greenplumn tuptoaster 源码
greenplumn tuptoaster 代码
文件路径：/src/backend/access/heap/tuptoaster.c
/*-------------------------------------------------------------------------
*
* tuptoaster.c
* Support routines for external and compressed storage of
* variable size attributes.
*
* Copyright (c) 2000-2019, PostgreSQL Global Development Group
*
*
* IDENTIFICATION
* src/backend/access/heap/tuptoaster.c
*
*
* INTERFACE ROUTINES
* toast_insert_or_update -
* Try to make a given tuple fit into one page by compressing
* or moving off attributes
*
* toast_delete -
* Reclaim toast storage when a tuple is deleted
*
* heap_tuple_untoast_attr -
* Fetch back a given value from the "secondary" relation
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include <unistd.h>
#include <fcntl.h>
#include "access/genam.h"
#include "access/heapam.h"
#include "access/tuptoaster.h"
#include "access/xact.h"
#include "catalog/catalog.h"
#include "common/pg_lzcompress.h"
#include "miscadmin.h"
#include "utils/expandeddatum.h"
#include "utils/fmgroids.h"
#include "utils/rel.h"
#include "utils/snapmgr.h"
#include "utils/typcache.h"
/* GPDB additions */
#include "utils/faultinjector.h"
#undef TOAST_DEBUG
/*
* The information at the start of the compressed toast data.
*/
typedef struct toast_compress_header
{
int32 vl_len_; /* varlena header (do not touch directly!) */
int32 rawsize;
} toast_compress_header;
/*
* Utilities for manipulation of header information for compressed
* toast entries.
*/
#define TOAST_COMPRESS_HDRSZ ((int32) sizeof(toast_compress_header))
#define TOAST_COMPRESS_RAWSIZE(ptr) (((toast_compress_header *) (ptr))->rawsize)
#define TOAST_COMPRESS_RAWDATA(ptr) \
(((char *) (ptr)) + TOAST_COMPRESS_HDRSZ)
#define TOAST_COMPRESS_SET_RAWSIZE(ptr, len) \
(((toast_compress_header *) (ptr))->rawsize = (len))
static Datum toast_save_datum(Relation rel, Datum value,
struct varlena *oldexternal, bool isFrozen, int options);
static bool toastrel_valueid_exists(Relation toastrel, Oid valueid);
static bool toastid_valueid_exists(Oid toastrelid, Oid valueid);
static struct varlena *toast_fetch_datum(struct varlena *attr);
static struct varlena *toast_fetch_datum_slice(struct varlena *attr,
int32 sliceoffset, int32 length);
static struct varlena *toast_decompress_datum(struct varlena *attr);
static struct varlena *toast_decompress_datum_slice(struct varlena *attr, int32 slicelength);
static int toast_open_indexes(Relation toastrel,
LOCKMODE lock,
Relation **toastidxs,
int *num_indexes);
static void toast_close_indexes(Relation *toastidxs, int num_indexes,
LOCKMODE lock);
static void init_toast_snapshot(Snapshot toast_snapshot);
/* ----------
* heap_tuple_fetch_attr -
*
* Public entry point to get back a toasted value from
* external source (possibly still in compressed format).
*
* This will return a datum that contains all the data internally, ie, not
* relying on external storage or memory, but it can still be compressed or
* have a short header. Note some callers assume that if the input is an
* EXTERNAL datum, the result will be a pfree'able chunk.
* ----------
*/
struct varlena *
heap_tuple_fetch_attr(struct varlena *attr)
{
struct varlena *result;
if (VARATT_IS_EXTERNAL_ONDISK(attr))
{
/*
* This is an external stored plain value
*/
result = toast_fetch_datum(attr);
}
else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
{
/*
* This is an indirect pointer --- dereference it
*/
struct varatt_indirect redirect;
VARATT_EXTERNAL_GET_POINTER(redirect, attr);
attr = (struct varlena *) redirect.pointer;
/* nested indirect Datums aren't allowed */
Assert(!VARATT_IS_EXTERNAL_INDIRECT(attr));
/* recurse if value is still external in some other way */
if (VARATT_IS_EXTERNAL(attr))
return heap_tuple_fetch_attr(attr);
/*
* Copy into the caller's memory context, in case caller tries to
* pfree the result.
*/
result = (struct varlena *) palloc(VARSIZE_ANY(attr));
memcpy(result, attr, VARSIZE_ANY(attr));
}
else if (VARATT_IS_EXTERNAL_EXPANDED(attr))
{
/*
* This is an expanded-object pointer --- get flat format
*/
ExpandedObjectHeader *eoh;
Size resultsize;
eoh = DatumGetEOHP(PointerGetDatum(attr));
resultsize = EOH_get_flat_size(eoh);
result = (struct varlena *) palloc(resultsize);
EOH_flatten_into(eoh, (void *) result, resultsize);
}
else
{
/*
* This is a plain value inside of the main tuple - why am I called?
*/
result = attr;
}
return result;
}
/*
* If this function is changed then update varattrib_untoast_ptr_len as well
*/
int
varattrib_untoast_len(Datum d)
{
if (DatumGetPointer(d) == NULL)
{
ereport(ERROR,
(errcode(ERRCODE_INTERNAL_ERROR),
errmsg(" Unable to detoast datum "),
errprintstack(true)));
}
struct varlena *attr = (struct varlena *) DatumGetPointer(d);
struct varlena *result;
int len = -1;
void *toFree = NULL;
if (VARATT_IS_EXTENDED(attr))
{
if (VARATT_IS_EXTERNAL(attr))
{
result = toast_fetch_datum(attr);
/* toast_fetch_datum will palloc, so set it up for free */
toFree = result;
}
if (VARATT_IS_COMPRESSED(attr))
{
len = TOAST_COMPRESS_RAWSIZE(attr);
}
else if (VARATT_IS_SHORT(attr))
{
len = VARSIZE_SHORT(attr) - VARHDRSZ_SHORT;
}
}
if(len == -1)
len = VARSIZE(attr) - VARHDRSZ;
if (toFree)
pfree(toFree);
Assert(len >= 0);
return len;
}
/*
* If this function is changed then update varattrib_untoast_len as well
*/
void
varattrib_untoast_ptr_len(Datum d, char **datastart, int *len, void **tofree)
{
if (DatumGetPointer(d) == NULL)
{
ereport(ERROR,
(errcode(ERRCODE_INTERNAL_ERROR),
errmsg(" Unable to detoast datum "),
errprintstack(true)));
}
struct varlena *va = (struct varlena *) DatumGetPointer(d);
struct varlena *attr = va;
*len = -1;
*tofree = NULL;
if (VARATT_IS_EXTENDED(va))
{
if (VARATT_IS_EXTERNAL(va))
{
attr = toast_fetch_datum(va);
/* toast_fetch_datum will palloc, so set it up for free */
*tofree = attr;
}
if (VARATT_IS_COMPRESSED(attr))
{
struct varlena *tmp = attr;
attr = toast_decompress_datum(tmp);
/* If tofree is set, that is, we get it from toast_fetch_datum.
* We need to free it here
*/
if(*tofree)
pfree(*tofree);
*tofree = attr;
}
else if (VARATT_IS_SHORT(attr))
{
/* Warning! Return unaligned pointer! */
*len = VARSIZE_SHORT(attr) - VARHDRSZ_SHORT;
*datastart = VARDATA_SHORT(attr);
attr = NULL;
}
}
if (*len == -1)
{
*datastart = VARDATA(attr);
*len = VARSIZE(attr) - VARHDRSZ;
}
Assert(*len >= 0);
}
/* ----------
* heap_tuple_untoast_attr -
*
* Public entry point to get back a toasted value from compression
* or external storage. The result is always non-extended varlena form.
*
* Note some callers assume that if the input is an EXTERNAL or COMPRESSED
* datum, the result will be a pfree'able chunk.
* ----------
*/
struct varlena *
heap_tuple_untoast_attr(struct varlena *attr)
{
if (VARATT_IS_EXTERNAL_ONDISK(attr))
{
/*
* This is an externally stored datum --- fetch it back from there
*/
attr = toast_fetch_datum(attr);
/* If it's compressed, decompress it */
if (VARATT_IS_COMPRESSED(attr))
{
struct varlena *tmp = attr;
attr = toast_decompress_datum(tmp);
pfree(tmp);
}
}
else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
{
/*
* This is an indirect pointer --- dereference it
*/
struct varatt_indirect redirect;
VARATT_EXTERNAL_GET_POINTER(redirect, attr);
attr = (struct varlena *) redirect.pointer;
/* nested indirect Datums aren't allowed */
Assert(!VARATT_IS_EXTERNAL_INDIRECT(attr));
/* recurse in case value is still extended in some other way */
attr = heap_tuple_untoast_attr(attr);
/* if it isn't, we'd better copy it */
if (attr == (struct varlena *) redirect.pointer)
{
struct varlena *result;
result = (struct varlena *) palloc(VARSIZE_ANY(attr));
memcpy(result, attr, VARSIZE_ANY(attr));
attr = result;
}
}
else if (VARATT_IS_EXTERNAL_EXPANDED(attr))
{
/*
* This is an expanded-object pointer --- get flat format
*/
attr = heap_tuple_fetch_attr(attr);
/* flatteners are not allowed to produce compressed/short output */
Assert(!VARATT_IS_EXTENDED(attr));
}
else if (VARATT_IS_COMPRESSED(attr))
{
/*
* This is a compressed value inside of the main tuple
*/
attr = toast_decompress_datum(attr);
}
else if (VARATT_IS_SHORT(attr))
{
/*
* This is a short-header varlena --- convert to 4-byte header format
*/
Size data_size = VARSIZE_SHORT(attr) - VARHDRSZ_SHORT;
Size new_size = data_size + VARHDRSZ;
struct varlena *new_attr;
new_attr = (struct varlena *) palloc(new_size);
SET_VARSIZE(new_attr, new_size);
memcpy(VARDATA(new_attr), VARDATA_SHORT(attr), data_size);
attr = new_attr;
}
return attr;
}
/* ----------
* heap_tuple_untoast_attr_slice -
*
* Public entry point to get back part of a toasted value
* from compression or external storage.
