1999-10-16 21:49:28 +02:00
|
|
|
/*-------------------------------------------------------------------------
|
|
|
|
*
|
|
|
|
* logtape.c
|
|
|
|
* Management of "logical tapes" within temporary files.
|
|
|
|
*
|
|
|
|
* This module exists to support sorting via multiple merge passes (see
|
1999-10-18 00:15:09 +02:00
|
|
|
* tuplesort.c). Merging is an ideal algorithm for tape devices, but if
|
|
|
|
* we implement it on disk by creating a separate file for each "tape",
|
1999-10-16 21:49:28 +02:00
|
|
|
* there is an annoying problem: the peak space usage is at least twice
|
2000-04-12 19:17:23 +02:00
|
|
|
* the volume of actual data to be sorted. (This must be so because each
|
1999-10-16 21:49:28 +02:00
|
|
|
* datum will appear in both the input and output tapes of the final
|
2000-04-12 19:17:23 +02:00
|
|
|
* merge pass. For seven-tape polyphase merge, which is otherwise a
|
1999-10-16 21:49:28 +02:00
|
|
|
* pretty good algorithm, peak usage is more like 4x actual data volume.)
|
|
|
|
*
|
|
|
|
* We can work around this problem by recognizing that any one tape
|
|
|
|
* dataset (with the possible exception of the final output) is written
|
2000-04-12 19:17:23 +02:00
|
|
|
* and read exactly once in a perfectly sequential manner. Therefore,
|
1999-10-16 21:49:28 +02:00
|
|
|
* a datum once read will not be required again, and we can recycle its
|
|
|
|
* space for use by the new tape dataset(s) being generated. In this way,
|
|
|
|
* the total space usage is essentially just the actual data volume, plus
|
|
|
|
* insignificant bookkeeping and start/stop overhead.
|
|
|
|
*
|
|
|
|
* Few OSes allow arbitrary parts of a file to be released back to the OS,
|
|
|
|
* so we have to implement this space-recycling ourselves within a single
|
|
|
|
* logical file. logtape.c exists to perform this bookkeeping and provide
|
1999-10-18 00:15:09 +02:00
|
|
|
* the illusion of N independent tape devices to tuplesort.c. Note that
|
1999-10-16 21:49:28 +02:00
|
|
|
* logtape.c itself depends on buffile.c to provide a "logical file" of
|
|
|
|
* larger size than the underlying OS may support.
|
|
|
|
*
|
|
|
|
* For simplicity, we allocate and release space in the underlying file
|
|
|
|
* in BLCKSZ-size blocks. Space allocation boils down to keeping track
|
|
|
|
* of which blocks in the underlying file belong to which logical tape,
|
|
|
|
* plus any blocks that are free (recycled and not yet reused). Normally
|
|
|
|
* there are not very many free blocks, so we just keep those in a list.
|
|
|
|
* The blocks in each logical tape are remembered using a method borrowed
|
|
|
|
* from the Unix HFS filesystem: we store data block numbers in an
|
|
|
|
* "indirect block". If an indirect block fills up, we write it out to
|
|
|
|
* the underlying file and remember its location in a second-level indirect
|
|
|
|
* block. In the same way second-level blocks are remembered in third-
|
|
|
|
* level blocks, and so on if necessary (of course we're talking huge
|
|
|
|
* amounts of data here). The topmost indirect block of a given logical
|
|
|
|
* tape is never actually written out to the physical file, but all lower-
|
|
|
|
* level indirect blocks will be.
|
|
|
|
*
|
|
|
|
* The initial write pass is guaranteed to fill the underlying file
|
|
|
|
* perfectly sequentially, no matter how data is divided into logical tapes.
|
|
|
|
* Once we begin merge passes, the access pattern becomes considerably
|
|
|
|
* less predictable --- but the seeking involved should be comparable to
|
|
|
|
* what would happen if we kept each logical tape in a separate file,
|
|
|
|
* so there's no serious performance penalty paid to obtain the space
|
|
|
|
* savings of recycling. We try to localize the write accesses by always
|
|
|
|
* writing to the lowest-numbered free block when we have a choice; it's
|
|
|
|
* not clear this helps much, but it can't hurt. (XXX perhaps a LIFO
|
|
|
|
* policy for free blocks would be better?)
|
|
|
|
*
|
|
|
|
* Since all the bookkeeping and buffer memory is allocated with palloc(),
|
|
|
|
* and the underlying file(s) are made with OpenTemporaryFile, all resources
|
|
|
|
* for a logical tape set are certain to be cleaned up even if processing
|
|
|
|
* is aborted by elog(ERROR). To avoid confusion, the caller should take
|
|
|
|
* care that all calls for a single LogicalTapeSet are made in the same
|
|
|
|
* palloc context.
|
2000-04-12 19:17:23 +02:00
|
|
|
*
|
2000-01-26 06:58:53 +01:00
|
|
|
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
|
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
1999-10-16 21:49:28 +02:00
|
|
|
*
|
|
|
|
* IDENTIFICATION
|
2000-04-12 19:17:23 +02:00
|
|
|
* $Header: /cvsroot/pgsql/src/backend/utils/sort/logtape.c,v 1.5 2000/04/12 17:16:11 momjian Exp $
|
1999-10-16 21:49:28 +02:00
|
|
|
*
|
|
|
|
*-------------------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "postgres.h"
|
|
|
|
|
|
|
|
#include "storage/buffile.h"
|
|
|
|
#include "utils/logtape.h"
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Block indexes are "long"s, so we can fit this many per indirect block.
|
|
|
|
* NB: we assume this is an exact fit!
