bufmgr.c 61.9 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 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 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 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 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 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217
/*-------------------------------------------------------------------------
 *
 * bufmgr.c
 *	  buffer manager interface routines
 *
 * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/storage/buffer/bufmgr.c,v 1.221 2007/06/18 00:47:20 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
/*
 * ReadBuffer() -- find or create a buffer holding the requested page,
 *		and pin it so that no one can destroy it while this process
 *		is using it.
 *
 * ReadOrZeroBuffer() -- like ReadBuffer, but if the page is not already in
 *		cache we don't read it, but just return a zeroed-out buffer.  Useful
 *		when the caller intends to fill the page from scratch, since this
 *		saves I/O and avoids unnecessary failure if the page-on-disk has
 *		corrupt page headers.  Caution: do not use this to read a page that
 *		is beyond the relation's current physical EOF; that is likely to
 *		cause problems in md.c when the page is modified and written out.
 *
 * ReleaseBuffer() -- unpin a buffer
 *
 * MarkBufferDirty() -- mark a pinned buffer's contents as "dirty".
 *		The disk write is delayed until buffer replacement or checkpoint.
 *
 * BufferSync() -- flush all dirty buffers in the buffer pool.
 *
 * BgBufferSync() -- flush some dirty buffers in the buffer pool.
 *
 * InitBufferPool() -- Init the buffer module.
 *
 * See other files:
 *		freelist.c -- chooses victim for buffer replacement
 *		buf_table.c -- manages the buffer lookup table
 */
#include "postgres.h"

#include <sys/file.h>
#include <unistd.h>

#include "miscadmin.h"
#include "postmaster/bgwriter.h"
#include "storage/buf_internals.h"
#include "storage/bufpage.h"
#include "storage/ipc.h"
#include "storage/proc.h"
#include "storage/smgr.h"
#include "utils/resowner.h"
#include "pgstat.h"


/* Note: these two macros only work on shared buffers, not local ones! */
#define BufHdrGetBlock(bufHdr)	((Block) (BufferBlocks + ((Size) (bufHdr)->buf_id) * BLCKSZ))
#define BufferGetLSN(bufHdr)	(*((XLogRecPtr*) BufHdrGetBlock(bufHdr)))

/* Note: this macro only works on local buffers, not shared ones! */
#define LocalBufHdrGetBlock(bufHdr) \
	LocalBufferBlockPointers[-((bufHdr)->buf_id + 2)]

/* interval for calling AbsorbFsyncRequests in BufferSync */
#define WRITES_PER_ABSORB		1000


/* GUC variables */
bool		zero_damaged_pages = false;
double		bgwriter_lru_percent = 1.0;
double		bgwriter_all_percent = 0.333;
int			bgwriter_lru_maxpages = 5;
int			bgwriter_all_maxpages = 5;


long		NDirectFileRead;	/* some I/O's are direct file access. bypass
								 * bufmgr */
long		NDirectFileWrite;	/* e.g., I/O in psort and hashjoin. */


/* local state for StartBufferIO and related functions */
static volatile BufferDesc *InProgressBuf = NULL;
static bool IsForInput;

/* local state for LockBufferForCleanup */
static volatile BufferDesc *PinCountWaitBuf = NULL;


static Buffer ReadBuffer_common(Relation reln, BlockNumber blockNum,
								bool zeroPage,
								BufferAccessStrategy strategy);
static bool PinBuffer(volatile BufferDesc *buf, BufferAccessStrategy strategy);
static void PinBuffer_Locked(volatile BufferDesc *buf);
static void UnpinBuffer(volatile BufferDesc *buf, bool fixOwner);
static bool SyncOneBuffer(int buf_id, bool skip_pinned);
static void WaitIO(volatile BufferDesc *buf);
static bool StartBufferIO(volatile BufferDesc *buf, bool forInput);
static void TerminateBufferIO(volatile BufferDesc *buf, bool clear_dirty,
				  int set_flag_bits);
static void buffer_write_error_callback(void *arg);
static volatile BufferDesc *BufferAlloc(Relation reln, BlockNumber blockNum,
										BufferAccessStrategy strategy,
										bool *foundPtr);
static void FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln);
static void AtProcExit_Buffers(int code, Datum arg);


/*
 * ReadBuffer -- returns a buffer containing the requested
 *		block of the requested relation.  If the blknum
 *		requested is P_NEW, extend the relation file and
 *		allocate a new block.  (Caller is responsible for
 *		ensuring that only one backend tries to extend a
 *		relation at the same time!)
 *
 * Returns: the buffer number for the buffer containing
 *		the block read.  The returned buffer has been pinned.
 *		Does not return on error --- elog's instead.
 *
 * Assume when this function is called, that reln has been
 *		opened already.
 */
Buffer
ReadBuffer(Relation reln, BlockNumber blockNum)
{
	return ReadBuffer_common(reln, blockNum, false, NULL);
}

/*
 * ReadBufferWithStrategy -- same as ReadBuffer, except caller can specify
 *		a nondefault buffer access strategy.  See buffer/README for details.
 */
Buffer
ReadBufferWithStrategy(Relation reln, BlockNumber blockNum,
					   BufferAccessStrategy strategy)
{
	return ReadBuffer_common(reln, blockNum, false, strategy);
}

/*
 * ReadOrZeroBuffer -- like ReadBuffer, but if the page isn't in buffer
 *		cache already, it's filled with zeros instead of reading it from
 *		disk. The caller is expected to overwrite the whole buffer,
 *		so that the current page contents are not interesting.
 *		Caution: do not use this to read a page that is beyond the relation's
 *		current physical EOF; that is likely to cause problems in md.c when
 *		the page is modified and written out.  P_NEW is OK, though.
 */
Buffer
ReadOrZeroBuffer(Relation reln, BlockNumber blockNum)
{
	return ReadBuffer_common(reln, blockNum, true, NULL);
}

/*
 * ReadBuffer_common -- common logic for ReadBuffer variants
 */
static Buffer
ReadBuffer_common(Relation reln, BlockNumber blockNum, bool zeroPage,
				  BufferAccessStrategy strategy)
{
	volatile BufferDesc *bufHdr;
	Block		bufBlock;
	bool		found;
	bool		isExtend;
	bool		isLocalBuf;

	/* Make sure we will have room to remember the buffer pin */
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

	isExtend = (blockNum == P_NEW);
	isLocalBuf = reln->rd_istemp;

	/* Open it at the smgr level if not already done */
	RelationOpenSmgr(reln);

	/* Substitute proper block number if caller asked for P_NEW */
	if (isExtend)
		blockNum = smgrnblocks(reln->rd_smgr);

	pgstat_count_buffer_read(reln);

	if (isLocalBuf)
	{
		ReadLocalBufferCount++;
		bufHdr = LocalBufferAlloc(reln, blockNum, &found);
		if (found)
			LocalBufferHitCount++;
	}
	else
	{
		ReadBufferCount++;

		/*
		 * lookup the buffer.  IO_IN_PROGRESS is set if the requested block is
		 * not currently in memory.
		 */
		bufHdr = BufferAlloc(reln, blockNum, strategy, &found);
		if (found)
			BufferHitCount++;
	}

	/* At this point we do NOT hold any locks. */

	/* if it was already in the buffer pool, we're done */
	if (found)
	{
		if (!isExtend)
		{
			/* Just need to update stats before we exit */
			pgstat_count_buffer_hit(reln);

			if (VacuumCostActive)
				VacuumCostBalance += VacuumCostPageHit;

			return BufferDescriptorGetBuffer(bufHdr);
		}

		/*
		 * We get here only in the corner case where we are trying to extend
		 * the relation but we found a pre-existing buffer marked BM_VALID.
		 * This can happen because mdread doesn't complain about reads beyond
		 * EOF (when zero_damaged_pages is ON) and so a previous attempt to
		 * read a block beyond EOF could have left a "valid" zero-filled
		 * buffer.  Unfortunately, we have also seen this case occurring
		 * because of buggy Linux kernels that sometimes return an
		 * lseek(SEEK_END) result that doesn't account for a recent write.
		 * In that situation, the pre-existing buffer would contain valid data
		 * that we don't want to overwrite.  Since the legitimate case should
		 * always have left a zero-filled buffer, complain if not PageIsNew.
		 */
		bufBlock = isLocalBuf ? LocalBufHdrGetBlock(bufHdr) : BufHdrGetBlock(bufHdr);
		if (!PageIsNew((PageHeader) bufBlock))
			ereport(ERROR,
					(errmsg("unexpected data beyond EOF in block %u of relation \"%s\"",
							blockNum, RelationGetRelationName(reln)),
					 errhint("This has been seen to occur with buggy kernels; consider updating your system.")));