* ----------
*/
struct varlena *
heap_tuple_untoast_attr_slice(struct varlena *attr,
int32 sliceoffset, int32 slicelength)
{
struct varlena *preslice;
struct varlena *result;
char *attrdata;
int32 attrsize;
if (VARATT_IS_EXTERNAL_ONDISK(attr))
{
struct varatt_external toast_pointer;
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
/* fast path for non-compressed external datums */
if (!VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer))
return toast_fetch_datum_slice(attr, sliceoffset, slicelength);
/* fetch it back (compressed marker will get set automatically) */
preslice = toast_fetch_datum(attr);
}
else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
{
struct varatt_indirect redirect;
VARATT_EXTERNAL_GET_POINTER(redirect, attr);
/* nested indirect Datums aren't allowed */
Assert(!VARATT_IS_EXTERNAL_INDIRECT(redirect.pointer));
return heap_tuple_untoast_attr_slice(redirect.pointer,
sliceoffset, slicelength);
}
else if (VARATT_IS_EXTERNAL_EXPANDED(attr))
{
/* pass it off to heap_tuple_fetch_attr to flatten */
preslice = heap_tuple_fetch_attr(attr);
}
else
preslice = attr;
Assert(!VARATT_IS_EXTERNAL(preslice));
if (VARATT_IS_COMPRESSED(preslice))
{
struct varlena *tmp = preslice;
/* Decompress enough to encompass the slice and the offset */
if (slicelength > 0 && sliceoffset >= 0)
preslice = toast_decompress_datum_slice(tmp, slicelength + sliceoffset);
else
preslice = toast_decompress_datum(tmp);
if (tmp != attr)
pfree(tmp);
}
if (VARATT_IS_SHORT(preslice))
{
attrdata = VARDATA_SHORT(preslice);
attrsize = VARSIZE_SHORT(preslice) - VARHDRSZ_SHORT;
}
else
{
attrdata = VARDATA(preslice);
attrsize = VARSIZE(preslice) - VARHDRSZ;
}
/* slicing of datum for compressed cases and plain value */
if (sliceoffset >= attrsize)
{
sliceoffset = 0;
slicelength = 0;
}
if (((sliceoffset + slicelength) > attrsize) || slicelength < 0)
slicelength = attrsize - sliceoffset;
result = (struct varlena *) palloc(slicelength + VARHDRSZ);
SET_VARSIZE(result, slicelength + VARHDRSZ);
memcpy(VARDATA(result), attrdata + sliceoffset, slicelength);
if (preslice != attr)
pfree(preslice);
return result;
}
/* ----------
* toast_raw_datum_size -
*
* Return the raw (detoasted) size of a varlena datum
* (including the VARHDRSZ header)
* ----------
*/
Size
toast_raw_datum_size(Datum value)
{
struct varlena *attr = (struct varlena *) DatumGetPointer(value);
Size result;
if (VARATT_IS_EXTERNAL_ONDISK(attr))
{
/* va_rawsize is the size of the original datum -- including header */
struct varatt_external toast_pointer;
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
result = toast_pointer.va_rawsize;
}
else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
{
struct varatt_indirect toast_pointer;
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
/* nested indirect Datums aren't allowed */
Assert(!VARATT_IS_EXTERNAL_INDIRECT(toast_pointer.pointer));
return toast_raw_datum_size(PointerGetDatum(toast_pointer.pointer));
}
else if (VARATT_IS_EXTERNAL_EXPANDED(attr))
{
result = EOH_get_flat_size(DatumGetEOHP(value));
}
else if (VARATT_IS_COMPRESSED(attr))
{
/* here, va_rawsize is just the payload size */
result = VARRAWSIZE_4B_C(attr) + VARHDRSZ;
}
else if (VARATT_IS_SHORT(attr))
{
/*
* we have to normalize the header length to VARHDRSZ or else the
* callers of this function will be confused.
*/
result = VARSIZE_SHORT(attr) - VARHDRSZ_SHORT + VARHDRSZ;
}
else
{
/* plain untoasted datum */
result = VARSIZE(attr);
}
return result;
}
/* ----------
* toast_datum_size
*
* Return the physical storage size (possibly compressed) of a varlena datum
* ----------
*/
Size
toast_datum_size(Datum value)
{
struct varlena *attr = (struct varlena *) DatumGetPointer(value);
Size result;
if (VARATT_IS_EXTERNAL_ONDISK(attr))
{
/*
* Attribute is stored externally - return the extsize whether
* compressed or not. We do not count the size of the toast pointer
* ... should we?
*/
struct varatt_external toast_pointer;
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
result = toast_pointer.va_extsize;
}
else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
{
struct varatt_indirect toast_pointer;
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
/* nested indirect Datums aren't allowed */
Assert(!VARATT_IS_EXTERNAL_INDIRECT(attr));
return toast_datum_size(PointerGetDatum(toast_pointer.pointer));
}
else if (VARATT_IS_EXTERNAL_EXPANDED(attr))
{
result = EOH_get_flat_size(DatumGetEOHP(value));
}
else if (VARATT_IS_SHORT(attr))
{
result = VARSIZE_SHORT(attr);
}
else
{
/*
* Attribute is stored inline either compressed or not, just calculate
* the size of the datum in either case.
*/
result = VARSIZE(attr);
}
return result;
}
/* ----------
* toast_delete -
*
* Cascaded delete toast-entries on DELETE
* ----------
*/
void
toast_delete(Relation rel, HeapTuple oldtup, bool is_speculative)
{
TupleDesc tupleDesc;
int numAttrs;
int i;
Datum toast_values[MaxHeapAttributeNumber];
bool toast_isnull[MaxHeapAttributeNumber];
/*
* We should only ever be called for tuples of plain relations ---
* recursing on a toast rel is bad news.
*/
Assert(rel->rd_rel->relkind == RELKIND_RELATION);
/*
* We should only ever be called for tuples of plain relations or
* materialized views --- recursing on a toast rel is bad news.
*/
Assert(rel->rd_rel->relkind == RELKIND_RELATION ||
rel->rd_rel->relkind == RELKIND_MATVIEW);
/*
* Get the tuple descriptor and break down the tuple into fields.
*
* NOTE: it's debatable whether to use heap_deform_tuple() here or just
* heap_getattr() only the varlena columns. The latter could win if there
* are few varlena columns and many non-varlena ones. However,
* heap_deform_tuple costs only O(N) while the heap_getattr way would cost
* O(N^2) if there are many varlena columns, so it seems better to err on
* the side of linear cost. (We won't even be here unless there's at
* least one varlena column, by the way.)
*/
tupleDesc = rel->rd_att;
numAttrs = tupleDesc->natts;
Assert(numAttrs <= MaxHeapAttributeNumber);
heap_deform_tuple((HeapTuple) oldtup, tupleDesc, toast_values, toast_isnull);
/*
* Check for external stored attributes and delete them from the secondary
* relation.
*/
for (i = 0; i < numAttrs; i++)
{
if (TupleDescAttr(tupleDesc, i)->attlen == -1)
{
Datum value = toast_values[i];
if (toast_isnull[i])
continue;
else if (VARATT_IS_EXTERNAL_ONDISK(PointerGetDatum(value)))
toast_delete_datum(rel, value, is_speculative);
}
}
}
/* ----------
* toast_insert_or_update -
*
* Delete no-longer-used toast-entries and create new ones to
* make the new tuple fit on INSERT or UPDATE
*
* Inputs:
* newtup: the candidate new tuple to be inserted
* oldtup: the old row version for UPDATE, or NULL for INSERT
* options: options to be passed to heap_insert() for toast rows
* Result:
* either newtup if no toasting is needed, or a palloc'd modified tuple
* that is what should actually get stored
*
* NOTE: neither newtup nor oldtup will be modified. This is a change
* from the pre-8.1 API of this routine.
* ----------
*/
static int
compute_dest_tuplen(TupleDesc tupdesc, MemTupleBinding *pbind, bool hasnull, Datum *d, bool *isnull)
{
if(pbind)
{
uint32 nullsave_dummy;
return (int) compute_memtuple_size(pbind, d, isnull, &nullsave_dummy, &hasnull);
}
return heap_compute_data_size(tupdesc, d, isnull);
}
static void *
toast_insert_or_update_generic(Relation rel, void *newtup, void *oldtup,
MemTupleBinding *pbind, int toast_tuple_target,
bool isFrozen, int options, bool ismemtuple)
{
void *result_gtuple;
TupleDesc tupleDesc;
int numAttrs;
int i;
bool need_change = false;
bool need_free = false;
bool need_delold = false;
bool has_nulls = false;
Size maxDataLen;
Size hoff;
char toast_action[MaxHeapAttributeNumber];
bool toast_isnull[MaxHeapAttributeNumber];
bool toast_oldisnull[MaxHeapAttributeNumber];
Datum toast_values[MaxHeapAttributeNumber];
Datum toast_oldvalues[MaxHeapAttributeNumber];
struct varlena *toast_oldexternal[MaxHeapAttributeNumber];
int32 toast_sizes[MaxHeapAttributeNumber];
bool toast_free[MaxHeapAttributeNumber];
bool toast_delold[MaxHeapAttributeNumber];
AssertImply(ismemtuple, pbind);
AssertImply(!ismemtuple, !pbind);
Assert(toast_tuple_target > 0);
/*
* Ignore the INSERT_SPECULATIVE option. Speculative insertions/super
* deletions just normally insert/delete the toast values. It seems
* easiest to deal with that here, instead on, potentially, multiple
* callers.
*/
options &= ~HEAP_INSERT_SPECULATIVE;
/*
* We should only ever be called for tuples of plain relations or
* materialized views --- recursing on a toast rel is bad news.
*/
Assert(rel->rd_rel->relkind == RELKIND_RELATION ||
rel->rd_rel->relkind == RELKIND_MATVIEW);
/*
* Get the tuple descriptor and break down the tuple(s) into fields.
