busbey commented on a change in pull request #623: HBASE-22749: Distributed MOB
compactions
URL: https://github.com/apache/hbase/pull/623#discussion_r336715592
##########
File path: hbase-server/src/main/java/org/apache/hadoop/hbase/mob/MobUtils.java
##########
@@ -907,6 +789,143 @@ public static boolean hasMobColumns(TableDescriptor htd)
{
return false;
}
+ /**
+ * Get list of Mob column families (if any exists)
+ * @param htd table descriptor
+ * @return list of Mob column families
+ */
+ public static List<ColumnFamilyDescriptor>
getMobColumnFamilies(TableDescriptor htd){
+
+ List<ColumnFamilyDescriptor> fams = new
ArrayList<ColumnFamilyDescriptor>();
+ ColumnFamilyDescriptor[] hcds = htd.getColumnFamilies();
+ for (ColumnFamilyDescriptor hcd : hcds) {
+ if (hcd.isMobEnabled()) {
+ fams.add(hcd);
+ }
+ }
+ return fams;
+ }
+
+ /**
+ * Performs housekeeping file cleaning (called by MOB Cleaner chore)
+ * @param conf configuration
+ * @param table table name
+ * @throws IOException
+ */
+ public static void cleanupObsoleteMobFiles(Configuration conf, TableName
table)
+ throws IOException {
+
+ try (final Connection conn = ConnectionFactory.createConnection(conf);
+ final Admin admin = conn.getAdmin();) {
+ TableDescriptor htd = admin.getDescriptor(table);
+ List<ColumnFamilyDescriptor> list = getMobColumnFamilies(htd);
+ if (list.size() == 0) {
+ LOG.info("Skipping non-MOB table [" + table + "]");
+ return;
+ }
+ Path rootDir = FSUtils.getRootDir(conf);
+ Path tableDir = FSUtils.getTableDir(rootDir, table);
+ // How safe is this call?
+ List<Path> regionDirs = FSUtils.getRegionDirs(FileSystem.get(conf),
tableDir);
+
+ Set<String> allActiveMobFileName = new HashSet<String>();
+ FileSystem fs = FileSystem.get(conf);
+ for (Path regionPath: regionDirs) {
+ for (ColumnFamilyDescriptor hcd: list) {
+ String family = hcd.getNameAsString();
+ Path storePath = new Path(regionPath, family);
+ boolean succeed = false;
+ Set<String> regionMobs = new HashSet<String>();
+ while(!succeed) {
+ //TODO handle FNFE
+ RemoteIterator<LocatedFileStatus> rit =
fs.listLocatedStatus(storePath);
+ List<Path> storeFiles = new ArrayList<Path>();
+ // Load list of store files first
+ while(rit.hasNext()) {
+ Path p = rit.next().getPath();
+ if (fs.isFile(p)) {
+ storeFiles.add(p);
+ }
+ }
+ try {
+ for(Path pp: storeFiles) {
+ HStoreFile sf = new HStoreFile(fs, pp, conf,
CacheConfig.DISABLED,
+ BloomType.NONE, true);
+ sf.initReader();
+ byte[] mobRefData =
sf.getMetadataValue(HStoreFile.MOB_FILE_REFS);
+ byte[] mobCellCountData =
sf.getMetadataValue(HStoreFile.MOB_CELLS_COUNT);
+ byte[] bulkloadMarkerData =
sf.getMetadataValue(HStoreFile.BULKLOAD_TASK_KEY);
+ if (mobRefData == null && (mobCellCountData != null ||
+ bulkloadMarkerData == null)) {
+ LOG.info("Found old store file with no MOB_FILE_REFS: " + pp
+ +" - can not proceed until all old files will be
MOB-compacted");
+ return;
+ } else if (mobRefData == null) {
+ LOG.info("Skipping file without MOB references (can be
bulkloaded file):"+ pp);
+ continue;
+ }
+ String[] mobs = new String(mobRefData).split(",");
+ regionMobs.addAll(Arrays.asList(mobs));
+ }
+ } catch (FileNotFoundException e) {
+ //TODO
+ LOG.warn(e.getMessage());
+ continue;
+ }
+ succeed = true;
+ }
+ // Add MOB refs for current region/family
+ allActiveMobFileName.addAll(regionMobs);
+ } // END column families
+ }//END regions
+
+ // Now scan MOB directories and find MOB files with no references to them
+ long now = System.currentTimeMillis();
+ long minAgeToArchive =
conf.getLong(MobConstants.MOB_MINIMUM_FILE_AGE_TO_ARCHIVE_KEY,
+
MobConstants.DEFAULT_MOB_MINIMUM_FILE_AGE_TO_ARCHIVE);
+ for (ColumnFamilyDescriptor hcd: list) {
+ List<Path> toArchive = new ArrayList<Path>();
+ String family = hcd.getNameAsString();
+ Path dir = getMobFamilyPath(conf, table, family);
+ RemoteIterator<LocatedFileStatus> rit = fs.listLocatedStatus(dir);
+ while(rit.hasNext()) {
+ LocatedFileStatus lfs = rit.next();
+ Path p = lfs.getPath();
+ if (!allActiveMobFileName.contains(p.getName())) {
Review comment:
Right, but when we roll a version onto a cluster that used the original mob
implementation it's very likely thy will have _del marker files. And those _del
marker files are necessary for that implementation to operator correctly. I
think that means once someone upgrades to this they can't go back.
that's probably fine for minor releases, but we'll need to release note it
with a strong warning.
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