		/*
		 * We *must* do smgrextend before succeeding, else the page will not
		 * be reserved by the kernel, and the next P_NEW call will decide to
		 * return the same page.  Clear the BM_VALID bit, do the StartBufferIO
		 * call that BufferAlloc didn't, and proceed.
		 */
		if (isLocalBuf)
		{
			/* Only need to adjust flags */
			Assert(bufHdr->flags & BM_VALID);
			bufHdr->flags &= ~BM_VALID;
		}
		else
		{
			/*
			 * Loop to handle the very small possibility that someone re-sets
			 * BM_VALID between our clearing it and StartBufferIO inspecting
			 * it.
			 */
			do
			{
				LockBufHdr(bufHdr);
				Assert(bufHdr->flags & BM_VALID);
				bufHdr->flags &= ~BM_VALID;
				UnlockBufHdr(bufHdr);
			} while (!StartBufferIO(bufHdr, true));
		}
	}

	/*
	 * if we have gotten to this point, we have allocated a buffer for the
	 * page but its contents are not yet valid.  IO_IN_PROGRESS is set for it,
	 * if it's a shared buffer.
	 *
	 * Note: if smgrextend fails, we will end up with a buffer that is
	 * allocated but not marked BM_VALID.  P_NEW will still select the same
	 * block number (because the relation didn't get any longer on disk) and
	 * so future attempts to extend the relation will find the same buffer (if
	 * it's not been recycled) but come right back here to try smgrextend
	 * again.
	 */
	Assert(!(bufHdr->flags & BM_VALID));		/* spinlock not needed */

	bufBlock = isLocalBuf ? LocalBufHdrGetBlock(bufHdr) : BufHdrGetBlock(bufHdr);

	if (isExtend)
	{
		/* new buffers are zero-filled */
		MemSet((char *) bufBlock, 0, BLCKSZ);
		smgrextend(reln->rd_smgr, blockNum, (char *) bufBlock,
				   reln->rd_istemp);
	}
	else
	{
		/* 
		 * Read in the page, unless the caller intends to overwrite it
		 * and just wants us to allocate a buffer.
		 */
		if (zeroPage)
			MemSet((char *) bufBlock, 0, BLCKSZ);
		else
			smgrread(reln->rd_smgr, blockNum, (char *) bufBlock);
		/* check for garbage data */
		if (!PageHeaderIsValid((PageHeader) bufBlock))
		{
			if (zero_damaged_pages)
			{
				ereport(WARNING,
						(errcode(ERRCODE_DATA_CORRUPTED),
						 errmsg("invalid page header in block %u of relation \"%s\"; zeroing out page",
								blockNum, RelationGetRelationName(reln))));
				MemSet((char *) bufBlock, 0, BLCKSZ);
			}
			else
				ereport(ERROR,
						(errcode(ERRCODE_DATA_CORRUPTED),
				 errmsg("invalid page header in block %u of relation \"%s\"",
						blockNum, RelationGetRelationName(reln))));
		}
	}

	if (isLocalBuf)
	{
		/* Only need to adjust flags */
		bufHdr->flags |= BM_VALID;
	}
	else
	{
		/* Set BM_VALID, terminate IO, and wake up any waiters */
		TerminateBufferIO(bufHdr, false, BM_VALID);
	}

	if (VacuumCostActive)
		VacuumCostBalance += VacuumCostPageMiss;

	return BufferDescriptorGetBuffer(bufHdr);
}

/*
 * BufferAlloc -- subroutine for ReadBuffer.  Handles lookup of a shared
 *		buffer.  If no buffer exists already, selects a replacement
 *		victim and evicts the old page, but does NOT read in new page.
 *
 * "strategy" can be a buffer replacement strategy object, or NULL for
 * the default strategy.  The selected buffer's usage_count is advanced when
 * using the default strategy, but otherwise possibly not (see PinBuffer).
 *
 * The returned buffer is pinned and is already marked as holding the
 * desired page.  If it already did have the desired page, *foundPtr is
 * set TRUE.  Otherwise, *foundPtr is set FALSE and the buffer is marked
 * as IO_IN_PROGRESS; ReadBuffer will now need to do I/O to fill it.
 *
 * *foundPtr is actually redundant with the buffer's BM_VALID flag, but
 * we keep it for simplicity in ReadBuffer.
 *
 * No locks are held either at entry or exit.
 */
static volatile BufferDesc *
BufferAlloc(Relation reln,
			BlockNumber blockNum,
			BufferAccessStrategy strategy,
			bool *foundPtr)
{
	BufferTag	newTag;			/* identity of requested block */
	uint32		newHash;		/* hash value for newTag */
	LWLockId	newPartitionLock;		/* buffer partition lock for it */
	BufferTag	oldTag;			/* previous identity of selected buffer */
	uint32		oldHash;		/* hash value for oldTag */
	LWLockId	oldPartitionLock;		/* buffer partition lock for it */
	BufFlags	oldFlags;
	int			buf_id;
	volatile BufferDesc *buf;
	bool		valid;

	/* create a tag so we can lookup the buffer */
	INIT_BUFFERTAG(newTag, reln, blockNum);

	/* determine its hash code and partition lock ID */
	newHash = BufTableHashCode(&newTag);
	newPartitionLock = BufMappingPartitionLock(newHash);

	/* see if the block is in the buffer pool already */
	LWLockAcquire(newPartitionLock, LW_SHARED);
	buf_id = BufTableLookup(&newTag, newHash);
	if (buf_id >= 0)
	{
		/*
		 * Found it.  Now, pin the buffer so no one can steal it from the
		 * buffer pool, and check to see if the correct data has been loaded
		 * into the buffer.
		 */
		buf = &BufferDescriptors[buf_id];

		valid = PinBuffer(buf, strategy);

		/* Can release the mapping lock as soon as we've pinned it */
		LWLockRelease(newPartitionLock);

		*foundPtr = TRUE;

		if (!valid)
		{
			/*
			 * We can only get here if (a) someone else is still reading in
			 * the page, or (b) a previous read attempt failed.  We have to
			 * wait for any active read attempt to finish, and then set up our
			 * own read attempt if the page is still not BM_VALID.
			 * StartBufferIO does it all.
			 */
			if (StartBufferIO(buf, true))
			{
				/*
				 * If we get here, previous attempts to read the buffer must
				 * have failed ... but we shall bravely try again.
				 */
				*foundPtr = FALSE;
			}
		}

		return buf;
	}

	/*
	 * Didn't find it in the buffer pool.  We'll have to initialize a new
	 * buffer.	Remember to unlock the mapping lock while doing the work.
	 */
	LWLockRelease(newPartitionLock);

	/* Loop here in case we have to try another victim buffer */
	for (;;)
	{
		bool lock_held;

		/*
		 * Select a victim buffer.	The buffer is returned with its header
		 * spinlock still held!  Also (in most cases) the BufFreelistLock is
		 * still held, since it would be bad to hold the spinlock while
		 * possibly waking up other processes.
		 */
		buf = StrategyGetBuffer(strategy, &lock_held);

		Assert(buf->refcount == 0);

		/* Must copy buffer flags while we still hold the spinlock */
		oldFlags = buf->flags;

		/* Pin the buffer and then release the buffer spinlock */
		PinBuffer_Locked(buf);

		/* Now it's safe to release the freelist lock */
		if (lock_held)
			LWLockRelease(BufFreelistLock);

		/*
		 * If the buffer was dirty, try to write it out.  There is a race
		 * condition here, in that someone might dirty it after we released it
		 * above, or even while we are writing it out (since our share-lock
		 * won't prevent hint-bit updates).  We will recheck the dirty bit
		 * after re-locking the buffer header.
		 */
		if (oldFlags & BM_DIRTY)
		{
			/*
			 * We need a share-lock on the buffer contents to write it out
			 * (else we might write invalid data, eg because someone else is
			 * compacting the page contents while we write).  We must use a
			 * conditional lock acquisition here to avoid deadlock.  Even
			 * though the buffer was not pinned (and therefore surely not
			 * locked) when StrategyGetBuffer returned it, someone else could
			 * have pinned and exclusive-locked it by the time we get here. If
			 * we try to get the lock unconditionally, we'd block waiting for
			 * them; if they later block waiting for us, deadlock ensues.
			 * (This has been observed to happen when two backends are both
			 * trying to split btree index pages, and the second one just
			 * happens to be trying to split the page the first one got from
			 * StrategyGetBuffer.)
			 */
			if (LWLockConditionalAcquire(buf->content_lock, LW_SHARED))
			{
				/*
				 * If using a nondefault strategy, and writing the buffer
				 * would require a WAL flush, let the strategy decide whether
				 * to go ahead and write/reuse the buffer or to choose another
				 * victim.  We need lock to inspect the page LSN, so this
				 * can't be done inside StrategyGetBuffer.
				 */
				if (strategy != NULL &&
					XLogNeedsFlush(BufferGetLSN(buf)) &&
					StrategyRejectBuffer(strategy, buf))
				{
					/* Drop lock/pin and loop around for another buffer */
					LWLockRelease(buf->content_lock);
					UnpinBuffer(buf, true);
					continue;
				}

				/* OK, do the I/O */
				FlushBuffer(buf, NULL);
				LWLockRelease(buf->content_lock);
			}
			else
			{
				/*
				 * Someone else has locked the buffer, so give it up and loop
				 * back to get another one.
				 */
				UnpinBuffer(buf, true);
				continue;
			}
		}