*/
tupleDesc = rel->rd_att;
numAttrs = tupleDesc->natts;
Assert(numAttrs <= MaxHeapAttributeNumber);
if(ismemtuple)
memtuple_deform((MemTuple) newtup, pbind, toast_values, toast_isnull);
else
heap_deform_tuple((HeapTuple) newtup, tupleDesc, toast_values, toast_isnull);
if (oldtup != NULL)
{
if(ismemtuple)
memtuple_deform((MemTuple) oldtup, pbind, toast_oldvalues, toast_oldisnull);
else
heap_deform_tuple((HeapTuple) oldtup, tupleDesc, toast_oldvalues, toast_oldisnull);
}
/* ----------
* Then collect information about the values given
*
* NOTE: toast_action[i] can have these values:
* ' ' default handling
* 'p' already processed --- don't touch it
* 'x' incompressible, but OK to move off
*
* NOTE: toast_sizes[i] is only made valid for varlena attributes with
* toast_action[i] different from 'p'.
* ----------
*/
memset(toast_action, ' ', numAttrs * sizeof(char));
memset(toast_oldexternal, 0, numAttrs * sizeof(struct varlena *));
memset(toast_free, 0, numAttrs * sizeof(bool));
memset(toast_delold, 0, numAttrs * sizeof(bool));
for (i = 0; i < numAttrs; i++)
{
Form_pg_attribute att = TupleDescAttr(tupleDesc, i);
struct varlena *old_value;
struct varlena *new_value;
if (oldtup != NULL)
{
/*
* For UPDATE get the old and new values of this attribute
*/
old_value = (struct varlena *) DatumGetPointer(toast_oldvalues[i]);
new_value = (struct varlena *) DatumGetPointer(toast_values[i]);
/*
* If the old value is stored on disk, check if it has changed so
* we have to delete it later.
*/
if (att->attlen == -1 && !toast_oldisnull[i] &&
VARATT_IS_EXTERNAL_ONDISK(old_value))
{
if (toast_isnull[i] || !VARATT_IS_EXTERNAL_ONDISK(new_value) ||
memcmp((char *) old_value, (char *) new_value,
VARSIZE_EXTERNAL(old_value)) != 0)
{
/*
* The old external stored value isn't needed any more
* after the update
*/
toast_delold[i] = true;
need_delold = true;
}
else
{
/*
* This attribute isn't changed by this update so we reuse
* the original reference to the old value in the new
* tuple.
*/
toast_action[i] = 'p';
continue;
}
}
}
else
{
/*
* For INSERT simply get the new value
*/
new_value = (struct varlena *) DatumGetPointer(toast_values[i]);
}
/*
* Handle NULL attributes
*/
if (toast_isnull[i])
{
toast_action[i] = 'p';
has_nulls = true;
continue;
}
/*
* Now look at varlena attributes
*/
if (att->attlen == -1)
{
/*
* If the table's attribute says PLAIN always, force it so.
*/
if (att->attstorage == 'p')
toast_action[i] = 'p';
/*
* We took care of UPDATE above, so any external value we find
* still in the tuple must be someone else's that we cannot reuse
* (this includes the case of an out-of-line in-memory datum).
* Fetch it back (without decompression, unless we are forcing
* PLAIN storage). If necessary, we'll push it out as a new
* external value below.
*/
if (VARATT_IS_EXTERNAL(new_value))
{
toast_oldexternal[i] = new_value;
if (att->attstorage == 'p')
new_value = heap_tuple_untoast_attr(new_value);
else
new_value = heap_tuple_fetch_attr(new_value);
toast_values[i] = PointerGetDatum(new_value);
toast_free[i] = true;
need_change = true;
need_free = true;
}
/*
* Remember the size of this attribute
*/
toast_sizes[i] = VARSIZE_ANY(new_value);
}
else
{
/*
* Not a varlena attribute, plain storage always
*/
toast_action[i] = 'p';
}
}
/* ----------
* Compress and/or save external until data fits into target length
*
* 1: Inline compress attributes with attstorage 'x', and store very
* large attributes with attstorage 'x' or 'e' external immediately
* 2: Store attributes with attstorage 'x' or 'e' external
* 3: Inline compress attributes with attstorage 'm'
* 4: Store attributes with attstorage 'm' external
* ----------
*/
if (!ismemtuple)
{
/* compute header overhead --- this should match heap_form_tuple() */
hoff = SizeofHeapTupleHeader;
if (has_nulls)
hoff += BITMAPLEN(numAttrs);
hoff = MAXALIGN(hoff);
/* now convert to a limit on the tuple data size */
maxDataLen = RelationGetToastTupleTarget(rel, TOAST_TUPLE_TARGET) - hoff;
}
else
{
maxDataLen = toast_tuple_target;
hoff = -1; /* keep compiler quiet about using 'hoff' uninitialized */
}
/*
* Look for attributes with attstorage 'x' to compress. Also find large
* attributes with attstorage 'x' or 'e', and store them external.
*/
while (compute_dest_tuplen(tupleDesc, pbind, has_nulls,
toast_values, toast_isnull) > maxDataLen)
{
int biggest_attno = -1;
int32 biggest_size = MAXALIGN(TOAST_POINTER_SIZE);
Datum old_value;
Datum new_value;
/*
* Search for the biggest yet unprocessed internal attribute
*/
for (i = 0; i < numAttrs; i++)
{
Form_pg_attribute att = TupleDescAttr(tupleDesc, i);
if (toast_action[i] != ' ')
continue;
if (VARATT_IS_EXTERNAL(DatumGetPointer(toast_values[i])))
continue; /* can't happen, toast_action would be 'p' */
if (VARATT_IS_COMPRESSED(DatumGetPointer(toast_values[i])))
continue;
if (att->attstorage != 'x' && att->attstorage != 'e')
continue;
if (toast_sizes[i] > biggest_size)
{
biggest_attno = i;
biggest_size = toast_sizes[i];
}
}
if (biggest_attno < 0)
break;
/*
* Attempt to compress it inline, if it has attstorage 'x'
*/
i = biggest_attno;
if (TupleDescAttr(tupleDesc, i)->attstorage == 'x')
{
old_value = toast_values[i];
new_value = toast_compress_datum(old_value);
if (DatumGetPointer(new_value) != NULL)
{
/* successful compression */
if (toast_free[i])
pfree(DatumGetPointer(old_value));
toast_values[i] = new_value;
toast_free[i] = true;
toast_sizes[i] = VARSIZE(DatumGetPointer(toast_values[i]));
need_change = true;
need_free = true;
}
else
{
/* incompressible, ignore on subsequent compression passes */
toast_action[i] = 'x';
}
}
else
{
/* has attstorage 'e', ignore on subsequent compression passes */
toast_action[i] = 'x';
}
/*
* If this value is by itself more than maxDataLen (after compression
* if any), push it out to the toast table immediately, if possible.
* This avoids uselessly compressing other fields in the common case
* where we have one long field and several short ones.
*
* XXX maybe the threshold should be less than maxDataLen?
*/
if (toast_sizes[i] > maxDataLen &&
rel->rd_rel->reltoastrelid != InvalidOid)
{
old_value = toast_values[i];
toast_action[i] = 'p';
toast_values[i] = toast_save_datum(rel, toast_values[i],
toast_oldexternal[i], isFrozen, options);
if (toast_free[i])
pfree(DatumGetPointer(old_value));
toast_free[i] = true;
need_change = true;
need_free = true;
}
}
/*
* Second we look for attributes of attstorage 'x' or 'e' that are still
* inline. But skip this if there's no toast table to push them to.
*/
while (compute_dest_tuplen(tupleDesc, pbind, has_nulls,
toast_values, toast_isnull) > maxDataLen &&
rel->rd_rel->reltoastrelid != InvalidOid)
{
int biggest_attno = -1;
int32 biggest_size = MAXALIGN(TOAST_POINTER_SIZE);
Datum old_value;
/*------
* Search for the biggest yet inlined attribute with
* attstorage equals 'x' or 'e'
*------
*/
for (i = 0; i < numAttrs; i++)
{
Form_pg_attribute att = TupleDescAttr(tupleDesc, i);
if (toast_action[i] == 'p')
continue;
if (VARATT_IS_EXTERNAL(DatumGetPointer(toast_values[i])))
continue; /* can't happen, toast_action would be 'p' */
if (att->attstorage != 'x' && att->attstorage != 'e')
continue;
if (toast_sizes[i] > biggest_size)
{
biggest_attno = i;
biggest_size = toast_sizes[i];
}
}
if (biggest_attno < 0)
break;
/*
* Store this external
*/
i = biggest_attno;
old_value = toast_values[i];
toast_action[i] = 'p';
toast_values[i] = toast_save_datum(rel, toast_values[i],
toast_oldexternal[i], isFrozen, options);
if (toast_free[i])
pfree(DatumGetPointer(old_value));
toast_free[i] = true;
need_change = true;
need_free = true;
}
/*
* Round 3 - this time we take attributes with storage 'm' into
* compression
*/
while (compute_dest_tuplen(tupleDesc, pbind, has_nulls,
toast_values, toast_isnull) > maxDataLen)
{
int biggest_attno = -1;
int32 biggest_size = MAXALIGN(TOAST_POINTER_SIZE);
Datum old_value;
Datum new_value;
/*
* Search for the biggest yet uncompressed internal attribute
*/
for (i = 0; i < numAttrs; i++)
{
if (toast_action[i] != ' ')
continue;
if (VARATT_IS_EXTERNAL(DatumGetPointer(toast_values[i])))
continue; /* can't happen, toast_action would be 'p' */
if (VARATT_IS_COMPRESSED(DatumGetPointer(toast_values[i])))
continue;
if (TupleDescAttr(tupleDesc, i)->attstorage != 'm')
continue;
if (toast_sizes[i] > biggest_size)
{
biggest_attno = i;
biggest_size = toast_sizes[i];
}
}
if (biggest_attno < 0)
break;
/*
* Attempt to compress it inline
*/
i = biggest_attno;
old_value = toast_values[i];
new_value = toast_compress_datum(old_value);
if (DatumGetPointer(new_value) != NULL)
{
/* successful compression */
if (toast_free[i])
pfree(DatumGetPointer(old_value));
toast_values[i] = new_value;
toast_free[i] = true;
toast_sizes[i] = VARSIZE(DatumGetPointer(toast_values[i]));
need_change = true;
need_free = true;
}
else
{
/* incompressible, ignore on subsequent compression passes */
toast_action[i] = 'x';
}
}
/*
* Finally we store attributes of type 'm' externally. At this point we
* increase the target tuple size, so that 'm' attributes aren't stored
* externally unless really necessary.
