nbtinsert.c 44.5 KB
Newer Older
1 2 3 4 5 6 7 8 9
/*-------------------------------------------------------------------------
 *
 * btinsert.c--
 *    Item insertion in Lehman and Yao btrees for Postgres.
 *
 * Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
10
 *    $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtinsert.c,v 1.13 1997/05/30 18:35:31 vadim Exp $
11 12 13 14
 *
 *-------------------------------------------------------------------------
 */

Marc G. Fournier's avatar
Marc G. Fournier committed
15
#include <postgres.h>
16

Marc G. Fournier's avatar
Marc G. Fournier committed
17 18 19
#include <utils/memutils.h>
#include <storage/bufpage.h>
#include <access/nbtree.h>
20
#include <access/heapam.h>
Marc G. Fournier's avatar
Marc G. Fournier committed
21
#include <storage/bufmgr.h>
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
22
#include <fmgr.h>
Marc G. Fournier's avatar
Marc G. Fournier committed
23

24
#ifndef HAVE_MEMMOVE
Marc G. Fournier's avatar
Marc G. Fournier committed
25
# include <regex/utils.h>
26 27 28 29
#else
# include <string.h>
#endif

30
static InsertIndexResult _bt_insertonpg(Relation rel, Buffer buf, BTStack stack, int keysz, ScanKey scankey, BTItem btitem, BTItem afteritem);
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
31
static Buffer _bt_split(Relation rel, Buffer buf, BTItem hiRightItem);
32 33 34 35
static OffsetNumber _bt_findsplitloc(Relation rel, Page page, OffsetNumber start, OffsetNumber maxoff, Size llimit);
static void _bt_newroot(Relation rel, Buffer lbuf, Buffer rbuf);
static OffsetNumber _bt_pgaddtup(Relation rel, Buffer buf, int keysz, ScanKey itup_scankey, Size itemsize, BTItem btitem, BTItem afteritem);
static bool _bt_goesonpg(Relation rel, Buffer buf, Size keysz, ScanKey scankey, BTItem afteritem);
36
static void _bt_updateitem(Relation rel, Size keysz, Buffer buf, BTItem oldItem, BTItem newItem);
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
37
static bool _bt_isequal (TupleDesc itupdesc, Page page, OffsetNumber offnum, int keysz, ScanKey scankey);
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
38
static InsertIndexResult _bt_shift (Relation rel, Buffer buf, BTStack stack, int keysz, ScanKey scankey, BTItem btitem, BTItem hikey);
39 40 41 42 43 44 45 46 47

/*
 *  _bt_doinsert() -- Handle insertion of a single btitem in the tree.
 *
 *	This routine is called by the public interface routines, btbuild
 *	and btinsert.  By here, btitem is filled in, and has a unique
 *	(xid, seqno) pair.
 */
InsertIndexResult
48
_bt_doinsert(Relation rel, BTItem btitem, bool index_is_unique, Relation heapRel)
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
{
    ScanKey itup_scankey;
    IndexTuple itup;
    BTStack stack;
    Buffer buf;
    BlockNumber blkno;
    int natts;
    InsertIndexResult res;
    
    itup = &(btitem->bti_itup);
    
    /* we need a scan key to do our search, so build one */
    itup_scankey = _bt_mkscankey(rel, itup);
    natts = rel->rd_rel->relnatts;
    
    /* find the page containing this key */
    stack = _bt_search(rel, natts, itup_scankey, &buf);
66

67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
    blkno = BufferGetBlockNumber(buf);
    
    /* trade in our read lock for a write lock */
    _bt_relbuf(rel, buf, BT_READ);
    buf = _bt_getbuf(rel, blkno, BT_WRITE);
    
    /*
     *  If the page was split between the time that we surrendered our
     *  read lock and acquired our write lock, then this page may no
     *  longer be the right place for the key we want to insert.  In this
     *  case, we need to move right in the tree.  See Lehman and Yao for
     *  an excruciatingly precise description.
     */
    
    buf = _bt_moveright(rel, buf, natts, itup_scankey, BT_WRITE);
82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109

    /* if we're not allowing duplicates, make sure the key isn't */
    /* already in the node */
    if ( index_is_unique )
    {
	OffsetNumber offset, maxoff;
	Page page;

	page = BufferGetPage(buf);
	maxoff = PageGetMaxOffsetNumber (page);

	offset = _bt_binsrch(rel, buf, natts, itup_scankey, BT_DESCENT);

	/* make sure the offset we're given points to an actual */
	/* key on the page before trying to compare it */
	if ( !PageIsEmpty (page) && offset <= maxoff )
	{
	    TupleDesc itupdesc;
	    BTItem btitem;
	    IndexTuple itup;
	    HeapTuple htup;
	    BTPageOpaque opaque;
	    Buffer nbuf;
	    BlockNumber blkno;
	    
	    itupdesc = RelationGetTupleDescriptor(rel);
	    nbuf = InvalidBuffer;
	    opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
110 111 112 113 114 115
	    /*
	     * _bt_compare returns 0 for (1,NULL) and (1,NULL) -
	     * this's how we handling NULLs - and so we must not use
	     * _bt_compare in real comparison, but only for
	     * ordering/finding items on pages.	- vadim 03/24/97

116 117
	    while ( !_bt_compare (rel, itupdesc, page, 
			    	natts, itup_scankey, offset) )
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
118 119
	     */
	    while ( _bt_isequal (itupdesc, page, offset, natts, itup_scankey) )
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
	    {	/* they're equal */
		btitem = (BTItem) PageGetItem(page, PageGetItemId(page, offset));
		itup = &(btitem->bti_itup);
		htup = heap_fetch (heapRel, SelfTimeQual, &(itup->t_tid), NULL);
		if ( htup != (HeapTuple) NULL )
		{	/* it is a duplicate */
		    elog(WARN, "Cannot insert a duplicate key into a unique index.");
		}
	    	/* get next offnum */
	    	if ( offset < maxoff )
	    	{
	    	    offset = OffsetNumberNext(offset);
	    	}
	    	else
	    	{	/* move right ? */
		    if ( P_RIGHTMOST (opaque) )
		    	break;
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
137 138
	    	    if ( !_bt_isequal (itupdesc, page, P_HIKEY, 
	    	    				natts, itup_scankey) )
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174
			break;
		    /* 
		     * min key of the right page is the same,
		     * ooh - so many dead duplicates...
		     */
		    blkno = opaque->btpo_next;
		    if ( nbuf != InvalidBuffer )
		    	_bt_relbuf (rel, nbuf, BT_READ);
		    for (nbuf = InvalidBuffer; ; )
		    {
		    	nbuf = _bt_getbuf (rel, blkno, BT_READ);
		    	page = BufferGetPage (nbuf);
		    	maxoff = PageGetMaxOffsetNumber(page);
		    	opaque = (BTPageOpaque) PageGetSpecialPointer(page);
		    	offset = P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY;
		    	if ( ! PageIsEmpty (page) && offset <= maxoff )
		    	{	/* Found some key */
			    break;
			}
			else
			{	/* Empty or "pseudo"-empty page - get next */
			    blkno = opaque->btpo_next;
		    	    _bt_relbuf (rel, nbuf, BT_READ);
		    	    nbuf = InvalidBuffer;
		    	    if ( blkno == P_NONE )
		    	    	break;
			}
		    }
		    if ( nbuf == InvalidBuffer )
		    	break;
	    	}
	    }
	    if ( nbuf != InvalidBuffer )
		_bt_relbuf(rel, nbuf, BT_READ);
	}
    }
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229
    
