int numFiles; /* number of physical files in set */
/* all files except the last have length exactly MAX_PHYSICAL_FILESIZE */
File *files; /* palloc'd array with numFiles entries */
- off_t *offsets; /* palloc'd array with numFiles entries */
-
- /*
- * offsets[i] is the current seek position of files[i]. We use this to
- * avoid making redundant FileSeek calls.
- */
bool isInterXact; /* keep open over transactions? */
bool dirty; /* does buffer need to be written? */
BufFile *file = (BufFile *) palloc(sizeof(BufFile));
file->numFiles = nfiles;
- file->offsets = (off_t *) palloc0(sizeof(off_t) * nfiles);
file->isInterXact = false;
file->dirty = false;
file->resowner = CurrentResourceOwner;
file->files = (File *) repalloc(file->files,
(file->numFiles + 1) * sizeof(File));
- file->offsets = (off_t *) repalloc(file->offsets,
- (file->numFiles + 1) * sizeof(off_t));
file->files[file->numFiles] = pfile;
- file->offsets[file->numFiles] = 0L;
file->numFiles++;
}
FileClose(file->files[i]);
/* release the buffer space */
pfree(file->files);
- pfree(file->offsets);
pfree(file);
}
file->curOffset = 0L;
}
- /*
- * May need to reposition physical file.
- */
- thisfile = file->files[file->curFile];
- if (file->curOffset != file->offsets[file->curFile])
- {
- if (FileSeek(thisfile, file->curOffset, SEEK_SET) != file->curOffset)
- return; /* seek failed, read nothing */
- file->offsets[file->curFile] = file->curOffset;
- }
-
/*
* Read whatever we can get, up to a full bufferload.
*/
+ thisfile = file->files[file->curFile];
file->nbytes = FileRead(thisfile,
file->buffer.data,
sizeof(file->buffer),
+ file->curOffset,
WAIT_EVENT_BUFFILE_READ);
if (file->nbytes < 0)
file->nbytes = 0;
- file->offsets[file->curFile] += file->nbytes;
/* we choose not to advance curOffset here */
if (file->nbytes > 0)
if ((off_t) bytestowrite > availbytes)
bytestowrite = (int) availbytes;
- /*
- * May need to reposition physical file.
- */
thisfile = file->files[file->curFile];
- if (file->curOffset != file->offsets[file->curFile])
- {
- if (FileSeek(thisfile, file->curOffset, SEEK_SET) != file->curOffset)
- return; /* seek failed, give up */
- file->offsets[file->curFile] = file->curOffset;
- }
bytestowrite = FileWrite(thisfile,
file->buffer.data + wpos,
bytestowrite,
+ file->curOffset,
WAIT_EVENT_BUFFILE_WRITE);
if (bytestowrite <= 0)
return; /* failed to write */
- file->offsets[file->curFile] += bytestowrite;
file->curOffset += bytestowrite;
wpos += bytestowrite;
{
off_t lastFileSize;
- /* Get the size of the last physical file by seeking to end. */
- lastFileSize = FileSeek(file->files[file->numFiles - 1], 0, SEEK_END);
+ /* Get the size of the last physical file. */
+ lastFileSize = FileSize(file->files[file->numFiles - 1]);
if (lastFileSize < 0)
return -1;
- file->offsets[file->numFiles - 1] = lastFileSize;
return ((file->numFiles - 1) * (off_t) MAX_PHYSICAL_FILESIZE) +
lastFileSize;
target->files = (File *)
repalloc(target->files, sizeof(File) * newNumFiles);
- target->offsets = (off_t *)
- repalloc(target->offsets, sizeof(off_t) * newNumFiles);
for (i = target->numFiles; i < newNumFiles; i++)
- {
target->files[i] = source->files[i - target->numFiles];
- target->offsets[i] = source->offsets[i - target->numFiles];
- }
target->numFiles = newNumFiles;
return startBlock;
* including base tables, scratch files (e.g., sort and hash spool
* files), and random calls to C library routines like system(3); it
* is quite easy to exceed system limits on the number of open files a
- * single process can have. (This is around 256 on many modern
- * operating systems, but can be as low as 32 on others.)
+ * single process can have. (This is around 1024 on many modern
+ * operating systems, but may be lower on others.)