		/*
		 * To change the association of a valid buffer, we'll need to have
		 * exclusive lock on both the old and new mapping partitions.
		 */
		if (oldFlags & BM_TAG_VALID)
		{
			/*
			 * Need to compute the old tag's hashcode and partition lock ID.
			 * XXX is it worth storing the hashcode in BufferDesc so we need
			 * not recompute it here?  Probably not.
			 */
			oldTag = buf->tag;
			oldHash = BufTableHashCode(&oldTag);
			oldPartitionLock = BufMappingPartitionLock(oldHash);

			/*
			 * Must lock the lower-numbered partition first to avoid
			 * deadlocks.
			 */
			if (oldPartitionLock < newPartitionLock)
			{
				LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
				LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
			}
			else if (oldPartitionLock > newPartitionLock)
			{
				LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
				LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
			}
			else
			{
				/* only one partition, only one lock */
				LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
			}
		}
		else
		{
			/* if it wasn't valid, we need only the new partition */
			LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
			/* these just keep the compiler quiet about uninit variables */
			oldHash = 0;
			oldPartitionLock = 0;
		}

		/*
		 * Try to make a hashtable entry for the buffer under its new tag.
		 * This could fail because while we were writing someone else
		 * allocated another buffer for the same block we want to read in.
		 * Note that we have not yet removed the hashtable entry for the old
		 * tag.
		 */
		buf_id = BufTableInsert(&newTag, newHash, buf->buf_id);

		if (buf_id >= 0)
		{
			/*
			 * Got a collision. Someone has already done what we were about to
			 * do. We'll just handle this as if it were found in the buffer
			 * pool in the first place.  First, give up the buffer we were
			 * planning to use.
			 */
			UnpinBuffer(buf, true);

			/* Can give up that buffer's mapping partition lock now */
			if ((oldFlags & BM_TAG_VALID) &&
				oldPartitionLock != newPartitionLock)
				LWLockRelease(oldPartitionLock);

			/* remaining code should match code at top of routine */

			buf = &BufferDescriptors[buf_id];

			valid = PinBuffer(buf, strategy);

			/* Can release the mapping lock as soon as we've pinned it */
			LWLockRelease(newPartitionLock);

			*foundPtr = TRUE;

			if (!valid)
			{
				/*
				 * We can only get here if (a) someone else is still reading
				 * in the page, or (b) a previous read attempt failed.	We
				 * have to wait for any active read attempt to finish, and
				 * then set up our own read attempt if the page is still not
				 * BM_VALID.  StartBufferIO does it all.
				 */
				if (StartBufferIO(buf, true))
				{
					/*
					 * If we get here, previous attempts to read the buffer
					 * must have failed ... but we shall bravely try again.
					 */
					*foundPtr = FALSE;
				}
			}

			return buf;
		}

		/*
		 * Need to lock the buffer header too in order to change its tag.
		 */
		LockBufHdr(buf);

		/*
		 * Somebody could have pinned or re-dirtied the buffer while we were
		 * doing the I/O and making the new hashtable entry.  If so, we can't
		 * recycle this buffer; we must undo everything we've done and start
		 * over with a new victim buffer.
		 */
		oldFlags = buf->flags;
		if (buf->refcount == 1 && !(oldFlags & BM_DIRTY))
			break;

		UnlockBufHdr(buf);
		BufTableDelete(&newTag, newHash);
		if ((oldFlags & BM_TAG_VALID) &&
			oldPartitionLock != newPartitionLock)
			LWLockRelease(oldPartitionLock);
		LWLockRelease(newPartitionLock);
		UnpinBuffer(buf, true);
	}

	/*
	 * Okay, it's finally safe to rename the buffer.
	 *
	 * Clearing BM_VALID here is necessary, clearing the dirtybits is just
	 * paranoia.  We also reset the usage_count since any recency of use of
	 * the old content is no longer relevant.  (The usage_count starts out
	 * at 1 so that the buffer can survive one clock-sweep pass.)
	 */
	buf->tag = newTag;
	buf->flags &= ~(BM_VALID | BM_DIRTY | BM_JUST_DIRTIED | BM_IO_ERROR);
	buf->flags |= BM_TAG_VALID;
	buf->usage_count = 1;

	UnlockBufHdr(buf);

	if (oldFlags & BM_TAG_VALID)
	{
		BufTableDelete(&oldTag, oldHash);
		if (oldPartitionLock != newPartitionLock)
			LWLockRelease(oldPartitionLock);
	}

	LWLockRelease(newPartitionLock);

	/*
	 * Buffer contents are currently invalid.  Try to get the io_in_progress
	 * lock.  If StartBufferIO returns false, then someone else managed to
	 * read it before we did, so there's nothing left for BufferAlloc() to do.
	 */
	if (StartBufferIO(buf, true))
		*foundPtr = FALSE;
	else
		*foundPtr = TRUE;

	return buf;
}

/*
 * InvalidateBuffer -- mark a shared buffer invalid and return it to the
 * freelist.
 *
 * The buffer header spinlock must be held at entry.  We drop it before
 * returning.  (This is sane because the caller must have locked the
 * buffer in order to be sure it should be dropped.)
 *
 * This is used only in contexts such as dropping a relation.  We assume
 * that no other backend could possibly be interested in using the page,
 * so the only reason the buffer might be pinned is if someone else is
 * trying to write it out.	We have to let them finish before we can
 * reclaim the buffer.
 *
 * The buffer could get reclaimed by someone else while we are waiting
 * to acquire the necessary locks; if so, don't mess it up.
 */
static void
InvalidateBuffer(volatile BufferDesc *buf)
{
	BufferTag	oldTag;
	uint32		oldHash;		/* hash value for oldTag */
	LWLockId	oldPartitionLock;		/* buffer partition lock for it */
	BufFlags	oldFlags;

	/* Save the original buffer tag before dropping the spinlock */
	oldTag = buf->tag;

	UnlockBufHdr(buf);

	/*
	 * Need to compute the old tag's hashcode and partition lock ID. XXX is it
	 * worth storing the hashcode in BufferDesc so we need not recompute it
	 * here?  Probably not.
	 */
	oldHash = BufTableHashCode(&oldTag);
	oldPartitionLock = BufMappingPartitionLock(oldHash);

retry:

	/*
	 * Acquire exclusive mapping lock in preparation for changing the buffer's
	 * association.
	 */
	LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);

	/* Re-lock the buffer header */
	LockBufHdr(buf);

	/* If it's changed while we were waiting for lock, do nothing */
	if (!BUFFERTAGS_EQUAL(buf->tag, oldTag))
	{
		UnlockBufHdr(buf);
		LWLockRelease(oldPartitionLock);
		return;
	}

	/*
	 * We assume the only reason for it to be pinned is that someone else is
	 * flushing the page out.  Wait for them to finish.  (This could be an
	 * infinite loop if the refcount is messed up... it would be nice to time
	 * out after awhile, but there seems no way to be sure how many loops may
	 * be needed.  Note that if the other guy has pinned the buffer but not
	 * yet done StartBufferIO, WaitIO will fall through and we'll effectively
	 * be busy-looping here.)
	 */
	if (buf->refcount != 0)
	{
		UnlockBufHdr(buf);
		LWLockRelease(oldPartitionLock);
		/* safety check: should definitely not be our *own* pin */
		if (PrivateRefCount[buf->buf_id] != 0)
			elog(ERROR, "buffer is pinned in InvalidateBuffer");
		WaitIO(buf);
		goto retry;
	}

	/*
	 * Clear out the buffer's tag and flags.  We must do this to ensure that
	 * linear scans of the buffer array don't think the buffer is valid.
	 */
	oldFlags = buf->flags;
	CLEAR_BUFFERTAG(buf->tag);
	buf->flags = 0;
	buf->usage_count = 0;

	UnlockBufHdr(buf);

	/*
	 * Remove the buffer from the lookup hashtable, if it was in there.
	 */
	if (oldFlags & BM_TAG_VALID)
		BufTableDelete(&oldTag, oldHash);

	/*
	 * Done with mapping lock.
	 */
	LWLockRelease(oldPartitionLock);

	/*
	 * Insert the buffer at the head of the list of free buffers.
	 */
	StrategyFreeBuffer(buf);
}

/*
 * MarkBufferDirty
 *
 *		Marks buffer contents as dirty (actual write happens later).
 *
 * Buffer must be pinned and exclusive-locked.	(If caller does not hold
 * exclusive lock, then somebody could be in process of writing the buffer,
 * leading to risk of bad data written to disk.)
 */
void
MarkBufferDirty(Buffer buffer)
{
	volatile BufferDesc *bufHdr;

	if (!BufferIsValid(buffer))
		elog(ERROR, "bad buffer id: %d", buffer);

	if (BufferIsLocal(buffer))
	{
		MarkLocalBufferDirty(buffer);
		return;
	}

	bufHdr = &BufferDescriptors[buffer - 1];