*/
/*
* FIXME: Should we do something like this with memtuples on
* AO tables too? Currently we do not increase the target tuple size for AO
* table, so there are occasions when columns of type 'm' will be stored
* out-of-line but they could otherwise be accommodated in-block
* c.f. upstream Postgres commit ca7c8168de76459380577eda56a3ed09b4f6195c
*/
if (!ismemtuple)
maxDataLen = TOAST_TUPLE_TARGET_MAIN - hoff;
while (compute_dest_tuplen(tupleDesc, pbind, has_nulls,
toast_values, toast_isnull) > maxDataLen &&
rel->rd_rel->reltoastrelid != InvalidOid)
{
int biggest_attno = -1;
int32 biggest_size = MAXALIGN(TOAST_POINTER_SIZE);
Datum old_value;
/*--------
* Search for the biggest yet inlined attribute with
* attstorage = 'm'
*--------
*/
for (i = 0; i < numAttrs; i++)
{
if (toast_action[i] == 'p')
continue;
if (VARATT_IS_EXTERNAL(DatumGetPointer(toast_values[i])))
continue; /* can't happen, toast_action would be 'p' */
if (TupleDescAttr(tupleDesc, i)->attstorage != 'm')
continue;
if (toast_sizes[i] > biggest_size)
{
biggest_attno = i;
biggest_size = toast_sizes[i];
}
}
if (biggest_attno < 0)
break;
/*
* Store this external
*/
i = biggest_attno;
old_value = toast_values[i];
toast_action[i] = 'p';
toast_values[i] = toast_save_datum(rel, toast_values[i],
toast_oldexternal[i], isFrozen, options);
if (toast_free[i])
pfree(DatumGetPointer(old_value));
toast_free[i] = true;
need_change = true;
need_free = true;
}
/* XXX Maybe we should check here for any compressed inline attributes that
* didn't save enough to warrant keeping. In particular attributes whose
* rawsize is < 128 bytes and didn't save at least 3 bytes... or even maybe
* more given alignment issues
*/
/*
* In the case we toasted any values, we need to build a new heap tuple
* with the changed values.
*/
if (need_change)
{
if(ismemtuple)
{
result_gtuple = (void *) memtuple_form(pbind, toast_values, toast_isnull);
}
else
{
HeapTupleHeader olddata = ((HeapTuple) newtup)->t_data;
HeapTupleHeader new_data;
int32 new_header_len;
int32 new_data_len;
int32 new_tuple_len;
HeapTuple result_tuple;
/*
* Calculate the new size of the tuple.
*
* Note: we used to assume here that the old tuple's t_hoff must equal
* the new_header_len value, but that was incorrect. The old tuple
* might have a smaller-than-current natts, if there's been an ALTER
* TABLE ADD COLUMN since it was stored; and that would lead to a
* different conclusion about the size of the null bitmap, or even
* whether there needs to be one at all.
*/
new_header_len = SizeofHeapTupleHeader;
if (has_nulls)
new_header_len += BITMAPLEN(numAttrs);
new_header_len = MAXALIGN(new_header_len);
new_data_len = heap_compute_data_size(tupleDesc,
toast_values, toast_isnull);
new_tuple_len = new_header_len + new_data_len;
/*
* Allocate and zero the space needed, and fill HeapTupleData fields.
*/
result_tuple = (HeapTuple) palloc0(HEAPTUPLESIZE + new_tuple_len);
result_tuple->t_len = new_tuple_len;
result_tuple->t_self = ((HeapTuple) newtup)->t_self;
result_tuple->t_tableOid = ((HeapTuple) newtup)->t_tableOid;
new_data = (HeapTupleHeader) ((char *) result_tuple + HEAPTUPLESIZE);
result_tuple->t_data = new_data;
/*
* Copy the existing tuple header, but adjust natts and t_hoff.
*/
memcpy(new_data, olddata, SizeofHeapTupleHeader);
HeapTupleHeaderSetNatts(new_data, numAttrs);
new_data->t_hoff = new_header_len;
/* Copy over the data, and fill the null bitmap if needed */
heap_fill_tuple(tupleDesc,
toast_values,
toast_isnull,
(char *) new_data + new_header_len,
new_data_len,
&(new_data->t_infomask),
has_nulls ? new_data->t_bits : NULL);
result_gtuple = (void *) result_tuple;
}
}
else
result_gtuple = newtup;
/*
* Free allocated temp values
*/
if (need_free)
for (i = 0; i < numAttrs; i++)
if (toast_free[i])
pfree(DatumGetPointer(toast_values[i]));
/*
* Delete external values from the old tuple
*/
if (need_delold)
for (i = 0; i < numAttrs; i++)
if (toast_delold[i])
toast_delete_datum(rel, toast_oldvalues[i], false);
return result_gtuple;
}
HeapTuple
toast_insert_or_update(Relation rel, HeapTuple newtup, HeapTuple oldtup,
int toast_tuple_target,
bool isFrozen, int options)
{
return (HeapTuple) toast_insert_or_update_generic(rel,
(void *) newtup,
(void *) oldtup,
NULL,
toast_tuple_target,
isFrozen,
options,
false);
}
MemTuple
toast_insert_or_update_memtup(Relation rel, MemTuple newtup, MemTuple oldtup,
MemTupleBinding *pbind, int toast_tuple_target,
bool isFrozen, int options)
{
return (MemTuple) toast_insert_or_update_generic(rel,
(void *) newtup,
(void *) oldtup,
pbind,
toast_tuple_target,
isFrozen,
options,
true);
}
/* ----------
* toast_flatten_tuple -
*
* "Flatten" a tuple to contain no out-of-line toasted fields.
* (This does not eliminate compressed or short-header datums.)
*
* Note: we expect the caller already checked HeapTupleHasExternal(tup),
* so there is no need for a short-circuit path.
* ----------
*/
HeapTuple
toast_flatten_tuple(HeapTuple tup, TupleDesc tupleDesc)
{
HeapTuple new_tuple;
int numAttrs = tupleDesc->natts;
int i;
Datum toast_values[MaxTupleAttributeNumber];
bool toast_isnull[MaxTupleAttributeNumber];
bool toast_free[MaxTupleAttributeNumber];
/*
* Break down the tuple into fields.
*/
Assert(numAttrs <= MaxTupleAttributeNumber);
heap_deform_tuple(tup, tupleDesc, toast_values, toast_isnull);
memset(toast_free, 0, numAttrs * sizeof(bool));
for (i = 0; i < numAttrs; i++)
{
/*
* Look at non-null varlena attributes
*/
if (!toast_isnull[i] && TupleDescAttr(tupleDesc, i)->attlen == -1)
{
struct varlena *new_value;
new_value = (struct varlena *) DatumGetPointer(toast_values[i]);
if (VARATT_IS_EXTERNAL(new_value))
{
new_value = heap_tuple_fetch_attr(new_value);
toast_values[i] = PointerGetDatum(new_value);
toast_free[i] = true;
}
}
}
/*
* Form the reconfigured tuple.
*/
new_tuple = heap_form_tuple(tupleDesc, toast_values, toast_isnull);
/*
* Be sure to copy the tuple's identity fields. We also make a point of
* copying visibility info, just in case anybody looks at those fields in
* a syscache entry.
*/
new_tuple->t_self = tup->t_self;
new_tuple->t_tableOid = tup->t_tableOid;
new_tuple->t_data->t_choice = tup->t_data->t_choice;
new_tuple->t_data->t_ctid = tup->t_data->t_ctid;
new_tuple->t_data->t_infomask &= ~HEAP_XACT_MASK;
new_tuple->t_data->t_infomask |=
tup->t_data->t_infomask & HEAP_XACT_MASK;
new_tuple->t_data->t_infomask2 &= ~HEAP2_XACT_MASK;
new_tuple->t_data->t_infomask2 |=
tup->t_data->t_infomask2 & HEAP2_XACT_MASK;
/*
* Free allocated temp values
*/
for (i = 0; i < numAttrs; i++)
if (toast_free[i])
pfree(DatumGetPointer(toast_values[i]));
return new_tuple;
}
/* ----------
* toast_flatten_tuple_to_datum -
*
* "Flatten" a tuple containing out-of-line toasted fields into a Datum.
* The result is always palloc'd in the current memory context.
*
* We have a general rule that Datums of container types (rows, arrays,
* ranges, etc) must not contain any external TOAST pointers. Without
* this rule, we'd have to look inside each Datum when preparing a tuple
* for storage, which would be expensive and would fail to extend cleanly
* to new sorts of container types.
*
* However, we don't want to say that tuples represented as HeapTuples
* can't contain toasted fields, so instead this routine should be called
* when such a HeapTuple is being converted into a Datum.
*
* While we're at it, we decompress any compressed fields too. This is not
* necessary for correctness, but reflects an expectation that compression
* will be more effective if applied to the whole tuple not individual
* fields. We are not so concerned about that that we want to deconstruct
* and reconstruct tuples just to get rid of compressed fields, however.
* So callers typically won't call this unless they see that the tuple has
* at least one external field.
*
* On the other hand, in-line short-header varlena fields are left alone.
* If we "untoasted" them here, they'd just get changed back to short-header
* format anyway within heap_fill_tuple.