|
|
|
|
*/
|
2000-04-12 19:17:23 +02:00
|
|
|
#define BLOCKS_PER_INDIR_BLOCK ((int) (BLCKSZ / sizeof(long)))
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We use a struct like this for each active indirection level of each
|
|
|
|
* logical tape. If the indirect block is not the highest level of its
|
|
|
|
* tape, the "nextup" link points to the next higher level. Only the
|
|
|
|
* "ptrs" array is written out if we have to dump the indirect block to
|
|
|
|
* disk. If "ptrs" is not completely full, we store -1L in the first
|
|
|
|
* unused slot at completion of the write phase for the logical tape.
|
|
|
|
*/
|
|
|
|
typedef struct IndirectBlock
|
|
|
|
{
|
|
|
|
int nextSlot; /* next pointer slot to write or read */
|
2000-04-12 19:17:23 +02:00
|
|
|
struct IndirectBlock *nextup; /* parent indirect level, or NULL
|
|
|
|
* if top */
|
|
|
|
long ptrs[BLOCKS_PER_INDIR_BLOCK]; /* indexes of contained
|
|
|
|
* blocks */
|
1999-10-16 21:49:28 +02:00
|
|
|
} IndirectBlock;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This data structure represents a single "logical tape" within the set
|
|
|
|
* of logical tapes stored in the same file. We must keep track of the
|
|
|
|
* current partially-read-or-written data block as well as the active
|
|
|
|
* indirect block level(s).
|
|
|
|
*/
|
|
|
|
typedef struct LogicalTape
|
|
|
|
{
|
|
|
|
IndirectBlock *indirect; /* bottom of my indirect-block hierarchy */
|
|
|
|
bool writing; /* T while in write phase */
|
2000-04-12 19:17:23 +02:00
|
|
|
bool frozen; /* T if blocks should not be freed when
|
|
|
|
* read */
|
1999-10-16 21:49:28 +02:00
|
|
|
bool dirty; /* does buffer need to be written? */
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* The total data volume in the logical tape is numFullBlocks * BLCKSZ
|
2000-04-12 19:17:23 +02:00
|
|
|
* + lastBlockBytes. BUT: we do not update lastBlockBytes during
|
|
|
|
* writing, only at completion of a write phase.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
long numFullBlocks; /* number of complete blocks in log tape */
|
2000-04-12 19:17:23 +02:00
|
|
|
int lastBlockBytes; /* valid bytes in last (incomplete) block */
|
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Buffer for current data block. Note we don't bother to store the
|
|
|
|
* actual file block number of the data block (during the write phase
|
2000-04-12 19:17:23 +02:00
|
|
|
* it hasn't been assigned yet, and during read we don't care
|
|
|
|
* anymore). But we do need the relative block number so we can detect
|
|
|
|
* end-of-tape while reading.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
2000-04-12 19:17:23 +02:00
|
|
|
long curBlockNumber; /* this block's logical blk# within tape */
|
1999-10-16 21:49:28 +02:00
|
|
|
int pos; /* next read/write position in buffer */
|
|
|
|
int nbytes; /* total # of valid bytes in buffer */
|
|
|
|
char buffer[BLCKSZ];
|
|
|
|
} LogicalTape;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This data structure represents a set of related "logical tapes" sharing
|
|
|
|
* space in a single underlying file. (But that "file" may be multiple files
|
|
|
|
* if needed to escape OS limits on file size; buffile.c handles that for us.)
|
|
|
|
* The number of tapes is fixed at creation.
|
|
|
|
*/
|
|
|
|
struct LogicalTapeSet
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
BufFile *pfile; /* underlying file for whole tape set */
|
1999-10-16 21:49:28 +02:00
|
|
|
long nFileBlocks; /* # of blocks used in underlying file */
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
2000-04-12 19:17:23 +02:00
|
|
|
* We store the numbers of recycled-and-available blocks in
|
|
|
|
* freeBlocks[]. When there are no such blocks, we extend the
|
|
|
|
* underlying file. Note that the block numbers in freeBlocks are
|
|
|
|
* always in *decreasing* order, so that removing the last entry gives
|
|
|
|
* us the lowest free block.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
long *freeBlocks; /* resizable array */
|
|
|
|
int nFreeBlocks; /* # of currently free blocks */
|
2000-04-12 19:17:23 +02:00
|
|
|
int freeBlocksLen; /* current allocated length of
|
|
|
|
* freeBlocks[] */
|
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* tapes[] is declared size 1 since C wants a fixed size, but actually
|
|
|
|
* it is of length nTapes.
|
|
|
|
*/
|
|
|
|
int nTapes; /* # of logical tapes in set */
|
|
|
|
LogicalTape *tapes[1]; /* must be last in struct! */
|
|
|
|
};
|
|
|
|
|
|
|
|
static void ltsWriteBlock(LogicalTapeSet *lts, long blocknum, void *buffer);
|
|
|
|
static void ltsReadBlock(LogicalTapeSet *lts, long blocknum, void *buffer);
|
|
|
|
static long ltsGetFreeBlock(LogicalTapeSet *lts);
|
|
|
|
static void ltsReleaseBlock(LogicalTapeSet *lts, long blocknum);
|
|
|
|
static void ltsRecordBlockNum(LogicalTapeSet *lts, IndirectBlock *indirect,
|
2000-04-12 19:17:23 +02:00
|
|
|
long blocknum);
|
1999-10-16 21:49:28 +02:00
|
|
|
static long ltsRewindIndirectBlock(LogicalTapeSet *lts,
|
2000-04-12 19:17:23 +02:00
|
|
|
IndirectBlock *indirect,
|
|
|
|
bool freezing);
|
1999-10-16 21:49:28 +02:00
|
|
|
static long ltsRewindFrozenIndirectBlock(LogicalTapeSet *lts,
|
2000-04-12 19:17:23 +02:00
|
|
|
IndirectBlock *indirect);
|
1999-10-16 21:49:28 +02:00
|
|
|
static long ltsRecallNextBlockNum(LogicalTapeSet *lts,
|
2000-04-12 19:17:23 +02:00
|
|
|
IndirectBlock *indirect,
|
|
|
|
bool frozen);
|
1999-10-16 21:49:28 +02:00
|
|
|
static long ltsRecallPrevBlockNum(LogicalTapeSet *lts,
|
2000-04-12 19:17:23 +02:00
|
|
|
IndirectBlock *indirect);
|
1999-10-16 21:49:28 +02:00
|
|
|
static void ltsDumpBuffer(LogicalTapeSet *lts, LogicalTape *lt);
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Write a block-sized buffer to the specified block of the underlying file.
