/*
* Issue the error message after failure of SlruPhysicalReadPage or
* SlruPhysicalWritePage. Call this after cleaning up shared-memory state.
*/
static void
SlruReportIOError(SlruCtl ctl, int pageno, TransactionId xid)
{
int segno = pageno / SLRU_PAGES_PER_SEGMENT;
int rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
int offset = rpageno * BLCKSZ;
char path[MAXPGPATH];
SlruFileName(ctl, path, segno);
errno = slru_errno;
switch (slru_errcause)
{
case SLRU_OPEN_FAILED:
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not access status of transaction %u", xid),
errdetail("Could not open file \"%s\": %m.", path)));
break;
case SLRU_SEEK_FAILED:
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not access status of transaction %u", xid),
errdetail("Could not seek in file \"%s\" to offset %u: %m.",
path, offset)));
break;
case SLRU_READ_FAILED:
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not access status of transaction %u", xid),
errdetail("Could not read from file \"%s\" at offset %u: %m.",
path, offset)));
break;
case SLRU_WRITE_FAILED:
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not access status of transaction %u", xid),
errdetail("Could not write to file \"%s\" at offset %u: %m.",
path, offset)));
break;
case SLRU_FSYNC_FAILED:
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not access status of transaction %u", xid),
errdetail("Could not fsync file \"%s\": %m.",
path)));
break;
case SLRU_CLOSE_FAILED:
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not access status of transaction %u", xid),
errdetail("Could not close file \"%s\": %m.",
path)));
break;
default:
/* can't get here, we trust */
elog(ERROR, "unrecognized SimpleLru error cause: %d",
(int) slru_errcause);
break;
}
}
/*
* Return whether the given page exists on disk.
*
* A false return means that either the file does not exist, or that it's not
* large enough to contain the given page.
*/
bool
SimpleLruDoesPhysicalPageExist(SlruCtl ctl, int pageno)
{
int segno = pageno / SLRU_PAGES_PER_SEGMENT;
int rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
int offset = rpageno * BLCKSZ;
char path[MAXPGPATH];
int fd;
bool result;
off_t endpos;
SlruFileName(ctl, path, segno);
fd = OpenTransientFile(path, O_RDWR | PG_BINARY, S_IRUSR | S_IWUSR);
if (fd < 0)
{
/* expected: file doesn't exist */
if (errno == ENOENT)
return false;
/* report error normally */
slru_errcause = SLRU_OPEN_FAILED;
slru_errno = errno;
SlruReportIOError(ctl, pageno, 0);
}
if ((endpos = lseek(fd, 0, SEEK_END)) < 0)
{
slru_errcause = SLRU_OPEN_FAILED;
slru_errno = errno;
SlruReportIOError(ctl, pageno, 0);
}
result = endpos >= (off_t) (offset + BLCKSZ);
CloseTransientFile(fd);
return result;
}
/*
* Physical write of a page from a buffer slot
*
* On failure, we cannot just ereport(ERROR) since caller has put state in
* shared memory that must be undone. So, we return FALSE and save enough
* info in static variables to let SlruReportIOError make the report.
*
* For now, assume it's not worth keeping a file pointer open across
* independent read/write operations. We do batch operations during
* SimpleLruFlush, though.
*
* fdata is NULL for a standalone write, pointer to open-file info during
* SimpleLruFlush.
*/
static bool
SlruPhysicalWritePage(SlruCtl ctl, int pageno, int slotno, SlruFlush fdata)
{
SlruShared shared = ctl->shared;
int segno = pageno / SLRU_PAGES_PER_SEGMENT;
int rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
int offset = rpageno * BLCKSZ;
char path[MAXPGPATH];
int fd = -1;
struct timeval tv;
/*
* Honor the write-WAL-before-data rule, if appropriate, so that we do not
* write out data before associated WAL records. This is the same action
* performed during FlushBuffer() in the main buffer manager.