* ----------
*/
Datum
toast_flatten_tuple_to_datum(HeapTupleHeader tup,
uint32 tup_len,
TupleDesc tupleDesc)
{
HeapTupleHeader new_data;
int32 new_header_len;
int32 new_data_len;
int32 new_tuple_len;
HeapTupleData tmptup;
int numAttrs = tupleDesc->natts;
int i;
bool has_nulls = false;
Datum toast_values[MaxTupleAttributeNumber];
bool toast_isnull[MaxTupleAttributeNumber];
bool toast_free[MaxTupleAttributeNumber];
/* Build a temporary HeapTuple control structure */
tmptup.t_len = tup_len;
ItemPointerSetInvalid(&(tmptup.t_self));
tmptup.t_tableOid = InvalidOid;
tmptup.t_data = tup;
/*
* Break down the tuple into fields.
*/
Assert(numAttrs <= MaxTupleAttributeNumber);
heap_deform_tuple(&tmptup, tupleDesc, toast_values, toast_isnull);
memset(toast_free, 0, numAttrs * sizeof(bool));
for (i = 0; i < numAttrs; i++)
{
/*
* Look at non-null varlena attributes
*/
if (toast_isnull[i])
has_nulls = true;
else if (TupleDescAttr(tupleDesc, i)->attlen == -1)
{
struct varlena *new_value;
new_value = (struct varlena *) DatumGetPointer(toast_values[i]);
if (VARATT_IS_EXTERNAL(new_value) ||
VARATT_IS_COMPRESSED(new_value))
{
new_value = heap_tuple_untoast_attr(new_value);
toast_values[i] = PointerGetDatum(new_value);
toast_free[i] = true;
}
}
}
/*
* Calculate the new size of the tuple.
*
* This should match the reconstruction code in toast_insert_or_update.
*/
new_header_len = SizeofHeapTupleHeader;
if (has_nulls)
new_header_len += BITMAPLEN(numAttrs);
new_header_len = MAXALIGN(new_header_len);
new_data_len = heap_compute_data_size(tupleDesc,
toast_values, toast_isnull);
new_tuple_len = new_header_len + new_data_len;
new_data = (HeapTupleHeader) palloc0(new_tuple_len);
/*
* Copy the existing tuple header, but adjust natts and t_hoff.
*/
memcpy(new_data, tup, SizeofHeapTupleHeader);
HeapTupleHeaderSetNatts(new_data, numAttrs);
new_data->t_hoff = new_header_len;
/* Set the composite-Datum header fields correctly */
HeapTupleHeaderSetDatumLength(new_data, new_tuple_len);
HeapTupleHeaderSetTypeId(new_data, tupleDesc->tdtypeid);
HeapTupleHeaderSetTypMod(new_data, tupleDesc->tdtypmod);
/* Copy over the data, and fill the null bitmap if needed */
heap_fill_tuple(tupleDesc,
toast_values,
toast_isnull,
(char *) new_data + new_header_len,
new_data_len,
&(new_data->t_infomask),
has_nulls ? new_data->t_bits : NULL);
/*
* Free allocated temp values
*/
for (i = 0; i < numAttrs; i++)
if (toast_free[i])
pfree(DatumGetPointer(toast_values[i]));
return PointerGetDatum(new_data);
}
/* ----------
* toast_build_flattened_tuple -
*
* Build a tuple containing no out-of-line toasted fields.
* (This does not eliminate compressed or short-header datums.)
*
* This is essentially just like heap_form_tuple, except that it will
* expand any external-data pointers beforehand.
*
* It's not very clear whether it would be preferable to decompress
* in-line compressed datums while at it. For now, we don't.
* ----------
*/
HeapTuple
toast_build_flattened_tuple(TupleDesc tupleDesc,
Datum *values,
bool *isnull)
{
HeapTuple new_tuple;
int numAttrs = tupleDesc->natts;
int num_to_free;
int i;
Datum new_values[MaxTupleAttributeNumber];
Pointer freeable_values[MaxTupleAttributeNumber];
/*
* We can pass the caller's isnull array directly to heap_form_tuple, but
* we potentially need to modify the values array.
*/
Assert(numAttrs <= MaxTupleAttributeNumber);
memcpy(new_values, values, numAttrs * sizeof(Datum));
num_to_free = 0;
for (i = 0; i < numAttrs; i++)
{
/*
* Look at non-null varlena attributes
*/
if (!isnull[i] && TupleDescAttr(tupleDesc, i)->attlen == -1)
{
struct varlena *new_value;
new_value = (struct varlena *) DatumGetPointer(new_values[i]);
if (VARATT_IS_EXTERNAL(new_value))
{
new_value = heap_tuple_fetch_attr(new_value);
new_values[i] = PointerGetDatum(new_value);
freeable_values[num_to_free++] = (Pointer) new_value;
}
}
}
/*
* Form the reconfigured tuple.
*/
new_tuple = heap_form_tuple(tupleDesc, new_values, isnull);
/*
* Free allocated temp values
*/
for (i = 0; i < num_to_free; i++)
pfree(freeable_values[i]);
return new_tuple;
}
/* ----------
* toast_compress_datum -
*
* Create a compressed version of a varlena datum
*
* If we fail (ie, compressed result is actually bigger than original)
* then return NULL. We must not use compressed data if it'd expand
* the tuple!
*
* We use VAR{SIZE,DATA}_ANY so we can handle short varlenas here without
* copying them. But we can't handle external or compressed datums.
* ----------
*/
Datum
toast_compress_datum(Datum value)
{
struct varlena *tmp;
int32 valsize = VARSIZE_ANY_EXHDR(DatumGetPointer(value));
int32 len;
Assert(!VARATT_IS_EXTERNAL(DatumGetPointer(value)));
Assert(!VARATT_IS_COMPRESSED(DatumGetPointer(value)));
/*
* No point in wasting a palloc cycle if value size is out of the allowed
* range for compression
*/
if (valsize < PGLZ_strategy_default->min_input_size ||
valsize > PGLZ_strategy_default->max_input_size)
return PointerGetDatum(NULL);
tmp = (struct varlena *) palloc(PGLZ_MAX_OUTPUT(valsize) +
TOAST_COMPRESS_HDRSZ);
/*
* We recheck the actual size even if pglz_compress() reports success,
* because it might be satisfied with having saved as little as one byte
* in the compressed data --- which could turn into a net loss once you
* consider header and alignment padding. Worst case, the compressed
* format might require three padding bytes (plus header, which is
* included in VARSIZE(tmp)), whereas the uncompressed format would take
* only one header byte and no padding if the value is short enough. So
* we insist on a savings of more than 2 bytes to ensure we have a gain.
*/
len = pglz_compress(VARDATA_ANY(DatumGetPointer(value)),
valsize,
TOAST_COMPRESS_RAWDATA(tmp),
PGLZ_strategy_default);
if (len >= 0 &&
len + TOAST_COMPRESS_HDRSZ < valsize - 2)
{
TOAST_COMPRESS_SET_RAWSIZE(tmp, valsize);
SET_VARSIZE_COMPRESSED(tmp, len + TOAST_COMPRESS_HDRSZ);
/* successful compression */
return PointerGetDatum(tmp);
}
else
{
/* incompressible data */
pfree(tmp);
return PointerGetDatum(NULL);
}
}
/* ----------
* toast_get_valid_index
*
* Get OID of valid index associated to given toast relation. A toast
* relation can have only one valid index at the same time.
*/
Oid
toast_get_valid_index(Oid toastoid, LOCKMODE lock)
{
int num_indexes;
int validIndex;
Oid validIndexOid;
Relation *toastidxs;
Relation toastrel;
/* Open the toast relation */
toastrel = table_open(toastoid, lock);
/* Look for the valid index of the toast relation */
validIndex = toast_open_indexes(toastrel,
lock,
&toastidxs,
&num_indexes);
validIndexOid = RelationGetRelid(toastidxs[validIndex]);
/* Close the toast relation and all its indexes */
toast_close_indexes(toastidxs, num_indexes, lock);
table_close(toastrel, lock);
return validIndexOid;
}
/* ----------
* toast_save_datum -
*
* Save one single datum into the secondary relation and return
* a Datum reference for it.
*
* rel: the main relation we're working with (not the toast rel!)
* value: datum to be pushed to toast storage
* oldexternal: if not NULL, toast pointer previously representing the datum
* options: options to be passed to heap_insert() for toast rows
* ----------
*/
static Datum
toast_save_datum(Relation rel, Datum value,
struct varlena *oldexternal, bool isFrozen, int options)
{
Relation toastrel;
Relation *toastidxs;
HeapTuple toasttup;
TupleDesc toasttupDesc;
Datum t_values[3];
bool t_isnull[3];
TransactionId myxid = GetCurrentTransactionId();
CommandId mycid = GetCurrentCommandId(true);
struct varlena *result;
struct varatt_external toast_pointer;
union
{
struct varlena hdr;
/* this is to make the union big enough for a chunk: */
char data[TOAST_MAX_CHUNK_SIZE + VARHDRSZ];
/* ensure union is aligned well enough: */
int32 align_it;
} chunk_data;
int32 chunk_size;
int32 chunk_seq = 0;
char *data_p;
int32 data_todo;
Pointer dval = DatumGetPointer(value);
int num_indexes;
int validIndex;
Assert(!VARATT_IS_EXTERNAL(value));
int32 max_chunk_size = TOAST_MAX_CHUNK_SIZE;
/*
* Open the toast relation and its indexes. We can use the index to check
* uniqueness of the OID we assign to the toasted item, even though it has
* additional columns besides OID.
*/
toastrel = table_open(rel->rd_rel->reltoastrelid, RowExclusiveLock);
toasttupDesc = toastrel->rd_att;
/* Open all the toast indexes and look for the valid one */
validIndex = toast_open_indexes(toastrel,
RowExclusiveLock,
&toastidxs,
&num_indexes);
/*
* Get the data pointer and length, and compute va_rawsize and va_extsize.
*
* va_rawsize is the size of the equivalent fully uncompressed datum, so
* we have to adjust for short headers.
*
* va_extsize is the actual size of the data payload in the toast records.
