hemantk-12 commented on code in PR #4045:
URL: https://github.com/apache/ozone/pull/4045#discussion_r1054848338
##########
hadoop-hdds/rocksdb-checkpoint-differ/src/main/java/org/apache/ozone/rocksdiff/RocksDBCheckpointDiffer.java:
##########
@@ -939,6 +980,290 @@ private void populateCompactionDAG(List<String>
inputFiles,
}
+ /**
+ * This is the task definition which is run periodically by the service
+ * executor at fixed delay.
+ * It looks for snapshots in compaction DAG which are older than the allowed
+ * time to be in compaction DAG and removes them from the DAG.
+ */
+ public void pruneOlderSnapshotsWithCompactionHistory() {
+ List<Path> olderSnapshotsLogFilePaths =
+ getOlderSnapshotsCompactionLogFilePaths();
+
+ List<String> lastCompactionSstFiles =
+ getLastCompactionSstFiles(olderSnapshotsLogFilePaths);
+
+ Set<String> sstFileNodesRemoved =
+ pruneSnapshotFileNodesFromDag(lastCompactionSstFiles);
+ removeSstFile(sstFileNodesRemoved);
+ deleteOlderSnapshotsCompactionFiles(olderSnapshotsLogFilePaths);
+ }
+
+ /**
+ * Deletes the SST file from the backup directory if exists.
+ */
+ private void removeSstFile(Set<String> sstFileNodes) {
+ for (String sstFileNode: sstFileNodes) {
+ File file = new File(sstBackupDir + sstFileNode + SST_FILE_EXTENSION);
+ try {
+ Files.deleteIfExists(file.toPath());
+ } catch (IOException exception) {
+ LOG.warn("Failed to delete SST file: " + sstFileNode, exception);
+ }
+ }
+ }
+
+ /**
+ * Returns the list of compaction log files which are older than allowed
+ * max time in the compaction DAG.
+ */
+ private List<Path> getOlderSnapshotsCompactionLogFilePaths() {
+ List<Path> olderSnapshotLogPaths = new ArrayList<>();
+
+ long compactionLogPruneStartTime = System.currentTimeMillis();
+
+ List<Path> compactionFiles =
+ listCompactionLogFileFromCompactionLogDirectory();
+
+ for (Path compactionLogPath : compactionFiles) {
+ SnapshotLogInfo snapshotLogInfo =
+ getSnapshotInfoFromLog(compactionLogPath);
+
+ if (snapshotLogInfo == null) {
Review Comment:
My bad, you are right. This fill still needs to get added to
`olderSnapshotLogPaths` to be included.
##########
hadoop-hdds/rocksdb-checkpoint-differ/src/main/java/org/apache/ozone/rocksdiff/RocksDBCheckpointDiffer.java:
##########
@@ -939,6 +980,290 @@ private void populateCompactionDAG(List<String>
inputFiles,
}
+ /**
+ * This is the task definition which is run periodically by the service
+ * executor at fixed delay.
+ * It looks for snapshots in compaction DAG which are older than the allowed
+ * time to be in compaction DAG and removes them from the DAG.
+ */
+ public void pruneOlderSnapshotsWithCompactionHistory() {
+ List<Path> olderSnapshotsLogFilePaths =
+ getOlderSnapshotsCompactionLogFilePaths();
+
+ List<String> lastCompactionSstFiles =
+ getLastCompactionSstFiles(olderSnapshotsLogFilePaths);
+
+ Set<String> sstFileNodesRemoved =
+ pruneSnapshotFileNodesFromDag(lastCompactionSstFiles);
+ removeSstFile(sstFileNodesRemoved);
+ deleteOlderSnapshotsCompactionFiles(olderSnapshotsLogFilePaths);
+ }
+
+ /**
+ * Deletes the SST file from the backup directory if exists.
+ */
+ private void removeSstFile(Set<String> sstFileNodes) {
+ for (String sstFileNode: sstFileNodes) {
+ File file = new File(sstBackupDir + sstFileNode + SST_FILE_EXTENSION);
+ try {
+ Files.deleteIfExists(file.toPath());
+ } catch (IOException exception) {
+ LOG.warn("Failed to delete SST file: " + sstFileNode, exception);
+ }
+ }
+ }
+
+ /**
+ * Returns the list of compaction log files which are older than allowed
+ * max time in the compaction DAG.
+ */
+ private List<Path> getOlderSnapshotsCompactionLogFilePaths() {
+ List<Path> olderSnapshotLogPaths = new ArrayList<>();
+
+ long compactionLogPruneStartTime = System.currentTimeMillis();
+
+ List<Path> compactionFiles =
+ listCompactionLogFileFromCompactionLogDirectory();
+
+ for (Path compactionLogPath : compactionFiles) {
+ SnapshotLogInfo snapshotLogInfo =
+ getSnapshotInfoFromLog(compactionLogPath);
+
+ if (snapshotLogInfo == null) {
Review Comment:
My bad, you are right. This file still needs to get added to
`olderSnapshotLogPaths` to be included.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
