Remove forced toast recompression in VACUUM FULL/CLUSTER

michaelpq · michaelpq · commit dbab0c07e5ba · 2021-06-14T09:25:50.000+09:00
The extra checks added by the recompression of toast data introduced in bbe0a81 is proving to have a performance impact on VACUUM or CLUSTER even if no recompression is done. This is more noticeable with more toastable columns that contain non-NULL values. Improvements could be done to make those extra checks less expensive, but that's not material for 14 at this stage, and we are not sure either if the code path of VACUUM FULL/CLUSTER is adapted for this job. Per discussion with several people, including Andres Freund, Robert Haas, Álvaro Herrera, Tom Lane and myself. Discussion: https://postgr.es/m/20210527003144.xxqppojoiwurc2iz@alap3.anarazel.de
diff --git a/doc/src/sgml/ref/alter_table.sgml b/doc/src/sgml/ref/alter_table.sgml
@@ -394,8 +394,7 @@ WITH ( MODULUS <replaceable class="parameter">numeric_literal</replaceable>, REM
       values inserted in future will be compressed (if the storage mode
       permits compression at all).
       This does not cause the table to be rewritten, so existing data may still
-      be compressed with other compression methods.  If the table is rewritten with
-      <command>VACUUM FULL</command> or <command>CLUSTER</command>, or restored
+      be compressed with other compression methods.  If the table is restored
       with <application>pg_restore</application>, then all values are rewritten
       with the configured compression method.
       However, when data is inserted from another relation (for example,
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
@@ -19,15 +19,13 @@
  */
 #include "postgres.h"
 
-#include "access/detoast.h"
 #include "access/genam.h"
 #include "access/heapam.h"
 #include "access/heaptoast.h"
 #include "access/multixact.h"
 #include "access/rewriteheap.h"
 #include "access/syncscan.h"
 #include "access/tableam.h"
-#include "access/toast_compression.h"
 #include "access/tsmapi.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
@@ -2463,78 +2461,21 @@ reform_and_rewrite_tuple(HeapTuple tuple,
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	HeapTuple	copiedTuple;
 	int			i;
-	bool		values_free[MaxTupleAttributeNumber];
-
-	memset(values_free, 0, newTupDesc->natts * sizeof(bool));
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
+	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
-		/* Be sure to null out any dropped columns */
 		if (TupleDescAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
-		else if (!isnull[i] && TupleDescAttr(newTupDesc, i)->attlen == -1)
-		{
-			/*
-			 * Use this opportunity to force recompression of any data that's
-			 * compressed with some TOAST compression method other than the
-			 * one configured for the column.  We don't actually need to
-			 * perform the compression here; we just need to decompress.  That
-			 * will trigger recompression later on.
-			 */
-			struct varlena *new_value;
-			ToastCompressionId cmid;
-			char		cmethod;
-			char		targetmethod;
-
-			new_value = (struct varlena *) DatumGetPointer(values[i]);
-			cmid = toast_get_compression_id(new_value);
-
-			/* nothing to be done for uncompressed data */
-			if (cmid == TOAST_INVALID_COMPRESSION_ID)
-				continue;
-
-			/* convert existing compression id to compression method */
-			switch (cmid)
-			{
-				case TOAST_PGLZ_COMPRESSION_ID:
-					cmethod = TOAST_PGLZ_COMPRESSION;
-					break;
-				case TOAST_LZ4_COMPRESSION_ID:
-					cmethod = TOAST_LZ4_COMPRESSION;
-					break;
-				default:
-					elog(ERROR, "invalid compression method id %d", cmid);
-					cmethod = '\0'; /* keep compiler quiet */
-			}
-
-			/* figure out what the target method is */
-			targetmethod = TupleDescAttr(newTupDesc, i)->attcompression;
-			if (!CompressionMethodIsValid(targetmethod))
-				targetmethod = default_toast_compression;
-
-			/* if compression method doesn't match then detoast the value */
-			if (targetmethod != cmethod)
-			{
-				values[i] = PointerGetDatum(detoast_attr(new_value));
-				values_free[i] = true;
-			}
-		}
 	}
 
 	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
 
-	/* Free any value detoasted previously */
-	for (i = 0; i < newTupDesc->natts; i++)
-	{
-		if (values_free[i])
-			pfree(DatumGetPointer(values[i]));
-	}
-
 	heap_freetuple(copiedTuple);
 }
 
diff --git a/src/test/regress/expected/compression.out b/src/test/regress/expected/compression.out
@@ -297,7 +297,7 @@ SELECT pg_column_compression(f1) FROM cmpart2;
  lz4
 (2 rows)
 
---vacuum full to recompress the data
+-- VACUUM FULL does not recompress
 SELECT pg_column_compression(f1) FROM cmdata;
  pg_column_compression 
 -----------------------
@@ -309,7 +309,7 @@ VACUUM FULL cmdata;
 SELECT pg_column_compression(f1) FROM cmdata;
  pg_column_compression 
 -----------------------
- lz4
+ pglz
  lz4
 (2 rows)
 
diff --git a/src/test/regress/expected/compression_1.out b/src/test/regress/expected/compression_1.out
@@ -293,7 +293,7 @@ SELECT pg_column_compression(f1) FROM cmpart2;
 -----------------------
 (0 rows)
 
---vacuum full to recompress the data
+-- VACUUM FULL does not recompress
 SELECT pg_column_compression(f1) FROM cmdata;
  pg_column_compression 
 -----------------------
diff --git a/src/test/regress/sql/compression.sql b/src/test/regress/sql/compression.sql
@@ -126,7 +126,7 @@ INSERT INTO cmpart VALUES (repeat('123456789', 4004));
 SELECT pg_column_compression(f1) FROM cmpart1;
 SELECT pg_column_compression(f1) FROM cmpart2;
 
---vacuum full to recompress the data
+-- VACUUM FULL does not recompress
 SELECT pg_column_compression(f1) FROM cmdata;
 VACUUM FULL cmdata;
 SELECT pg_column_compression(f1) FROM cmdata;
