Minor tweaks to query planning weights so that when STAT4 is enabled

and functioning, a full table scan is more likely to be selected if
that seems like the fastest solution.  Only do this when STAT4 info
is available because an error has a large potential downside.

FossilOrigin-Name: 0e7e113d9f2c929c1f8a85e2cfad8e2e60f0e8770212b5e5320fb2a2c42911f8

3 files changed, 18 insertions, 1 deletions

diff --git a/src/analyze.c b/src/analyze.c
index 9a9de991d..dc77220a5 100644
--- a/src/analyze.c
+++ b/src/analyze.c
@@ -1772,6 +1772,7 @@ static int loadStatTbl(
     }
     pSpace = (tRowcnt*)&pIdx->aSample[nSample];
     pIdx->aAvgEq = pSpace; pSpace += nIdxCol;
+    pIdx->pTable->tabFlags |= TF_HasStat4;
     for(i=0; i<nSample; i++){
       pIdx->aSample[i].anEq = pSpace; pSpace += nIdxCol;
       pIdx->aSample[i].anLt = pSpace; pSpace += nIdxCol;
diff --git a/src/sqliteInt.h b/src/sqliteInt.h
index ec832eca6..467062277 100644
--- a/src/sqliteInt.h
+++ b/src/sqliteInt.h
@@ -2187,6 +2187,7 @@ struct Table {
 #define TF_OOOHidden       0x0400    /* Out-of-Order hidden columns */
 #define TF_HasNotNull      0x0800    /* Contains NOT NULL constraints */
 #define TF_Shadow          0x1000    /* True for a shadow table */
+#define TF_HasStat4        0x2000    /* STAT4 info available for this table */
 
 /*
 ** Test to see whether or not a table is a virtual table.  This is
diff --git a/src/where.c b/src/where.c
index ec00482e9..9f35dce02 100644
--- a/src/where.c
+++ b/src/where.c
@@ -3042,8 +3042,23 @@ static int whereLoopAddBtree(
 
       /* Full table scan */
       pNew->iSortIdx = b ? iSortIdx : 0;
-      /* TUNING: Cost of full table scan is (N*3.0). */
+      /* TUNING: Cost of full table scan is 3.0*N.  The 3.0 factor is an
+      ** extra cost designed to discourage the use of full table scans,
+      ** since index lookups have better worst-case performance if our
+      ** stat guesses are wrong.  Reduce the 3.0 penalty slightly
+      ** (to 2.75) if we have valid STAT4 information for the table.
+      ** At 2.75, a full table scan is preferred over using an index on
+      ** a column with just two distinct values where each value has about
+      ** an equal number of appearances.  Without STAT4 data, we still want
+      ** to use an index in that case, since the constraint might be for
+      ** the scarcer of the two values, and in that case an index lookup is
+      ** better.
+      */
+#ifdef SQLITE_ENABLE_STAT4
+      pNew->rRun = rSize + 16 - 2*((pTab->tabFlags & TF_HasStat4)!=0);
+#else
       pNew->rRun = rSize + 16;
+#endif
       ApplyCostMultiplier(pNew->rRun, pTab->costMult);
       whereLoopOutputAdjust(pWC, pNew, rSize);
       rc = whereLoopInsert(pBuilder, pNew);