    /* do the insertion */
    res = _bt_insertonpg(rel, buf, stack, natts, itup_scankey,
			 btitem, (BTItem) NULL);
    
    /* be tidy */
    _bt_freestack(stack);
    _bt_freeskey(itup_scankey);
    
    return (res);
}

/*
 *  _bt_insertonpg() -- Insert a tuple on a particular page in the index.
 *
 *	This recursive procedure does the following things:
 *
 *	    +  if necessary, splits the target page.
 *	    +  finds the right place to insert the tuple (taking into
 *	       account any changes induced by a split).
 *	    +  inserts the tuple.
 *	    +  if the page was split, pops the parent stack, and finds the
 *	       right place to insert the new child pointer (by walking
 *	       right using information stored in the parent stack).
 *	    +  invoking itself with the appropriate tuple for the right
 *	       child page on the parent.
 *
 *	On entry, we must have the right buffer on which to do the
 *	insertion, and the buffer must be pinned and locked.  On return,
 *	we will have dropped both the pin and the write lock on the buffer.
 *
 *	The locking interactions in this code are critical.  You should
 *	grok Lehman and Yao's paper before making any changes.  In addition,
 *	you need to understand how we disambiguate duplicate keys in this
 *	implementation, in order to be able to find our location using
 *	L&Y "move right" operations.  Since we may insert duplicate user
 *	keys, and since these dups may propogate up the tree, we use the
 *	'afteritem' parameter to position ourselves correctly for the
 *	insertion on internal pages.
 */
static InsertIndexResult
_bt_insertonpg(Relation rel,
	       Buffer buf,
	       BTStack stack,
	       int keysz,
	       ScanKey scankey,
	       BTItem btitem,
	       BTItem afteritem)
{
    InsertIndexResult res;
    Page page;
    Buffer rbuf;
    Buffer pbuf;
    Page rpage;
    BTItem ritem;
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
230
    BTPageOpaque lpageop;
231 232 233 234
    BTPageOpaque rpageop;
    BlockNumber rbknum, itup_blkno;
    OffsetNumber itup_off;
    int itemsz;
235 236
    Page ppage;
    BTPageOpaque ppageop;
237 238
    
    page = BufferGetPage(buf);
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
239 240
    lpageop = (BTPageOpaque) PageGetSpecialPointer(page);

241 242 243 244 245
    itemsz = IndexTupleDSize(btitem->bti_itup)
	+ (sizeof(BTItemData) - sizeof(IndexTupleData));

    itemsz = DOUBLEALIGN(itemsz);	/* be safe, PageAddItem will do this
					   but we need to be consistent */
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280
    /*
     * If we have to insert item on the leftmost page which is the first
     * page in the chain of duplicates then:
     * 1. if scankey == hikey (i.e. - new duplicate item) then
     *    insert it here;
     * 2. if scankey < hikey then we grab new page, copy current page
     *    content there and insert new item on the current page.
     */
    if ( lpageop->btpo_flags & BTP_CHAIN )
    {
    	OffsetNumber maxoff = PageGetMaxOffsetNumber (page);
    	ItemId hitemid;
    	BTItem hitem;
    	
	Assert ( !P_RIGHTMOST(lpageop) );
	hitemid = PageGetItemId(page, P_HIKEY);
	hitem = (BTItem) PageGetItem(page, hitemid);
    	if ( maxoff > P_HIKEY && 
    		!_bt_itemcmp (rel, keysz, hitem, 
    		   (BTItem) PageGetItem(page, PageGetItemId(page, P_FIRSTKEY)),
    	    		    BTEqualStrategyNumber) )
	    elog (FATAL, "btree: bad key on the page in the chain of duplicates");

    	if ( !_bt_skeycmp (rel, keysz, scankey, page, hitemid, 
    	    				BTEqualStrategyNumber) )
	{
    	    if ( !P_LEFTMOST(lpageop) )
	    	elog (FATAL, "btree: attempt to insert bad key on the non-leftmost page in the chain of duplicates");
    	    if ( !_bt_skeycmp (rel, keysz, scankey, page, hitemid, 
    	    				BTLessStrategyNumber) )
	    	elog (FATAL, "btree: attempt to insert higher key on the leftmost page in the chain of duplicates");
	    return (_bt_shift(rel, buf, stack, keysz, scankey, btitem, hitem));
	}
    }

281
    
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368
    if (PageGetFreeSpace(page) < itemsz)
    {
    	BlockNumber bknum = BufferGetBlockNumber(buf);
    	BTItem lowLeftItem;
    	BTItem hiRightItem = NULL;
	
	/* 
	 * If we have to split leaf page in the chain of duplicates
	 * then we try to move righter to avoid splitting.
	 */
	if ( ( lpageop->btpo_flags & BTP_CHAIN ) &&
			( lpageop->btpo_flags & BTP_LEAF ) )
	{
    	    bool use_left = true;
    		
    	    for ( ; ; )
    	    {
    		bool keys_equal = false;
    		    
	    	rbuf = _bt_getbuf(rel, lpageop->btpo_next, BT_WRITE);
	    	rpage = BufferGetPage(rbuf);
	    	rpageop = (BTPageOpaque) PageGetSpecialPointer(rpage);
	    	if ( P_RIGHTMOST (rpageop) )
	    	{
	    	    Assert ( !( rpageop->btpo_flags & BTP_CHAIN ) );
	    	    use_left = false;
	    	    break;
	    	}
	    	/*
	    	 * If we have the same hikey here then it's
	    	 * yet another page in chain and we may move
	    	 * even righter.
	    	 */
    	    	if ( _bt_skeycmp (rel, keysz, scankey, rpage, 
    	    				PageGetItemId(rpage, P_HIKEY), 
    	    				BTEqualStrategyNumber) )
    	    	{
    	    	    if ( !( rpageop->btpo_flags & BTP_CHAIN ) )
    	    	    	elog (FATAL, "btree: lost page in the chain of duplicates");
    	    	    keys_equal = true;
    	    	}
    	    	else if ( _bt_skeycmp (rel, keysz, scankey, rpage, 
    	    				PageGetItemId(rpage, P_HIKEY), 
    	    				BTGreaterStrategyNumber) )
    	    	    elog (FATAL, "btree: hikey is out of order");
	    	/*
	    	 * If hikey > scankey and BTP_CHAIN is ON 
	    	 * then it's first page of the chain of higher keys:
	    	 * our left sibling hikey was lying! We can't add new 
	    	 * item here, but we can turn BTP_CHAIN off on our
	    	 * left page and overwrite its hikey.
	    	 */
	    	if ( !keys_equal && ( rpageop->btpo_flags & BTP_CHAIN ) )
	    	{
    		    BTItem tmp;
    		    
