* subtrans.c
* PostgreSQL subtransaction-log manager
*
- * The pg_subtrans manager is a pg_clog-like manager that stores the parent
+ * The pg_subtrans manager is a pg_xact-like manager that stores the parent
* transaction Id for each transaction. It is a fundamental part of the
- * nested transactions implementation. A main transaction has a parent
+ * nested transactions implementation. A main transaction has a parent
* of InvalidTransactionId, and each subtransaction has its immediate parent.
* The tree can easily be walked from child to parent, but not in the
* opposite direction.
*
- * This code is based on clog.c, but the robustness requirements
- * are completely different from pg_clog, because we only need to remember
+ * This code is based on xact.c, but the robustness requirements
+ * are completely different from pg_xact, because we only need to remember
* pg_subtrans information for currently-open transactions. Thus, there is
* no need to preserve data over a crash and restart.
*
* data across crashes. During database startup, we simply force the
* currently-active page of SUBTRANS to zeroes.
*
- * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $PostgreSQL: pgsql/src/backend/access/transam/subtrans.c,v 1.9 2005/06/17 22:32:42 tgl Exp $
+ * src/backend/access/transam/subtrans.c
*
*-------------------------------------------------------------------------
*/
#include "access/slru.h"
#include "access/subtrans.h"
-#include "utils/tqual.h"
+#include "access/transam.h"
+#include "pg_trace.h"
+#include "utils/snapmgr.h"
/*
* Note: because TransactionIds are 32 bits and wrap around at 0xFFFFFFFF,
* SubTrans page numbering also wraps around at
* 0xFFFFFFFF/SUBTRANS_XACTS_PER_PAGE, and segment numbering at
- * 0xFFFFFFFF/SUBTRANS_XACTS_PER_PAGE/SLRU_SEGMENTS_PER_PAGE. We need take no
+ * 0xFFFFFFFF/SUBTRANS_XACTS_PER_PAGE/SLRU_PAGES_PER_SEGMENT. We need take no
* explicit notice of that fact in this module, except when comparing segment
- * and page numbers in TruncateSUBTRANS (see SubTransPagePrecedes).
+ * and page numbers in TruncateSUBTRANS (see SubTransPagePrecedes) and zeroing
+ * them in StartupSUBTRANS.
*/
/* We need four bytes per xact */
int slotno;
TransactionId *ptr;
+ Assert(TransactionIdIsValid(parent));
+ Assert(TransactionIdFollows(xid, parent));
+
LWLockAcquire(SubtransControlLock, LW_EXCLUSIVE);
- slotno = SimpleLruReadPage(SubTransCtl, pageno, xid);
+ slotno = SimpleLruReadPage(SubTransCtl, pageno, true, xid);
ptr = (TransactionId *) SubTransCtl->shared->page_buffer[slotno];
ptr += entryno;
- /* Current state should be 0 */
- Assert(*ptr == InvalidTransactionId);
-
- *ptr = parent;
-
- SubTransCtl->shared->page_status[slotno] = SLRU_PAGE_DIRTY;
+ /*
+ * It's possible we'll try to set the parent xid multiple times but we
+ * shouldn't ever be changing the xid from one valid xid to another valid
+ * xid, which would corrupt the data structure.
+ */
+ if (*ptr != parent)
+ {
+ Assert(*ptr == InvalidTransactionId);
+ *ptr = parent;
+ SubTransCtl->shared->page_dirty[slotno] = true;
+ }
LWLockRelease(SubtransControlLock);
}
if (!TransactionIdIsNormal(xid))
return InvalidTransactionId;
- LWLockAcquire(SubtransControlLock, LW_EXCLUSIVE);
+ /* lock is acquired by SimpleLruReadPage_ReadOnly */
- slotno = SimpleLruReadPage(SubTransCtl, pageno, xid);
+ slotno = SimpleLruReadPage_ReadOnly(SubTransCtl, pageno, xid);
ptr = (TransactionId *) SubTransCtl->shared->page_buffer[slotno];
ptr += entryno;
if (TransactionIdPrecedes(parentXid, TransactionXmin))
break;
parentXid = SubTransGetParent(parentXid);
+
+ /*
+ * By convention the parent xid gets allocated first, so should always
+ * precede the child xid. Anything else points to a corrupted data
+ * structure that could lead to an infinite loop, so exit.