|
|
|
|
*
|
|
|
|
* NB: should not attempt to write beyond current end of file (ie, create
|
|
|
|
* "holes" in file), since BufFile doesn't allow that. The first write pass
|
|
|
|
* must write blocks sequentially.
|
|
|
|
*
|
|
|
|
* No need for an error return convention; we elog() on any error.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
ltsWriteBlock(LogicalTapeSet *lts, long blocknum, void *buffer)
|
|
|
|
{
|
|
|
|
if (BufFileSeekBlock(lts->pfile, blocknum) != 0 ||
|
|
|
|
BufFileWrite(lts->pfile, buffer, BLCKSZ) != BLCKSZ)
|
|
|
|
elog(ERROR, "ltsWriteBlock: failed to write block %ld of temporary file\n\t\tPerhaps out of disk space?",
|
|
|
|
blocknum);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Read a block-sized buffer from the specified block of the underlying file.
|
|
|
|
*
|
2000-04-12 19:17:23 +02:00
|
|
|
* No need for an error return convention; we elog() on any error. This
|
1999-10-16 21:49:28 +02:00
|
|
|
* module should never attempt to read a block it doesn't know is there.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
ltsReadBlock(LogicalTapeSet *lts, long blocknum, void *buffer)
|
|
|
|
{
|
|
|
|
if (BufFileSeekBlock(lts->pfile, blocknum) != 0 ||
|
|
|
|
BufFileRead(lts->pfile, buffer, BLCKSZ) != BLCKSZ)
|
|
|
|
elog(ERROR, "ltsReadBlock: failed to read block %ld of temporary file",
|
|
|
|
blocknum);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Select a currently unused block for writing to.
|
|
|
|
*
|
|
|
|
* NB: should only be called when writer is ready to write immediately,
|
|
|
|
* to ensure that first write pass is sequential.
|
|
|
|
*/
|
|
|
|
static long
|
|
|
|
ltsGetFreeBlock(LogicalTapeSet *lts)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If there are multiple free blocks, we select the one appearing last
|
|
|
|
* in freeBlocks[]. If there are none, assign the next block at the
|
|
|
|
* end of the file.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
if (lts->nFreeBlocks > 0)
|
|
|
|
return lts->freeBlocks[--lts->nFreeBlocks];
|
|
|
|
else
|
|
|
|
return lts->nFileBlocks++;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Return a block# to the freelist.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
ltsReleaseBlock(LogicalTapeSet *lts, long blocknum)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
int ndx;
|
|
|
|
long *ptr;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Enlarge freeBlocks array if full.
|
|
|
|
*/
|
|
|
|
if (lts->nFreeBlocks >= lts->freeBlocksLen)
|
|
|
|
{
|
|
|
|
lts->freeBlocksLen *= 2;
|
|
|
|
lts->freeBlocks = (long *) repalloc(lts->freeBlocks,
|
2000-04-12 19:17:23 +02:00
|
|
|
lts->freeBlocksLen * sizeof(long));
|
1999-10-16 21:49:28 +02:00
|
|
|
}
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Insert blocknum into array, preserving decreasing order (so that
|
2000-04-12 19:17:23 +02:00
|
|
|
* ltsGetFreeBlock returns the lowest available block number). This
|
|
|
|
* could get fairly slow if there were many free blocks, but we don't
|
|
|
|
* expect there to be very many at one time.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
ndx = lts->nFreeBlocks++;
|
|
|
|
ptr = lts->freeBlocks + ndx;
|
|
|
|
while (ndx > 0 && ptr[-1] < blocknum)
|
|
|
|
{
|
|
|
|
ptr[0] = ptr[-1];
|
|
|
|
ndx--, ptr--;
|
|
|
|
}
|
|
|
|
ptr[0] = blocknum;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* These routines manipulate indirect-block hierarchies. All are recursive
|
|
|
|
* so that they don't have any specific limit on the depth of hierarchy.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Record a data block number in a logical tape's lowest indirect block,
|
|
|
|
* or record an indirect block's number in the next higher indirect level.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
ltsRecordBlockNum(LogicalTapeSet *lts, IndirectBlock *indirect,
|
|
|
|
long blocknum)
|
|
|
|
{
|
|
|
|
if (indirect->nextSlot >= BLOCKS_PER_INDIR_BLOCK)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* This indirect block is full, so dump it out and recursively
|
2000-04-12 19:17:23 +02:00
|
|
|
* save its address in the next indirection level. Create a new
|
|
|
|
* indirection level if there wasn't one before.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
2000-04-12 19:17:23 +02:00
|
|
|
long indirblock = ltsGetFreeBlock(lts);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
ltsWriteBlock(lts, indirblock, (void *) indirect->ptrs);
|
|
|
|
if (indirect->nextup == NULL)
|
|
|
|
{
|
|
|
|
indirect->nextup = (IndirectBlock *) palloc(sizeof(IndirectBlock));
|
|
|
|
indirect->nextup->nextSlot = 0;
|
|
|
|
indirect->nextup->nextup = NULL;
|
|
|
|
}
|
|
|
|
ltsRecordBlockNum(lts, indirect->nextup, indirblock);
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Reset to fill another indirect block at this level.