	    	    lpageop->btpo_flags &= ~BTP_CHAIN;
	    	    tmp = (BTItem) PageGetItem(rpage, 
	    	    			PageGetItemId(rpage, P_HIKEY));
	    	    hiRightItem = _bt_formitem(&(tmp->bti_itup));
    	    	    break;
    	    	}
	    	/* 
	    	 * if there is room here or hikey > scankey (so it's our
	    	 * last page in the chain and we can't move righter) 
	    	 * we have to use this page .
	    	 */
	    	if ( PageGetFreeSpace (rpage) > itemsz || !keys_equal )
	    	{
	    	    use_left = false;
	    	    break;
	    	}
	    	/* try to move righter */
	    	_bt_relbuf(rel, buf, BT_WRITE);
	    	buf = rbuf;
	    	page = rpage;
	    	lpageop = rpageop;
	    }
	    if ( !use_left )	/* insert on the right page */
	    {
	    	_bt_relbuf(rel, buf, BT_WRITE);
		return ( _bt_insertonpg(rel, rbuf, stack, keysz, 
		    			scankey, btitem, afteritem) );
	    }
	    _bt_relbuf(rel, rbuf, BT_WRITE);
    	    bknum = BufferGetBlockNumber(buf);
	}
369 370
	
	/* split the buffer into left and right halves */
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
371 372 373 374
	rbuf = _bt_split(rel, buf, hiRightItem);
	
	if ( hiRightItem != (BTItem) NULL )
	    pfree (hiRightItem);
375 376 377 378 379 380 381 382 383 384 385 386 387 388
	
	/* which new page (left half or right half) gets the tuple? */
	if (_bt_goesonpg(rel, buf, keysz, scankey, afteritem)) {
	    /* left page */
	    itup_off = _bt_pgaddtup(rel, buf, keysz, scankey,
				    itemsz, btitem, afteritem);
	    itup_blkno = BufferGetBlockNumber(buf);
	} else {
	    /* right page */
	    itup_off = _bt_pgaddtup(rel, rbuf, keysz, scankey,
				    itemsz, btitem, afteritem);
	    itup_blkno = BufferGetBlockNumber(rbuf);
	}
	
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
389 390 391 392 393 394 395 396
	lowLeftItem = (BTItem) PageGetItem(page,
					 PageGetItemId(page, P_FIRSTKEY));
	
    	if ( _bt_itemcmp (rel, keysz, lowLeftItem, 
	    	(BTItem) PageGetItem(page, PageGetItemId(page, P_HIKEY)), 
	    			BTEqualStrategyNumber) ) 
	    lpageop->btpo_flags |= BTP_CHAIN;

397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
	/*
	 *  By here,
	 *
	 *	+  our target page has been split;
	 *	+  the original tuple has been inserted;
	 *	+  we have write locks on both the old (left half) and new
	 *	   (right half) buffers, after the split; and
	 *	+  we have the key we want to insert into the parent.
	 *
	 *  Do the parent insertion.  We need to hold onto the locks for
	 *  the child pages until we locate the parent, but we can release
	 *  them before doing the actual insertion (see Lehman and Yao for
	 *  the reasoning).
	 */
	
	if (stack == (BTStack) NULL) {
	    
	    /* create a new root node and release the split buffers */
	    _bt_newroot(rel, buf, rbuf);
	    _bt_relbuf(rel, buf, BT_WRITE);
	    _bt_relbuf(rel, rbuf, BT_WRITE);
	    
	} else {
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
420 421 422 423 424
    	    ScanKey newskey;
    	    InsertIndexResult newres;
    	    BTItem new_item;
    	    OffsetNumber upditem_offset = P_HIKEY;
    	    bool do_update = false;
425 426 427 428 429 430 431

	    /* form a index tuple that points at the new right page */
	    rbknum = BufferGetBlockNumber(rbuf);
	    rpage = BufferGetPage(rbuf);
	    rpageop = (BTPageOpaque) PageGetSpecialPointer(rpage);
	    
	    /*
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
432
	     *  By convention, the first entry (1) on every
433 434
	     *  non-rightmost page is the high key for that page.  In
	     *  order to get the lowest key on the new right page, we
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
435
	     *  actually look at its second (2) entry.
436 437
	     */
	    
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
438 439
	    if (! P_RIGHTMOST(rpageop))
	    {
440 441
		ritem = (BTItem) PageGetItem(rpage,
					     PageGetItemId(rpage, P_FIRSTKEY));
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
442 443 444 445 446 447 448
    		if ( _bt_itemcmp (rel, keysz, ritem, 
	    		(BTItem) PageGetItem(rpage, 
	    				PageGetItemId(rpage, P_HIKEY)), 
	    			BTEqualStrategyNumber) ) 
	    	rpageop->btpo_flags |= BTP_CHAIN;
	    }
	    else
449 450 451 452 453 454 455 456
		ritem = (BTItem) PageGetItem(rpage,
					     PageGetItemId(rpage, P_HIKEY));
	    
	    /* get a unique btitem for this key */
	    new_item = _bt_formitem(&(ritem->bti_itup));
	    
	    ItemPointerSet(&(new_item->bti_itup.t_tid), rbknum, P_HIKEY);
	    
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
457 458 459 460 461 462 463 464 465
	    /* 
	     * Find the parent buffer and get the parent page.
	     *
	     * Oops - if we were moved right then we need to
	     * change stack item! We want to find parent pointing to
	     * where we are, right ?	- vadim 05/27/97
	     */
	    ItemPointerSet(&(stack->bts_btitem->bti_itup.t_tid), 
			       bknum, P_HIKEY);
466
	    pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
467 468
	    ppage = BufferGetPage(pbuf);
	    ppageop = (BTPageOpaque) PageGetSpecialPointer(ppage);
469 470 471 472 473 474 475 476 477 478 479 480 481 482 483
	    
