• Tom Lane's avatar
    Get rid of slru.c's hardwired insistence on a fixed number of slots per · 887a7c61
    Tom Lane authored
    SLRU area.  The number of slots is still a compile-time constant (someday
    we might want to change that), but at least it's a different constant for
    each SLRU area.  Increase number of subtrans buffers to 32 based on
    experimentation with a heavily subtrans-bashing test case, and increase
    number of multixact member buffers to 16, since it's obviously silly for
    it not to be at least twice the number of multixact offset buffers.
    887a7c61
clog.c 12.5 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
/*-------------------------------------------------------------------------
 *
 * clog.c
 *		PostgreSQL transaction-commit-log manager
 *
 * This module replaces the old "pg_log" access code, which treated pg_log
 * essentially like a relation, in that it went through the regular buffer
 * manager.  The problem with that was that there wasn't any good way to
 * recycle storage space for transactions so old that they'll never be
 * looked up again.  Now we use specialized access code so that the commit
 * log can be broken into relatively small, independent segments.
 *
 * XLOG interactions: this module generates an XLOG record whenever a new
 * CLOG page is initialized to zeroes.	Other writes of CLOG come from
 * recording of transaction commit or abort in xact.c, which generates its
 * own XLOG records for these events and will re-perform the status update
 * on redo; so we need make no additional XLOG entry here.	Also, the XLOG
 * is guaranteed flushed through the XLOG commit record before we are called
 * to log a commit, so the WAL rule "write xlog before data" is satisfied
 * automatically for commits, and we don't really care for aborts.  Therefore,
 * we don't need to mark CLOG pages with LSN information; we have enough
 * synchronization already.
 *
 * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * $PostgreSQL: pgsql/src/backend/access/transam/clog.c,v 1.36 2005/12/06 23:08:32 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/clog.h"
#include "access/slru.h"
#include "postmaster/bgwriter.h"


/*
 * Defines for CLOG page sizes.  A page is the same BLCKSZ as is used
 * everywhere else in Postgres.
 *
 * Note: because TransactionIds are 32 bits and wrap around at 0xFFFFFFFF,
 * CLOG page numbering also wraps around at 0xFFFFFFFF/CLOG_XACTS_PER_PAGE,
 * and CLOG segment numbering at 0xFFFFFFFF/CLOG_XACTS_PER_SEGMENT.  We need
 * take no explicit notice of that fact in this module, except when comparing
 * segment and page numbers in TruncateCLOG (see CLOGPagePrecedes).
 */

/* We need two bits per xact, so four xacts fit in a byte */
#define CLOG_BITS_PER_XACT	2
#define CLOG_XACTS_PER_BYTE 4
#define CLOG_XACTS_PER_PAGE (BLCKSZ * CLOG_XACTS_PER_BYTE)
#define CLOG_XACT_BITMASK	((1 << CLOG_BITS_PER_XACT) - 1)

#define TransactionIdToPage(xid)	((xid) / (TransactionId) CLOG_XACTS_PER_PAGE)
#define TransactionIdToPgIndex(xid) ((xid) % (TransactionId) CLOG_XACTS_PER_PAGE)
#define TransactionIdToByte(xid)	(TransactionIdToPgIndex(xid) / CLOG_XACTS_PER_BYTE)
#define TransactionIdToBIndex(xid)	((xid) % (TransactionId) CLOG_XACTS_PER_BYTE)


/*
 * Link to shared-memory data structures for CLOG control
 */
static SlruCtlData ClogCtlData;

#define ClogCtl (&ClogCtlData)


static int	ZeroCLOGPage(int pageno, bool writeXlog);
static bool CLOGPagePrecedes(int page1, int page2);
static void WriteZeroPageXlogRec(int pageno);