|
|
|
|
*/
|
|
|
|
indirect->nextSlot = 0;
|
|
|
|
}
|
|
|
|
indirect->ptrs[indirect->nextSlot++] = blocknum;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Reset a logical tape's indirect-block hierarchy after a write pass
|
2000-04-12 19:17:23 +02:00
|
|
|
* to prepare for reading. We dump out partly-filled blocks except
|
1999-10-16 21:49:28 +02:00
|
|
|
* at the top of the hierarchy, and we rewind each level to the start.
|
|
|
|
* This call returns the first data block number, or -1L if the tape
|
|
|
|
* is empty.
|
|
|
|
*
|
|
|
|
* Unless 'freezing' is true, release indirect blocks to the free pool after
|
|
|
|
* reading them.
|
|
|
|
*/
|
|
|
|
static long
|
|
|
|
ltsRewindIndirectBlock(LogicalTapeSet *lts,
|
|
|
|
IndirectBlock *indirect,
|
|
|
|
bool freezing)
|
|
|
|
{
|
|
|
|
/* Insert sentinel if block is not full */
|
|
|
|
if (indirect->nextSlot < BLOCKS_PER_INDIR_BLOCK)
|
|
|
|
indirect->ptrs[indirect->nextSlot] = -1L;
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* If block is not topmost, write it out, and recurse to obtain
|
2000-04-12 19:17:23 +02:00
|
|
|
* address of first block in this hierarchy level. Read that one in.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
if (indirect->nextup != NULL)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long indirblock = ltsGetFreeBlock(lts);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
ltsWriteBlock(lts, indirblock, (void *) indirect->ptrs);
|
|
|
|
ltsRecordBlockNum(lts, indirect->nextup, indirblock);
|
|
|
|
indirblock = ltsRewindIndirectBlock(lts, indirect->nextup, freezing);
|
|
|
|
Assert(indirblock != -1L);
|
|
|
|
ltsReadBlock(lts, indirblock, (void *) indirect->ptrs);
|
2000-04-12 19:17:23 +02:00
|
|
|
if (!freezing)
|
1999-10-16 21:49:28 +02:00
|
|
|
ltsReleaseBlock(lts, indirblock);
|
|
|
|
}
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Reset my next-block pointer, and then fetch a block number if any.
|
|
|
|
*/
|
|
|
|
indirect->nextSlot = 0;
|
|
|
|
if (indirect->ptrs[0] == -1L)
|
|
|
|
return -1L;
|
|
|
|
return indirect->ptrs[indirect->nextSlot++];
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Rewind a previously-frozen indirect-block hierarchy for another read pass.
|
|
|
|
* This call returns the first data block number, or -1L if the tape
|
|
|
|
* is empty.
|
|
|
|
*/
|
|
|
|
static long
|
|
|
|
ltsRewindFrozenIndirectBlock(LogicalTapeSet *lts,
|
|
|
|
IndirectBlock *indirect)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
2000-04-12 19:17:23 +02:00
|
|
|
* If block is not topmost, recurse to obtain address of first block
|
|
|
|
* in this hierarchy level. Read that one in.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
if (indirect->nextup != NULL)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long indirblock;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
indirblock = ltsRewindFrozenIndirectBlock(lts, indirect->nextup);
|
|
|
|
Assert(indirblock != -1L);
|
|
|
|
ltsReadBlock(lts, indirblock, (void *) indirect->ptrs);
|
|
|
|
}
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Reset my next-block pointer, and then fetch a block number if any.
|
|
|
|
*/
|
|
|
|
indirect->nextSlot = 0;
|
|
|
|
if (indirect->ptrs[0] == -1L)
|
|
|
|
return -1L;
|
|
|
|
return indirect->ptrs[indirect->nextSlot++];
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Obtain next data block number in the forward direction, or -1L if no more.
|
|
|
|
*
|
|
|
|
* Unless 'frozen' is true, release indirect blocks to the free pool after
|
|
|
|
* reading them.
|
|
|
|
*/
|
|
|
|
static long
|
|
|
|
ltsRecallNextBlockNum(LogicalTapeSet *lts,
|
|
|
|
IndirectBlock *indirect,
|
|
|
|
bool frozen)
|
|
|
|
{
|
|
|
|
if (indirect->nextSlot >= BLOCKS_PER_INDIR_BLOCK ||
|
|
|
|
indirect->ptrs[indirect->nextSlot] == -1L)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long indirblock;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
if (indirect->nextup == NULL)
|
|
|
|
return -1L; /* nothing left at this level */
|
|
|
|
indirblock = ltsRecallNextBlockNum(lts, indirect->nextup, frozen);
|
|
|
|
if (indirblock == -1L)
|
|
|
|
return -1L; /* nothing left at this level */
|
|
|
|
ltsReadBlock(lts, indirblock, (void *) indirect->ptrs);
|
2000-04-12 19:17:23 +02:00
|
|
|
if (!frozen)
|
1999-10-16 21:49:28 +02:00
|
|
|
ltsReleaseBlock(lts, indirblock);
|
|
|
|
indirect->nextSlot = 0;
|
|
|
|
}
|
|
|
|
if (indirect->ptrs[indirect->nextSlot] == -1L)
|
|
|
|
return -1L;
|
|
|
|
return indirect->ptrs[indirect->nextSlot++];
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Obtain next data block number in the reverse direction, or -1L if no more.
