mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-08-25 07:07:18 +02:00
Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
240 lines
7.2 KiB
C
240 lines
7.2 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* pg_buffercache_pages.c
|
|
* display some contents of the buffer cache
|
|
*
|
|
* contrib/pg_buffercache/pg_buffercache_pages.c
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
#include "postgres.h"
|
|
|
|
#include "access/htup_details.h"
|
|
#include "catalog/pg_type.h"
|
|
#include "funcapi.h"
|
|
#include "storage/buf_internals.h"
|
|
#include "storage/bufmgr.h"
|
|
|
|
|
|
#define NUM_BUFFERCACHE_PAGES_MIN_ELEM 8
|
|
#define NUM_BUFFERCACHE_PAGES_ELEM 9
|
|
|
|
PG_MODULE_MAGIC;
|
|
|
|
/*
|
|
* Record structure holding the to be exposed cache data.
|
|
*/
|
|
typedef struct
|
|
{
|
|
uint32 bufferid;
|
|
Oid relfilenode;
|
|
Oid reltablespace;
|
|
Oid reldatabase;
|
|
ForkNumber forknum;
|
|
BlockNumber blocknum;
|
|
bool isvalid;
|
|
bool isdirty;
|
|
uint16 usagecount;
|
|
|
|
/*
|
|
* An int32 is sufficiently large, as MAX_BACKENDS prevents a buffer from
|
|
* being pinned by too many backends and each backend will only pin once
|
|
* because of bufmgr.c's PrivateRefCount infrastructure.
|
|
*/
|
|
int32 pinning_backends;
|
|
} BufferCachePagesRec;
|
|
|
|
|
|
/*
|
|
* Function context for data persisting over repeated calls.
|
|
*/
|
|
typedef struct
|
|
{
|
|
TupleDesc tupdesc;
|
|
BufferCachePagesRec *record;
|
|
} BufferCachePagesContext;
|
|
|
|
|
|
/*
|
|
* Function returning data from the shared buffer cache - buffer number,
|
|
* relation node/tablespace/database/blocknum and dirty indicator.
|
|
*/
|
|
PG_FUNCTION_INFO_V1(pg_buffercache_pages);
|
|
|
|
Datum
|
|
pg_buffercache_pages(PG_FUNCTION_ARGS)
|
|
{
|
|
FuncCallContext *funcctx;
|
|
Datum result;
|
|
MemoryContext oldcontext;
|
|
BufferCachePagesContext *fctx; /* User function context. */
|
|
TupleDesc tupledesc;
|
|
TupleDesc expected_tupledesc;
|
|
HeapTuple tuple;
|
|
|
|
if (SRF_IS_FIRSTCALL())
|
|
{
|
|
int i;
|
|
|
|
funcctx = SRF_FIRSTCALL_INIT();
|
|
|
|
/* Switch context when allocating stuff to be used in later calls */
|
|
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
|
|
|
|
/* Create a user function context for cross-call persistence */
|
|
fctx = (BufferCachePagesContext *) palloc(sizeof(BufferCachePagesContext));
|
|
|
|
/*
|
|
* To smoothly support upgrades from version 1.0 of this extension
|
|
* transparently handle the (non-)existence of the pinning_backends
|
|
* column. We unfortunately have to get the result type for that... -
|
|
* we can't use the result type determined by the function definition
|
|
* without potentially crashing when somebody uses the old (or even
|
|
* wrong) function definition though.
|
|
*/
|
|
if (get_call_result_type(fcinfo, NULL, &expected_tupledesc) != TYPEFUNC_COMPOSITE)
|
|
elog(ERROR, "return type must be a row type");
|
|
|
|
if (expected_tupledesc->natts < NUM_BUFFERCACHE_PAGES_MIN_ELEM ||
|
|
expected_tupledesc->natts > NUM_BUFFERCACHE_PAGES_ELEM)
|
|
elog(ERROR, "incorrect number of output arguments");
|
|
|
|
/* Construct a tuple descriptor for the result rows. */
|
|
tupledesc = CreateTemplateTupleDesc(expected_tupledesc->natts);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 1, "bufferid",
|
|
INT4OID, -1, 0);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 2, "relfilenode",
|
|
OIDOID, -1, 0);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 3, "reltablespace",
|
|
OIDOID, -1, 0);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 4, "reldatabase",
|
|
OIDOID, -1, 0);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 5, "relforknumber",
|
|
INT2OID, -1, 0);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 6, "relblocknumber",
|
|
INT8OID, -1, 0);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 7, "isdirty",
|
|
BOOLOID, -1, 0);
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 8, "usage_count",
|
|
INT2OID, -1, 0);
|
|
|
|
if (expected_tupledesc->natts == NUM_BUFFERCACHE_PAGES_ELEM)
|
|
TupleDescInitEntry(tupledesc, (AttrNumber) 9, "pinning_backends",
|
|
INT4OID, -1, 0);
|
|
|
|
fctx->tupdesc = BlessTupleDesc(tupledesc);
|
|
|
|
/* Allocate NBuffers worth of BufferCachePagesRec records. */
|
|
fctx->record = (BufferCachePagesRec *)
|
|
MemoryContextAllocHuge(CurrentMemoryContext,
|
|
sizeof(BufferCachePagesRec) * NBuffers);
|
|
|
|
/* Set max calls and remember the user function context. */
|
|
funcctx->max_calls = NBuffers;
|
|
funcctx->user_fctx = fctx;
|
|
|
|
/* Return to original context when allocating transient memory */
|
|
MemoryContextSwitchTo(oldcontext);
|
|
|
|
/*
|
|
* Scan through all the buffers, saving the relevant fields in the
|
|
* fctx->record structure.