*
* VFDs are managed as an LRU pool, with actual OS file descriptors
* being opened and closed as needed. Obviously, if a routine is
#define FileIsNotOpen(file) (VfdCache[file].fd == VFD_CLOSED)
-/*
- * Note: a VFD's seekPos is normally always valid, but if for some reason
- * an lseek() fails, it might become set to FileUnknownPos. We can struggle
- * along without knowing the seek position in many cases, but in some places
- * we have to fail if we don't have it.
- */
-#define FileUnknownPos ((off_t) -1)
-#define FilePosIsUnknown(pos) ((pos) < 0)
-
/* these are the assigned bits in fdstate below: */
#define FD_DELETE_AT_CLOSE (1 << 0) /* T = delete when closed */
#define FD_CLOSE_AT_EOXACT (1 << 1) /* T = close at eoXact */
File nextFree; /* link to next free VFD, if in freelist */
File lruMoreRecently; /* doubly linked recency-of-use list */
File lruLessRecently;
- off_t seekPos; /* current logical file position, or -1 */
off_t fileSize; /* current size of file (0 if not temporary) */
char *fileName; /* name of file, or NULL for unused VFD */
/* NB: fileName is malloc'd, and must be free'd when closing the VFD */
/*
* pg_flush_data --- advise OS that the described dirty data should be flushed
*
- * offset of 0 with nbytes 0 means that the entire file should be flushed;
- * in this case, this function may have side-effects on the file's
- * seek position!
+ * offset of 0 with nbytes 0 means that the entire file should be flushed
*/
void
pg_flush_data(int fd, off_t offset, off_t nbytes)
vfdP = &VfdCache[file];
- /*
- * Normally we should know the seek position, but if for some reason we
- * have lost track of it, try again to get it. If we still can't get it,
- * we have a problem: we will be unable to restore the file seek position
- * when and if the file is re-opened. But we can't really throw an error
- * and refuse to close the file, or activities such as transaction cleanup
- * will be broken.
- */
- if (FilePosIsUnknown(vfdP->seekPos))
- {
- vfdP->seekPos = lseek(vfdP->fd, (off_t) 0, SEEK_CUR);
- if (FilePosIsUnknown(vfdP->seekPos))
- elog(LOG, "could not seek file \"%s\" before closing: %m",
- vfdP->fileName);
- }
-
/*
* Close the file. We aren't expecting this to fail; if it does, better
* to leak the FD than to mess up our internal state.
{
++nfile;
}
-
- /*
- * Seek to the right position. We need no special case for seekPos
- * equal to FileUnknownPos, as lseek() will certainly reject that
- * (thus completing the logic noted in LruDelete() that we will fail
- * to re-open a file if we couldn't get its seek position before
- * closing).
- */
- if (vfdP->seekPos != (off_t) 0)
- {
- if (lseek(vfdP->fd, vfdP->seekPos, SEEK_SET) < 0)
- {
- /*
- * If we fail to restore the seek position, treat it like an
- * open() failure.
- */
- int save_errno = errno;
-
- elog(LOG, "could not seek file \"%s\" after re-opening: %m",
- vfdP->fileName);
- (void) close(vfdP->fd);
- vfdP->fd = VFD_CLOSED;
- --nfile;
- errno = save_errno;
- return -1;
- }
- }
}
/*
/* Saved flags are adjusted to be OK for re-opening file */
vfdP->fileFlags = fileFlags & ~(O_CREAT | O_TRUNC | O_EXCL);
vfdP->fileMode = fileMode;
- vfdP->seekPos = 0;
vfdP->fileSize = 0;
vfdP->fdstate = 0x0;
vfdP->resowner = NULL;
/*
* FilePrefetch - initiate asynchronous read of a given range of the file.
- * The logical seek position is unaffected.
*
* Currently the only implementation of this function is using posix_fadvise
* which is the simplest standardized interface that accomplishes this.
file, VfdCache[file].fileName,
(int64) offset, (int64) nbytes));
- /*
- * Caution: do not call pg_flush_data with nbytes = 0, it could trash the
- * file's seek position. We prefer to define that as a no-op here.