|
|
|
|
*
|
|
|
|
* Note this fetches the block# before the one last returned, no matter which
|
|
|
|
* direction of call returned that one. If we fail, no change in state.
|
|
|
|
*
|
|
|
|
* This routine can only be used in 'frozen' state, so there's no need to
|
|
|
|
* pass a parameter telling whether to release blocks ... we never do.
|
|
|
|
*/
|
|
|
|
static long
|
|
|
|
ltsRecallPrevBlockNum(LogicalTapeSet *lts,
|
|
|
|
IndirectBlock *indirect)
|
|
|
|
{
|
|
|
|
if (indirect->nextSlot <= 1)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long indirblock;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
if (indirect->nextup == NULL)
|
|
|
|
return -1L; /* nothing left at this level */
|
|
|
|
indirblock = ltsRecallPrevBlockNum(lts, indirect->nextup);
|
|
|
|
if (indirblock == -1L)
|
|
|
|
return -1L; /* nothing left at this level */
|
|
|
|
ltsReadBlock(lts, indirblock, (void *) indirect->ptrs);
|
2000-04-12 19:17:23 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The previous block would only have been written out if full, so
|
|
|
|
* we need not search it for a -1 sentinel.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
2000-04-12 19:17:23 +02:00
|
|
|
indirect->nextSlot = BLOCKS_PER_INDIR_BLOCK + 1;
|
1999-10-16 21:49:28 +02:00
|
|
|
}
|
|
|
|
indirect->nextSlot--;
|
2000-04-12 19:17:23 +02:00
|
|
|
return indirect->ptrs[indirect->nextSlot - 1];
|
1999-10-16 21:49:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Create a set of logical tapes in a temporary underlying file.
|
|
|
|
*
|
|
|
|
* Each tape is initialized in write state.
|
|
|
|
*/
|
|
|
|
LogicalTapeSet *
|
|
|
|
LogicalTapeSetCreate(int ntapes)
|
|
|
|
{
|
|
|
|
LogicalTapeSet *lts;
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
|
|
|
int i;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Create top-level struct. First LogicalTape pointer is already
|
|
|
|
* counted in sizeof(LogicalTapeSet).
|
|
|
|
*/
|
|
|
|
Assert(ntapes > 0);
|
|
|
|
lts = (LogicalTapeSet *) palloc(sizeof(LogicalTapeSet) +
|
2000-04-12 19:17:23 +02:00
|
|
|
(ntapes - 1) *sizeof(LogicalTape *));
|
1999-10-16 21:49:28 +02:00
|
|
|
lts->pfile = BufFileCreateTemp();
|
|
|
|
lts->nFileBlocks = 0L;
|
|
|
|
lts->freeBlocksLen = 32; /* reasonable initial guess */
|
|
|
|
lts->freeBlocks = (long *) palloc(lts->freeBlocksLen * sizeof(long));
|
|
|
|
lts->nFreeBlocks = 0;
|
|
|
|
lts->nTapes = ntapes;
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Create per-tape structs, including first-level indirect blocks.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < ntapes; i++)
|
|
|
|
{
|
|
|
|
lt = (LogicalTape *) palloc(sizeof(LogicalTape));
|
|
|
|
lts->tapes[i] = lt;
|
|
|
|
lt->indirect = (IndirectBlock *) palloc(sizeof(IndirectBlock));
|
|
|
|
lt->indirect->nextSlot = 0;
|
|
|
|
lt->indirect->nextup = NULL;
|
|
|
|
lt->writing = true;
|
|
|
|
lt->frozen = false;
|
|
|
|
lt->dirty = false;
|
|
|
|
lt->numFullBlocks = 0L;
|
|
|
|
lt->lastBlockBytes = 0;
|
|
|
|
lt->curBlockNumber = 0L;
|
|
|
|
lt->pos = 0;
|
|
|
|
lt->nbytes = 0;
|
|
|
|
}
|
|
|
|
return lts;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Close a logical tape set and release all resources.
|
|
|
|
*/
|
2000-04-12 19:17:23 +02:00
|
|
|
void
|
|
|
|
LogicalTapeSetClose(LogicalTapeSet *lts)
|
1999-10-16 21:49:28 +02:00
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
|
|
|
IndirectBlock *ib,
|
|
|
|
*nextib;
|
|
|
|
int i;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
BufFileClose(lts->pfile);
|
|
|
|
for (i = 0; i < lts->nTapes; i++)
|
|
|
|
{
|
|
|
|
lt = lts->tapes[i];
|
|
|
|
for (ib = lt->indirect; ib != NULL; ib = nextib)
|
|
|
|
{
|
|
|
|
nextib = ib->nextup;
|
|
|
|
pfree(ib);
|
|
|
|
}
|
|
|
|
pfree(lt);
|
|
|
|
}
|
|
|
|
pfree(lts->freeBlocks);
|
|
|
|
pfree(lts);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Dump the dirty buffer of a logical tape.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
ltsDumpBuffer(LogicalTapeSet *lts, LogicalTape *lt)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long datablock = ltsGetFreeBlock(lts);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(lt->dirty);
|
|
|
|
ltsWriteBlock(lts, datablock, (void *) lt->buffer);
|
|
|
|
ltsRecordBlockNum(lts, lt->indirect, datablock);
|
|
|
|
lt->dirty = false;
|
|
|
|
/* Caller must do other state update as needed */
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Write to a logical tape.
|
|
|
|
*
|
|
|
|
* There are no error returns; we elog() on failure.