/*
 * Record the final state of a transaction in the commit log.
 *
 * NB: this is a low-level routine and is NOT the preferred entry point
 * for most uses; TransactionLogUpdate() in transam.c is the intended caller.
 */
void
TransactionIdSetStatus(TransactionId xid, XidStatus status)
{
	int			pageno = TransactionIdToPage(xid);
	int			byteno = TransactionIdToByte(xid);
	int			bshift = TransactionIdToBIndex(xid) * CLOG_BITS_PER_XACT;
	int			slotno;
	char	   *byteptr;
	char		byteval;

	Assert(status == TRANSACTION_STATUS_COMMITTED ||
		   status == TRANSACTION_STATUS_ABORTED ||
		   status == TRANSACTION_STATUS_SUB_COMMITTED);

	LWLockAcquire(CLogControlLock, LW_EXCLUSIVE);

	slotno = SimpleLruReadPage(ClogCtl, pageno, xid);
	byteptr = ClogCtl->shared->page_buffer[slotno] + byteno;

	/* Current state should be 0, subcommitted or target state */
	Assert(((*byteptr >> bshift) & CLOG_XACT_BITMASK) == 0 ||
		   ((*byteptr >> bshift) & CLOG_XACT_BITMASK) == TRANSACTION_STATUS_SUB_COMMITTED ||
		   ((*byteptr >> bshift) & CLOG_XACT_BITMASK) == status);

	/* note this assumes exclusive access to the clog page */
	byteval = *byteptr;
	byteval &= ~(((1 << CLOG_BITS_PER_XACT) - 1) << bshift);
	byteval |= (status << bshift);
	*byteptr = byteval;

	ClogCtl->shared->page_dirty[slotno] = true;

	LWLockRelease(CLogControlLock);
}

/*
 * Interrogate the state of a transaction in the commit log.
 *
 * NB: this is a low-level routine and is NOT the preferred entry point
 * for most uses; TransactionLogFetch() in transam.c is the intended caller.
 */
XidStatus
TransactionIdGetStatus(TransactionId xid)
{
	int			pageno = TransactionIdToPage(xid);
	int			byteno = TransactionIdToByte(xid);
	int			bshift = TransactionIdToBIndex(xid) * CLOG_BITS_PER_XACT;
	int			slotno;
	char	   *byteptr;
	XidStatus	status;

	/* lock is acquired by SimpleLruReadPage_ReadOnly */

	slotno = SimpleLruReadPage_ReadOnly(ClogCtl, pageno, xid);
	byteptr = ClogCtl->shared->page_buffer[slotno] + byteno;

	status = (*byteptr >> bshift) & CLOG_XACT_BITMASK;

	LWLockRelease(CLogControlLock);

	return status;
}


/*
 * Initialization of shared memory for CLOG
 */
Size
CLOGShmemSize(void)
{
	return SimpleLruShmemSize(NUM_CLOG_BUFFERS);
}

void
CLOGShmemInit(void)
{
	ClogCtl->PagePrecedes = CLOGPagePrecedes;
	SimpleLruInit(ClogCtl, "CLOG Ctl", NUM_CLOG_BUFFERS,
				  CLogControlLock, "pg_clog");
}

/*
 * This func must be called ONCE on system install.  It creates
 * the initial CLOG segment.  (The CLOG directory is assumed to
 * have been created by the initdb shell script, and CLOGShmemInit
 * must have been called already.)
 */
void
BootStrapCLOG(void)
{
	int			slotno;

	LWLockAcquire(CLogControlLock, LW_EXCLUSIVE);

	/* Create and zero the first page of the commit log */
	slotno = ZeroCLOGPage(0, false);

	/* Make sure it's written out */
	SimpleLruWritePage(ClogCtl, slotno, NULL);
	Assert(!ClogCtl->shared->page_dirty[slotno]);