*/
if (VARATT_IS_SHORT(dval))
{
data_p = VARDATA_SHORT(dval);
data_todo = VARSIZE_SHORT(dval) - VARHDRSZ_SHORT;
toast_pointer.va_rawsize = data_todo + VARHDRSZ; /* as if not short */
toast_pointer.va_extsize = data_todo;
}
else if (VARATT_IS_COMPRESSED(dval))
{
data_p = VARDATA(dval);
data_todo = VARSIZE(dval) - VARHDRSZ;
/* rawsize in a compressed datum is just the size of the payload */
toast_pointer.va_rawsize = VARRAWSIZE_4B_C(dval) + VARHDRSZ;
toast_pointer.va_extsize = data_todo;
/* Assert that the numbers look like it's compressed */
Assert(VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer));
}
else
{
data_p = VARDATA(dval);
data_todo = VARSIZE(dval) - VARHDRSZ;
toast_pointer.va_rawsize = VARSIZE(dval);
toast_pointer.va_extsize = data_todo;
}
/*
* Insert the correct table OID into the result TOAST pointer.
*
* Normally this is the actual OID of the target toast table, but during
* table-rewriting operations such as CLUSTER, we have to insert the OID
* of the table's real permanent toast table instead. rd_toastoid is set
* if we have to substitute such an OID.
*/
if (OidIsValid(rel->rd_toastoid))
toast_pointer.va_toastrelid = rel->rd_toastoid;
else
toast_pointer.va_toastrelid = RelationGetRelid(toastrel);
/*
* Choose an OID to use as the value ID for this toast value.
*
* Normally we just choose an unused OID within the toast table. But
* during table-rewriting operations where we are preserving an existing
* toast table OID, we want to preserve toast value OIDs too. So, if
* rd_toastoid is set and we had a prior external value from that same
* toast table, re-use its value ID. If we didn't have a prior external
* value (which is a corner case, but possible if the table's attstorage
* options have been changed), we have to pick a value ID that doesn't
* conflict with either new or existing toast value OIDs.
*/
if (!OidIsValid(rel->rd_toastoid))
{
/* normal case: just choose an unused OID */
toast_pointer.va_valueid =
GetNewOidWithIndex(toastrel,
RelationGetRelid(toastidxs[validIndex]),
(AttrNumber) 1);
}
else
{
/* rewrite case: check to see if value was in old toast table */
toast_pointer.va_valueid = InvalidOid;
if (oldexternal != NULL)
{
struct varatt_external old_toast_pointer;
Assert(VARATT_IS_EXTERNAL_ONDISK(oldexternal));
/* Must copy to access aligned fields */
VARATT_EXTERNAL_GET_POINTER(old_toast_pointer, oldexternal);
if (old_toast_pointer.va_toastrelid == rel->rd_toastoid)
{
/* This value came from the old toast table; reuse its OID */
toast_pointer.va_valueid = old_toast_pointer.va_valueid;
/*
* There is a corner case here: the table rewrite might have
* to copy both live and recently-dead versions of a row, and
* those versions could easily reference the same toast value.
* When we copy the second or later version of such a row,
* reusing the OID will mean we select an OID that's already
* in the new toast table. Check for that, and if so, just
* fall through without writing the data again.
*
* While annoying and ugly-looking, this is a good thing
* because it ensures that we wind up with only one copy of
* the toast value when there is only one copy in the old
* toast table. Before we detected this case, we'd have made
* multiple copies, wasting space; and what's worse, the
* copies belonging to already-deleted heap tuples would not
* be reclaimed by VACUUM.
*/
if (toastrel_valueid_exists(toastrel,
toast_pointer.va_valueid))
{
/* Match, so short-circuit the data storage loop below */
data_todo = 0;
}
}
}
if (toast_pointer.va_valueid == InvalidOid)
{
/*
* new value; must choose an OID that doesn't conflict in either
* old or new toast table
*/
do
{
toast_pointer.va_valueid =
GetNewOidWithIndex(toastrel,
RelationGetRelid(toastidxs[validIndex]),
(AttrNumber) 1);
} while (toastid_valueid_exists(rel->rd_toastoid,
toast_pointer.va_valueid));
}
}
#ifdef USE_ASSERT_CHECKING
Assert((VARATT_IS_COMPRESSED(value) || 0) == (VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer) || 0));
if (VARATT_IS_COMPRESSED(value))
{
Assert(VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer));
elog(DEBUG4,
"saved toast datum, original varsize %ud rawsize %ud new extsize %ud rawsize %uld\n",
VARSIZE(value), VARRAWSIZE_4B_C(value) + VARHDRSZ,
toast_pointer.va_extsize, toast_pointer.va_rawsize);
}
else
{
Assert(!VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer));
elog(DEBUG4,
"saved toast datum, original varsize %ud new extsize %ud rawsize %ud\n",
VARSIZE(value),
toast_pointer.va_extsize, toast_pointer.va_rawsize);
}
#endif
/*
* Initialize constant parts of the tuple data
*/
t_values[0] = ObjectIdGetDatum(toast_pointer.va_valueid);
t_values[2] = PointerGetDatum(&chunk_data);
t_isnull[0] = false;
t_isnull[1] = false;
t_isnull[2] = false;
#ifdef FAULT_INJECTOR
/*
* GPDB: for upgrade testing purposes, allow the maximum chunk size to be
* modified (here, we decrease it by one). The result must still fit into
* TOAST_MAX_CHUNK_SIZE so that it doesn't overflow our chunk_data struct.
*/
if (FaultInjector_InjectFaultIfSet("decrease_toast_max_chunk_size",
DDLNotSpecified,
"", /* databaseName */
"" /* tableName */) != FaultInjectorTypeNotSpecified)
{
max_chunk_size--;
}
#endif
/*
* Split up the item into chunks
*/
while (data_todo > 0)
{
int i;
CHECK_FOR_INTERRUPTS();
/*
* Calculate the size of this chunk
*/
chunk_size = Min(max_chunk_size, data_todo);
/*
* Build a tuple and store it
*/
t_values[1] = Int32GetDatum(chunk_seq++);
SET_VARSIZE(&chunk_data, chunk_size + VARHDRSZ);
memcpy(VARDATA(&chunk_data), data_p, chunk_size);
toasttup = heap_form_tuple(toasttupDesc, t_values, t_isnull);
if (!isFrozen)
{
/* the normal case. regular insert */
heap_insert(toastrel, toasttup, mycid, options, NULL, myxid);
}
else
{
/* insert and freeze the tuple. used for errtables and their related toast data */
frozen_heap_insert(toastrel, toasttup);
}
/*
* Create the index entry. We cheat a little here by not using
* FormIndexDatum: this relies on the knowledge that the index columns
* are the same as the initial columns of the table for all the
* indexes. We also cheat by not providing an IndexInfo: this is okay
* for now because btree doesn't need one, but we might have to be
* more honest someday.
*
* Note also that there had better not be any user-created index on
* the TOAST table, since we don't bother to update anything else.
*/
for (i = 0; i < num_indexes; i++)
{
/* Only index relations marked as ready can be updated */
if (toastidxs[i]->rd_index->indisready)
index_insert(toastidxs[i], t_values, t_isnull,
&(toasttup->t_self),
toastrel,
toastidxs[i]->rd_index->indisunique ?
UNIQUE_CHECK_YES : UNIQUE_CHECK_NO,
NULL);
}
/*
* Free memory
*/
heap_freetuple(toasttup);
/*
* Move on to next chunk
*/
data_todo -= chunk_size;
data_p += chunk_size;
}
/*
* Done - close toast relation and its indexes
*/
toast_close_indexes(toastidxs, num_indexes, RowExclusiveLock);
table_close(toastrel, RowExclusiveLock);
/*
* Create the TOAST pointer value that we'll return
*/
result = (struct varlena *) palloc(TOAST_POINTER_SIZE);
SET_VARTAG_EXTERNAL(result, VARTAG_ONDISK);
memcpy(VARDATA_EXTERNAL(result), &toast_pointer, sizeof(toast_pointer));
return PointerGetDatum(result);
}
/* ----------
* toast_delete_datum -
*
* Delete a single external stored value.
* ----------
*/
void
toast_delete_datum(Relation rel, Datum value, bool is_speculative)
{
struct varlena *attr = (struct varlena *) DatumGetPointer(value);
struct varatt_external toast_pointer;
Relation toastrel;
Relation *toastidxs;
ScanKeyData toastkey;
SysScanDesc toastscan;
HeapTuple toasttup;
int num_indexes;
int validIndex;
SnapshotData SnapshotToast;
if (!VARATT_IS_EXTERNAL_ONDISK(attr))
return;
/* Must copy to access aligned fields */
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
/*
* Open the toast relation and its indexes
*/
toastrel = table_open(toast_pointer.va_toastrelid, RowExclusiveLock);
/* Fetch valid relation used for process */
validIndex = toast_open_indexes(toastrel,
RowExclusiveLock,
&toastidxs,
&num_indexes);
/*
* Setup a scan key to find chunks with matching va_valueid
*/
ScanKeyInit(&toastkey,
(AttrNumber) 1,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(toast_pointer.va_valueid));
/*
* Find all the chunks. (We don't actually care whether we see them in
* sequence or not, but since we've already locked the index we might as
* well use systable_beginscan_ordered.)
*/
init_toast_snapshot(&SnapshotToast);
toastscan = systable_beginscan_ordered(toastrel, toastidxs[validIndex],
&SnapshotToast, 1, &toastkey);
while ((toasttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL)
{
/*
* Have a chunk, delete it
*/
if (is_speculative)
heap_abort_speculative(toastrel, &toasttup->t_self);
else
simple_heap_delete(toastrel, &toasttup->t_self);
}
/*
* End scan and close relations
*/
systable_endscan_ordered(toastscan);
toast_close_indexes(toastidxs, num_indexes, RowExclusiveLock);
table_close(toastrel, RowExclusiveLock);
}
/* ----------
* toastrel_valueid_exists -
*
* Test whether a toast value with the given ID exists in the toast relation.