	    /*
	     *  If the key of new_item is < than the key of the item
	     *  in the parent page pointing to the left page
	     *  (stack->bts_btitem), we have to update the latter key;
	     *  otherwise the keys on the parent page wouldn't be
	     *  monotonically increasing after we inserted the new
	     *  pointer to the right page (new_item). This only
	     *  happens if our left page is the leftmost page and a
	     *  new minimum key had been inserted before, which is not
	     *  reflected in the parent page but didn't matter so
	     *  far. If there are duplicate keys and this new minimum
	     *  key spills over to our new right page, we get an
	     *  inconsistency if we don't update the left key in the
	     *  parent page.
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
484 485 486 487 488
	     *
	     *  Also, new duplicates handling code require us to update
	     *  parent item if some smaller items left on the left page 
	     *  (which is possible in splitting leftmost page) and 
	     *  current parent item == new_item.	- vadim 05/27/97
489
	     */
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
490 491 492 493 494 495 496 497
	    if ( _bt_itemcmp (rel, keysz, stack->bts_btitem, new_item,
	                    			BTGreaterStrategyNumber) ||
	    		( _bt_itemcmp(rel, keysz, stack->bts_btitem, 
	    				new_item, BTEqualStrategyNumber) &&
	    		  _bt_itemcmp(rel, keysz, lowLeftItem, 
	    				new_item, BTLessStrategyNumber) ) )
	    {
	        do_update = true;
498
		/* 
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
499 500
		 * figure out which key is leftmost (if the parent page
		 * is rightmost, too, it must be the root)
501
		 */
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536
		if(P_RIGHTMOST(ppageop))
		    upditem_offset = P_HIKEY;
		else
		    upditem_offset = P_FIRSTKEY;
		if ( !P_LEFTMOST(lpageop) || 
			stack->bts_offset != upditem_offset )
		    elog (FATAL, "btree: items are out of order");
	    }
	    /*
	     * There was bug caused by deletion all minimum keys (K1) from 
	     * an index page and insertion there (up to page splitting) 
	     * higher duplicate keys (K2): after it parent item for left
	     * page contained K1 and the next item (for new right page) - K2, 
	     * - and scan for the key = K2 lost items on the left page.
	     * So, we have to update parent item if its key < minimum
	     * key on the left and minimum keys on the left and on the right
	     * are equal. It would be nice to update hikey on the previous
	     * page of the left one too, but we may get deadlock here
	     * (read comments in _bt_split), so we leave previous page
	     * hikey _inconsistent_, but there should to be BTP_CHAIN flag
	     * on it, which privents _bt_moveright from dangerous movings 
	     * from there.	- vadim 05/27/97
	     */
	    else if ( _bt_itemcmp (rel, keysz, stack->bts_btitem, 
	    				lowLeftItem, BTLessStrategyNumber) && 
	    		_bt_itemcmp (rel, keysz, new_item, 
	    				lowLeftItem, BTEqualStrategyNumber) ) 
	    {
	        do_update = true;
	        upditem_offset = stack->bts_offset;
	    }
	    
	    if ( do_update )
	    {
		/* Try to update in place. */
537 538 539 540
	    	if ( DOUBLEALIGN (IndexTupleDSize (lowLeftItem->bti_itup)) ==
       			DOUBLEALIGN (IndexTupleDSize (stack->bts_btitem->bti_itup)) ) 
       		{
		    _bt_updateitem(rel, keysz, pbuf, 
541
		    		stack->bts_btitem, lowLeftItem);
542 543 544 545 546
		    _bt_relbuf(rel, buf, BT_WRITE);
		    _bt_relbuf(rel, rbuf, BT_WRITE);
		}
		else
		{
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
547
       		    PageIndexTupleDelete(ppage, upditem_offset);
548
		
549 550 551
		   /* 
		    * don't write anything out yet--we still have the write
		    * lock, and now we call another _bt_insertonpg to
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
552 553 554 555
		    * insert the correct key.
		    * First, make a new item, using the tuple data from
		    * lowLeftItem. Point it to the left child.
		    * Update it on the stack at the same time.
556 557 558 559
		    */
		    pfree(stack->bts_btitem);
		    stack->bts_btitem = _bt_formitem(&(lowLeftItem->bti_itup));
		    ItemPointerSet(&(stack->bts_btitem->bti_itup.t_tid), 
560 561
			       bknum, P_HIKEY);
		
562 563 564
		    /* unlock the children before doing this */
		    _bt_relbuf(rel, buf, BT_WRITE);
		    _bt_relbuf(rel, rbuf, BT_WRITE);
565
		
566
		    /* 
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
567 568 569 570
		     * A regular _bt_binsrch should find the right place to
		     * put the new entry, since it should be either lower 
		     * than any other key on the page or unique. 
		     * Therefore set afteritem to NULL.
571 572 573
		     */
		    newskey = _bt_mkscankey(rel, &(stack->bts_btitem->bti_itup));
		    newres = _bt_insertonpg(rel, pbuf, stack->bts_parent,
574 575 576
					keysz, newskey, stack->bts_btitem,
					NULL);

577 578
		    pfree(newres);
		    pfree(newskey);
579
	    
580 581 582 583 584 585 586 587 588 589 590
		    /* 
		     * we have now lost our lock on the parent buffer, and
		     * need to get it back.
		     */
		    pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
		}
	    }
	    else
	    {
	    	_bt_relbuf(rel, buf, BT_WRITE);
	    	_bt_relbuf(rel, rbuf, BT_WRITE);
591
	    }
592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625
	    
	    newskey = _bt_mkscankey(rel, &(new_item->bti_itup));
	    newres = _bt_insertonpg(rel, pbuf, stack->bts_parent,
				    keysz, newskey, new_item,
				    stack->bts_btitem);
	    
	    /* be tidy */
	    pfree(newres);
	    pfree(newskey);
	    pfree(new_item);
	}
    } else {
	itup_off = _bt_pgaddtup(rel, buf, keysz, scankey,
				itemsz, btitem, afteritem);
	itup_blkno = BufferGetBlockNumber(buf);
	
	_bt_relbuf(rel, buf, BT_WRITE);
    }
    
    /* by here, the new tuple is inserted */
    res = (InsertIndexResult) palloc(sizeof(InsertIndexResultData));
    ItemPointerSet(&(res->pointerData), itup_blkno, itup_off);
    
    return (res);
}

/*
 *  _bt_split() -- split a page in the btree.
 *
 *	On entry, buf is the page to split, and is write-locked and pinned.
 *	Returns the new right sibling of buf, pinned and write-locked.  The
 *	pin and lock on buf are maintained.
 */
static Buffer
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
626
_bt_split(Relation rel, Buffer buf, BTItem hiRightItem)
627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659
{
    Buffer rbuf;
    Page origpage;
    Page leftpage, rightpage;
    BTPageOpaque ropaque, lopaque, oopaque;
    Buffer sbuf;
    Page spage;
    BTPageOpaque sopaque;
    Size itemsz;
    ItemId itemid;
    BTItem item;
    OffsetNumber leftoff, rightoff;
    OffsetNumber start;
    OffsetNumber maxoff;
    OffsetNumber firstright;
    OffsetNumber i;
    Size llimit;
    
    rbuf = _bt_getbuf(rel, P_NEW, BT_WRITE);
    origpage = BufferGetPage(buf);
    leftpage = PageGetTempPage(origpage, sizeof(BTPageOpaqueData));
    rightpage = BufferGetPage(rbuf);
    
    _bt_pageinit(rightpage, BufferGetPageSize(rbuf));
    _bt_pageinit(leftpage, BufferGetPageSize(buf));
    
    /* init btree private data */
    oopaque = (BTPageOpaque) PageGetSpecialPointer(origpage);
    lopaque = (BTPageOpaque) PageGetSpecialPointer(leftpage);
    ropaque = (BTPageOpaque) PageGetSpecialPointer(rightpage);
    
