Repair longstanding bug in slru/clog logic: it is possible for two backends

to try to create a log segment file concurrently, but the code erroneously
specified O_EXCL to open(), resulting in a needless failure.  Before 7.4,
it was even a PANIC condition :-(.  Correct code is actually simpler than
what we had, because we can just say O_CREAT to start with and not need a
second open() call.  I believe this accounts for several recent reports of
hard-to-reproduce "could not create file ...: File exists" errors in both
pg_clog and pg_subtrans.

diff --git a/src/backend/access/transam/slru.c b/src/backend/access/transam/slru.c
index d1bfd9570c1088832d3b91f343026c14259aa2db..2079d08b1e6ac7545e7edc8caab5ac33ebd9628b 100644 (file)
--- a/src/backend/access/transam/slru.c
+++ b/src/backend/access/transam/slru.c
@@ -41,7 +41,7 @@
  * 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/slru.c,v 1.33 2005/12/06 23:08:32 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/access/transam/slru.c,v 1.34 2006/01/21 04:38:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -128,7 +128,6 @@ typedef struct SlruFlushData
 typedef enum
 {
        SLRU_OPEN_FAILED,
-       SLRU_CREATE_FAILED,
        SLRU_SEEK_FAILED,
        SLRU_READ_FAILED,
        SLRU_WRITE_FAILED,
@@ -652,26 +651,19 @@ SlruPhysicalWritePage(SlruCtl ctl, int pageno, int slotno, SlruFlush fdata)
                 * transactions that have already been truncated from the commit log.
                 * Easiest way to deal with that is to accept references to
                 * nonexistent files here and in SlruPhysicalReadPage.)
+                *
+                * Note: it is possible for more than one backend to be executing
+                * this code simultaneously for different pages of the same file.
+                * Hence, don't use O_EXCL or O_TRUNC or anything like that.
                 */
                SlruFileName(ctl, path, segno);
-               fd = BasicOpenFile(path, O_RDWR | PG_BINARY, S_IRUSR | S_IWUSR);
+               fd = BasicOpenFile(path, O_RDWR | O_CREAT | PG_BINARY,
+                                                  S_IRUSR | S_IWUSR);
                if (fd < 0)
                {
-                       if (errno != ENOENT)
-                       {
-                               slru_errcause = SLRU_OPEN_FAILED;
-                               slru_errno = errno;
-                               return false;
-                       }
-
-                       fd = BasicOpenFile(path, O_RDWR | O_CREAT | O_EXCL | PG_BINARY,
-                                                          S_IRUSR | S_IWUSR);
-                       if (fd < 0)
-                       {
-                               slru_errcause = SLRU_CREATE_FAILED;
-                               slru_errno = errno;
-                               return false;
-                       }
+                       slru_errcause = SLRU_OPEN_FAILED;
+                       slru_errno = errno;
+                       return false;
                }
 
                if (fdata)
@@ -763,13 +755,6 @@ SlruReportIOError(SlruCtl ctl, int pageno, TransactionId xid)
                                         errdetail("could not open file \"%s\": %m",
                                                           path)));
                        break;
-               case SLRU_CREATE_FAILED:
-                       ereport(ERROR,
-                                       (errcode_for_file_access(),
-                                        errmsg("could not access status of transaction %u", xid),
-                                        errdetail("could not create file \"%s\": %m",
-                                                          path)));
-                       break;
                case SLRU_SEEK_FAILED:
                        ereport(ERROR,
                                        (errcode_for_file_access(),