToCompact.subList(start,
end));
}
// 进入if的条件是major compaction为false，出来的时候major compaction可能是false，也可能是true
} else {
// all files included in this compaction
for (long i : fileSizes) {
totalSize += i;
}
}
this.lastCompactSize = totalSize;
// Max-sequenceID is the last key in the files we're compacting
long maxId = StoreFile.getMaxSequenceIdInList(filesToCompact);
// Ready to go. Have list of files to compact.
LOG.info("Started compaction of " + filesToCompact.size() + " file(s) in cf=" +
this.storeNameStr +
(references? ", hasReferences=true,": " ") + " into " +
region.getTmpDir() + ", seqid=" + maxId +
", totalSize=" + StringUtils.humanReadableInt(totalSize));
// 选择好了store file， compact就是真正去做merge的函数了
StoreFile.Writer writer = compact(filesToCompact, majorcompaction, maxId);
// Move the compaction into place.
StoreFile sf = completeCompaction(filesToCompact, writer);
if (LOG.isInfoEnabled()) {
LOG.info("Completed" + (majorcompaction? " major ": " ") +
"compaction of " + filesToCompact.size() +
" file(s), new file=" + (sf == null? "none": sf.toString()) +
", size=" + (sf == null? "none": StringUtils.humanReadableInt(sf.getReader().length())) +
"; total size for store is " + StringUtils.humanReadableInt(storeSize));
}
}
return checkSplit(forceSplit);
}
2011.12.13添加
几个关于compaction的hbase jira:
HBASE-3189 Stagger Major Compactions
HBASE-3209 : New Compaction Algorithm
HBASE-1476 Multithreaded Compactions
HBASE-3857 Change the HFile Format