When computing STAT1 values using ANALYZE, if a ratio comes out to be between

1.0 and 1.1, then round it down to 1 rather than the using the default rounding
rule of changing it to 2.  The reduces the estimation error for the
case where a column value is very nearly, but not quite unique.

FossilOrigin-Name: eb59c46a5aed69bc6fd096997bf24c082e533c1085439f6ec1fbe5ff78e8b374

diff --git a/manifest b/manifest
index 5d25cfd023e8d50294dd68ab332b7433c0c223ee..dcee977a82d6dc188f9275a6f41bd632c4689e7c 100644 (file)
--- a/manifest
+++ b/manifest
@@ -1,5 +1,5 @@
-C Fix\sa\stest\sproblem\sin\srbubusy.test\scausing\sa\scrash\sunder\ssome\scircumstances.
-D 2022-04-27T13:33:48.684
+C When\scomputing\sSTAT1\svalues\susing\sANALYZE,\sif\sa\sratio\scomes\sout\sto\sbe\sbetween\n1.0\sand\s1.1,\sthen\sround\sit\sdown\sto\s1\srather\sthan\sthe\susing\sthe\sdefault\srounding\nrule\sof\schanging\sit\sto\s2.\s\sThe\sreduces\sthe\sestimation\serror\sfor\sthe\ncase\swhere\sa\scolumn\svalue\sis\svery\snearly,\sbut\snot\squite\sunique.
+D 2022-04-27T16:41:56.099
 F .fossil-settings/empty-dirs dbb81e8fc0401ac46a1491ab34a7f2c7c0452f2f06b54ebb845d024ca8283ef1
 F .fossil-settings/ignore-glob 35175cdfcf539b2318cb04a9901442804be81cd677d8b889fcc9149c21f239ea
 F LICENSE.md df5091916dbb40e6e9686186587125e1b2ff51f022cc334e886c19a0e9982724
@@ -487,7 +487,7 @@ F sqlite.pc.in 42b7bf0d02e08b9e77734a47798d1a55a9e0716b
 F sqlite3.1 fc7ad8990fc8409983309bb80de8c811a7506786
 F sqlite3.pc.in 48fed132e7cb71ab676105d2a4dc77127d8c1f3a
 F src/alter.c 9395ece9850ad57c6fbb453aeb5185be4bae3b159c4b37611425c565124ee849
-F src/analyze.c 3a119baeb03053c154029877454d41bb8fd79d4d1eb583392f2289b3554a75bc
+F src/analyze.c aabdf3769c7fd9954a8ec508eb7041ae174b66f88d12c47199fabbea9a646467
 F src/attach.c 4431f82f0247bf3aaf91589acafdff77d1882235c95407b36da1585c765fbbc8
 F src/auth.c f4fa91b6a90bbc8e0d0f738aa284551739c9543a367071f55574681e0f24f8cf
 F src/backup.c a2891172438e385fdbe97c11c9745676bec54f518d4447090af97189fd8e52d7
@@ -1951,8 +1951,8 @@ F vsixtest/vsixtest.tcl 6a9a6ab600c25a91a7acc6293828957a386a8a93
 F vsixtest/vsixtest.vcxproj.data 2ed517e100c66dc455b492e1a33350c1b20fbcdc
 F vsixtest/vsixtest.vcxproj.filters 37e51ffedcdb064aad6ff33b6148725226cd608e
 F vsixtest/vsixtest_TemporaryKey.pfx e5b1b036facdb453873e7084e1cae9102ccc67a0
-P b1bec72043f798f4d4d30e6b60a45ed4dc521115c8a9f97bb8228e3f089deefb
-R f8e9d661e065b7babfd72a5655e4ad71
-U dan
-Z 3cd41b751eccac6d73d356239c542a95
+P bc5bbd9fa636cc9ef0cbbc0600b8fc1404b9732670ac4e7a8b5a230fbce758d5
+R 5515b70c241c679d58c02a7cda432aa8
+U drh
+Z e146713923a218edc001415f7d000194
 # Remove this line to create a well-formed Fossil manifest.

diff --git a/manifest.uuid b/manifest.uuid
index 9b2e970b934c31409e880497cdbca7f39b872540..0444092686adda5976a48fde759fdb2acf7df83b 100644 (file)
--- a/manifest.uuid
+++ b/manifest.uuid
@@ -1 +1 @@
-bc5bbd9fa636cc9ef0cbbc0600b8fc1404b9732670ac4e7a8b5a230fbce758d5
\ No newline at end of file
+eb59c46a5aed69bc6fd096997bf24c082e533c1085439f6ec1fbe5ff78e8b374
\ No newline at end of file

diff --git a/src/analyze.c b/src/analyze.c
index e8699653f7da5ea9a0528690963540bfcbfe5304..39009899ab7d757f76c9c572eb3234327490ee81 100644 (file)
--- a/src/analyze.c
+++ b/src/analyze.c
@@ -847,9 +847,14 @@ static void statGet(
     **   * "WHERE a=? AND b=?" matches 2 rows.
     **
     ** If D is the count of distinct values and K is the total number of 
-    ** rows, then each estimate is computed as:
+    ** rows, then each estimate is usually computed as:
     **
     **        I = (K+D-1)/D
+    **
+    ** In other words, I is K/D rounded up to the next whole integer.
+    ** However, if I is between 1.0 and 1.1 (in other words if I is
+    ** close to 1.0 but just a little larger) then do not round up but
+    ** instead keep the I value at 1.0.
     */
     sqlite3_str sStat;   /* Text of the constructed "stat" line */
     int i;               /* Loop counter */
@@ -860,6 +865,7 @@ static void statGet(
     for(i=0; i<p->nKeyCol; i++){
       u64 nDistinct = p->current.anDLt[i] + 1;
       u64 iVal = (p->nRow + nDistinct - 1) / nDistinct;
+      if( iVal==2 && p->nRow*10 <= nDistinct*11 ) iVal = 1;
       sqlite3_str_appendf(&sStat, " %llu", iVal);
       assert( p->current.anEq[i] );
     }