+ */
+ if (!TransactionIdPrecedes(parentXid, previousXid))
+ elog(ERROR, "pg_subtrans contains invalid entry: xid %u points to parent xid %u",
+ previousXid, parentXid);
}
Assert(TransactionIdIsValid(previousXid));
/*
* Initialization of shared memory for SUBTRANS
*/
-
-int
+Size
SUBTRANSShmemSize(void)
{
- return SimpleLruShmemSize();
+ return SimpleLruShmemSize(NUM_SUBTRANS_BUFFERS, 0);
}
void
SUBTRANSShmemInit(void)
{
SubTransCtl->PagePrecedes = SubTransPagePrecedes;
- SimpleLruInit(SubTransCtl, "SUBTRANS Ctl",
- SubtransControlLock, "pg_subtrans");
+ SimpleLruInit(SubTransCtl, "subtrans", NUM_SUBTRANS_BUFFERS, 0,
+ SubtransControlLock, "pg_subtrans",
+ LWTRANCHE_SUBTRANS_BUFFERS);
/* Override default assumption that writes should be fsync'd */
SubTransCtl->do_fsync = false;
}
* must have been called already.)
*
* Note: it's not really necessary to create the initial segment now,
- * since slru.c would create it on first write anyway. But we may as well
+ * since slru.c would create it on first write anyway. But we may as well
* do it to be sure the directory is set up correctly.
*/
void
slotno = ZeroSUBTRANSPage(0);
/* Make sure it's written out */
- SimpleLruWritePage(SubTransCtl, slotno, NULL);
- Assert(SubTransCtl->shared->page_status[slotno] == SLRU_PAGE_CLEAN);
+ SimpleLruWritePage(SubTransCtl, slotno);
+ Assert(!SubTransCtl->shared->page_dirty[slotno]);
LWLockRelease(SubtransControlLock);
}
/*
* Since we don't expect pg_subtrans to be valid across crashes, we
* initialize the currently-active page(s) to zeroes during startup.
- * Whenever we advance into a new page, ExtendSUBTRANS will likewise
- * zero the new page without regard to whatever was previously on
- * disk.
+ * Whenever we advance into a new page, ExtendSUBTRANS will likewise zero
+ * the new page without regard to whatever was previously on disk.
*/
LWLockAcquire(SubtransControlLock, LW_EXCLUSIVE);
{
(void) ZeroSUBTRANSPage(startPage);
startPage++;
+ /* must account for wraparound */
+ if (startPage > TransactionIdToPage(MaxTransactionId))
+ startPage = 0;
}
(void) ZeroSUBTRANSPage(startPage);
* This is not actually necessary from a correctness point of view. We do
* it merely as a debugging aid.
*/
+ TRACE_POSTGRESQL_SUBTRANS_CHECKPOINT_START(false);
SimpleLruFlush(SubTransCtl, false);
+ TRACE_POSTGRESQL_SUBTRANS_CHECKPOINT_DONE(false);
}
/*
* Flush dirty SUBTRANS pages to disk
*
* This is not actually necessary from a correctness point of view. We do
- * it merely to improve the odds that writing of dirty pages is done
- * by the checkpoint process and not by backends.
+ * it merely to improve the odds that writing of dirty pages is done by
+ * the checkpoint process and not by backends.
*/
+ TRACE_POSTGRESQL_SUBTRANS_CHECKPOINT_START(true);
SimpleLruFlush(SubTransCtl, true);
+ TRACE_POSTGRESQL_SUBTRANS_CHECKPOINT_DONE(true);
}
int cutoffPage;
/*
- * The cutoff point is the start of the segment containing oldestXact.
- * We pass the *page* containing oldestXact to SimpleLruTruncate.
+ * The cutoff point is the start of the segment containing oldestXact. We
+ * pass the *page* containing oldestXact to SimpleLruTruncate. We step
+ * back one transaction to avoid passing a cutoff page that hasn't been
+ * created yet in the rare case that oldestXact would be the first item on
+ * a page and oldestXact == next XID. In that case, if we didn't subtract
+ * one, we'd trigger SimpleLruTruncate's wraparound detection.
*/
+ TransactionIdRetreat(oldestXact);
cutoffPage = TransactionIdToPage(oldestXact);
SimpleLruTruncate(SubTransCtl, cutoffPage);