MDEV-17401: LOAD DATA from very big file into MyISAM table results in EOF error and corrupt index

my_read fixed as in higher versions.
my_pread made as my_read aware of partial read of huge chunks of files
MY_FULL_IO enabled for file operations

mysys/mf_iocache.c

@@ -282,6 +282,10 @@ int init_io_cache(IO_CACHE *info, File file, size_t cachesize,
   }
   info->inited=info->aio_result.pending=0;
 #endif
+  if (type == READ_CACHE || type == WRITE_CACHE || type == SEQ_READ_APPEND)
+    info->myflags|= MY_FULL_IO;
+  else
+    info->myflags&= ~MY_FULL_IO;
   DBUG_RETURN(0);
 }						/* init_io_cache */
 

mysys/my_pread.c

@@ -47,8 +47,7 @@
 size_t my_pread(File Filedes, uchar *Buffer, size_t Count, my_off_t offset,
                 myf MyFlags)
 {
-  size_t readbytes;
-  int error= 0;
+  size_t readbytes, save_count= 0;
 
   DBUG_ENTER("my_pread");
 
@@ -66,11 +65,10 @@ size_t my_pread(File Filedes, uchar *Buffer, size_t Count, my_off_t offset,
 #else
     readbytes= pread(Filedes, Buffer, Count, offset);
 #endif
-    error = (readbytes != Count);
 
-    if (error)
+    if (readbytes != Count)
     {
-      my_errno= errno ? errno : -1;
+      my_errno= errno;
       if (errno == 0 || (readbytes != (size_t) -1 &&
                          (MyFlags & (MY_NABP | MY_FNABP))))
         my_errno= HA_ERR_FILE_TOO_SHORT;
@@ -82,6 +80,18 @@ size_t my_pread(File Filedes, uchar *Buffer, size_t Count, my_off_t offset,
                              (int) readbytes));
         continue;                              /* Interrupted */
       }
+
+      /* Do a read retry if we didn't get enough data on first read */
+      if (readbytes != (size_t) -1 && readbytes != 0 &&
+          (MyFlags & MY_FULL_IO))
+      {
+        Buffer+= readbytes;
+        Count-= readbytes;
+        save_count+= readbytes;
+        offset+= readbytes;
+        continue;
+      }
+
       if (MyFlags & (MY_WME | MY_FAE | MY_FNABP))
       {
 	if (readbytes == (size_t) -1)
@@ -97,8 +107,10 @@ size_t my_pread(File Filedes, uchar *Buffer, size_t Count, my_off_t offset,
         DBUG_RETURN(MY_FILE_ERROR);         /* Return with error */
     }
     if (MyFlags & (MY_NABP | MY_FNABP))
-      DBUG_RETURN(0);                      /* Read went ok; Return 0 */
-    DBUG_RETURN(readbytes);                /* purecov: inspected */
+      readbytes= 0;                       /* Read went ok; Return 0 */
+    else
+      readbytes+= save_count;
+    DBUG_RETURN(readbytes);
   }
 } /* my_pread */
 

mysys/my_read.c

@@ -35,17 +35,16 @@
 
 size_t my_read(File Filedes, uchar *Buffer, size_t Count, myf MyFlags)
 {
-  size_t readbytes, save_count;
+  size_t readbytes, save_count= 0;
   DBUG_ENTER("my_read");
-  DBUG_PRINT("my",("fd: %d  Buffer: %p  Count: %lu  MyFlags: %d",
-                   Filedes, Buffer, (ulong) Count, MyFlags));
-  save_count= Count;
+  DBUG_PRINT("my",("fd: %d  Buffer: %p  Count: %lu  MyFlags: %lu",
+                   Filedes, Buffer, (ulong) Count, (ulong) MyFlags));
   if (!(MyFlags & (MY_WME | MY_FAE | MY_FNABP)))
     MyFlags|= my_global_flags;
 
   for (;;)
   {
-    errno= 0;					/* Linux, Windows don't reset this on EOF/success */
+    errno= 0;                                   /* Linux, Windows don't reset this on EOF/success */
 #ifdef _WIN32
     readbytes= my_win_read(Filedes, Buffer, Count);
 #else
@@ -61,47 +60,52 @@ size_t my_read(File Filedes, uchar *Buffer, size_t Count, myf MyFlags)
 
     if (readbytes != Count)
     {
-      my_errno= errno;
-      if (errno == 0 || (readbytes != (size_t) -1 &&
-                         (MyFlags & (MY_NABP | MY_FNABP))))
-        my_errno= HA_ERR_FILE_TOO_SHORT;
+      int got_errno= my_errno= errno;
       DBUG_PRINT("warning",("Read only %d bytes off %lu from %d, errno: %d",
                             (int) readbytes, (ulong) Count, Filedes,
-                            my_errno));
+                            got_errno));
+
+      if (got_errno == 0 || (readbytes != (size_t) -1 &&
+                         (MyFlags & (MY_NABP | MY_FNABP))))
+        my_errno= HA_ERR_FILE_TOO_SHORT;
 
-      if ((readbytes == 0 || (int) readbytes == -1) && errno == EINTR)
-      {  
+      if ((readbytes == 0 || (int) readbytes == -1) && got_errno == EINTR)
+      {
         DBUG_PRINT("debug", ("my_read() was interrupted and returned %ld",
                              (long) readbytes));
         continue;                              /* Interrupted */
       }
 
+      /* Do a read retry if we didn't get enough data on first read */
+      if (readbytes != (size_t) -1 && readbytes != 0 &&
+          (MyFlags & MY_FULL_IO))
+      {
+        Buffer+= readbytes;
+        Count-= readbytes;
+        save_count+= readbytes;
+        continue;
+      }
+
       if (MyFlags & (MY_WME | MY_FAE | MY_FNABP))
       {
         if (readbytes == (size_t) -1)
           my_error(EE_READ,
                    MYF(ME_BELL | ME_WAITTANG | (MyFlags & (ME_JUST_INFO | ME_NOREFRESH))),
-                   my_filename(Filedes),my_errno);
+                   my_filename(Filedes), got_errno);
         else if (MyFlags & (MY_NABP | MY_FNABP))
           my_error(EE_EOFERR,
                    MYF(ME_BELL | ME_WAITTANG | (MyFlags & (ME_JUST_INFO | ME_NOREFRESH))),
-                   my_filename(Filedes),my_errno);
+                   my_filename(Filedes), got_errno);
       }
       if (readbytes == (size_t) -1 ||
           ((MyFlags & (MY_FNABP | MY_NABP)) && !(MyFlags & MY_FULL_IO)))
-        DBUG_RETURN(MY_FILE_ERROR);	/* Return with error */
-      if (readbytes != (size_t) -1 && (MyFlags & MY_FULL_IO))
-      {
-        Buffer+= readbytes;
-        Count-= readbytes;
-        continue;
-      }
+        DBUG_RETURN(MY_FILE_ERROR);     /* Return with error */
     }
 
     if (MyFlags & (MY_NABP | MY_FNABP))
-      readbytes= 0;			/* Ok on read */
-    else if (MyFlags & MY_FULL_IO)
-      readbytes= save_count;
+      readbytes= 0;                     /* Ok on read */
+    else
+      readbytes+= save_count;
     break;
   }
   DBUG_RETURN(readbytes);