* For safety, we consider a value to exist if there are either live or dead
* toast rows with that ID; see notes for GetNewOidWithIndex().
* ----------
*/
static bool
toastrel_valueid_exists(Relation toastrel, Oid valueid)
{
bool result = false;
ScanKeyData toastkey;
SysScanDesc toastscan;
int num_indexes;
int validIndex;
Relation *toastidxs;
/* Fetch a valid index relation */
validIndex = toast_open_indexes(toastrel,
RowExclusiveLock,
&toastidxs,
&num_indexes);
/*
* Setup a scan key to find chunks with matching va_valueid
*/
ScanKeyInit(&toastkey,
(AttrNumber) 1,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(valueid));
/*
* Is there any such chunk?
*/
toastscan = systable_beginscan(toastrel,
RelationGetRelid(toastidxs[validIndex]),
true, SnapshotAny, 1, &toastkey);
if (systable_getnext(toastscan) != NULL)
result = true;
systable_endscan(toastscan);
/* Clean up */
toast_close_indexes(toastidxs, num_indexes, RowExclusiveLock);
return result;
}
/* ----------
* toastid_valueid_exists -
*
* As above, but work from toast rel's OID not an open relation
* ----------
*/
static bool
toastid_valueid_exists(Oid toastrelid, Oid valueid)
{
bool result;
Relation toastrel;
toastrel = table_open(toastrelid, AccessShareLock);
result = toastrel_valueid_exists(toastrel, valueid);
table_close(toastrel, AccessShareLock);
return result;
}
/* ----------
* toast_fetch_datum -
*
* Reconstruct an in memory Datum from the chunks saved
* in the toast relation
* ----------
*/
static struct varlena *
toast_fetch_datum(struct varlena *attr)
{
Relation toastrel;
Relation *toastidxs;
ScanKeyData toastkey;
SysScanDesc toastscan;
HeapTuple ttup;
TupleDesc toasttupDesc;
struct varlena *result;
struct varatt_external toast_pointer;
int32 ressize;
int32 residx,
nextidx;
int32 numchunks;
Pointer chunk;
bool isnull;
char *chunkdata;
int32 chunksize;
int num_indexes;
int validIndex;
SnapshotData SnapshotToast;
if (!VARATT_IS_EXTERNAL_ONDISK(attr))
elog(ERROR, "toast_fetch_datum shouldn't be called for non-ondisk datums");
/*
* GPDB: start with the assumption that chunks max out at
* TOAST_MAX_CHUNK_SIZE. This may later prove false (e.g. if we've upgraded
* from GPDB 4.3), in which case we'll readjust numchunks later.
*/
int32 actual_max_chunk_size = TOAST_MAX_CHUNK_SIZE;
/* Must copy to access aligned fields */
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
ressize = toast_pointer.va_extsize;
numchunks = ((ressize - 1) / actual_max_chunk_size) + 1;
result = (struct varlena *) palloc(ressize + VARHDRSZ);
if (VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer))
SET_VARSIZE_COMPRESSED(result, ressize + VARHDRSZ);
else
SET_VARSIZE(result, ressize + VARHDRSZ);
/*
* Open the toast relation and its indexes
*/
toastrel = table_open(toast_pointer.va_toastrelid, AccessShareLock);
toasttupDesc = toastrel->rd_att;
/* Look for the valid index of the toast relation */
validIndex = toast_open_indexes(toastrel,
AccessShareLock,
&toastidxs,
&num_indexes);
/*
* Setup a scan key to fetch from the index by va_valueid
*/
ScanKeyInit(&toastkey,
(AttrNumber) 1,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(toast_pointer.va_valueid));
/*
* Read the chunks by index
*
* Note that because the index is actually on (valueid, chunkidx) we will
* see the chunks in chunkidx order, even though we didn't explicitly ask
* for it.
*/
nextidx = 0;
init_toast_snapshot(&SnapshotToast);
toastscan = systable_beginscan_ordered(toastrel, toastidxs[validIndex],
&SnapshotToast, 1, &toastkey);
while ((ttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL)
{
/*
* Have a chunk, extract the sequence number and the data
*/
residx = DatumGetInt32(fastgetattr(ttup, 2, toasttupDesc, &isnull));
Assert(!isnull);
chunk = DatumGetPointer(fastgetattr(ttup, 3, toasttupDesc, &isnull));
Assert(!isnull);
if (!VARATT_IS_EXTENDED(chunk))
{
chunksize = VARSIZE(chunk) - VARHDRSZ;
chunkdata = VARDATA(chunk);
}
else if (VARATT_IS_SHORT(chunk))
{
/* could happen due to heap_form_tuple doing its thing */
chunksize = VARSIZE_SHORT(chunk) - VARHDRSZ_SHORT;
chunkdata = VARDATA_SHORT(chunk);
}
else
{
/* should never happen */
elog(ERROR, "found toasted toast chunk for toast value %u in %s",
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
chunksize = 0; /* keep compiler quiet */
chunkdata = NULL;
}
/*
* Some checks on the data we've found
*/
if (residx != nextidx)
elog(ERROR, "unexpected chunk number %d (expected %d) for toast value %u in %s",
residx, nextidx,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
if ((residx == 0) && (chunksize < ressize)
&& (chunksize != actual_max_chunk_size))
{
/*
* GPDB: This toasted tuple is using a different max chunk size.
* This can happen after an upgrade, for instance. Realign our
* expectations.
*
* Only perform this check on the first chunk (the max size isn't
* allowed to change partway through), and only if we expect more
* chunks to come after this based on ressize.
*/
elog(DEBUG4, "readjusting max chunk size from %d to %d for toast value %u in %s",
actual_max_chunk_size, chunksize, toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
actual_max_chunk_size = chunksize;
numchunks = ((ressize - 1) / actual_max_chunk_size) + 1;
}
if (residx < numchunks - 1)
{
if (chunksize != actual_max_chunk_size)
elog(ERROR, "unexpected chunk size %d (expected %d) in chunk %d of %d for toast value %u in %s",
chunksize, (int) actual_max_chunk_size,
residx, numchunks,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
}
else if (residx == numchunks - 1)
{
if ((residx * actual_max_chunk_size + chunksize) != ressize)
elog(ERROR, "unexpected chunk size %d (expected %d) in final chunk %d for toast value %u in %s",
chunksize,
(int) (ressize - residx * actual_max_chunk_size),
residx,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
}
else
elog(ERROR, "unexpected chunk number %d (out of range %d..%d) for toast value %u in %s",
residx,
0, numchunks - 1,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
/*
* Copy the data into proper place in our result
*/
memcpy(VARDATA(result) + residx * actual_max_chunk_size,
chunkdata,
chunksize);
nextidx++;
}
/*
* Final checks that we successfully fetched the datum
*/
if (nextidx != numchunks)
elog(ERROR, "missing chunk number %d for toast value %u in %s",
nextidx,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
/*
* End scan and close relations
*/
systable_endscan_ordered(toastscan);
toast_close_indexes(toastidxs, num_indexes, AccessShareLock);
table_close(toastrel, AccessShareLock);
return (struct varlena *)result;
}
/* ----------
* toast_fetch_datum_slice -
*
* Reconstruct a segment of a Datum from the chunks saved
* in the toast relation
*
* Note that this function only supports non-compressed external datums.
* ----------
*/
static struct varlena *
toast_fetch_datum_slice(struct varlena *attr, int32 sliceoffset, int32 length)
{
Relation toastrel;
Relation *toastidxs;
ScanKeyData toastkey[3];
int nscankeys;
SysScanDesc toastscan;
HeapTuple ttup;
TupleDesc toasttupDesc;
struct varlena *result;
struct varatt_external toast_pointer;
int32 attrsize;
int32 residx;
int32 nextidx;
int numchunks;
int startchunk;
int endchunk;
int32 startoffset;
int32 endoffset;
int totalchunks;
Pointer chunk;
bool isnull;
char *chunkdata;
int32 chunksize;
int32 chcpystrt;
int32 chcpyend;
int num_indexes;
int validIndex;
SnapshotData SnapshotToast;
/*
* GPDB: start with the assumption that chunks max out at
* TOAST_MAX_CHUNK_SIZE. This may later prove false (e.g. if we've upgraded
* from GPDB 4.3), in which case we'll readjust everything later.
*/
int32 actual_max_chunk_size = TOAST_MAX_CHUNK_SIZE;
if (!VARATT_IS_EXTERNAL_ONDISK(attr))
elog(ERROR, "toast_fetch_datum_slice shouldn't be called for non-ondisk datums");
/* Must copy to access aligned fields */
VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
/*
* It's nonsense to fetch slices of a compressed datum -- this isn't lo_*
* we can't return a compressed datum which is meaningful to toast later
*/
Assert(!VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer));
attrsize = toast_pointer.va_extsize;
if (sliceoffset >= attrsize)
{
sliceoffset = 0;
length = 0;
}
if (((sliceoffset + length) > attrsize) || length < 0)
length = attrsize - sliceoffset;
result = (struct varlena *) palloc(length + VARHDRSZ);
SET_VARSIZE(result, length + VARHDRSZ);
if (length == 0)
return (struct varlena *)result; /* Can save a lot of work at this point! */
/*
* Open the toast relation and its index
*/
toastrel = table_open(toast_pointer.va_toastrelid, AccessShareLock);
toasttupDesc = toastrel->rd_att;
/* Look for the valid index of toast relation */
validIndex = toast_open_indexes(toastrel,
AccessShareLock,
&toastidxs,
&num_indexes);
{
/*
* GPDB: because we allow upgrades from clusters with different
* TOAST_MAX_CHUNK_SIZEs, we can't compute our chunk offsets yet. Open
* the first chunk and check its size.