|
|
|
|
*/
|
|
|
|
void
|
|
|
|
LogicalTapeWrite(LogicalTapeSet *lts, int tapenum,
|
|
|
|
void *ptr, size_t size)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
|
|
|
size_t nthistime;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(tapenum >= 0 && tapenum < lts->nTapes);
|
|
|
|
lt = lts->tapes[tapenum];
|
|
|
|
Assert(lt->writing);
|
|
|
|
|
|
|
|
while (size > 0)
|
|
|
|
{
|
|
|
|
if (lt->pos >= BLCKSZ)
|
|
|
|
{
|
|
|
|
/* Buffer full, dump it out */
|
|
|
|
if (lt->dirty)
|
|
|
|
ltsDumpBuffer(lts, lt);
|
|
|
|
else
|
|
|
|
{
|
|
|
|
/* Hmm, went directly from reading to writing? */
|
|
|
|
elog(ERROR, "LogicalTapeWrite: impossible state");
|
|
|
|
}
|
|
|
|
lt->numFullBlocks++;
|
|
|
|
lt->curBlockNumber++;
|
|
|
|
lt->pos = 0;
|
|
|
|
lt->nbytes = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
nthistime = BLCKSZ - lt->pos;
|
|
|
|
if (nthistime > size)
|
|
|
|
nthistime = size;
|
|
|
|
Assert(nthistime > 0);
|
|
|
|
|
|
|
|
memcpy(lt->buffer + lt->pos, ptr, nthistime);
|
|
|
|
|
|
|
|
lt->dirty = true;
|
|
|
|
lt->pos += nthistime;
|
|
|
|
if (lt->nbytes < lt->pos)
|
|
|
|
lt->nbytes = lt->pos;
|
|
|
|
ptr = (void *) ((char *) ptr + nthistime);
|
|
|
|
size -= nthistime;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Rewind logical tape and switch from writing to reading or vice versa.
|
|
|
|
*
|
|
|
|
* Unless the tape has been "frozen" in read state, forWrite must be the
|
|
|
|
* opposite of the previous tape state.
|
|
|
|
*/
|
|
|
|
void
|
|
|
|
LogicalTapeRewind(LogicalTapeSet *lts, int tapenum, bool forWrite)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
|
|
|
long datablocknum;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(tapenum >= 0 && tapenum < lts->nTapes);
|
|
|
|
lt = lts->tapes[tapenum];
|
|
|
|
|
2000-04-12 19:17:23 +02:00
|
|
|
if (!forWrite)
|
1999-10-16 21:49:28 +02:00
|
|
|
{
|
|
|
|
if (lt->writing)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Completion of a write phase. Flush last partial data
|
2000-04-12 19:17:23 +02:00
|
|
|
* block, flush any partial indirect blocks, rewind for normal
|
|
|
|
* (destructive) read.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
if (lt->dirty)
|
|
|
|
ltsDumpBuffer(lts, lt);
|
|
|
|
lt->lastBlockBytes = lt->nbytes;
|
|
|
|
lt->writing = false;
|
|
|
|
datablocknum = ltsRewindIndirectBlock(lts, lt->indirect, false);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* This is only OK if tape is frozen; we rewind for (another)
|
|
|
|
* read pass.
|
|
|
|
*/
|
|
|
|
Assert(lt->frozen);
|
|
|
|
datablocknum = ltsRewindFrozenIndirectBlock(lts, lt->indirect);
|
|
|
|
}
|
|
|
|
/* Read the first block, or reset if tape is empty */
|
|
|
|
lt->curBlockNumber = 0L;
|
|
|
|
lt->pos = 0;
|
|
|
|
lt->nbytes = 0;
|
|
|
|
if (datablocknum != -1L)
|
|
|
|
{
|
|
|
|
ltsReadBlock(lts, datablocknum, (void *) lt->buffer);
|
2000-04-12 19:17:23 +02:00
|
|
|
if (!lt->frozen)
|
1999-10-16 21:49:28 +02:00
|
|
|
ltsReleaseBlock(lts, datablocknum);
|
|
|
|
lt->nbytes = (lt->curBlockNumber < lt->numFullBlocks) ?
|
|
|
|
BLCKSZ : lt->lastBlockBytes;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
2000-04-12 19:17:23 +02:00
|
|
|
* Completion of a read phase. Rewind and prepare for write.
|
1999-10-16 21:49:28 +02:00
|
|
|
*
|
2000-04-12 19:17:23 +02:00
|
|
|
* NOTE: we assume the caller has read the tape to the end; otherwise
|
|
|
|
* untouched data and indirect blocks will not have been freed. We
|
|
|
|
* could add more code to free any unread blocks, but in current
|
|
|
|
* usage of this module it'd be useless code.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
2000-04-12 19:17:23 +02:00
|
|
|
IndirectBlock *ib,
|
|
|
|
*nextib;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
2000-04-12 19:17:23 +02:00
|
|
|
Assert(!lt->writing && !lt->frozen);
|
1999-10-16 21:49:28 +02:00
|
|
|
/* Must truncate the indirect-block hierarchy down to one level. */
|
|
|
|
for (ib = lt->indirect->nextup; ib != NULL; ib = nextib)
|
|
|
|
{
|
|
|
|
nextib = ib->nextup;
|
|
|
|
pfree(ib);
|
|
|
|
}
|
|
|
|
lt->indirect->nextSlot = 0;
|
|
|
|
lt->indirect->nextup = NULL;
|
|
|
|
lt->writing = true;
|
|
|
|
lt->dirty = false;
|
|
|
|
lt->numFullBlocks = 0L;
|
|
|
|
lt->lastBlockBytes = 0;
|
|
|
|
lt->curBlockNumber = 0L;
|
|
|
|
lt->pos = 0;
|
|
|
|
lt->nbytes = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Read from a logical tape.