- */
if (nbytes <= 0)
return;
}
int
-FileRead(File file, char *buffer, int amount, uint32 wait_event_info)
+FileRead(File file, char *buffer, int amount, off_t offset,
+ uint32 wait_event_info)
{
int returnCode;
Vfd *vfdP;
DO_DB(elog(LOG, "FileRead: %d (%s) " INT64_FORMAT " %d %p",
file, VfdCache[file].fileName,
- (int64) VfdCache[file].seekPos,
+ (int64) offset,
amount, buffer));
returnCode = FileAccess(file);
retry:
pgstat_report_wait_start(wait_event_info);
- returnCode = read(vfdP->fd, buffer, amount);
+ returnCode = pg_pread(vfdP->fd, buffer, amount, offset);
pgstat_report_wait_end();
- if (returnCode >= 0)
- {
- /* if seekPos is unknown, leave it that way */
- if (!FilePosIsUnknown(vfdP->seekPos))
- vfdP->seekPos += returnCode;
- }
- else
+ if (returnCode < 0)
{
/*
* Windows may run out of kernel buffers and return "Insufficient
/* OK to retry if interrupted */
if (errno == EINTR)
goto retry;
-
- /* Trouble, so assume we don't know the file position anymore */
- vfdP->seekPos = FileUnknownPos;
}
return returnCode;
}
int
-FileWrite(File file, char *buffer, int amount, uint32 wait_event_info)
+FileWrite(File file, char *buffer, int amount, off_t offset,
+ uint32 wait_event_info)
{
int returnCode;
Vfd *vfdP;
DO_DB(elog(LOG, "FileWrite: %d (%s) " INT64_FORMAT " %d %p",
file, VfdCache[file].fileName,
- (int64) VfdCache[file].seekPos,
+ (int64) offset,
amount, buffer));
returnCode = FileAccess(file);
*/
if (temp_file_limit >= 0 && (vfdP->fdstate & FD_TEMP_FILE_LIMIT))
{
- off_t newPos;
+ off_t past_write = offset + amount;
- /*
- * Normally we should know the seek position, but if for some reason
- * we have lost track of it, try again to get it. Here, it's fine to
- * throw an error if we still can't get it.
- */
- if (FilePosIsUnknown(vfdP->seekPos))
- {
- vfdP->seekPos = lseek(vfdP->fd, (off_t) 0, SEEK_CUR);
- if (FilePosIsUnknown(vfdP->seekPos))
- elog(ERROR, "could not seek file \"%s\": %m", vfdP->fileName);
- }
-
- newPos = vfdP->seekPos + amount;
- if (newPos > vfdP->fileSize)
+ if (past_write > vfdP->fileSize)
{
uint64 newTotal = temporary_files_size;
- newTotal += newPos - vfdP->fileSize;
+ newTotal += past_write - vfdP->fileSize;
if (newTotal > (uint64) temp_file_limit * (uint64) 1024)
ereport(ERROR,
(errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
retry:
errno = 0;
pgstat_report_wait_start(wait_event_info);
- returnCode = write(vfdP->fd, buffer, amount);
+ returnCode = pg_pwrite(VfdCache[file].fd, buffer, amount, offset);
pgstat_report_wait_end();
/* if write didn't set errno, assume problem is no disk space */
if (returnCode >= 0)
{
- /* if seekPos is unknown, leave it that way */
- if (!FilePosIsUnknown(vfdP->seekPos))
- vfdP->seekPos += returnCode;
-
/*
* Maintain fileSize and temporary_files_size if it's a temp file.