*/
ScanKeyInit(&toastkey[0],
(AttrNumber) 1,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(toast_pointer.va_valueid));
ScanKeyInit(&toastkey[1],
(AttrNumber) 2,
BTEqualStrategyNumber, F_INT4EQ,
Int32GetDatum(0));
nscankeys = 2;
init_toast_snapshot(&SnapshotToast);
toastscan = systable_beginscan_ordered(toastrel, toastidxs[validIndex],
&SnapshotToast, nscankeys, toastkey);
if ((ttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL)
{
/*
* Have a chunk, extract the sequence number and the data
*/
residx = DatumGetInt32(fastgetattr(ttup, 2, toasttupDesc, &isnull));
Assert(!isnull);
chunk = DatumGetPointer(fastgetattr(ttup, 3, toasttupDesc, &isnull));
Assert(!isnull);
if (!VARATT_IS_EXTENDED(chunk))
{
chunksize = VARSIZE(chunk) - VARHDRSZ;
}
else if (VARATT_IS_SHORT(chunk))
{
/* could happen due to heap_form_tuple doing its thing */
chunksize = VARSIZE_SHORT(chunk) - VARHDRSZ_SHORT;
}
else
{
/* should never happen */
elog(ERROR, "found toasted toast chunk for toast value %u in %s",
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
chunksize = 0; /* keep compiler quiet */
}
if (chunksize < attrsize)
{
/*
* Only adjust the max chunk size if this isn't the only chunk.
*/
actual_max_chunk_size = chunksize;
}
}
systable_endscan_ordered(toastscan);
}
totalchunks = ((attrsize - 1) / actual_max_chunk_size) + 1;
startchunk = sliceoffset / actual_max_chunk_size;
endchunk = (sliceoffset + length - 1) / actual_max_chunk_size;
numchunks = (endchunk - startchunk) + 1;
startoffset = sliceoffset % actual_max_chunk_size;
endoffset = (sliceoffset + length - 1) % actual_max_chunk_size;
/*
* Setup a scan key to fetch from the index. This is either two keys or
* three depending on the number of chunks.
*/
ScanKeyInit(&toastkey[0],
(AttrNumber) 1,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(toast_pointer.va_valueid));
/*
* Use equality condition for one chunk, a range condition otherwise:
*/
if (numchunks == 1)
{
ScanKeyInit(&toastkey[1],
(AttrNumber) 2,
BTEqualStrategyNumber, F_INT4EQ,
Int32GetDatum(startchunk));
nscankeys = 2;
}
else
{
ScanKeyInit(&toastkey[1],
(AttrNumber) 2,
BTGreaterEqualStrategyNumber, F_INT4GE,
Int32GetDatum(startchunk));
ScanKeyInit(&toastkey[2],
(AttrNumber) 2,
BTLessEqualStrategyNumber, F_INT4LE,
Int32GetDatum(endchunk));
nscankeys = 3;
}
/*
* Read the chunks by index
*
* The index is on (valueid, chunkidx) so they will come in order
*/
init_toast_snapshot(&SnapshotToast);
nextidx = startchunk;
toastscan = systable_beginscan_ordered(toastrel, toastidxs[validIndex],
&SnapshotToast, nscankeys, toastkey);
while ((ttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL)
{
/*
* Have a chunk, extract the sequence number and the data
*/
residx = DatumGetInt32(fastgetattr(ttup, 2, toasttupDesc, &isnull));
Assert(!isnull);
chunk = DatumGetPointer(fastgetattr(ttup, 3, toasttupDesc, &isnull));
Assert(!isnull);
if (!VARATT_IS_EXTENDED(chunk))
{
chunksize = VARSIZE(chunk) - VARHDRSZ;
chunkdata = VARDATA(chunk);
}
else if (VARATT_IS_SHORT(chunk))
{
/* could happen due to heap_form_tuple doing its thing */
chunksize = VARSIZE_SHORT(chunk) - VARHDRSZ_SHORT;
chunkdata = VARDATA_SHORT(chunk);
}
else
{
/* should never happen */
elog(ERROR, "found toasted toast chunk for toast value %u in %s",
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
chunksize = 0; /* keep compiler quiet */
chunkdata = NULL;
}
/*
* Some checks on the data we've found
*/
if ((residx != nextidx) || (residx > endchunk) || (residx < startchunk))
elog(ERROR, "unexpected chunk number %d (expected %d) for toast value %u in %s",
residx, nextidx,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
if (residx < totalchunks - 1)
{
if (chunksize != actual_max_chunk_size)
elog(ERROR, "unexpected chunk size %d (expected %d) in chunk %d of %d for toast value %u in %s when fetching slice",
chunksize, (int) actual_max_chunk_size,
residx, totalchunks,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
}
else if (residx == totalchunks - 1)
{
if ((residx * actual_max_chunk_size + chunksize) != attrsize)
elog(ERROR, "unexpected chunk size %d (expected %d) in final chunk %d for toast value %u in %s when fetching slice",
chunksize,
(int) (attrsize - residx * actual_max_chunk_size),
residx,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
}
else
elog(ERROR, "unexpected chunk number %d (out of range %d..%d) for toast value %u in %s",
residx,
0, totalchunks - 1,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
/*
* Copy the data into proper place in our result
*/
chcpystrt = 0;
chcpyend = chunksize - 1;
if (residx == startchunk)
chcpystrt = startoffset;
if (residx == endchunk)
chcpyend = endoffset;
memcpy(VARDATA(result) +
(residx * actual_max_chunk_size - sliceoffset) + chcpystrt,
chunkdata + chcpystrt,
(chcpyend - chcpystrt) + 1);
nextidx++;
}
/*
* Final checks that we successfully fetched the datum
*/
if (nextidx != (endchunk + 1))
elog(ERROR, "missing chunk number %d for toast value %u in %s",
nextidx,
toast_pointer.va_valueid,
RelationGetRelationName(toastrel));
/*
* End scan and close relations
*/
systable_endscan_ordered(toastscan);
toast_close_indexes(toastidxs, num_indexes, AccessShareLock);
table_close(toastrel, AccessShareLock);
return (struct varlena *)result;
}
/* ----------
* toast_decompress_datum -
*
* Decompress a compressed version of a varlena datum
*/
static struct varlena *
toast_decompress_datum(struct varlena *attr)
{
struct varlena *result;
Assert(VARATT_IS_COMPRESSED(attr));
result = (struct varlena *)
palloc(TOAST_COMPRESS_RAWSIZE(attr) + VARHDRSZ);
SET_VARSIZE(result, TOAST_COMPRESS_RAWSIZE(attr) + VARHDRSZ);
if (pglz_decompress(TOAST_COMPRESS_RAWDATA(attr),
VARSIZE(attr) - TOAST_COMPRESS_HDRSZ,
VARDATA(result),
TOAST_COMPRESS_RAWSIZE(attr), true) < 0)
elog(ERROR, "compressed data is corrupted");
return result;
}
/* ----------
* toast_decompress_datum_slice -
*
* Decompress the front of a compressed version of a varlena datum.
* offset handling happens in heap_tuple_untoast_attr_slice.
* Here we just decompress a slice from the front.
*/
static struct varlena *
toast_decompress_datum_slice(struct varlena *attr, int32 slicelength)
{
struct varlena *result;
int32 rawsize;
Assert(VARATT_IS_COMPRESSED(attr));
result = (struct varlena *) palloc(slicelength + VARHDRSZ);
rawsize = pglz_decompress(TOAST_COMPRESS_RAWDATA(attr),
VARSIZE(attr) - TOAST_COMPRESS_HDRSZ,
VARDATA(result),
slicelength, false);
if (rawsize < 0)
elog(ERROR, "compressed data is corrupted");
SET_VARSIZE(result, rawsize + VARHDRSZ);
return result;
}
/* ----------
* toast_open_indexes
*
* Get an array of the indexes associated to the given toast relation
* and return as well the position of the valid index used by the toast
* relation in this array. It is the responsibility of the caller of this
* function to close the indexes as well as free them.
*/
static int
toast_open_indexes(Relation toastrel,
LOCKMODE lock,
Relation **toastidxs,
int *num_indexes)
{
int i = 0;
int res = 0;
bool found = false;
List *indexlist;
ListCell *lc;
/* Get index list of the toast relation */
indexlist = RelationGetIndexList(toastrel);
Assert(indexlist != NIL);
*num_indexes = list_length(indexlist);
/* Open all the index relations */
*toastidxs = (Relation *) palloc(*num_indexes * sizeof(Relation));
foreach(lc, indexlist)
(*toastidxs)[i++] = index_open(lfirst_oid(lc), lock);
/* Fetch the first valid index in list */
for (i = 0; i < *num_indexes; i++)
{
Relation toastidx = (*toastidxs)[i];
if (toastidx->rd_index->indisvalid)
{
res = i;
found = true;
break;
}
}
/*
* Free index list, not necessary anymore as relations are opened and a
* valid index has been found.
*/
list_free(indexlist);
/*
* The toast relation should have one valid index, so something is going
* wrong if there is nothing.
*/
if (!found)
elog(ERROR, "no valid index found for toast relation with Oid %u",
RelationGetRelid(toastrel));
return res;
}
/* ----------
* toast_close_indexes
*
* Close an array of indexes for a toast relation and free it. This should
* be called for a set of indexes opened previously with toast_open_indexes.
*/
static void
toast_close_indexes(Relation *toastidxs, int num_indexes, LOCKMODE lock)
{
int i;
/* Close relations and clean up things */
for (i = 0; i < num_indexes; i++)
index_close(toastidxs[i], lock);
pfree(toastidxs);
}
/* ----------
* init_toast_snapshot
*
* Initialize an appropriate TOAST snapshot. We must use an MVCC snapshot
* to initialize the TOAST snapshot; since we don't know which one to use,
* just use the oldest one. This is safe: at worst, we will get a "snapshot
* too old" error that might have been avoided otherwise.
*/
static void
init_toast_snapshot(Snapshot toast_snapshot)
{
Snapshot snapshot = GetOldestSnapshot();
if (snapshot == NULL)
elog(ERROR, "no known snapshots");
InitToastSnapshot(*toast_snapshot, snapshot->lsn, snapshot->whenTaken);
}
相关信息
相关文章
0
赞
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
6、 golang
-
8、 openharmony