Reduce timing overhead of EXPLAIN ANALYZE using rdtsc (PG19, v11)

configure

@@ -5341,6 +5341,7 @@ if test x"$pgac_cv_prog_CC_cflags__Werror_vla" = x"yes"; then
 fi
 
 
+  # -Wvla is not applicable for C++
   # On macOS, complain about usage of symbols newer than the deployment target
 
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether ${CC} supports -Werror=unguarded-availability-new, for CFLAGS" >&5
@@ -5433,7 +5434,6 @@ if test x"$pgac_cv_prog_CXX_cxxflags__Werror_unguarded_availability_new" = x"yes
 fi
 
 
-  # -Wvla is not applicable for C++
 
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether ${CC} supports -Wendif-labels, for CFLAGS" >&5
 $as_echo_n "checking whether ${CC} supports -Wendif-labels, for CFLAGS... " >&6; }
@@ -17657,7 +17657,8 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
   fi
 fi
 
-# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+# Check for __get_cpuid_count() and __cpuidex() separately, since we sometimes
+# need __cpuidex() even if __get_cpuid_count() is available.
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
 $as_echo_n "checking for __get_cpuid_count... " >&6; }
 if ${pgac_cv__get_cpuid_count+:} false; then :
@@ -17690,21 +17691,25 @@ if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
 
 $as_echo "#define HAVE__GET_CPUID_COUNT 1" >>confdefs.h
 
-else
-  # __cpuidex()
-  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+fi
+# __cpuidex()
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
 $as_echo_n "checking for __cpuidex... " >&6; }
 if ${pgac_cv__cpuidex+:} false; then :
   $as_echo_n "(cached) " >&6
 else
   cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
-#include <intrin.h>
+#ifdef _MSC_VER
+    #include <intrin.h>
+    #else
+    #include <cpuid.h>
+    #endif
 int
 main ()
 {
-unsigned int exx[4] = {0, 0, 0, 0};
-    __cpuidex(exx, 7, 0);
+int exx[4] = {0, 0, 0, 0};
+  __cpuidex(exx, 7, 0);
 
   ;
   return 0;
@@ -17720,11 +17725,10 @@ rm -f core conftest.err conftest.$ac_objext \
 fi
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
 $as_echo "$pgac_cv__cpuidex" >&6; }
-  if test x"$pgac_cv__cpuidex" = x"yes"; then
+if test x"$pgac_cv__cpuidex" = x"yes"; then
 
 $as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
 
-  fi
 fi
 
 # Check for XSAVE intrinsics

configure.ac

@@ -549,10 +549,10 @@ if test "$GCC" = yes -a "$ICC" = no; then
   AC_SUBST(PERMIT_DECLARATION_AFTER_STATEMENT)
   # Really don't want VLAs to be used in our dialect of C
   PGAC_PROG_CC_CFLAGS_OPT([-Werror=vla])
+  # -Wvla is not applicable for C++
   # On macOS, complain about usage of symbols newer than the deployment target
   PGAC_PROG_CC_CFLAGS_OPT([-Werror=unguarded-availability-new])
   PGAC_PROG_CXX_CFLAGS_OPT([-Werror=unguarded-availability-new])
-  # -Wvla is not applicable for C++
   PGAC_PROG_CC_CFLAGS_OPT([-Wendif-labels])
   PGAC_PROG_CXX_CFLAGS_OPT([-Wendif-labels])
   PGAC_PROG_CC_CFLAGS_OPT([-Wmissing-format-attribute])
@@ -2104,7 +2104,8 @@ else
   fi
 fi
 
-# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+# Check for __get_cpuid_count() and __cpuidex() separately, since we sometimes
+# need __cpuidex() even if __get_cpuid_count() is available.
 AC_CACHE_CHECK([for __get_cpuid_count], [pgac_cv__get_cpuid_count],
 [AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <cpuid.h>],
   [[unsigned int exx[4] = {0, 0, 0, 0};
@@ -2114,18 +2115,21 @@ AC_CACHE_CHECK([for __get_cpuid_count], [pgac_cv__get_cpuid_count],
   [pgac_cv__get_cpuid_count="no"])])
 if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
   AC_DEFINE(HAVE__GET_CPUID_COUNT, 1, [Define to 1 if you have __get_cpuid_count.])
-else
-  # __cpuidex()
-  AC_CACHE_CHECK([for __cpuidex], [pgac_cv__cpuidex],
-  [AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <intrin.h>],
-    [[unsigned int exx[4] = {0, 0, 0, 0};
-    __cpuidex(exx, 7, 0);
-    ]])],
-    [pgac_cv__cpuidex="yes"],
-    [pgac_cv__cpuidex="no"])])
-  if test x"$pgac_cv__cpuidex" = x"yes"; then
-    AC_DEFINE(HAVE__CPUIDEX, 1, [Define to 1 if you have __cpuidex.])
-  fi
+fi
+# __cpuidex()
+AC_CACHE_CHECK([for __cpuidex], [pgac_cv__cpuidex],
+[AC_LINK_IFELSE([AC_LANG_PROGRAM([#ifdef _MSC_VER
+    #include <intrin.h>
+    #else
+    #include <cpuid.h>
+    #endif],
+  [[int exx[4] = {0, 0, 0, 0};
+  __cpuidex(exx, 7, 0);
+  ]])],
+  [pgac_cv__cpuidex="yes"],
+  [pgac_cv__cpuidex="no"])])
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+  AC_DEFINE(HAVE__CPUIDEX, 1, [Define to 1 if you have __cpuidex.])
 fi
 