    /* if we're splitting this page, it won't be the root when we're done */
    oopaque->btpo_flags &= ~BTP_ROOT;
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
660
    oopaque->btpo_flags &= ~BTP_CHAIN;
661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684
    lopaque->btpo_flags = ropaque->btpo_flags = oopaque->btpo_flags;
    lopaque->btpo_prev = oopaque->btpo_prev;
    ropaque->btpo_prev = BufferGetBlockNumber(buf);
    lopaque->btpo_next = BufferGetBlockNumber(rbuf);
    ropaque->btpo_next = oopaque->btpo_next;
    
    /*
     *  If the page we're splitting is not the rightmost page at its
     *  level in the tree, then the first (0) entry on the page is the
     *  high key for the page.  We need to copy that to the right
     *  half.  Otherwise (meaning the rightmost page case), we should
     *  treat the line pointers beginning at zero as user data.
     *
     *  We leave a blank space at the start of the line table for the
     *  left page.  We'll come back later and fill it in with the high
     *  key item we get from the right key.
     */
    
    leftoff = P_FIRSTKEY;
    ropaque->btpo_next = oopaque->btpo_next;
    if (! P_RIGHTMOST(oopaque)) {
	/* splitting a non-rightmost page, start at the first data item */
	start = P_FIRSTKEY;

Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701
	/* 
	 * Copy the original high key to the new page if high key
	 * was not passed by caller.
	 */
	if ( hiRightItem == NULL )
	{
	    itemid = PageGetItemId(origpage, P_HIKEY);
	    itemsz = ItemIdGetLength(itemid);
	    item = (BTItem) PageGetItem(origpage, itemid);
	}
	else
	{
	    item = hiRightItem;
    	    itemsz = IndexTupleDSize(hiRightItem->bti_itup)
			+ (sizeof(BTItemData) - sizeof(IndexTupleData));
    	    itemsz = DOUBLEALIGN(itemsz);
	}
702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843
	(void) PageAddItem(rightpage, (Item) item, itemsz, P_HIKEY, LP_USED);
	rightoff = P_FIRSTKEY;
    } else {
	/* splitting a rightmost page, "high key" is the first data item */
	start = P_HIKEY;

	/* the new rightmost page will not have a high key */
	rightoff = P_HIKEY;
    }
    maxoff = PageGetMaxOffsetNumber(origpage);
    llimit = PageGetFreeSpace(leftpage) / 2;
    firstright = _bt_findsplitloc(rel, origpage, start, maxoff, llimit);
    
    for (i = start; i <= maxoff; i = OffsetNumberNext(i)) {
	itemid = PageGetItemId(origpage, i);
	itemsz = ItemIdGetLength(itemid);
	item = (BTItem) PageGetItem(origpage, itemid);
	
	/* decide which page to put it on */
	if (i < firstright) {
	    (void) PageAddItem(leftpage, (Item) item, itemsz, leftoff,
			       LP_USED);
	    leftoff = OffsetNumberNext(leftoff);
	} else {
	    (void) PageAddItem(rightpage, (Item) item, itemsz, rightoff,
			       LP_USED);
	    rightoff = OffsetNumberNext(rightoff);
	}
    }
    
    /*
     *  Okay, page has been split, high key on right page is correct.  Now
     *  set the high key on the left page to be the min key on the right
     *  page.
     */
    
    if (P_RIGHTMOST(ropaque)) {
	itemid = PageGetItemId(rightpage, P_HIKEY);
    } else {
	itemid = PageGetItemId(rightpage, P_FIRSTKEY);
    }
    itemsz = ItemIdGetLength(itemid);
    item = (BTItem) PageGetItem(rightpage, itemid);
    
    /*
     *  We left a hole for the high key on the left page; fill it.  The
     *  modal crap is to tell the page manager to put the new item on the
     *  page and not screw around with anything else.  Whoever designed
     *  this interface has presumably crawled back into the dung heap they
     *  came from.  No one here will admit to it.
     */
    
    PageManagerModeSet(OverwritePageManagerMode);
    (void) PageAddItem(leftpage, (Item) item, itemsz, P_HIKEY, LP_USED);
    PageManagerModeSet(ShufflePageManagerMode);
    
    /*
     *  By here, the original data page has been split into two new halves,
     *  and these are correct.  The algorithm requires that the left page
     *  never move during a split, so we copy the new left page back on top
     *  of the original.  Note that this is not a waste of time, since we
     *  also require (in the page management code) that the center of a
     *  page always be clean, and the most efficient way to guarantee this
     *  is just to compact the data by reinserting it into a new left page.
     */
    
    PageRestoreTempPage(leftpage, origpage);
    
    /* write these guys out */
    _bt_wrtnorelbuf(rel, rbuf);
    _bt_wrtnorelbuf(rel, buf);
    
    /*
     *  Finally, we need to grab the right sibling (if any) and fix the
     *  prev pointer there.  We are guaranteed that this is deadlock-free
     *  since no other writer will be moving holding a lock on that page
     *  and trying to move left, and all readers release locks on a page
     *  before trying to fetch its neighbors.
     */
    
    if (! P_RIGHTMOST(ropaque)) {
	sbuf = _bt_getbuf(rel, ropaque->btpo_next, BT_WRITE);
	spage = BufferGetPage(sbuf);
	sopaque = (BTPageOpaque) PageGetSpecialPointer(spage);
	sopaque->btpo_prev = BufferGetBlockNumber(rbuf);
	
	/* write and release the old right sibling */
	_bt_wrtbuf(rel, sbuf);
    }
    
    /* split's done */
    return (rbuf);
}

/*
 *  _bt_findsplitloc() -- find a safe place to split a page.
 *
 *	In order to guarantee the proper handling of searches for duplicate
 *	keys, the first duplicate in the chain must either be the first
 *	item on the page after the split, or the entire chain must be on
 *	one of the two pages.  That is,
 *		[1 2 2 2 3 4 5]
 *	must become
 *		[1] [2 2 2 3 4 5]
 *	or
 *		[1 2 2 2] [3 4 5]
 *	but not
 *		[1 2 2] [2 3 4 5].
 *	However,
 *		[2 2 2 2 2 3 4]
 *	may be split as
 *		[2 2 2 2] [2 3 4].
 */
static OffsetNumber
_bt_findsplitloc(Relation rel,
		 Page page,
		 OffsetNumber start,
		 OffsetNumber maxoff,
		 Size llimit)
{
    OffsetNumber i;
    OffsetNumber saferight;
    ItemId nxtitemid, safeitemid;
    BTItem safeitem, nxtitem;
    Size nbytes;
    int natts;
    
    natts = rel->rd_rel->relnatts;
    saferight = start;
    safeitemid = PageGetItemId(page, saferight);
    nbytes = ItemIdGetLength(safeitemid) + sizeof(ItemIdData);
    safeitem = (BTItem) PageGetItem(page, safeitemid);
    
    i = OffsetNumberNext(start);
    
    while (nbytes < llimit) {
	
	/* check the next item on the page */
	nxtitemid = PageGetItemId(page, i);
	nbytes += (ItemIdGetLength(nxtitemid) + sizeof(ItemIdData));
	nxtitem = (BTItem) PageGetItem(page, nxtitemid);