|
|
*
|
|
* We don't hold the partition locks, so we don't get a consistent
|
|
* snapshot across all buffers, but we do grab the buffer header
|
|
* locks, so the information of each buffer is self-consistent.
|
|
*/
|
|
for (i = 0; i < NBuffers; i++)
|
|
{
|
|
BufferDesc *bufHdr;
|
|
uint32 buf_state;
|
|
|
|
bufHdr = GetBufferDescriptor(i);
|
|
/* Lock each buffer header before inspecting. */
|
|
buf_state = LockBufHdr(bufHdr);
|
|
|
|
fctx->record[i].bufferid = BufferDescriptorGetBuffer(bufHdr);
|
|
fctx->record[i].relfilenode = bufHdr->tag.rnode.relNode;
|
|
fctx->record[i].reltablespace = bufHdr->tag.rnode.spcNode;
|
|
fctx->record[i].reldatabase = bufHdr->tag.rnode.dbNode;
|
|
fctx->record[i].forknum = bufHdr->tag.forkNum;
|
|
fctx->record[i].blocknum = bufHdr->tag.blockNum;
|
|
fctx->record[i].usagecount = BUF_STATE_GET_USAGECOUNT(buf_state);
|
|
fctx->record[i].pinning_backends = BUF_STATE_GET_REFCOUNT(buf_state);
|
|
|
|
if (buf_state & BM_DIRTY)
|
|
fctx->record[i].isdirty = true;
|
|
else
|
|
fctx->record[i].isdirty = false;
|
|
|
|
/* Note if the buffer is valid, and has storage created */
|
|
if ((buf_state & BM_VALID) && (buf_state & BM_TAG_VALID))
|
|
fctx->record[i].isvalid = true;
|
|
else
|
|
fctx->record[i].isvalid = false;
|
|
|
|
UnlockBufHdr(bufHdr, buf_state);
|
|
}
|
|
}
|
|
|
|
funcctx = SRF_PERCALL_SETUP();
|
|
|
|
/* Get the saved state */
|
|
fctx = funcctx->user_fctx;
|
|
|
|
if (funcctx->call_cntr < funcctx->max_calls)
|
|
{
|
|
uint32 i = funcctx->call_cntr;
|
|
Datum values[NUM_BUFFERCACHE_PAGES_ELEM];
|
|
bool nulls[NUM_BUFFERCACHE_PAGES_ELEM];
|
|
|
|
values[0] = Int32GetDatum(fctx->record[i].bufferid);
|
|
nulls[0] = false;
|
|
|
|
/*
|
|
* Set all fields except the bufferid to null if the buffer is unused
|
|
* or not valid.
|
|
*/
|
|
if (fctx->record[i].blocknum == InvalidBlockNumber ||
|
|
fctx->record[i].isvalid == false)
|
|
{
|
|
nulls[1] = true;
|
|
nulls[2] = true;
|
|
nulls[3] = true;
|
|
nulls[4] = true;
|
|
nulls[5] = true;
|
|
nulls[6] = true;
|
|
nulls[7] = true;
|
|
/* unused for v1.0 callers, but the array is always long enough */
|
|
nulls[8] = true;
|
|
}
|
|
else
|
|
{
|
|
values[1] = ObjectIdGetDatum(fctx->record[i].relfilenode);
|
|
nulls[1] = false;
|
|
values[2] = ObjectIdGetDatum(fctx->record[i].reltablespace);
|
|
nulls[2] = false;
|
|
values[3] = ObjectIdGetDatum(fctx->record[i].reldatabase);
|
|
nulls[3] = false;
|
|
values[4] = ObjectIdGetDatum(fctx->record[i].forknum);
|
|
nulls[4] = false;
|
|
values[5] = Int64GetDatum((int64) fctx->record[i].blocknum);
|
|
nulls[5] = false;
|
|
values[6] = BoolGetDatum(fctx->record[i].isdirty);
|
|
nulls[6] = false;
|
|
values[7] = Int16GetDatum(fctx->record[i].usagecount);
|
|
nulls[7] = false;
|
|
/* unused for v1.0 callers, but the array is always long enough */
|
|
values[8] = Int32GetDatum(fctx->record[i].pinning_backends);
|
|
nulls[8] = false;
|
|
}
|
|
|
|
/* Build and return the tuple. */
|
|
tuple = heap_form_tuple(fctx->tupdesc, values, nulls);
|
|
result = HeapTupleGetDatum(tuple);
|
|
|
|
SRF_RETURN_NEXT(funcctx, result);
|
|
}
|
|
else
|
|
SRF_RETURN_DONE(funcctx);
|
|
}
|