 # Check for XSAVE intrinsics

contrib/bloom/blscan.c

@@ -18,6 +18,7 @@
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "storage/bufmgr.h"
+#include "storage/read_stream.h"
 
 /*
  * Begin scan of bloom index.
@@ -76,11 +77,13 @@ int64
 blgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 {
 	int64		ntids = 0;
-	BlockNumber blkno = BLOOM_HEAD_BLKNO,
+	BlockNumber blkno,
 				npages;
 	int			i;
 	BufferAccessStrategy bas;
 	BloomScanOpaque so = (BloomScanOpaque) scan->opaque;
+	BlockRangeReadStreamPrivate p;
+	ReadStream *stream;
 
 	if (so->sign == NULL)
 	{
@@ -120,14 +123,29 @@ blgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 	if (scan->instrument)
 		scan->instrument->nsearches++;
 
+	/* Scan all blocks except the metapage using streaming reads */
+	p.current_blocknum = BLOOM_HEAD_BLKNO;
+	p.last_exclusive = npages;
+
+	/*
+	 * It is safe to use batchmode as block_range_read_stream_cb takes no
+	 * locks.
+	 */
+	stream = read_stream_begin_relation(READ_STREAM_FULL |
+										READ_STREAM_USE_BATCHING,
+										bas,
+										scan->indexRelation,
+										MAIN_FORKNUM,
+										block_range_read_stream_cb,
+										&p,
+										0);
+
 	for (blkno = BLOOM_HEAD_BLKNO; blkno < npages; blkno++)
 	{
 		Buffer		buffer;
 		Page		page;
 
-		buffer = ReadBufferExtended(scan->indexRelation, MAIN_FORKNUM,
-									blkno, RBM_NORMAL, bas);
-
+		buffer = read_stream_next_buffer(stream, NULL);
 		LockBuffer(buffer, BUFFER_LOCK_SHARE);
 		page = BufferGetPage(buffer);
 
@@ -163,6 +181,9 @@ blgetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 		UnlockReleaseBuffer(buffer);
 		CHECK_FOR_INTERRUPTS();
 	}
+
+	Assert(read_stream_next_buffer(stream, NULL) == InvalidBuffer);
+	read_stream_end(stream);
 	FreeAccessStrategy(bas);
 
 	return ntids;

doc/src/sgml/config.sgml

@@ -2533,6 +2533,60 @@ include_dir 'conf.d'
      </variablelist>
     </sect2>
 
+    <sect2 id="runtime-config-resource-time">
+     <title>Timing</title>
+
+     <variablelist>
+     <varlistentry id="guc-timing-clock-source" xreflabel="timing_clock_source">
+      <term><varname>timing_clock_source</varname> (<type>enum</type>)
+      <indexterm>
+       <primary><varname>timing_clock_source</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Selects the method for making timing measurements using the OS or specialized CPU
+        instructions. Possible values are:
+         <itemizedlist>
+          <listitem>
+           <para>
+            <literal>auto</literal> (automatically chooses TSC clock source for modern CPUs,
+            otherwise uses the OS system clock)
+           </para>
+          </listitem>
+          <listitem>
+           <para>
+            <literal>system</literal> (measures timing using the OS system clock)
+           </para>
+          </listitem>
+          <listitem>
+           <para>
+            <literal>tsc</literal> (measures timing using the x86-64 Time-Stamp Counter (TSC)
+            by directly executing RDTSC/RDTSCP instructions, see below)
+           </para>
+          </listitem>
+         </itemizedlist>
+         The default is <literal>auto</literal>.
+        </para>
+        <para>
+          If enabled, the TSC clock source will use the RDTSC instruction for the x86-64
+          Time-Stamp Counter (TSC) to perform certain time measurements, for example during
+          EXPLAIN ANALYZE. The RDTSC instruction has less overhead than going through the OS
+          clock source, which for an EXPLAIN ANALYZE statement will show timing closer to the
+          actual runtime when timing is off. For timings that require higher precision the
+          RDTSCP instruction is used, which avoids inaccuracies due to CPU instruction re-ordering.
+          Use of RDTSC/RDTSC is not supported on older CPUs or hypervisors that don't pass the TSC
+          frequency to guest VMs, and is not advised on systems that utilize an emulated TSC.
+        </para>
+        <para>
+          To help decide which clock source to use on an x86-64 system you can run the
+          <application>pg_test_timing</application> utility to check TSC availability, and
+          perform timing measurements.
+        </para>
+      </listitem>
+     </varlistentry>
+     </variablelist>
+    </sect2>
 
     <sect2 id="runtime-config-resource-background-writer">
      <title>Background Writer</title>