	Assert(PrivateRefCount[buffer - 1] > 0);
	/* unfortunately we can't check if the lock is held exclusively */
	Assert(LWLockHeldByMe(bufHdr->content_lock));

	LockBufHdr(bufHdr);

	Assert(bufHdr->refcount > 0);

	/*
	 * If the buffer was not dirty already, do vacuum cost accounting.
	 */
	if (!(bufHdr->flags & BM_DIRTY) && VacuumCostActive)
		VacuumCostBalance += VacuumCostPageDirty;

	bufHdr->flags |= (BM_DIRTY | BM_JUST_DIRTIED);

	UnlockBufHdr(bufHdr);
}

/*
 * ReleaseAndReadBuffer -- combine ReleaseBuffer() and ReadBuffer()
 *
 * Formerly, this saved one cycle of acquiring/releasing the BufMgrLock
 * compared to calling the two routines separately.  Now it's mainly just
 * a convenience function.	However, if the passed buffer is valid and
 * already contains the desired block, we just return it as-is; and that
 * does save considerable work compared to a full release and reacquire.
 *
 * Note: it is OK to pass buffer == InvalidBuffer, indicating that no old
 * buffer actually needs to be released.  This case is the same as ReadBuffer,
 * but can save some tests in the caller.
 */
Buffer
ReleaseAndReadBuffer(Buffer buffer,
					 Relation relation,
					 BlockNumber blockNum)
{
	volatile BufferDesc *bufHdr;

	if (BufferIsValid(buffer))
	{
		if (BufferIsLocal(buffer))
		{
			Assert(LocalRefCount[-buffer - 1] > 0);
			bufHdr = &LocalBufferDescriptors[-buffer - 1];
			if (bufHdr->tag.blockNum == blockNum &&
				RelFileNodeEquals(bufHdr->tag.rnode, relation->rd_node))
				return buffer;
			ResourceOwnerForgetBuffer(CurrentResourceOwner, buffer);
			LocalRefCount[-buffer - 1]--;
		}
		else
		{
			Assert(PrivateRefCount[buffer - 1] > 0);
			bufHdr = &BufferDescriptors[buffer - 1];
			/* we have pin, so it's ok to examine tag without spinlock */
			if (bufHdr->tag.blockNum == blockNum &&
				RelFileNodeEquals(bufHdr->tag.rnode, relation->rd_node))
				return buffer;
			UnpinBuffer(bufHdr, true);
		}
	}

	return ReadBuffer(relation, blockNum);
}

/*
 * PinBuffer -- make buffer unavailable for replacement.
 *
 * For the default access strategy, the buffer's usage_count is incremented
 * when we first pin it; for other strategies we just make sure the usage_count
 * isn't zero.  (The idea of the latter is that we don't want synchronized
 * heap scans to inflate the count, but we need it to not be zero to discourage
 * other backends from stealing buffers from our ring.  As long as we cycle
 * through the ring faster than the global clock-sweep cycles, buffers in
 * our ring won't be chosen as victims for replacement by other backends.)
 *
 * This should be applied only to shared buffers, never local ones.
 *
 * Note that ResourceOwnerEnlargeBuffers must have been done already.
 *
 * Returns TRUE if buffer is BM_VALID, else FALSE.	This provision allows
 * some callers to avoid an extra spinlock cycle.
 */
static bool
PinBuffer(volatile BufferDesc *buf, BufferAccessStrategy strategy)
{
	int			b = buf->buf_id;
	bool		result;

	if (PrivateRefCount[b] == 0)
	{
		LockBufHdr(buf);
		buf->refcount++;
		if (strategy == NULL)
		{
			if (buf->usage_count < BM_MAX_USAGE_COUNT)
				buf->usage_count++;
		}
		else
		{
			if (buf->usage_count == 0)
				buf->usage_count = 1;
		}
		result = (buf->flags & BM_VALID) != 0;
		UnlockBufHdr(buf);
	}
	else
	{
		/* If we previously pinned the buffer, it must surely be valid */
		result = true;
	}
	PrivateRefCount[b]++;
	Assert(PrivateRefCount[b] > 0);
	ResourceOwnerRememberBuffer(CurrentResourceOwner,
								BufferDescriptorGetBuffer(buf));
	return result;
}

/*
 * PinBuffer_Locked -- as above, but caller already locked the buffer header.
 * The spinlock is released before return.
 *
 * Currently, no callers of this function want to modify the buffer's
 * usage_count at all, so there's no need for a strategy parameter.
 * Also we don't bother with a BM_VALID test (the caller could check that for
 * itself).
 *
 * Note: use of this routine is frequently mandatory, not just an optimization
 * to save a spin lock/unlock cycle, because we need to pin a buffer before
 * its state can change under us.
 */
static void
PinBuffer_Locked(volatile BufferDesc *buf)
{
	int			b = buf->buf_id;

	if (PrivateRefCount[b] == 0)
		buf->refcount++;
	UnlockBufHdr(buf);
	PrivateRefCount[b]++;
	Assert(PrivateRefCount[b] > 0);
	ResourceOwnerRememberBuffer(CurrentResourceOwner,
								BufferDescriptorGetBuffer(buf));
}

/*
 * UnpinBuffer -- make buffer available for replacement.
 *
 * This should be applied only to shared buffers, never local ones.
 *
 * Most but not all callers want CurrentResourceOwner to be adjusted.
 * Those that don't should pass fixOwner = FALSE.
 */
static void
UnpinBuffer(volatile BufferDesc *buf, bool fixOwner)
{
	int			b = buf->buf_id;

	if (fixOwner)
		ResourceOwnerForgetBuffer(CurrentResourceOwner,
								  BufferDescriptorGetBuffer(buf));

	Assert(PrivateRefCount[b] > 0);
	PrivateRefCount[b]--;
	if (PrivateRefCount[b] == 0)
	{
		/* I'd better not still hold any locks on the buffer */
		Assert(!LWLockHeldByMe(buf->content_lock));
		Assert(!LWLockHeldByMe(buf->io_in_progress_lock));

		LockBufHdr(buf);

		/* Decrement the shared reference count */
		Assert(buf->refcount > 0);
		buf->refcount--;

		/* Support LockBufferForCleanup() */
		if ((buf->flags & BM_PIN_COUNT_WAITER) &&
			buf->refcount == 1)
		{
			/* we just released the last pin other than the waiter's */
			int			wait_backend_pid = buf->wait_backend_pid;

			buf->flags &= ~BM_PIN_COUNT_WAITER;
			UnlockBufHdr(buf);
			ProcSendSignal(wait_backend_pid);
		}
		else
			UnlockBufHdr(buf);
	}
}

/*
 * BufferSync -- Write out all dirty buffers in the pool.
 *
 * This is called at checkpoint time to write out all dirty shared buffers.
 */
void
BufferSync(void)
{
	int			buf_id;
	int			num_to_scan;
	int			absorb_counter;

	/*
	 * Find out where to start the circular scan.
	 */
	buf_id = StrategySyncStart();

	/* Make sure we can handle the pin inside SyncOneBuffer */
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

	/*
	 * Loop over all buffers.
	 */
	num_to_scan = NBuffers;
	absorb_counter = WRITES_PER_ABSORB;
	while (num_to_scan-- > 0)
	{
		if (SyncOneBuffer(buf_id, false))
		{
			BgWriterStats.m_buf_written_checkpoints++;

			/*
			 * If in bgwriter, absorb pending fsync requests after each
			 * WRITES_PER_ABSORB write operations, to prevent overflow of the
			 * fsync request queue.  If not in bgwriter process, this is a
			 * no-op.
			 */
			if (--absorb_counter <= 0)
			{
				AbsorbFsyncRequests();
				absorb_counter = WRITES_PER_ABSORB;
			}
		}
		if (++buf_id >= NBuffers)
			buf_id = 0;
	}
}

/*
 * BgBufferSync -- Write out some dirty buffers in the pool.
 *
 * This is called periodically by the background writer process.
 */
void
BgBufferSync(void)
{
	static int	buf_id1 = 0;
	int			buf_id2;
	int			num_to_scan;
	int			num_written;

	/* Make sure we can handle the pin inside SyncOneBuffer */
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

	/*
	 * To minimize work at checkpoint time, we want to try to keep all the
	 * buffers clean; this motivates a scan that proceeds sequentially through
	 * all buffers.  But we are also charged with ensuring that buffers that
	 * will be recycled soon are clean when needed; these buffers are the ones
	 * just ahead of the StrategySyncStart point.  We make a separate scan
	 * through those.
	 */