*
*/
if (vfdP->fdstate & FD_TEMP_FILE_LIMIT)
{
- off_t newPos = vfdP->seekPos;
+ off_t past_write = offset + amount;
- if (newPos > vfdP->fileSize)
+ if (past_write > vfdP->fileSize)
{
- temporary_files_size += newPos - vfdP->fileSize;
- vfdP->fileSize = newPos;
+ temporary_files_size += past_write - vfdP->fileSize;
+ vfdP->fileSize = past_write;
}
}
}
/* OK to retry if interrupted */
if (errno == EINTR)
goto retry;
-
- /* Trouble, so assume we don't know the file position anymore */
- vfdP->seekPos = FileUnknownPos;
}
return returnCode;
}
off_t
-FileSeek(File file, off_t offset, int whence)
+FileSize(File file)
{
Vfd *vfdP;
Assert(FileIsValid(file));
- DO_DB(elog(LOG, "FileSeek: %d (%s) " INT64_FORMAT " " INT64_FORMAT " %d",
- file, VfdCache[file].fileName,
- (int64) VfdCache[file].seekPos,
- (int64) offset, whence));
+ DO_DB(elog(LOG, "FileSize %d (%s)",
+ file, VfdCache[file].fileName));
vfdP = &VfdCache[file];
if (FileIsNotOpen(file))
{
- switch (whence)
- {
- case SEEK_SET:
- if (offset < 0)
- {
- errno = EINVAL;
- return (off_t) -1;
- }
- vfdP->seekPos = offset;
- break;
- case SEEK_CUR:
- if (FilePosIsUnknown(vfdP->seekPos) ||
- vfdP->seekPos + offset < 0)
- {
- errno = EINVAL;
- return (off_t) -1;
- }
- vfdP->seekPos += offset;
- break;
- case SEEK_END:
- if (FileAccess(file) < 0)
- return (off_t) -1;
- vfdP->seekPos = lseek(vfdP->fd, offset, whence);
- break;
- default:
- elog(ERROR, "invalid whence: %d", whence);
- break;
- }
+ if (FileAccess(file) < 0)
+ return (off_t) -1;
}
- else
- {
- switch (whence)
- {
- case SEEK_SET:
- if (offset < 0)
- {
- errno = EINVAL;
- return (off_t) -1;
- }
- if (vfdP->seekPos != offset)
- vfdP->seekPos = lseek(vfdP->fd, offset, whence);
- break;
- case SEEK_CUR:
- if (offset != 0 || FilePosIsUnknown(vfdP->seekPos))
- vfdP->seekPos = lseek(vfdP->fd, offset, whence);
- break;
- case SEEK_END:
- vfdP->seekPos = lseek(vfdP->fd, offset, whence);
- break;
- default:
- elog(ERROR, "invalid whence: %d", whence);
- break;
- }
- }
-
- return vfdP->seekPos;
-}
-/*
- * XXX not actually used but here for completeness
- */
-#ifdef NOT_USED
-off_t
-FileTell(File file)
-{
- Assert(FileIsValid(file));
- DO_DB(elog(LOG, "FileTell %d (%s)",
- file, VfdCache[file].fileName));
- return VfdCache[file].seekPos;
+ return lseek(VfdCache[file].fd, 0, SEEK_END);
}
-#endif
int
FileTruncate(File file, off_t offset, uint32 wait_event_info)
Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
- /*
- * Note: because caller usually obtained blocknum by calling mdnblocks,
- * which did a seek(SEEK_END), this seek is often redundant and will be
- * optimized away by fd.c. It's not redundant, however, if there is a
- * partial page at the end of the file. In that case we want to try to
- * overwrite the partial page with a full page. It's also not redundant
- * if bufmgr.c had to dump another buffer of the same file to make room
- * for the new page's buffer.
- */
- if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not seek to block %u in file \"%s\": %m",
- blocknum, FilePathName(v->mdfd_vfd))));
-
- if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_EXTEND)) != BLCKSZ)
+ if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_EXTEND)) != BLCKSZ)
{
if (nbytes < 0)
ereport(ERROR,
Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
- if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not seek to block %u in file \"%s\": %m",
- blocknum, FilePathName(v->mdfd_vfd))));
-
- nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_READ);
+ nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_READ);
TRACE_POSTGRESQL_SMGR_MD_READ_DONE(forknum, blocknum,
reln->smgr_rnode.node.spcNode,
Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
- if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not seek to block %u in file \"%s\": %m",
- blocknum, FilePathName(v->mdfd_vfd))));
-
- nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_WRITE);
+ nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_WRITE);
TRACE_POSTGRESQL_SMGR_MD_WRITE_DONE(forknum, blocknum,
reln->smgr_rnode.node.spcNode,
{
off_t len;
- len = FileSeek(seg->mdfd_vfd, 0L, SEEK_END);
+ len = FileSize(seg->mdfd_vfd);
if (len < 0)
ereport(ERROR,
(errcode_for_file_access(),
projects / users / rhaas / postgres.git / commitdiff