reuse old index file format for empty dmfile and just ignore it's siz…

…e in statistical data
pingcap · Apr 19, 2022 · a97fce9 · a97fce9
1 parent 636fcd2
commit a97fce9
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 7 deletions.
diff --git a/dbms/src/Storages/DeltaMerge/File/DMFileWriter.cpp b/dbms/src/Storages/DeltaMerge/File/DMFileWriter.cpp
@@ -360,10 +360,13 @@ void DMFileWriter::finalizeColumn(ColId col_id, DataTypePtr type)
                         dmfile->encryptionIndexPath(stream_name),
                         false,
                         write_limiter);
-                    if (!is_empty_file)
-                        stream->minmaxes->write(*type, buf);
+                    stream->minmaxes->write(*type, buf);
                     buf.sync();
-                    bytes_written += buf.getMaterializedBytes();
+                    // Ignore data written in index file because this dmfile is empty.
+                    // This is ok because the index file in this case is really small, and we already ignore other small files like meta and pack stat file.
+                    // The motivation to do this is to show a zero `stable_size_on_disk` for empty segments,
+                    // and we cannot change the index file format for empty dmfile because of backward compatibility.
+                    bytes_written += is_empty_file ? 0 : buf.getMaterializedBytes();
                 }
                 else
                 {
@@ -374,10 +377,13 @@ void DMFileWriter::finalizeColumn(ColId col_id, DataTypePtr type)
                                                                            write_limiter,
                                                                            dmfile->configuration->getChecksumAlgorithm(),
                                                                            dmfile->configuration->getChecksumFrameLength());
-                    if (!is_empty_file)
-                        stream->minmaxes->write(*type, *buf);
+                    stream->minmaxes->write(*type, *buf);
                     buf->sync();
-                    bytes_written += buf->getMaterializedBytes();
+                    // Ignore data written in index file because this dmfile is empty.
+                    // This is ok because the index file in this case is really small, and we already ignore other small files like meta and pack stat file.
+                    // The motivation to do this is to show a zero `stable_size_on_disk` for empty segments,
+                    // and we cannot change the index file format for empty dmfile because of backward compatibility.
+                    bytes_written += is_empty_file ? 0 : buf->getMaterializedBytes();
 #ifndef NDEBUG
                     examine_buffer_size(*buf, *this->file_provider);
 #endif

diff --git a/dbms/src/Storages/DeltaMerge/File/DMFileWriter.h b/dbms/src/Storages/DeltaMerge/File/DMFileWriter.h
@@ -250,7 +250,7 @@ class DMFileWriter
     FileProviderPtr file_provider;
     WriteLimiterPtr write_limiter;
 
-    // use to avoid write index data for empty file
+    // use to avoid count data written in index file for empty dmfile
     bool is_empty_file = true;
 };