	/*
	 * This loop runs over all buffers, including pinned ones.	The starting
	 * point advances through the buffer pool on successive calls.
	 *
	 * Note that we advance the static counter *before* trying to write. This
	 * ensures that, if we have a persistent write failure on a dirty buffer,
	 * we'll still be able to make progress writing other buffers. (The
	 * bgwriter will catch the error and just call us again later.)
	 */
	if (bgwriter_all_percent > 0.0 && bgwriter_all_maxpages > 0)
	{
		num_to_scan = (int) ((NBuffers * bgwriter_all_percent + 99) / 100);
		num_written = 0;

		while (num_to_scan-- > 0)
		{
			if (++buf_id1 >= NBuffers)
				buf_id1 = 0;
			if (SyncOneBuffer(buf_id1, false))
			{
				if (++num_written >= bgwriter_all_maxpages)
				{
					BgWriterStats.m_maxwritten_all++;
					break;
				}
			}
		}
		BgWriterStats.m_buf_written_all += num_written;
	}

	/*
	 * This loop considers only unpinned buffers close to the clock sweep
	 * point.
	 */
	if (bgwriter_lru_percent > 0.0 && bgwriter_lru_maxpages > 0)
	{
		num_to_scan = (int) ((NBuffers * bgwriter_lru_percent + 99) / 100);
		num_written = 0;

		buf_id2 = StrategySyncStart();

		while (num_to_scan-- > 0)
		{
			if (SyncOneBuffer(buf_id2, true))
			{
				if (++num_written >= bgwriter_lru_maxpages)
				{
					BgWriterStats.m_maxwritten_lru++;
					break;
				}
			}
			if (++buf_id2 >= NBuffers)
				buf_id2 = 0;
		}
		BgWriterStats.m_buf_written_lru += num_written;
	}
}

/*
 * SyncOneBuffer -- process a single buffer during syncing.
 *
 * If skip_pinned is true, we don't write currently-pinned buffers, nor
 * buffers marked recently used, as these are not replacement candidates.
 *
 * Returns true if buffer was written, else false.	(This could be in error
 * if FlushBuffers finds the buffer clean after locking it, but we don't
 * care all that much.)
 *
 * Note: caller must have done ResourceOwnerEnlargeBuffers.
 */
static bool
SyncOneBuffer(int buf_id, bool skip_pinned)
{
	volatile BufferDesc *bufHdr = &BufferDescriptors[buf_id];

	/*
	 * Check whether buffer needs writing.
	 *
	 * We can make this check without taking the buffer content lock so long
	 * as we mark pages dirty in access methods *before* logging changes with
	 * XLogInsert(): if someone marks the buffer dirty just after our check we
	 * don't worry because our checkpoint.redo points before log record for
	 * upcoming changes and so we are not required to write such dirty buffer.
	 */
	LockBufHdr(bufHdr);
	if (!(bufHdr->flags & BM_VALID) || !(bufHdr->flags & BM_DIRTY))
	{
		UnlockBufHdr(bufHdr);
		return false;
	}
	if (skip_pinned &&
		(bufHdr->refcount != 0 || bufHdr->usage_count != 0))
	{
		UnlockBufHdr(bufHdr);
		return false;
	}

	/*
	 * Pin it, share-lock it, write it.  (FlushBuffer will do nothing if the
	 * buffer is clean by the time we've locked it.)
	 */
	PinBuffer_Locked(bufHdr);
	LWLockAcquire(bufHdr->content_lock, LW_SHARED);

	FlushBuffer(bufHdr, NULL);

	LWLockRelease(bufHdr->content_lock);
	UnpinBuffer(bufHdr, true);

	return true;
}


/*
 * Return a palloc'd string containing buffer usage statistics.
 */
char *
ShowBufferUsage(void)
{
	StringInfoData str;
	float		hitrate;
	float		localhitrate;

	initStringInfo(&str);

	if (ReadBufferCount == 0)
		hitrate = 0.0;
	else
		hitrate = (float) BufferHitCount *100.0 / ReadBufferCount;

	if (ReadLocalBufferCount == 0)
		localhitrate = 0.0;
	else
		localhitrate = (float) LocalBufferHitCount *100.0 / ReadLocalBufferCount;

	appendStringInfo(&str,
	"!\tShared blocks: %10ld read, %10ld written, buffer hit rate = %.2f%%\n",
				ReadBufferCount - BufferHitCount, BufferFlushCount, hitrate);
	appendStringInfo(&str,
	"!\tLocal  blocks: %10ld read, %10ld written, buffer hit rate = %.2f%%\n",
					 ReadLocalBufferCount - LocalBufferHitCount, LocalBufferFlushCount, localhitrate);
	appendStringInfo(&str,
					 "!\tDirect blocks: %10ld read, %10ld written\n",
					 NDirectFileRead, NDirectFileWrite);

	return str.data;
}

void
ResetBufferUsage(void)
{
	BufferHitCount = 0;
	ReadBufferCount = 0;
	BufferFlushCount = 0;
	LocalBufferHitCount = 0;
	ReadLocalBufferCount = 0;
	LocalBufferFlushCount = 0;
	NDirectFileRead = 0;
	NDirectFileWrite = 0;
}

/*
 *		AtEOXact_Buffers - clean up at end of transaction.
 *
 *		As of PostgreSQL 8.0, buffer pins should get released by the
 *		ResourceOwner mechanism.  This routine is just a debugging
 *		cross-check that no pins remain.
 */
void
AtEOXact_Buffers(bool isCommit)
{
#ifdef USE_ASSERT_CHECKING
	if (assert_enabled)
	{
		int			i;

		for (i = 0; i < NBuffers; i++)
		{
			Assert(PrivateRefCount[i] == 0);
		}
	}
#endif

	AtEOXact_LocalBuffers(isCommit);
}

/*
 * InitBufferPoolBackend --- second-stage initialization of a new backend
 *
 * This is called after we have acquired a PGPROC and so can safely get
 * LWLocks.  We don't currently need to do anything at this stage ...
 * except register a shmem-exit callback.  AtProcExit_Buffers needs LWLock
 * access, and thereby has to be called at the corresponding phase of
 * backend shutdown.
 */
void
InitBufferPoolBackend(void)
{
	on_shmem_exit(AtProcExit_Buffers, 0);
}

/*
 * Ensure we have released all shared-buffer locks and pins during backend exit
 */
static void
AtProcExit_Buffers(int code, Datum arg)
{
	int			i;

	AbortBufferIO();
	UnlockBuffers();

	for (i = 0; i < NBuffers; i++)
	{
		if (PrivateRefCount[i] != 0)
		{
			volatile BufferDesc *buf = &(BufferDescriptors[i]);

			/*
			 * We don't worry about updating ResourceOwner; if we even got
			 * here, it suggests that ResourceOwners are messed up.
			 */
			PrivateRefCount[i] = 1;		/* make sure we release shared pin */
			UnpinBuffer(buf, false);
			Assert(PrivateRefCount[i] == 0);
		}
	}

	/* localbuf.c needs a chance too */
	AtProcExit_LocalBuffers();
}

/*
 * Helper routine to issue warnings when a buffer is unexpectedly pinned
 */
void
PrintBufferLeakWarning(Buffer buffer)
{
	volatile BufferDesc *buf;
	int32		loccount;

	Assert(BufferIsValid(buffer));
	if (BufferIsLocal(buffer))
	{
		buf = &LocalBufferDescriptors[-buffer - 1];
		loccount = LocalRefCount[-buffer - 1];
	}
	else
	{
		buf = &BufferDescriptors[buffer - 1];
		loccount = PrivateRefCount[buffer - 1];
	}

	/* theoretically we should lock the bufhdr here */
	elog(WARNING,
		 "buffer refcount leak: [%03d] "
		 "(rel=%u/%u/%u, blockNum=%u, flags=0x%x, refcount=%u %d)",
		 buffer,
		 buf->tag.rnode.spcNode, buf->tag.rnode.dbNode,
		 buf->tag.rnode.relNode,
		 buf->tag.blockNum, buf->flags,
		 buf->refcount, loccount);
}

/*
 * FlushBufferPool
 *
 * Flush all dirty blocks in buffer pool to disk at the checkpoint time.
 * Local relations do not participate in checkpoints, so they don't need to be
 * flushed.
 */
void
FlushBufferPool(void)
{
	BufferSync();
	smgrsync();
}


/*
 * Do whatever is needed to prepare for commit at the bufmgr and smgr levels
 */
void
BufmgrCommit(void)
{
	/* Nothing to do in bufmgr anymore... */

	smgrcommit();
}

/*
 * BufferGetBlockNumber
 *		Returns the block number associated with a buffer.
 *
 * Note:
 *		Assumes that the buffer is valid and pinned, else the
 *		value may be obsolete immediately...
 */
BlockNumber
BufferGetBlockNumber(Buffer buffer)
{
	volatile BufferDesc *bufHdr;

	Assert(BufferIsPinned(buffer));

	if (BufferIsLocal(buffer))
		bufHdr = &(LocalBufferDescriptors[-buffer - 1]);
	else
		bufHdr = &BufferDescriptors[buffer - 1];