844 845 846 847 848 849 850 851 852 853
	/* 
	 * Test against last known safe item:
	 * if the tuple we're looking at isn't equal to the last safe 
	 * one we saw, then it's our new safe tuple.
	 */
	if ( !_bt_itemcmp (rel, natts, 
			safeitem, nxtitem, BTEqualStrategyNumber) )
	{
	    safeitem = nxtitem;
	    saferight = i;
854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916
	}
	i = OffsetNumberNext(i);
    }
    
    /*
     *  If the chain of dups starts at the beginning of the page and extends
     *  past the halfway mark, we can split it in the middle.
     */
    
    if (saferight == start)
	saferight = i;
    
    return (saferight);
}

/*
 *  _bt_newroot() -- Create a new root page for the index.
 *
 *	We've just split the old root page and need to create a new one.
 *	In order to do this, we add a new root page to the file, then lock
 *	the metadata page and update it.  This is guaranteed to be deadlock-
 *	free, because all readers release their locks on the metadata page
 *	before trying to lock the root, and all writers lock the root before
 *	trying to lock the metadata page.  We have a write lock on the old
 *	root page, so we have not introduced any cycles into the waits-for
 *	graph.
 *
 *	On entry, lbuf (the old root) and rbuf (its new peer) are write-
 *	locked.  We don't drop the locks in this routine; that's done by
 *	the caller.  On exit, a new root page exists with entries for the
 *	two new children.  The new root page is neither pinned nor locked.
 */
static void
_bt_newroot(Relation rel, Buffer lbuf, Buffer rbuf)
{
    Buffer rootbuf;
    Page lpage, rpage, rootpage;
    BlockNumber lbkno, rbkno;
    BlockNumber rootbknum;
    BTPageOpaque rootopaque;
    ItemId itemid;
    BTItem item;
    Size itemsz;
    BTItem new_item;
    
    /* get a new root page */
    rootbuf = _bt_getbuf(rel, P_NEW, BT_WRITE);
    rootpage = BufferGetPage(rootbuf);
    _bt_pageinit(rootpage, BufferGetPageSize(rootbuf));
    
    /* set btree special data */
    rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);
    rootopaque->btpo_prev = rootopaque->btpo_next = P_NONE;
    rootopaque->btpo_flags |= BTP_ROOT;
    
    /*
     *  Insert the internal tuple pointers.
     */
    
    lbkno = BufferGetBlockNumber(lbuf);
    rbkno = BufferGetBlockNumber(rbuf);
    lpage = BufferGetPage(lbuf);
    rpage = BufferGetPage(rbuf);
917

918 919 920 921 922 923 924 925
    /*
     * step over the high key on the left page while building the 
     * left page pointer.
     */
    itemid = PageGetItemId(lpage, P_FIRSTKEY);
    itemsz = ItemIdGetLength(itemid);
    item = (BTItem) PageGetItem(lpage, itemid);
    new_item = _bt_formitem(&(item->bti_itup));
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
926
    ItemPointerSet(&(new_item->bti_itup.t_tid), lbkno, P_HIKEY);
927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956
    
    /*
     * insert the left page pointer into the new root page.  the root
     * page is the rightmost page on its level so the "high key" item
     * is the first data item.
     */
    (void) PageAddItem(rootpage, (Item) new_item, itemsz, P_HIKEY, LP_USED);
    pfree(new_item);
    
    /*
     * the right page is the rightmost page on the second level, so 
     * the "high key" item is the first data item on that page as well.
     */
    itemid = PageGetItemId(rpage, P_HIKEY);
    itemsz = ItemIdGetLength(itemid);
    item = (BTItem) PageGetItem(rpage, itemid);
    new_item = _bt_formitem(&(item->bti_itup));
    ItemPointerSet(&(new_item->bti_itup.t_tid), rbkno, P_HIKEY);
    
    /*
     * insert the right page pointer into the new root page.
     */
    (void) PageAddItem(rootpage, (Item) new_item, itemsz, P_FIRSTKEY, LP_USED);
    pfree(new_item);
    
    /* write and let go of the root buffer */
    rootbknum = BufferGetBlockNumber(rootbuf);
    _bt_wrtbuf(rel, rootbuf);
    
    /* update metadata page with new root block number */
957
    _bt_metaproot(rel, rootbknum, 0);
958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997
}

/*
 *  _bt_pgaddtup() -- add a tuple to a particular page in the index.
 *
 *	This routine adds the tuple to the page as requested, and keeps the
 *	write lock and reference associated with the page's buffer.  It is
 *	an error to call pgaddtup() without a write lock and reference.  If
 *	afteritem is non-null, it's the item that we expect our new item
 *	to follow.  Otherwise, we do a binary search for the correct place
 *	and insert the new item there.
 */
static OffsetNumber
_bt_pgaddtup(Relation rel,
	     Buffer buf,
	     int keysz,
	     ScanKey itup_scankey,
	     Size itemsize,
	     BTItem btitem,
	     BTItem afteritem)
{
    OffsetNumber itup_off;
    OffsetNumber first;
    Page page;
    BTPageOpaque opaque;
    BTItem chkitem;
    
    page = BufferGetPage(buf);
    opaque = (BTPageOpaque) PageGetSpecialPointer(page);
    first = P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY;
    
    if (afteritem == (BTItem) NULL) {
	itup_off = _bt_binsrch(rel, buf, keysz, itup_scankey, BT_INSERTION);
    } else {
	itup_off = first;
	
	do {
	    chkitem =
		(BTItem) PageGetItem(page, PageGetItemId(page, itup_off));
	    itup_off = OffsetNumberNext(itup_off);
998
	} while ( ! BTItemSame (chkitem, afteritem) );
999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
    }

    (void) PageAddItem(page, (Item) btitem, itemsize, itup_off, LP_USED);
    
    /* write the buffer, but hold our lock */
    _bt_wrtnorelbuf(rel, buf);
    
    return (itup_off);
}

/*
 *  _bt_goesonpg() -- Does a new tuple belong on this page?
 *
 *	This is part of the complexity introduced by allowing duplicate
 *	keys into the index.  The tuple belongs on this page if:
 *
 *		+ there is no page to the right of this one; or
 *		+ it is less than the high key on the page; or
 *		+ the item it is to follow ("afteritem") appears on this
 *		  page.
 */
static bool
_bt_goesonpg(Relation rel,
	     Buffer buf,
	     Size keysz,
	     ScanKey scankey,
	     BTItem afteritem)
{
    Page page;
    ItemId hikey;
    BTPageOpaque opaque;
    BTItem chkitem;
    OffsetNumber offnum, maxoff;
    bool found;
    
    page = BufferGetPage(buf);
    
    /* no right neighbor? */
    opaque = (BTPageOpaque) PageGetSpecialPointer(page);
    if (P_RIGHTMOST(opaque))
	return (true);
    