*/
if (shared->group_lsn != NULL)
{
/*
* We must determine the largest async-commit LSN for the page. This
* is a bit tedious, but since this entire function is a slow path
* anyway, it seems better to do this here than to maintain a per-page
* LSN variable (which'd need an extra comparison in the
* transaction-commit path).
*/
XLogRecPtr max_lsn;
int lsnindex,
lsnoff;
lsnindex = slotno * shared->lsn_groups_per_page;
max_lsn = shared->group_lsn[lsnindex++];
for (lsnoff = 1; lsnoff < shared->lsn_groups_per_page; lsnoff++)
{
XLogRecPtr this_lsn = shared->group_lsn[lsnindex++];
if (XLByteLT(max_lsn, this_lsn))
max_lsn = this_lsn;
}
if (!XLogRecPtrIsInvalid(max_lsn))
{
/*
* As noted above, elog(ERROR) is not acceptable here, so if
* XLogFlush were to fail, we must PANIC. This isn't much of a
* restriction because XLogFlush is just about all critical
* section anyway, but let's make sure.
*/
START_CRIT_SECTION();
XLogFlush(max_lsn);
END_CRIT_SECTION();
}
}
/*
* During a Flush, we may already have the desired file open.
*/
if (fdata)
{
int i;
for (i = 0; i < fdata->num_files; i++)
{
if (fdata->segno[i] == segno)
{
fd = fdata->fd[i];
break;
}
}
}
if (fd < 0)
{
/*
* If the file doesn't already exist, we should create it. It is
* possible for this to need to happen when writing a page that's not
* first in its segment; we assume the OS can cope with that. (Note:
* it might seem that it'd be okay to create files only when
* SimpleLruZeroPage is called for the first page of a segment.
* However, if after a crash and restart the REDO logic elects to
* replay the log from a checkpoint before the latest one, then it's
* possible that we will get commands to set transaction status of
* 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 | O_CREAT | PG_BINARY,
S_IRUSR | S_IWUSR);
if (fd < 0)
{
slru_errcause = SLRU_OPEN_FAILED;
slru_errno = errno;
return false;
}
if (fdata)
{
if (fdata->num_files < MAX_FLUSH_BUFFERS)
{
fdata->fd[fdata->num_files] = fd;
fdata->segno[fdata->num_files] = segno;
fdata->num_files++;
}
else
{
/*
* In the unlikely event that we exceed MAX_FLUSH_BUFFERS,
* fall back to treating it as a standalone write.
*/
fdata = NULL;
}
}
}
if (lseek(fd, (off_t) offset, SEEK_SET) < 0)
{
slru_errcause = SLRU_SEEK_FAILED;
slru_errno = errno;
if (!fdata)
close(fd);
return false;
}
errno = 0;
if (write(fd, shared->page_buffer[slotno], BLCKSZ) != BLCKSZ)
{
/* if write didn't set errno, assume problem is no disk space */
if (errno == 0)
errno = ENOSPC;
slru_errcause = SLRU_WRITE_FAILED;
slru_errno = errno;
if (!fdata)
close(fd);
return false;
}
#ifdef XP_TRACE_LRU_WRITE
gettimeofday(&tv, NULL);
ereport(TRACE_LEVEL,
(errmsg("%ld.%ld:\tWRITE:\tSlruPhysicalWritePage:\tfile:%s",
tv.tv_sec, tv.tv_usec, path)));
#endif
/*
* If not part of Flush, need to fsync now. We assume this happens
* infrequently enough that it's not a performance issue.
*/
if (!fdata)
{
if (ctl->do_fsync && pg_fsync(fd))
{
slru_errcause = SLRU_FSYNC_FAILED;
slru_errno = errno;
close(fd);
return false;
}
if (close(fd))
{
slru_errcause = SLRU_CLOSE_FAILED;
slru_errno = errno;
return false;
}
}
return true;
}
/*
* Physical read of a (previously existing) page into a buffer slot
*
* On failure, we cannot just ereport(ERROR) since caller has put state in
* shared memory that must be undone. So, we return FALSE and save enough
* info in static variables to let SlruReportIOError make the report.
