calculate exact size required for cleanup operations

patch by yukim; reviewed by jbellis for CASSANDRA-1404
thepaul · May 15, 2012 · 5979bce · 5979bce
1 parent 783e5d4
commit 5979bce
Show file tree

Hide file tree

Showing 4 changed files with 28 additions and 9 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -1,4 +1,5 @@
 1.1.1-dev
+ * calculate exact size required for cleanup operations (CASSANDRA-1404)
  * avoid blocking additional writes during flush when the commitlog
    gets behind temporarily (CASSANDRA-1991)
  * enable caching on index CFs based on data CF cache setting (CASSANDRA-4197)

diff --git a/src/java/org/apache/cassandra/db/ColumnFamilyStore.java b/src/java/org/apache/cassandra/db/ColumnFamilyStore.java
@@ -889,17 +889,35 @@ public void addSSTables(Collection<SSTableReader> sstables)
         CompactionManager.instance.submitBackground(this);
     }
 
-    /*
-     * Add up all the files sizes this is the worst case file
+    /**
+     * Calculate expected file size of SSTable after compaction.
+     *
+     * If operation type is {@code CLEANUP}, then we calculate expected file size
+     * with checking token range to be eliminated.
+     * Other than that, we just add up all the files' size, which is the worst case file
      * size for compaction of all the list of files given.
+     *
+     * @param sstables SSTables to calculate expected compacted file size
+     * @param operation Operation type
+     * @return Expected file size of SSTable after compaction
      */
-    public long getExpectedCompactedFileSize(Iterable<SSTableReader> sstables)
+    public long getExpectedCompactedFileSize(Iterable<SSTableReader> sstables, OperationType operation)
     {
         long expectedFileSize = 0;
-        for (SSTableReader sstable : sstables)
+        if (operation == OperationType.CLEANUP)
+        {
+            Collection<Range<Token>> ranges = StorageService.instance.getLocalRanges(table.name);
+            for (SSTableReader sstable : sstables)
+            {
+                List<Pair<Long, Long>> positions = sstable.getPositionsForRanges(ranges);
+                for (Pair<Long, Long> position : positions)
+                    expectedFileSize += position.right - position.left;
+            }
+        }
+        else
         {
-            long size = sstable.onDiskLength();
-            expectedFileSize = expectedFileSize + size;
+            for (SSTableReader sstable : sstables)
+                expectedFileSize += sstable.onDiskLength();
         }
         return expectedFileSize;
     }

diff --git a/src/java/org/apache/cassandra/db/compaction/CompactionManager.java b/src/java/org/apache/cassandra/db/compaction/CompactionManager.java
@@ -693,7 +693,7 @@ private void doCleanupCompaction(ColumnFamilyStore cfs, Collection<SSTableReader
 
             logger.info("Cleaning up " + sstable);
             // Calculate the expected compacted filesize
-            long expectedRangeFileSize = cfs.getExpectedCompactedFileSize(Arrays.asList(sstable)) / 2;
+            long expectedRangeFileSize = cfs.getExpectedCompactedFileSize(Arrays.asList(sstable), OperationType.CLEANUP);
             File compactionFileLocation = cfs.directories.getDirectoryForNewSSTables(expectedRangeFileSize);
             if (compactionFileLocation == null)
                 throw new IOException("disk full");

diff --git a/src/java/org/apache/cassandra/db/compaction/CompactionTask.java b/src/java/org/apache/cassandra/db/compaction/CompactionTask.java
@@ -74,7 +74,7 @@ public int execute(CompactionExecutorStatsCollector collector) throws IOExceptio
         if (!isCompactionInteresting(toCompact))
             return 0;
 
-        File compactionFileLocation = cfs.directories.getDirectoryForNewSSTables(cfs.getExpectedCompactedFileSize(toCompact));
+        File compactionFileLocation = cfs.directories.getDirectoryForNewSSTables(cfs.getExpectedCompactedFileSize(toCompact, compactionType));
         if (compactionFileLocation == null && partialCompactionsAcceptable())
         {
             // If the compaction file path is null that means we have no space left for this compaction.
@@ -85,7 +85,7 @@ public int execute(CompactionExecutorStatsCollector collector) throws IOExceptio
                 // Note that we have removed files that are still marked as compacting.
                 // This suboptimal but ok since the caller will unmark all the sstables at the end.
                 toCompact.remove(cfs.getMaxSizeFile(toCompact));
-                compactionFileLocation = cfs.directories.getDirectoryForNewSSTables(cfs.getExpectedCompactedFileSize(toCompact));
+                compactionFileLocation = cfs.directories.getDirectoryForNewSSTables(cfs.getExpectedCompactedFileSize(toCompact, compactionType));
             }
         }