	/* pinned, so OK to read tag without spinlock */
	return bufHdr->tag.blockNum;
}

/*
 * BufferGetFileNode
 *		Returns the relation ID (RelFileNode) associated with a buffer.
 *
 * This should make the same checks as BufferGetBlockNumber, but since the
 * two are generally called together, we don't bother.
 */
RelFileNode
BufferGetFileNode(Buffer buffer)
{
	volatile BufferDesc *bufHdr;

	if (BufferIsLocal(buffer))
		bufHdr = &(LocalBufferDescriptors[-buffer - 1]);
	else
		bufHdr = &BufferDescriptors[buffer - 1];

	return bufHdr->tag.rnode;
}

/*
 * FlushBuffer
 *		Physically write out a shared buffer.
 *
 * NOTE: this actually just passes the buffer contents to the kernel; the
 * real write to disk won't happen until the kernel feels like it.  This
 * is okay from our point of view since we can redo the changes from WAL.
 * However, we will need to force the changes to disk via fsync before
 * we can checkpoint WAL.
 *
 * The caller must hold a pin on the buffer and have share-locked the
 * buffer contents.  (Note: a share-lock does not prevent updates of
 * hint bits in the buffer, so the page could change while the write
 * is in progress, but we assume that that will not invalidate the data
 * written.)
 *
 * If the caller has an smgr reference for the buffer's relation, pass it
 * as the second parameter.  If not, pass NULL.
 */
static void
FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln)
{
	XLogRecPtr	recptr;
	ErrorContextCallback errcontext;

	/*
	 * Acquire the buffer's io_in_progress lock.  If StartBufferIO returns
	 * false, then someone else flushed the buffer before we could, so we need
	 * not do anything.
	 */
	if (!StartBufferIO(buf, false))
		return;

	/* Setup error traceback support for ereport() */
	errcontext.callback = buffer_write_error_callback;
	errcontext.arg = (void *) buf;
	errcontext.previous = error_context_stack;
	error_context_stack = &errcontext;

	/* Find smgr relation for buffer */
	if (reln == NULL)
		reln = smgropen(buf->tag.rnode);

	/*
	 * Force XLOG flush up to buffer's LSN.  This implements the basic WAL
	 * rule that log updates must hit disk before any of the data-file changes
	 * they describe do.
	 */
	recptr = BufferGetLSN(buf);
	XLogFlush(recptr);

	/*
	 * Now it's safe to write buffer to disk. Note that no one else should
	 * have been able to write it while we were busy with log flushing because
	 * we have the io_in_progress lock.
	 */

	/* To check if block content changes while flushing. - vadim 01/17/97 */
	LockBufHdr(buf);
	buf->flags &= ~BM_JUST_DIRTIED;
	UnlockBufHdr(buf);

	smgrwrite(reln,
			  buf->tag.blockNum,
			  (char *) BufHdrGetBlock(buf),
			  false);

	BufferFlushCount++;

	/*
	 * Mark the buffer as clean (unless BM_JUST_DIRTIED has become set) and
	 * end the io_in_progress state.
	 */
	TerminateBufferIO(buf, true, 0);

	/* Pop the error context stack */
	error_context_stack = errcontext.previous;
}

/*
 * RelationGetNumberOfBlocks
 *		Determines the current number of pages in the relation.
 */
BlockNumber
RelationGetNumberOfBlocks(Relation relation)
{
	/* Open it at the smgr level if not already done */
	RelationOpenSmgr(relation);

	return smgrnblocks(relation->rd_smgr);
}

/*
 * RelationTruncate
 *		Physically truncate a relation to the specified number of blocks.
 *
 * As of Postgres 8.1, this includes getting rid of any buffers for the
 * blocks that are to be dropped; previously, callers had to do that.
 */
void
RelationTruncate(Relation rel, BlockNumber nblocks)
{
	/* Open it at the smgr level if not already done */
	RelationOpenSmgr(rel);

	/* Make sure rd_targblock isn't pointing somewhere past end */
	rel->rd_targblock = InvalidBlockNumber;

	/* Do the real work */
	smgrtruncate(rel->rd_smgr, nblocks, rel->rd_istemp);
}

/* ---------------------------------------------------------------------
 *		DropRelFileNodeBuffers
 *
 *		This function removes from the buffer pool all the pages of the
 *		specified relation that have block numbers >= firstDelBlock.
 *		(In particular, with firstDelBlock = 0, all pages are removed.)
 *		Dirty pages are simply dropped, without bothering to write them
 *		out first.	Therefore, this is NOT rollback-able, and so should be
 *		used only with extreme caution!
 *
 *		Currently, this is called only from smgr.c when the underlying file
 *		is about to be deleted or truncated (firstDelBlock is needed for
 *		the truncation case).  The data in the affected pages would therefore
 *		be deleted momentarily anyway, and there is no point in writing it.
 *		It is the responsibility of higher-level code to ensure that the
 *		deletion or truncation does not lose any data that could be needed
 *		later.	It is also the responsibility of higher-level code to ensure
 *		that no other process could be trying to load more pages of the
 *		relation into buffers.
 *
 *		XXX currently it sequentially searches the buffer pool, should be
 *		changed to more clever ways of searching.  However, this routine
 *		is used only in code paths that aren't very performance-critical,
 *		and we shouldn't slow down the hot paths to make it faster ...
 * --------------------------------------------------------------------
 */
void
DropRelFileNodeBuffers(RelFileNode rnode, bool istemp,
					   BlockNumber firstDelBlock)
{
	int			i;

	if (istemp)
	{
		DropRelFileNodeLocalBuffers(rnode, firstDelBlock);
		return;
	}

	for (i = 0; i < NBuffers; i++)
	{
		volatile BufferDesc *bufHdr = &BufferDescriptors[i];

		LockBufHdr(bufHdr);
		if (RelFileNodeEquals(bufHdr->tag.rnode, rnode) &&
			bufHdr->tag.blockNum >= firstDelBlock)
			InvalidateBuffer(bufHdr);	/* releases spinlock */
		else
			UnlockBufHdr(bufHdr);
	}
}

/* ---------------------------------------------------------------------
 *		DropDatabaseBuffers
 *
 *		This function removes all the buffers in the buffer cache for a
 *		particular database.  Dirty pages are simply dropped, without
 *		bothering to write them out first.	This is used when we destroy a
 *		database, to avoid trying to flush data to disk when the directory
 *		tree no longer exists.	Implementation is pretty similar to
 *		DropRelFileNodeBuffers() which is for destroying just one relation.
 * --------------------------------------------------------------------
 */
void
DropDatabaseBuffers(Oid dbid)
{
	int			i;
	volatile BufferDesc *bufHdr;

	/*
	 * We needn't consider local buffers, since by assumption the target
	 * database isn't our own.
	 */

	for (i = 0; i < NBuffers; i++)
	{
		bufHdr = &BufferDescriptors[i];
		LockBufHdr(bufHdr);
		if (bufHdr->tag.rnode.dbNode == dbid)
			InvalidateBuffer(bufHdr);	/* releases spinlock */
		else
			UnlockBufHdr(bufHdr);
	}
}

/* -----------------------------------------------------------------
 *		PrintBufferDescs
 *
 *		this function prints all the buffer descriptors, for debugging
 *		use only.
 * -----------------------------------------------------------------
 */
#ifdef NOT_USED
void
PrintBufferDescs(void)
{
	int			i;
	volatile BufferDesc *buf = BufferDescriptors;

	for (i = 0; i < NBuffers; ++i, ++buf)
	{
		/* theoretically we should lock the bufhdr here */
		elog(LOG,
			 "[%02d] (freeNext=%d, rel=%u/%u/%u, "
			 "blockNum=%u, flags=0x%x, refcount=%u %d)",
			 i, buf->freeNext,
			 buf->tag.rnode.spcNode, buf->tag.rnode.dbNode,
			 buf->tag.rnode.relNode,
			 buf->tag.blockNum, buf->flags,
			 buf->refcount, PrivateRefCount[i]);
	}
}
#endif

#ifdef NOT_USED
void
PrintPinnedBufs(void)
{
	int			i;
	volatile BufferDesc *buf = BufferDescriptors;

	for (i = 0; i < NBuffers; ++i, ++buf)
	{
		if (PrivateRefCount[i] > 0)
		{
			/* theoretically we should lock the bufhdr here */
			elog(LOG,
				 "[%02d] (freeNext=%d, rel=%u/%u/%u, "
				 "blockNum=%u, flags=0x%x, refcount=%u %d)",
				 i, buf->freeNext,
				 buf->tag.rnode.spcNode, buf->tag.rnode.dbNode,
				 buf->tag.rnode.relNode,
				 buf->tag.blockNum, buf->flags,
				 buf->refcount, PrivateRefCount[i]);
		}
	}
}
#endif

/* ---------------------------------------------------------------------
 *		FlushRelationBuffers
 *
 *		This function writes all dirty pages of a relation out to disk
 *		(or more accurately, out to kernel disk buffers), ensuring that the
 *		kernel has an up-to-date view of the relation.
 *
 *		Generally, the caller should be holding AccessExclusiveLock on the
 *		target relation to ensure that no other backend is busy dirtying
 *		more blocks of the relation; the effects can't be expected to last
 *		after the lock is released.
 *
 *		XXX currently it sequentially searches the buffer pool, should be
 *		changed to more clever ways of searching.  This routine is not
 *		used in any performance-critical code paths, so it's not worth
 *		adding additional overhead to normal paths to make it go faster;
 *		but see also DropRelFileNodeBuffers.
 * --------------------------------------------------------------------
 */
void
FlushRelationBuffers(Relation rel)
{
	int			i;
	volatile BufferDesc *bufHdr;