    /*
     *  this is a non-rightmost page, so it must have a high key item.
     *
     *  If the scan key is < the high key (the min key on the next page),
     *  then it for sure belongs here.
     */
    hikey = PageGetItemId(page, P_HIKEY);
    if (_bt_skeycmp(rel, keysz, scankey, page, hikey, BTLessStrategyNumber))
	return (true);
    
    /*
     *  If the scan key is > the high key, then it for sure doesn't belong
     *  here.
     */
    
    if (_bt_skeycmp(rel, keysz, scankey, page, hikey, BTGreaterStrategyNumber))
	return (false);
    
    /*
     *  If we have no adjacency information, and the item is equal to the
     *  high key on the page (by here it is), then the item does not belong
     *  on this page.
     */
    
    if (afteritem == (BTItem) NULL)
	return (false);
    
    /* damn, have to work for it.  i hate that. */
    maxoff = PageGetMaxOffsetNumber(page);
    
    /*
     *  Search the entire page for the afteroid.  We need to do this, rather
     *  than doing a binary search and starting from there, because if the
     *  key we're searching for is the leftmost key in the tree at this
     *  level, then a binary search will do the wrong thing.  Splits are
     *  pretty infrequent, so the cost isn't as bad as it could be.
     */
    
    found = false;
    for (offnum = P_FIRSTKEY;
	 offnum <= maxoff;
	 offnum = OffsetNumberNext(offnum)) {
	chkitem = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
1084 1085

	if ( BTItemSame (chkitem, afteritem) ) {
1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109
	    found = true;
	    break;
	}
    }
    
    return (found);
}

/*
 *	_bt_itemcmp() -- compare item1 to item2 using a requested
 *		         strategy (<, <=, =, >=, >)
 *
 */
bool
_bt_itemcmp(Relation rel,
	    Size keysz,
	    BTItem item1,
	    BTItem item2,
	    StrategyNumber strat)
{
    TupleDesc tupDes;
    IndexTuple indexTuple1, indexTuple2;
    Datum attrDatum1, attrDatum2;
    int i;
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
1110
    bool isFirstNull, isSecondNull;
1111
    bool compare;
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
    bool useEqual = false;
    
    if ( strat == BTLessEqualStrategyNumber )
    {
	useEqual = true;
	strat = BTLessStrategyNumber;
    }
    else if ( strat == BTGreaterEqualStrategyNumber )
    {
	useEqual = true;
	strat = BTGreaterStrategyNumber;
    }
1124 1125 1126 1127 1128 1129
    
    tupDes = RelationGetTupleDescriptor(rel);
    indexTuple1 = &(item1->bti_itup);
    indexTuple2 = &(item2->bti_itup);
    
    for (i = 1; i <= keysz; i++) {
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
	attrDatum1 = index_getattr(indexTuple1, i, tupDes, &isFirstNull);
	attrDatum2 = index_getattr(indexTuple2, i, tupDes, &isSecondNull);
	
	/* see comments about NULLs handling in btbuild */
	if ( isFirstNull )	/* attr in item1 is NULL */
	{
    	    if ( isSecondNull )	/* attr in item2 is NULL too */
    	    	compare = ( strat == BTEqualStrategyNumber ) ? true : false;
    	    else
    	    	compare = ( strat == BTGreaterStrategyNumber ) ? true : false;
    	}
    	else if ( isSecondNull )	/* attr in item1 is NOT_NULL and */
    	{				/* and attr in item2 is NULL */
    	    compare = ( strat == BTLessStrategyNumber ) ? true : false;
    	}
    	else
    	{
	    compare = _bt_invokestrat(rel, i, strat, attrDatum1, attrDatum2);
	}
	
	if ( compare )	/* true for one of ">, <, =" */
	{
	    if ( strat != BTEqualStrategyNumber )
	    	return (true);
	}
	else		/* false for one of ">, <, =" */
	{
	    if ( strat == BTEqualStrategyNumber )
		return (false);
	    /*
	     * if original strat was "<=, >=" OR
	     * "<, >" but some attribute(s) left
	     * - need to test for Equality
	     */
	    if ( useEqual || i < keysz )
	    {
	    	if ( isFirstNull || isSecondNull )
	    	    compare = ( isFirstNull && isSecondNull ) ? true : false;
	    	else
		    compare = _bt_invokestrat(rel, i, BTEqualStrategyNumber, 
						attrDatum1, attrDatum2);
		if ( compare )	/* item1' and item2' attributes are equal */
		    continue;	/* - try to compare next attributes */
	    }
1174 1175 1176 1177 1178 1179 1180 1181
	    return (false);
	}
    }
    return (true);
}

/*
 *	_bt_updateitem() -- updates the key of the item identified by the
1182 1183
 *			    oid with the key of newItem (done in place if
 *			    possible)
1184 1185 1186 1187 1188 1189
 *
 */
static void
_bt_updateitem(Relation rel,
	       Size keysz,
	       Buffer buf,
1190
	       BTItem oldItem,
1191 1192 1193 1194 1195 1196
	       BTItem newItem)
{
    Page page;
    OffsetNumber maxoff;
    OffsetNumber i;
    ItemPointerData itemPtrData;
1197
    BTItem item;
1198
    IndexTuple oldIndexTuple, newIndexTuple;
1199
    int first;
1200 1201 1202 1203 1204
    
    page = BufferGetPage(buf);
    maxoff = PageGetMaxOffsetNumber(page);
    
    /* locate item on the page */
1205
    first = P_RIGHTMOST((BTPageOpaque) PageGetSpecialPointer(page))
1206 1207
        ? P_HIKEY : P_FIRSTKEY;
    i = first;
1208 1209 1210
    do {
	item = (BTItem) PageGetItem(page, PageGetItemId(page, i));
	i = OffsetNumberNext(i);
1211
    } while (i <= maxoff && ! BTItemSame (item, oldItem));
1212 1213
    
    /* this should never happen (in theory) */
1214
    if ( ! BTItemSame (item, oldItem) ) {
1215 1216 1217
	elog(FATAL, "_bt_getstackbuf was lying!!");
    }
    
1218 1219 1220 1221
    /*
     * It's  defined by caller (_bt_insertonpg)
     */
    /*
1222 1223 1224 1225 1226
    if(IndexTupleDSize(newItem->bti_itup) >
       IndexTupleDSize(item->bti_itup)) {
	elog(NOTICE, "trying to overwrite a smaller value with a bigger one in _bt_updateitem");
	elog(WARN, "this is not good.");
    }
1227
     */
1228

1229 1230
    oldIndexTuple = &(item->bti_itup);
    newIndexTuple = &(newItem->bti_itup);
1231 1232

	/* keep the original item pointer */
1233 1234 1235 1236
    ItemPointerCopy(&(oldIndexTuple->t_tid), &itemPtrData);
    CopyIndexTuple(newIndexTuple, &oldIndexTuple);
    ItemPointerCopy(&itemPtrData, &(oldIndexTuple->t_tid));
    
