[ 
https://issues.apache.org/jira/browse/HIVE-23956?focusedWorklogId=464658&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-464658
 ]

ASF GitHub Bot logged work on HIVE-23956:
-----------------------------------------

                Author: ASF GitHub Bot
            Created on: 30/Jul/20 17:28
            Start Date: 30/Jul/20 17:28
    Worklog Time Spent: 10m 
      Work Description: pvary commented on a change in pull request #1339:
URL: https://github.com/apache/hive/pull/1339#discussion_r463156735



##########
File path: ql/src/java/org/apache/hadoop/hive/ql/io/AcidInputFormat.java
##########
@@ -118,70 +123,183 @@
      */
     private long visibilityTxnId;
 
+    private List<DeltaFileMetaData> deltaFiles;
+
     public DeltaMetaData() {
-      this(0,0,new ArrayList<Integer>(), 0);
+      this(0, 0, new ArrayList<>(), 0, new ArrayList<>());
     }
     /**
+     * @param minWriteId min writeId of the delta directory
+     * @param maxWriteId max writeId of the delta directory
      * @param stmtIds delta dir suffixes when a single txn writes > 1 delta in 
the same partition
      * @param visibilityTxnId maybe 0, if the dir name didn't have it.  
txnid:0 is always visible
+     * @param deltaFileStatuses bucketFiles in the directory
      */
-    DeltaMetaData(long minWriteId, long maxWriteId, List<Integer> stmtIds, 
long visibilityTxnId) {
+    DeltaMetaData(long minWriteId, long maxWriteId, List<Integer> stmtIds, 
long visibilityTxnId,
+        List<HadoopShims.HdfsFileStatusWithId> deltaFileStatuses) {
       this.minWriteId = minWriteId;
       this.maxWriteId = maxWriteId;
       if (stmtIds == null) {
         throw new IllegalArgumentException("stmtIds == null");
       }
       this.stmtIds = stmtIds;
       this.visibilityTxnId = visibilityTxnId;
+      this.deltaFiles = new ArrayList<>();
+      for(HadoopShims.HdfsFileStatusWithId fileStatus : deltaFileStatuses) {
+        deltaFiles.add(new DeltaFileMetaData(fileStatus));
+      }
     }
+
     long getMinWriteId() {
       return minWriteId;
     }
+
     long getMaxWriteId() {
       return maxWriteId;
     }
+
     List<Integer> getStmtIds() {
       return stmtIds;
     }
+
     long getVisibilityTxnId() {
       return visibilityTxnId;
     }
+
+    public List<DeltaFileMetaData> getDeltaFiles() {
+      return deltaFiles;
+    }
+
     @Override
     public void write(DataOutput out) throws IOException {
       out.writeLong(minWriteId);
       out.writeLong(maxWriteId);
       out.writeInt(stmtIds.size());
-      for(Integer id : stmtIds) {
+      for (Integer id : stmtIds) {
         out.writeInt(id);
       }
       out.writeLong(visibilityTxnId);
+      out.writeInt(deltaFiles.size());
+      for (DeltaFileMetaData fileMeta : deltaFiles) {
+        fileMeta.write(out);
+      }
     }
+
     @Override
     public void readFields(DataInput in) throws IOException {
       minWriteId = in.readLong();
       maxWriteId = in.readLong();
       stmtIds.clear();
       int numStatements = in.readInt();
-      for(int i = 0; i < numStatements; i++) {
+      for (int i = 0; i < numStatements; i++) {
         stmtIds.add(in.readInt());
       }
       visibilityTxnId = in.readLong();
+
+      deltaFiles.clear();
+      int numFiles = in.readInt();
+      for(int i = 0; i< numFiles; i++) {
+        DeltaFileMetaData file = new DeltaFileMetaData();
+        file.readFields(in);
+        deltaFiles.add(file);
+      }
     }
-    String getName() {
+    private String getName() {
       assert stmtIds.isEmpty() : "use getName(int)";
       return AcidUtils.addVisibilitySuffix(AcidUtils
           .deleteDeltaSubdir(minWriteId, maxWriteId), visibilityTxnId);
     }
-    String getName(int stmtId) {
+    private String getName(int stmtId) {
       assert !stmtIds.isEmpty() : "use getName()";
       return AcidUtils.addVisibilitySuffix(AcidUtils
           .deleteDeltaSubdir(minWriteId, maxWriteId, stmtId), visibilityTxnId);
     }
+
+    public List<Path> getPaths(Path root) {
+      if (stmtIds.isEmpty()) {
+        return Collections.singletonList(new Path(root, getName()));
+      } else {
+        // To support multistatement transactions we may have multiple 
directories corresponding to one DeltaMetaData
+        return getStmtIds().stream().map(stmtId -> new Path(root, 
getName(stmtId))).collect(Collectors.toList());
+      }
+    }
     @Override
     public String toString() {
       return "Delta(?," + minWriteId + "," + maxWriteId + "," + stmtIds + "," 
+ visibilityTxnId + ")";
     }
   }
+  final class DeltaFileMetaData implements Writable {

Review comment:
       Nit: newline 




----------------------------------------------------------------
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


Issue Time Tracking
-------------------

    Worklog Id:     (was: 464658)
    Time Spent: 50m  (was: 40m)

> Delete delta directory file information should be pushed to execution side
> --------------------------------------------------------------------------
>
>                 Key: HIVE-23956
>                 URL: https://issues.apache.org/jira/browse/HIVE-23956
>             Project: Hive
>          Issue Type: Improvement
>            Reporter: Peter Varga
>            Assignee: Peter Varga
>            Priority: Major
>              Labels: pull-request-available
>          Time Spent: 50m
>  Remaining Estimate: 0h
>
> Since HIVE-23840 LLAP cache is used to retrieve the tail of the ORC bucket 
> files in the delete deltas, but to use the cache the fileId must be 
> determined, so one more FileSystem call is issued for each bucket.
> This fileId is already available during compilation in the AcidState 
> calculation, we should serialise this to the OrcSplit, and remove the 
> unnecessary FS calls.
> Furthermore instead of sending the SyntheticFileId directly, we should pass 
> the attemptId instead of the standard path hash, this way the path and the 
> SyntheticFileId. can be calculated, and it will work even, if the move free 
> delete operations will be introduced.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

Reply via email to