	/* Open rel at the smgr level if not already done */
	RelationOpenSmgr(rel);

	if (rel->rd_istemp)
	{
		for (i = 0; i < NLocBuffer; i++)
		{
			bufHdr = &LocalBufferDescriptors[i];
			if (RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node) &&
				(bufHdr->flags & BM_VALID) && (bufHdr->flags & BM_DIRTY))
			{
				ErrorContextCallback errcontext;

				/* Setup error traceback support for ereport() */
				errcontext.callback = buffer_write_error_callback;
				errcontext.arg = (void *) bufHdr;
				errcontext.previous = error_context_stack;
				error_context_stack = &errcontext;

				smgrwrite(rel->rd_smgr,
						  bufHdr->tag.blockNum,
						  (char *) LocalBufHdrGetBlock(bufHdr),
						  true);

				bufHdr->flags &= ~(BM_DIRTY | BM_JUST_DIRTIED);

				/* Pop the error context stack */
				error_context_stack = errcontext.previous;
			}
		}

		return;
	}

	/* Make sure we can handle the pin inside the loop */
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

	for (i = 0; i < NBuffers; i++)
	{
		bufHdr = &BufferDescriptors[i];
		LockBufHdr(bufHdr);
		if (RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node) &&
			(bufHdr->flags & BM_VALID) && (bufHdr->flags & BM_DIRTY))
		{
			PinBuffer_Locked(bufHdr);
			LWLockAcquire(bufHdr->content_lock, LW_SHARED);
			FlushBuffer(bufHdr, rel->rd_smgr);
			LWLockRelease(bufHdr->content_lock);
			UnpinBuffer(bufHdr, true);
		}
		else
			UnlockBufHdr(bufHdr);
	}
}

/*
 * ReleaseBuffer -- release the pin on a buffer
 */
void
ReleaseBuffer(Buffer buffer)
{
	volatile BufferDesc *bufHdr;

	if (!BufferIsValid(buffer))
		elog(ERROR, "bad buffer id: %d", buffer);

	ResourceOwnerForgetBuffer(CurrentResourceOwner, buffer);

	if (BufferIsLocal(buffer))
	{
		Assert(LocalRefCount[-buffer - 1] > 0);
		LocalRefCount[-buffer - 1]--;
		return;
	}

	bufHdr = &BufferDescriptors[buffer - 1];

	Assert(PrivateRefCount[buffer - 1] > 0);

	if (PrivateRefCount[buffer - 1] > 1)
		PrivateRefCount[buffer - 1]--;
	else
		UnpinBuffer(bufHdr, false);
}

/*
 * UnlockReleaseBuffer -- release the content lock and pin on a buffer
 *
 * This is just a shorthand for a common combination.
 */
void
UnlockReleaseBuffer(Buffer buffer)
{
	LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
	ReleaseBuffer(buffer);
}

/*
 * IncrBufferRefCount
 *		Increment the pin count on a buffer that we have *already* pinned
 *		at least once.
 *
 *		This function cannot be used on a buffer we do not have pinned,
 *		because it doesn't change the shared buffer state.
 */
void
IncrBufferRefCount(Buffer buffer)
{
	Assert(BufferIsPinned(buffer));
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);
	ResourceOwnerRememberBuffer(CurrentResourceOwner, buffer);
	if (BufferIsLocal(buffer))
		LocalRefCount[-buffer - 1]++;
	else
		PrivateRefCount[buffer - 1]++;
}

/*
 * SetBufferCommitInfoNeedsSave
 *
 *	Mark a buffer dirty when we have updated tuple commit-status bits in it.
 *
 * This is essentially the same as MarkBufferDirty, except that the caller
 * might have only share-lock instead of exclusive-lock on the buffer's
 * content lock.  We preserve the distinction mainly as a way of documenting
 * that the caller has not made a critical data change --- the status-bit
 * update could be redone by someone else just as easily.  Therefore, no WAL
 * log record need be generated, whereas calls to MarkBufferDirty really ought
 * to be associated with a WAL-entry-creating action.
 */
void
SetBufferCommitInfoNeedsSave(Buffer buffer)
{
	volatile BufferDesc *bufHdr;

	if (!BufferIsValid(buffer))
		elog(ERROR, "bad buffer id: %d", buffer);

	if (BufferIsLocal(buffer))
	{
		MarkLocalBufferDirty(buffer);
		return;
	}

	bufHdr = &BufferDescriptors[buffer - 1];

	Assert(PrivateRefCount[buffer - 1] > 0);
	/* here, either share or exclusive lock is OK */
	Assert(LWLockHeldByMe(bufHdr->content_lock));

	/*
	 * This routine might get called many times on the same page, if we are
	 * making the first scan after commit of an xact that added/deleted many
	 * tuples.	So, be as quick as we can if the buffer is already dirty.  We
	 * do this by not acquiring spinlock if it looks like the status bits are
	 * already OK.	(Note it is okay if someone else clears BM_JUST_DIRTIED
	 * immediately after we look, because the buffer content update is already
	 * done and will be reflected in the I/O.)
	 */
	if ((bufHdr->flags & (BM_DIRTY | BM_JUST_DIRTIED)) !=
		(BM_DIRTY | BM_JUST_DIRTIED))
	{
		LockBufHdr(bufHdr);
		Assert(bufHdr->refcount > 0);
		if (!(bufHdr->flags & BM_DIRTY) && VacuumCostActive)
			VacuumCostBalance += VacuumCostPageDirty;
		bufHdr->flags |= (BM_DIRTY | BM_JUST_DIRTIED);
		UnlockBufHdr(bufHdr);
	}
}

/*
 * Release buffer content locks for shared buffers.
 *
 * Used to clean up after errors.
 *
 * Currently, we can expect that lwlock.c's LWLockReleaseAll() took care
 * of releasing buffer content locks per se; the only thing we need to deal
 * with here is clearing any PIN_COUNT request that was in progress.
 */
void
UnlockBuffers(void)
{
	volatile BufferDesc *buf = PinCountWaitBuf;

	if (buf)
	{
		LockBufHdr(buf);

		/*
		 * Don't complain if flag bit not set; it could have been reset but we
		 * got a cancel/die interrupt before getting the signal.
		 */
		if ((buf->flags & BM_PIN_COUNT_WAITER) != 0 &&
			buf->wait_backend_pid == MyProcPid)
			buf->flags &= ~BM_PIN_COUNT_WAITER;

		UnlockBufHdr(buf);

		PinCountWaitBuf = NULL;
	}
}

/*
 * Acquire or release the content_lock for the buffer.
 */
void
LockBuffer(Buffer buffer, int mode)
{
	volatile BufferDesc *buf;

	Assert(BufferIsValid(buffer));
	if (BufferIsLocal(buffer))
		return;					/* local buffers need no lock */

	buf = &(BufferDescriptors[buffer - 1]);

	if (mode == BUFFER_LOCK_UNLOCK)
		LWLockRelease(buf->content_lock);
	else if (mode == BUFFER_LOCK_SHARE)
		LWLockAcquire(buf->content_lock, LW_SHARED);
	else if (mode == BUFFER_LOCK_EXCLUSIVE)
		LWLockAcquire(buf->content_lock, LW_EXCLUSIVE);
	else
		elog(ERROR, "unrecognized buffer lock mode: %d", mode);
}

/*
 * Acquire the content_lock for the buffer, but only if we don't have to wait.
 *
 * This assumes the caller wants BUFFER_LOCK_EXCLUSIVE mode.
 */
bool
ConditionalLockBuffer(Buffer buffer)
{
	volatile BufferDesc *buf;

	Assert(BufferIsValid(buffer));
	if (BufferIsLocal(buffer))
		return true;			/* act as though we got it */

	buf = &(BufferDescriptors[buffer - 1]);

	return LWLockConditionalAcquire(buf->content_lock, LW_EXCLUSIVE);
}

/*
 * LockBufferForCleanup - lock a buffer in preparation for deleting items
 *
 * Items may be deleted from a disk page only when the caller (a) holds an
 * exclusive lock on the buffer and (b) has observed that no other backend
 * holds a pin on the buffer.  If there is a pin, then the other backend
 * might have a pointer into the buffer (for example, a heapscan reference
 * to an item --- see README for more details).  It's OK if a pin is added
 * after the cleanup starts, however; the newly-arrived backend will be
 * unable to look at the page until we release the exclusive lock.
 *
 * To implement this protocol, a would-be deleter must pin the buffer and
 * then call LockBufferForCleanup().  LockBufferForCleanup() is similar to
 * LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE), except that it loops until
 * it has successfully observed pin count = 1.
 */
void
LockBufferForCleanup(Buffer buffer)
{
	volatile BufferDesc *bufHdr;