*
* For now, assume it's not worth keeping a file pointer open across
* read/write operations. We could cache one virtual file pointer ...
*/
static bool
SlruPhysicalReadPage(SlruCtl ctl, int pageno, int slotno)
{
SlruShared shared = ctl->shared;
int segno = pageno / SLRU_PAGES_PER_SEGMENT;
int rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
int offset = rpageno * BLCKSZ;
char path[MAXPGPATH];
int fd;
struct timeval tv;
SlruFileName(ctl, path, segno);
/*
* In a crash-and-restart situation, it's possible for us to receive
* commands to set the commit status of transactions whose bits are in
* already-truncated segments of the commit log (see notes in
* SlruPhysicalWritePage). Hence, if we are InRecovery, allow the case
* where the file doesn't exist, and return zeroes instead.
*/
fd = BasicOpenFile(path, O_RDWR | PG_BINARY, S_IRUSR | S_IWUSR);
if (fd < 0)
{
if (errno != ENOENT || !InRecovery)
{
slru_errcause = SLRU_OPEN_FAILED;
slru_errno = errno;
return false;
}
ereport(LOG,
(errmsg("file \"%s\" doesn't exist, reading as zeroes",
path)));
MemSet(shared->page_buffer[slotno], 0, BLCKSZ);
return true;
}
if (lseek(fd, (off_t) offset, SEEK_SET) < 0)
{
slru_errcause = SLRU_SEEK_FAILED;
slru_errno = errno;
close(fd);
return false;
}
errno = 0;
if (read(fd, shared->page_buffer[slotno], BLCKSZ) != BLCKSZ)
{
slru_errcause = SLRU_READ_FAILED;
slru_errno = errno;
close(fd);
return false;
}
#ifdef XP_TRACE_LRU_READ
gettimeofday(&tv, NULL);
#ifdef STACK_TRACE
xp_stack_trace(TRACE_SIZE);
#endif
ereport(TRACE_LEVEL,
(errmsg("%ld.%ld:\tREAD:\tSlruPhysicalReadPage:\tfile:%s",
tv.tv_sec, tv.tv_usec, path)));
#endif
if (close(fd))
{
slru_errcause = SLRU_CLOSE_FAILED;
slru_errno = errno;
return false;
}
return true;
}
/*
* Physical read of a (previously existing) page into a buffer slot
*
* On failure, we cannot just ereport(ERROR) since caller has put state in
* shared memory that must be undone. So, we return FALSE and save enough
* info in static variables to let SlruReportIOError make the report.
*
* For now, assume it's not worth keeping a file pointer open across
* read/write operations. We could cache one virtual file pointer ...
*/
static bool
SlruPhysicalReadPage(SlruCtl ctl, int pageno, int slotno)
{
SlruShared shared = ctl->shared;
int segno = pageno / SLRU_PAGES_PER_SEGMENT;
int rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
int offset = rpageno * BLCKSZ;
char path[MAXPGPATH];
int fd;
SlruFileName(ctl, path, segno);
/*
* In a crash-and-restart situation, it's possible for us to receive
* commands to set the commit status of transactions whose bits are in
* already-truncated segments of the commit log (see notes in
* SlruPhysicalWritePage). Hence, if we are InRecovery, allow the case
* where the file doesn't exist, and return zeroes instead.