	LWLockRelease(CLogControlLock);
}

/*
 * Initialize (or reinitialize) a page of CLOG to zeroes.
 * If writeXlog is TRUE, also emit an XLOG record saying we did this.
 *
 * The page is not actually written, just set up in shared memory.
 * The slot number of the new page is returned.
 *
 * Control lock must be held at entry, and will be held at exit.
 */
static int
ZeroCLOGPage(int pageno, bool writeXlog)
{
	int			slotno;

	slotno = SimpleLruZeroPage(ClogCtl, pageno);

	if (writeXlog)
		WriteZeroPageXlogRec(pageno);

	return slotno;
}

/*
 * This must be called ONCE during postmaster or standalone-backend startup,
 * after StartupXLOG has initialized ShmemVariableCache->nextXid.
 */
void
StartupCLOG(void)
{
	TransactionId xid = ShmemVariableCache->nextXid;
	int			pageno = TransactionIdToPage(xid);

	LWLockAcquire(CLogControlLock, LW_EXCLUSIVE);

	/*
	 * Initialize our idea of the latest page number.
	 */
	ClogCtl->shared->latest_page_number = pageno;

	/*
	 * Zero out the remainder of the current clog page.  Under normal
	 * circumstances it should be zeroes already, but it seems at least
	 * theoretically possible that XLOG replay will have settled on a nextXID
	 * value that is less than the last XID actually used and marked by the
	 * previous database lifecycle (since subtransaction commit writes clog
	 * but makes no WAL entry).  Let's just be safe. (We need not worry about
	 * pages beyond the current one, since those will be zeroed when first
	 * used.  For the same reason, there is no need to do anything when
	 * nextXid is exactly at a page boundary; and it's likely that the
	 * "current" page doesn't exist yet in that case.)
	 */
	if (TransactionIdToPgIndex(xid) != 0)
	{
		int			byteno = TransactionIdToByte(xid);
		int			bshift = TransactionIdToBIndex(xid) * CLOG_BITS_PER_XACT;
		int			slotno;
		char	   *byteptr;

		slotno = SimpleLruReadPage(ClogCtl, pageno, xid);
		byteptr = ClogCtl->shared->page_buffer[slotno] + byteno;

		/* Zero so-far-unused positions in the current byte */
		*byteptr &= (1 << bshift) - 1;
		/* Zero the rest of the page */
		MemSet(byteptr + 1, 0, BLCKSZ - byteno - 1);

		ClogCtl->shared->page_dirty[slotno] = true;
	}

	LWLockRelease(CLogControlLock);
}

/*
 * This must be called ONCE during postmaster or standalone-backend shutdown
 */
void
ShutdownCLOG(void)
{
	/* Flush dirty CLOG pages to disk */
	SimpleLruFlush(ClogCtl, false);
}

/*
 * Perform a checkpoint --- either during shutdown, or on-the-fly
 */
void
CheckPointCLOG(void)
{
	/* Flush dirty CLOG pages to disk */
	SimpleLruFlush(ClogCtl, true);
}


/*
 * Make sure that CLOG has room for a newly-allocated XID.
 *
 * NB: this is called while holding XidGenLock.  We want it to be very fast
 * most of the time; even when it's not so fast, no actual I/O need happen
 * unless we're forced to write out a dirty clog or xlog page to make room
 * in shared memory.
 */
void
ExtendCLOG(TransactionId newestXact)
{
	int			pageno;

	/*
	 * No work except at first XID of a page.  But beware: just after
	 * wraparound, the first XID of page zero is FirstNormalTransactionId.
	 */
	if (TransactionIdToPgIndex(newestXact) != 0 &&
		!TransactionIdEquals(newestXact, FirstNormalTransactionId))
		return;

	pageno = TransactionIdToPage(newestXact);

	LWLockAcquire(CLogControlLock, LW_EXCLUSIVE);

	/* Zero the page and make an XLOG entry about it */
	ZeroCLOGPage(pageno, true);