	Assert(BufferIsValid(buffer));
	Assert(PinCountWaitBuf == NULL);

	if (BufferIsLocal(buffer))
	{
		/* There should be exactly one pin */
		if (LocalRefCount[-buffer - 1] != 1)
			elog(ERROR, "incorrect local pin count: %d",
				 LocalRefCount[-buffer - 1]);
		/* Nobody else to wait for */
		return;
	}

	/* There should be exactly one local pin */
	if (PrivateRefCount[buffer - 1] != 1)
		elog(ERROR, "incorrect local pin count: %d",
			 PrivateRefCount[buffer - 1]);

	bufHdr = &BufferDescriptors[buffer - 1];

	for (;;)
	{
		/* Try to acquire lock */
		LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
		LockBufHdr(bufHdr);
		Assert(bufHdr->refcount > 0);
		if (bufHdr->refcount == 1)
		{
			/* Successfully acquired exclusive lock with pincount 1 */
			UnlockBufHdr(bufHdr);
			return;
		}
		/* Failed, so mark myself as waiting for pincount 1 */
		if (bufHdr->flags & BM_PIN_COUNT_WAITER)
		{
			UnlockBufHdr(bufHdr);
			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
			elog(ERROR, "multiple backends attempting to wait for pincount 1");
		}
		bufHdr->wait_backend_pid = MyProcPid;
		bufHdr->flags |= BM_PIN_COUNT_WAITER;
		PinCountWaitBuf = bufHdr;
		UnlockBufHdr(bufHdr);
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		/* Wait to be signaled by UnpinBuffer() */
		ProcWaitForSignal();
		PinCountWaitBuf = NULL;
		/* Loop back and try again */
	}
}

/*
 *	Functions for buffer I/O handling
 *
 *	Note: We assume that nested buffer I/O never occurs.
 *	i.e at most one io_in_progress lock is held per proc.
 *
 *	Also note that these are used only for shared buffers, not local ones.
 */

/*
 * WaitIO -- Block until the IO_IN_PROGRESS flag on 'buf' is cleared.
 */
static void
WaitIO(volatile BufferDesc *buf)
{
	/*
	 * Changed to wait until there's no IO - Inoue 01/13/2000
	 *
	 * Note this is *necessary* because an error abort in the process doing
	 * I/O could release the io_in_progress_lock prematurely. See
	 * AbortBufferIO.
	 */
	for (;;)
	{
		BufFlags	sv_flags;

		/*
		 * It may not be necessary to acquire the spinlock to check the flag
		 * here, but since this test is essential for correctness, we'd better
		 * play it safe.
		 */
		LockBufHdr(buf);
		sv_flags = buf->flags;
		UnlockBufHdr(buf);
		if (!(sv_flags & BM_IO_IN_PROGRESS))
			break;
		LWLockAcquire(buf->io_in_progress_lock, LW_SHARED);
		LWLockRelease(buf->io_in_progress_lock);
	}
}

/*
 * StartBufferIO: begin I/O on this buffer
 *	(Assumptions)
 *	My process is executing no IO
 *	The buffer is Pinned
 *
 * In some scenarios there are race conditions in which multiple backends
 * could attempt the same I/O operation concurrently.  If someone else
 * has already started I/O on this buffer then we will block on the
 * io_in_progress lock until he's done.
 *
 * Input operations are only attempted on buffers that are not BM_VALID,
 * and output operations only on buffers that are BM_VALID and BM_DIRTY,
 * so we can always tell if the work is already done.
 *
 * Returns TRUE if we successfully marked the buffer as I/O busy,
 * FALSE if someone else already did the work.
 */
static bool
StartBufferIO(volatile BufferDesc *buf, bool forInput)
{
	Assert(!InProgressBuf);

	for (;;)
	{
		/*
		 * Grab the io_in_progress lock so that other processes can wait for
		 * me to finish the I/O.
		 */
		LWLockAcquire(buf->io_in_progress_lock, LW_EXCLUSIVE);

		LockBufHdr(buf);

		if (!(buf->flags & BM_IO_IN_PROGRESS))
			break;

		/*
		 * The only way BM_IO_IN_PROGRESS could be set when the io_in_progress
		 * lock isn't held is if the process doing the I/O is recovering from
		 * an error (see AbortBufferIO).  If that's the case, we must wait for
		 * him to get unwedged.
		 */
		UnlockBufHdr(buf);
		LWLockRelease(buf->io_in_progress_lock);
		WaitIO(buf);
	}

	/* Once we get here, there is definitely no I/O active on this buffer */

	if (forInput ? (buf->flags & BM_VALID) : !(buf->flags & BM_DIRTY))
	{
		/* someone else already did the I/O */
		UnlockBufHdr(buf);
		LWLockRelease(buf->io_in_progress_lock);
		return false;
	}

	buf->flags |= BM_IO_IN_PROGRESS;

	UnlockBufHdr(buf);

	InProgressBuf = buf;
	IsForInput = forInput;

	return true;
}

/*
 * TerminateBufferIO: release a buffer we were doing I/O on
 *	(Assumptions)
 *	My process is executing IO for the buffer
 *	BM_IO_IN_PROGRESS bit is set for the buffer
 *	We hold the buffer's io_in_progress lock
 *	The buffer is Pinned
 *
 * If clear_dirty is TRUE and BM_JUST_DIRTIED is not set, we clear the
 * buffer's BM_DIRTY flag.  This is appropriate when terminating a
 * successful write.  The check on BM_JUST_DIRTIED is necessary to avoid
 * marking the buffer clean if it was re-dirtied while we were writing.
 *
 * set_flag_bits gets ORed into the buffer's flags.  It must include
 * BM_IO_ERROR in a failure case.  For successful completion it could
 * be 0, or BM_VALID if we just finished reading in the page.
 */
static void
TerminateBufferIO(volatile BufferDesc *buf, bool clear_dirty,
				  int set_flag_bits)
{
	Assert(buf == InProgressBuf);

	LockBufHdr(buf);

	Assert(buf->flags & BM_IO_IN_PROGRESS);
	buf->flags &= ~(BM_IO_IN_PROGRESS | BM_IO_ERROR);
	if (clear_dirty && !(buf->flags & BM_JUST_DIRTIED))
		buf->flags &= ~BM_DIRTY;
	buf->flags |= set_flag_bits;

	UnlockBufHdr(buf);

	InProgressBuf = NULL;

	LWLockRelease(buf->io_in_progress_lock);
}

/*
 * AbortBufferIO: Clean up any active buffer I/O after an error.
 *
 *	All LWLocks we might have held have been released,
 *	but we haven't yet released buffer pins, so the buffer is still pinned.
 *
 *	If I/O was in progress, we always set BM_IO_ERROR, even though it's
 *	possible the error condition wasn't related to the I/O.
 */
void
AbortBufferIO(void)
{
	volatile BufferDesc *buf = InProgressBuf;

	if (buf)
	{
		/*
		 * Since LWLockReleaseAll has already been called, we're not holding
		 * the buffer's io_in_progress_lock. We have to re-acquire it so that
		 * we can use TerminateBufferIO. Anyone who's executing WaitIO on the
		 * buffer will be in a busy spin until we succeed in doing this.
		 */
		LWLockAcquire(buf->io_in_progress_lock, LW_EXCLUSIVE);

		LockBufHdr(buf);
		Assert(buf->flags & BM_IO_IN_PROGRESS);
		if (IsForInput)
		{
			Assert(!(buf->flags & BM_DIRTY));
			/* We'd better not think buffer is valid yet */
			Assert(!(buf->flags & BM_VALID));
			UnlockBufHdr(buf);
		}
		else
		{
			BufFlags	sv_flags;

			sv_flags = buf->flags;
			Assert(sv_flags & BM_DIRTY);
			UnlockBufHdr(buf);
			/* Issue notice if this is not the first failure... */
			if (sv_flags & BM_IO_ERROR)
			{
				/* Buffer is pinned, so we can read tag without spinlock */
				ereport(WARNING,
						(errcode(ERRCODE_IO_ERROR),
						 errmsg("could not write block %u of %u/%u/%u",
								buf->tag.blockNum,
								buf->tag.rnode.spcNode,
								buf->tag.rnode.dbNode,
								buf->tag.rnode.relNode),
						 errdetail("Multiple failures --- write error might be permanent.")));
			}
		}
		TerminateBufferIO(buf, false, BM_IO_ERROR);
	}
}

/*
 * Error context callback for errors occurring during buffer writes.
 */
static void
buffer_write_error_callback(void *arg)
{
	volatile BufferDesc *bufHdr = (volatile BufferDesc *) arg;

	/* Buffer is pinned, so we can read the tag without locking the spinlock */
	if (bufHdr != NULL)
		errcontext("writing block %u of relation %u/%u/%u",
				   bufHdr->tag.blockNum,
				   bufHdr->tag.rnode.spcNode,
				   bufHdr->tag.rnode.dbNode,
				   bufHdr->tag.rnode.relNode);
}