*/
fd = OpenTransientFile(path, O_RDWR | PG_BINARY, S_IRUSR | S_IWUSR);
if (fd < 0)
{
if (errno != ENOENT || !InRecovery)
{
slru_errcause = SLRU_OPEN_FAILED;
slru_errno = errno;
return false;
}
ereport(LOG,
(errmsg("file \"%s\" doesn't exist, reading as zeroes",
path)));
MemSet(shared->page_buffer[slotno], 0, BLCKSZ);
return true;
}
if (lseek(fd, (off_t) offset, SEEK_SET) < 0)
{
slru_errcause = SLRU_SEEK_FAILED;
slru_errno = errno;
CloseTransientFile(fd);
return false;
}
errno = 0;
pgstat_report_wait_start(WAIT_EVENT_SLRU_READ);
if (read(fd, shared->page_buffer[slotno], BLCKSZ) != BLCKSZ)
{
pgstat_report_wait_end();
slru_errcause = SLRU_READ_FAILED;
slru_errno = errno;
CloseTransientFile(fd);
return false;
}
pgstat_report_wait_end();
if (CloseTransientFile(fd))
{
slru_errcause = SLRU_CLOSE_FAILED;
slru_errno = errno;
return false;
}
return true;
}
/*
* Physical write of a page from a buffer slot
*
* On failure, we cannot just ereport(ERROR) since caller has put state in
* shared memory that must be undone. So, we return FALSE and save enough
* info in static variables to let SlruReportIOError make the report.
*
* For now, assume it's not worth keeping a file pointer open across
* independent read/write operations. We do batch operations during
* SimpleLruFlush, though.
*
* fdata is NULL for a standalone write, pointer to open-file info during
* SimpleLruFlush.
*/
static bool
SlruPhysicalWritePage(SlruCtl ctl, int pageno, int slotno, SlruFlush fdata)
{
SlruShared shared = ctl->shared;
int segno = pageno / SLRU_PAGES_PER_SEGMENT;
int rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
int offset = rpageno * BLCKSZ;
char path[MAXPGPATH];
int fd = -1;
/*
* During a Flush, we may already have the desired file open.
*/
if (fdata)
{
int i;
for (i = 0; i < fdata->num_files; i++)
{
if (fdata->segno[i] == segno)
{
fd = fdata->fd[i];
break;
}
}
}
if (fd < 0)
{
/*
* If the file doesn't already exist, we should create it. It is
* possible for this to need to happen when writing a page that's not
* first in its segment; we assume the OS can cope with that. (Note:
* it might seem that it'd be okay to create files only when
* SimpleLruZeroPage is called for the first page of a segment.
* However, if after a crash and restart the REDO logic elects to
* replay the log from a checkpoint before the latest one, then it's
* possible that we will get commands to set transaction status of
* 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 | O_CREAT | PG_BINARY,
S_IRUSR | S_IWUSR);
if (fd < 0)
{
slru_errcause = SLRU_OPEN_FAILED;
slru_errno = errno;
return false;
}
if (fdata)
{
fdata->fd[fdata->num_files] = fd;
fdata->segno[fdata->num_files] = segno;
fdata->num_files++;
}
}
if (lseek(fd, (off_t) offset, SEEK_SET) < 0)
{
slru_errcause = SLRU_SEEK_FAILED;
slru_errno = errno;
if (!fdata)
close(fd);
return false;
}
errno = 0;
if (write(fd, shared->page_buffer[slotno], BLCKSZ) != BLCKSZ)
{
/* if write didn't set errno, assume problem is no disk space */
if (errno == 0)
errno = ENOSPC;
slru_errcause = SLRU_WRITE_FAILED;
slru_errno = errno;
if (!fdata)
close(fd);
return false;
}
/*
* If not part of Flush, need to fsync now. We assume this happens
* infrequently enough that it's not a performance issue.
*/
if (!fdata)
{
if (ctl->do_fsync && pg_fsync(fd))
{
slru_errcause = SLRU_FSYNC_FAILED;
slru_errno = errno;
close(fd);
return false;
}
if (close(fd))
{
slru_errcause = SLRU_CLOSE_FAILED;
slru_errno = errno;
return false;
}
}
return true;
}