1237
}
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279

/*
 * _bt_isequal - used in _bt_doinsert in check for duplicates.
 *
 * Rule is simple: NOT_NULL not equal NULL, NULL not_equal NULL too.
 */
static bool
_bt_isequal (TupleDesc itupdesc, Page page, OffsetNumber offnum,
					int keysz, ScanKey scankey)
{
    Datum datum;
    BTItem btitem;
    IndexTuple itup;
    ScanKey entry;
    AttrNumber attno;
    long result;
    int i;
    bool null;
    
    btitem = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
    itup = &(btitem->bti_itup);
    
    for (i = 1; i <= keysz; i++)
    {
	entry = &scankey[i - 1];
	attno = entry->sk_attno;
	Assert (attno == i);
	datum = index_getattr(itup, attno, itupdesc, &null);

	/* NULLs are not equal */
	if ( entry->sk_flags & SK_ISNULL || null )
	    return (false);
	
	result = (long) FMGR_PTR2(entry->sk_func, entry->sk_procedure,
					entry->sk_argument, datum);
	if (result != 0)
	    return (false);
    }
    
    /* by here, the keys are equal */
    return (true);
}
Vadim B. Mikheev's avatar
Vadim B. Mikheev committed
1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413

/*
 * _bt_shift - insert btitem on the passed page after shifting page 
 *	       to the right in the tree.
 *
 * NOTE: tested for shifting leftmost page only, having btitem < hikey.
 */
static InsertIndexResult 
_bt_shift (Relation rel, Buffer buf, BTStack stack, int keysz, 
			ScanKey scankey, BTItem btitem, BTItem hikey)
{
    InsertIndexResult res;
    int itemsz;
    Page page;
    BlockNumber bknum;
    BTPageOpaque pageop;
    Buffer rbuf;
    Page rpage;
    BTPageOpaque rpageop;
    Buffer pbuf;
    Page ppage;
    BTPageOpaque ppageop;
    Buffer nbuf;
    Page npage;
    BTPageOpaque npageop;
    BlockNumber nbknum;
    BTItem nitem;
    OffsetNumber afteroff;
    
    btitem = _bt_formitem(&(btitem->bti_itup));
    hikey = _bt_formitem(&(hikey->bti_itup));

    page = BufferGetPage(buf);

    /* grab new page */
    nbuf = _bt_getbuf(rel, P_NEW, BT_WRITE);
    nbknum = BufferGetBlockNumber(nbuf);
    npage = BufferGetPage(nbuf);
    _bt_pageinit(npage, BufferGetPageSize(nbuf));
    npageop = (BTPageOpaque) PageGetSpecialPointer(npage);
    
    /* copy content of the passed page */
    memmove ((char *) npage, (char *) page, BufferGetPageSize(buf));
    
    /* re-init old (passed) page */
    _bt_pageinit(page, BufferGetPageSize(buf));
    pageop = (BTPageOpaque) PageGetSpecialPointer(page);

    /* init old page opaque */
    pageop->btpo_flags = npageop->btpo_flags;	/* restore flags */
    pageop->btpo_flags &= ~BTP_CHAIN;
    if ( _bt_itemcmp (rel, keysz, hikey, btitem, BTEqualStrategyNumber) ) 
	pageop->btpo_flags |= BTP_CHAIN;
    pageop->btpo_prev = npageop->btpo_prev;	/* restore prev */
    pageop->btpo_next = nbknum;			/* next points to the new page */

    /* init shifted page opaque */
    npageop->btpo_prev = bknum = BufferGetBlockNumber(buf);
    
    /* shifted page is ok, populate old page */

    /* add passed hikey */
    itemsz = IndexTupleDSize(hikey->bti_itup)
	+ (sizeof(BTItemData) - sizeof(IndexTupleData));
    itemsz = DOUBLEALIGN(itemsz);
    (void) PageAddItem(page, (Item) hikey, itemsz, P_HIKEY, LP_USED);
    pfree (hikey);

    /* add btitem */
    itemsz = IndexTupleDSize(btitem->bti_itup)
	+ (sizeof(BTItemData) - sizeof(IndexTupleData));
    itemsz = DOUBLEALIGN(itemsz);
    (void) PageAddItem(page, (Item) btitem, itemsz, P_FIRSTKEY, LP_USED);
    pfree (btitem);
    nitem = (BTItem) PageGetItem(page, PageGetItemId(page, P_FIRSTKEY));
    btitem = _bt_formitem(&(nitem->bti_itup));
    ItemPointerSet(&(btitem->bti_itup.t_tid), bknum, P_HIKEY);
    
    /* ok, write them out */
    _bt_wrtnorelbuf(rel, nbuf);
    _bt_wrtnorelbuf(rel, buf);

    /* fix btpo_prev on right sibling of old page */
    if ( !P_RIGHTMOST (npageop) )
    {
	rbuf = _bt_getbuf(rel, npageop->btpo_next, BT_WRITE);
	rpage = BufferGetPage(rbuf);
	rpageop = (BTPageOpaque) PageGetSpecialPointer(rpage);
	rpageop->btpo_prev = nbknum;
	_bt_wrtbuf(rel, rbuf);
    }

    /* get parent pointing to the old page */
    ItemPointerSet(&(stack->bts_btitem->bti_itup.t_tid), 
			       bknum, P_HIKEY);
    pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
    ppage = BufferGetPage(pbuf);
    ppageop = (BTPageOpaque) PageGetSpecialPointer(ppage);

    _bt_relbuf(rel, nbuf, BT_WRITE);
    _bt_relbuf(rel, buf, BT_WRITE);
    
    /* re-set parent' pointer - we shifted our page to the right ! */
    nitem = (BTItem) PageGetItem (ppage, 
    				PageGetItemId (ppage, stack->bts_offset));
    ItemPointerSet(&(nitem->bti_itup.t_tid), nbknum, P_HIKEY);
    ItemPointerSet(&(stack->bts_btitem->bti_itup.t_tid), nbknum, P_HIKEY);
    _bt_wrtnorelbuf(rel, pbuf);

    /* 
     * Now we want insert into the parent pointer to our old page. It has to
     * be inserted before the pointer to new page. You may get problems here
     * (in the _bt_goesonpg and/or _bt_pgaddtup), but may be not - I don't 
     * know. It works if old page is leftmost (nitem is NULL) and 
     * btitem < hikey and it's all what we need currently. - vadim 05/30/97
     */
    nitem = NULL;
    afteroff = P_FIRSTKEY;
    if ( !P_RIGHTMOST (ppageop) )
    	afteroff = OffsetNumberNext (afteroff);
    if ( stack->bts_offset >= afteroff )
    {
    	afteroff = OffsetNumberPrev (stack->bts_offset);
    	nitem = (BTItem) PageGetItem (ppage, PageGetItemId (ppage, afteroff));
    	nitem = _bt_formitem(&(nitem->bti_itup));
    }
    res = _bt_insertonpg(rel, pbuf, stack->bts_parent,
				    keysz, scankey, btitem, nitem);
    pfree (btitem);
    		
    ItemPointerSet(&(res->pointerData), nbknum, P_HIKEY);
    
    return (res);
}