	LWLockRelease(CLogControlLock);
}


/*
 * Remove all CLOG segments before the one holding the passed transaction ID
 *
 * When this is called, we know that the database logically contains no
 * reference to transaction IDs older than oldestXact.	However, we must
 * not truncate the CLOG until we have performed a checkpoint, to ensure
 * that no such references remain on disk either; else a crash just after
 * the truncation might leave us with a problem.  Since CLOG segments hold
 * a large number of transactions, the opportunity to actually remove a
 * segment is fairly rare, and so it seems best not to do the checkpoint
 * unless we have confirmed that there is a removable segment.	Therefore
 * we issue the checkpoint command here, not in higher-level code as might
 * seem cleaner.
 */
void
TruncateCLOG(TransactionId oldestXact)
{
	int			cutoffPage;

	/*
	 * The cutoff point is the start of the segment containing oldestXact. We
	 * pass the *page* containing oldestXact to SimpleLruTruncate.
	 */
	cutoffPage = TransactionIdToPage(oldestXact);

	/* Check to see if there's any files that could be removed */
	if (!SlruScanDirectory(ClogCtl, cutoffPage, false))
		return;					/* nothing to remove */

	/* Perform a CHECKPOINT */
	RequestCheckpoint(true, false);

	/* Now we can remove the old CLOG segment(s) */
	SimpleLruTruncate(ClogCtl, cutoffPage);
}


/*
 * Decide which of two CLOG page numbers is "older" for truncation purposes.
 *
 * We need to use comparison of TransactionIds here in order to do the right
 * thing with wraparound XID arithmetic.  However, if we are asked about
 * page number zero, we don't want to hand InvalidTransactionId to
 * TransactionIdPrecedes: it'll get weird about permanent xact IDs.  So,
 * offset both xids by FirstNormalTransactionId to avoid that.
 */
static bool
CLOGPagePrecedes(int page1, int page2)
{
	TransactionId xid1;
	TransactionId xid2;

	xid1 = ((TransactionId) page1) * CLOG_XACTS_PER_PAGE;
	xid1 += FirstNormalTransactionId;
	xid2 = ((TransactionId) page2) * CLOG_XACTS_PER_PAGE;
	xid2 += FirstNormalTransactionId;

	return TransactionIdPrecedes(xid1, xid2);
}


/*
 * Write a ZEROPAGE xlog record
 *
 * Note: xlog record is marked as outside transaction control, since we
 * want it to be redone whether the invoking transaction commits or not.
 * (Besides which, this is normally done just before entering a transaction.)
 */
static void
WriteZeroPageXlogRec(int pageno)
{
	XLogRecData rdata;

	rdata.data = (char *) (&pageno);
	rdata.len = sizeof(int);
	rdata.buffer = InvalidBuffer;
	rdata.next = NULL;
	(void) XLogInsert(RM_CLOG_ID, CLOG_ZEROPAGE | XLOG_NO_TRAN, &rdata);
}

/*
 * CLOG resource manager's routines
 */
void
clog_redo(XLogRecPtr lsn, XLogRecord *record)
{
	uint8		info = record->xl_info & ~XLR_INFO_MASK;

	if (info == CLOG_ZEROPAGE)
	{
		int			pageno;
		int			slotno;

		memcpy(&pageno, XLogRecGetData(record), sizeof(int));

		LWLockAcquire(CLogControlLock, LW_EXCLUSIVE);

		slotno = ZeroCLOGPage(pageno, false);
		SimpleLruWritePage(ClogCtl, slotno, NULL);
		Assert(!ClogCtl->shared->page_dirty[slotno]);

		LWLockRelease(CLogControlLock);
	}
}

void
clog_desc(char *buf, uint8 xl_info, char *rec)
{
	uint8		info = xl_info & ~XLR_INFO_MASK;

	if (info == CLOG_ZEROPAGE)
	{
		int			pageno;

		memcpy(&pageno, rec, sizeof(int));
		sprintf(buf + strlen(buf), "zeropage: %d", pageno);
	}
	else
		strcat(buf, "UNKNOWN");
}