|
|
|
|
*
|
|
|
|
* Early EOF is indicated by return value less than #bytes requested.
|
|
|
|
*/
|
|
|
|
size_t
|
|
|
|
LogicalTapeRead(LogicalTapeSet *lts, int tapenum,
|
|
|
|
void *ptr, size_t size)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
|
|
|
size_t nread = 0;
|
|
|
|
size_t nthistime;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(tapenum >= 0 && tapenum < lts->nTapes);
|
|
|
|
lt = lts->tapes[tapenum];
|
2000-04-12 19:17:23 +02:00
|
|
|
Assert(!lt->writing);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
while (size > 0)
|
|
|
|
{
|
|
|
|
if (lt->pos >= lt->nbytes)
|
|
|
|
{
|
|
|
|
/* Try to load more data into buffer. */
|
2000-04-12 19:17:23 +02:00
|
|
|
long datablocknum = ltsRecallNextBlockNum(lts, lt->indirect,
|
|
|
|
lt->frozen);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
if (datablocknum == -1L)
|
|
|
|
break; /* EOF */
|
|
|
|
lt->curBlockNumber++;
|
|
|
|
lt->pos = 0;
|
|
|
|
ltsReadBlock(lts, datablocknum, (void *) lt->buffer);
|
2000-04-12 19:17:23 +02:00
|
|
|
if (!lt->frozen)
|
1999-10-16 21:49:28 +02:00
|
|
|
ltsReleaseBlock(lts, datablocknum);
|
|
|
|
lt->nbytes = (lt->curBlockNumber < lt->numFullBlocks) ?
|
|
|
|
BLCKSZ : lt->lastBlockBytes;
|
|
|
|
if (lt->nbytes <= 0)
|
|
|
|
break; /* EOF (possible here?) */
|
|
|
|
}
|
|
|
|
|
|
|
|
nthistime = lt->nbytes - lt->pos;
|
|
|
|
if (nthistime > size)
|
|
|
|
nthistime = size;
|
|
|
|
Assert(nthistime > 0);
|
|
|
|
|
|
|
|
memcpy(ptr, lt->buffer + lt->pos, nthistime);
|
|
|
|
|
|
|
|
lt->pos += nthistime;
|
|
|
|
ptr = (void *) ((char *) ptr + nthistime);
|
|
|
|
size -= nthistime;
|
|
|
|
nread += nthistime;
|
|
|
|
}
|
|
|
|
|
|
|
|
return nread;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* "Freeze" the contents of a tape so that it can be read multiple times
|
|
|
|
* and/or read backwards. Once a tape is frozen, its contents will not
|
|
|
|
* be released until the LogicalTapeSet is destroyed. This is expected
|
|
|
|
* to be used only for the final output pass of a merge.
|
|
|
|
*
|
|
|
|
* This *must* be called just at the end of a write pass, before the
|
|
|
|
* tape is rewound (after rewind is too late!). It performs a rewind
|
2000-04-12 19:17:23 +02:00
|
|
|
* and switch to read mode "for free". An immediately following rewind-
|
1999-10-16 21:49:28 +02:00
|
|
|
* for-read call is OK but not necessary.
|
|
|
|
*/
|
|
|
|
void
|
|
|
|
LogicalTapeFreeze(LogicalTapeSet *lts, int tapenum)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
|
|
|
long datablocknum;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(tapenum >= 0 && tapenum < lts->nTapes);
|
|
|
|
lt = lts->tapes[tapenum];
|
|
|
|
Assert(lt->writing);
|
|
|
|
|
|
|
|
/*
|
2000-04-12 19:17:23 +02:00
|
|
|
* Completion of a write phase. Flush last partial data block, flush
|
|
|
|
* any partial indirect blocks, rewind for nondestructive read.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
if (lt->dirty)
|
|
|
|
ltsDumpBuffer(lts, lt);
|
|
|
|
lt->lastBlockBytes = lt->nbytes;
|
|
|
|
lt->writing = false;
|
|
|
|
lt->frozen = true;
|
|
|
|
datablocknum = ltsRewindIndirectBlock(lts, lt->indirect, true);
|
|
|
|
/* Read the first block, or reset if tape is empty */
|
|
|
|
lt->curBlockNumber = 0L;
|
|
|
|
lt->pos = 0;
|
|
|
|
lt->nbytes = 0;
|
|
|
|
if (datablocknum != -1L)
|
|
|
|
{
|
|
|
|
ltsReadBlock(lts, datablocknum, (void *) lt->buffer);
|
|
|
|
lt->nbytes = (lt->curBlockNumber < lt->numFullBlocks) ?
|
|
|
|
BLCKSZ : lt->lastBlockBytes;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2000-04-12 19:17:23 +02:00
|
|
|
* Backspace the tape a given number of bytes. (We also support a more
|
1999-10-16 21:49:28 +02:00
|
|
|
* general seek interface, see below.)
|
|
|
|
*
|
|
|
|
* *Only* a frozen-for-read tape can be backed up; we don't support
|
|
|
|
* random access during write, and an unfrozen read tape may have
|
|
|
|
* already discarded the desired data!
|
|
|
|
*
|
|
|
|
* Return value is TRUE if seek successful, FALSE if there isn't that much
|
|
|
|
* data before the current point (in which case there's no state change).
|
|
|
|
*/
|
|
|
|
bool
|
|
|
|
LogicalTapeBackspace(LogicalTapeSet *lts, int tapenum, size_t size)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
|
|
|
long nblocks;
|
|
|
|
int newpos;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(tapenum >= 0 && tapenum < lts->nTapes);
|
|
|
|
lt = lts->tapes[tapenum];
|
|
|
|
Assert(lt->frozen);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Easy case for seek within current block.
|
|
|
|
*/
|
|
|
|
if (size <= (size_t) lt->pos)
|
|
|
|
{
|
|
|
|
lt->pos -= (int) size;
|
|
|
|
return true;
|
|
|
|
}
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Not-so-easy case. Figure out whether it's possible at all.
|
|
|
|
*/
|
|
|
|
size -= (size_t) lt->pos; /* part within this block */
|
|
|
|
nblocks = size / BLCKSZ;
|
|
|
|
size = size % BLCKSZ;
|
|
|
|
if (size)
|
|
|
|
{
|
|
|
|
nblocks++;
|
|
|
|
newpos = (int) (BLCKSZ - size);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
newpos = 0;
|
|
|
|
if (nblocks > lt->curBlockNumber)
|
|
|
|
return false; /* a seek too far... */
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
2000-04-12 19:17:23 +02:00
|
|
|
* OK, we need to back up nblocks blocks. This implementation would
|
|
|
|
* be pretty inefficient for long seeks, but we really aren't
|
|
|
|
* expecting that (a seek over one tuple is typical).
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
while (nblocks-- > 0)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long datablocknum = ltsRecallPrevBlockNum(lts, lt->indirect);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
if (datablocknum == -1L)
|
|
|
|
elog(ERROR, "LogicalTapeBackspace: unexpected end of tape");
|
|
|
|
lt->curBlockNumber--;
|
|
|
|
if (nblocks == 0)
|
|
|
|
{
|
|
|
|
ltsReadBlock(lts, datablocknum, (void *) lt->buffer);
|
|
|
|
lt->nbytes = BLCKSZ;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
lt->pos = newpos;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Seek to an arbitrary position in a logical tape.
|
|
|
|
*
|
|
|
|
* *Only* a frozen-for-read tape can be seeked.
|
|
|
|
*
|
|
|
|
* Return value is TRUE if seek successful, FALSE if there isn't that much
|
|
|
|
* data in the tape (in which case there's no state change).
|
|
|
|
*/
|
|
|
|
bool
|
|
|
|
LogicalTapeSeek(LogicalTapeSet *lts, int tapenum,
|
|
|
|
long blocknum, int offset)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(tapenum >= 0 && tapenum < lts->nTapes);
|
|
|
|
lt = lts->tapes[tapenum];
|
|
|
|
Assert(lt->frozen);
|
|
|
|
Assert(offset >= 0 && offset <= BLCKSZ);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Easy case for seek within current block.
|
|
|
|
*/
|
|
|
|
if (blocknum == lt->curBlockNumber && offset <= lt->nbytes)
|
|
|
|
{
|
|
|
|
lt->pos = offset;
|
|
|
|
return true;
|
|
|
|
}
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
|
|
|
* Not-so-easy case. Figure out whether it's possible at all.
|
|
|
|
*/
|
|
|
|
if (blocknum < 0 || blocknum > lt->numFullBlocks ||
|
|
|
|
(blocknum == lt->numFullBlocks && offset > lt->lastBlockBytes))
|
|
|
|
return false;
|
2000-04-12 19:17:23 +02:00
|
|
|
|
1999-10-16 21:49:28 +02:00
|
|
|
/*
|
2000-04-12 19:17:23 +02:00
|
|
|
* OK, advance or back up to the target block. This implementation
|
|
|
|
* would be pretty inefficient for long seeks, but we really aren't
|
|
|
|
* expecting that (a seek over one tuple is typical).
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
while (lt->curBlockNumber > blocknum)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long datablocknum = ltsRecallPrevBlockNum(lts, lt->indirect);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
if (datablocknum == -1L)
|
|
|
|
elog(ERROR, "LogicalTapeSeek: unexpected end of tape");
|
|
|
|
if (--lt->curBlockNumber == blocknum)
|
|
|
|
ltsReadBlock(lts, datablocknum, (void *) lt->buffer);
|
|
|
|
}
|
|
|
|
while (lt->curBlockNumber < blocknum)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
long datablocknum = ltsRecallNextBlockNum(lts, lt->indirect,
|
|
|
|
lt->frozen);
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
if (datablocknum == -1L)
|
|
|
|
elog(ERROR, "LogicalTapeSeek: unexpected end of tape");
|
|
|
|
if (++lt->curBlockNumber == blocknum)
|
|
|
|
ltsReadBlock(lts, datablocknum, (void *) lt->buffer);
|
|
|
|
}
|
|
|
|
lt->nbytes = (lt->curBlockNumber < lt->numFullBlocks) ?
|
|
|
|
BLCKSZ : lt->lastBlockBytes;
|
|
|
|
lt->pos = offset;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Obtain current position in a form suitable for a later LogicalTapeSeek.
|
|
|
|
*
|
|
|
|
* NOTE: it'd be OK to do this during write phase with intention of using
|
2000-04-12 19:17:23 +02:00
|
|
|
* the position for a seek after freezing. Not clear if anyone needs that.
|
1999-10-16 21:49:28 +02:00
|
|
|
*/
|
|
|
|
void
|
|
|
|
LogicalTapeTell(LogicalTapeSet *lts, int tapenum,
|
|
|
|
long *blocknum, int *offset)
|
|
|
|
{
|
2000-04-12 19:17:23 +02:00
|
|
|
LogicalTape *lt;
|
1999-10-16 21:49:28 +02:00
|
|
|
|
|
|
|
Assert(tapenum >= 0 && tapenum < lts->nTapes);
|
|
|
|
lt = lts->tapes[tapenum];
|
|
|
|
*blocknum = lt->curBlockNumber;
|
|
|
|
*offset = lt->pos;
|
|
|
|
}
|