/*
* PinBuffer -- make buffer unavailable for replacement.
*
* This should be applied only to shared buffers, never local ones.
* Bufmgr lock must be held by caller.
*/
void
PinBuffer(BufferDesc *buf)
{
int b = BufferDescriptorGetBuffer(buf) - 1;
if (buf->refcount == 0)
{
IsInQueue(buf);
/* remove from freelist queue */
/********* BEGIN NEW CODE ************/
if ( buf->buf_id == HeadPosition )
{
HeadPosition = buf->freeNext; // remove the head buffer, update position
}
/********* END NEW CODE ************/
BufferDescriptors[buf->freeNext].freePrev = buf->freePrev;
BufferDescriptors[buf->freePrev].freeNext = buf->freeNext;
buf->freeNext = buf->freePrev = INVALID_DESCRIPTOR;
/* mark buffer as no longer free */
buf->flags &= ~BM_FREE;
}
else
IsNotInQueue(buf);
if (PrivateRefCount[b] == 0)
buf->refcount++;
PrivateRefCount[b]++;
Assert(PrivateRefCount[b] > 0);
}
/*
* AddBufferToRing -- add a buffer to the buffer ring
*
* Caller must hold the buffer header spinlock on the buffer. Since this
* is called with the spinlock held, it had better be quite cheap.
*/
static void
AddBufferToRing(BufferAccessStrategy strategy, volatile BufferDesc *buf)
{
buf->order = maxOrder() + 1;
strategy->buffers[strategy->current] = BufferDescriptorGetBuffer(buf);
clean();
}
/*
* AddBufferToFreelist
*
* In theory, this is the only routine that needs to be changed
* if the buffer replacement strategy changes. Just change
* the manner in which buffers are added to the freelist queue.
* Currently, they are added on an LRU basis.
*/
static void
AddBufferToFreelist(BufferDesc *bf)
{
#ifdef BMTRACE
_bm_trace(bf->tag.relId.dbId, bf->tag.relId.relId, bf->tag.blockNum,
BufferDescriptorGetBuffer(bf), BMT_DEALLOC);
#endif /* BMTRACE */
IsNotInQueue(bf);
/* change bf so it points to inFrontOfNew and its successor */
/********* BEGIN OLD CODE***************/
// bf->freePrev = SharedFreeList->freePrev;
// bf->freeNext = Free_List_Descriptor;
/********* END OLD CODE*****************/
/********* BEGIN NEW CODE ************/
bf->freePrev = BufferDescriptors[HeadPosition].freePrev;
bf->freeNext = HeadPosition;
HeadPosition = bf->buf_id; // update the head position
/********* END NEW CODE *************/
/* insert new into chain */
BufferDescriptors[bf->freeNext].freePrev = bf->buf_id;
BufferDescriptors[bf->freePrev].freeNext = bf->buf_id;
}
/*
* UnpinBuffer -- make buffer available for replacement.
*
* This should be applied only to shared buffers, never local ones.
* Bufmgr lock must be held by caller.
*/
void
UnpinBuffer(BufferDesc *buf)
{
int b = BufferDescriptorGetBuffer(buf) - 1;
IsNotInQueue(buf);
Assert(buf->refcount > 0);
Assert(PrivateRefCount[b] > 0);
PrivateRefCount[b]--;
if (PrivateRefCount[b] == 0)
buf->refcount--;
if (buf->refcount == 0)
{
/* buffer is now unpinned */
AddBufferToFreelist(buf);
buf->flags |= BM_FREE;
}
else if ((buf->flags & BM_PIN_COUNT_WAITER) != 0 &&
buf->refcount == 1)
{
/* we just released the last pin other than the waiter's */
buf->flags &= ~BM_PIN_COUNT_WAITER;
ProcSendSignal(buf->wait_backend_id);
}
else
{
/* do nothing */
}
}
void
UnpinBuffer_Debug(char *file, int line, BufferDesc *buf)
{
UnpinBuffer(buf);
if (ShowPinTrace)
{
Buffer buffer = BufferDescriptorGetBuffer(buf);
fprintf(stderr, "UNPIN(Unpin) %ld relname = %s, blockNum = %d, \
refcount = %ld, file: %s, line: %d\n",
buffer, buf->blind.relname, buf->tag.blockNum,
PrivateRefCount[buffer - 1], file, line);
}
}
/*
* StrategyRejectBuffer -- consider rejecting a dirty buffer
*
* When a nondefault strategy is used, the buffer manager calls this function
* when it turns out that the buffer selected by StrategyGetBuffer needs to
* be written out and doing so would require flushing WAL too. This gives us
* a chance to choose a different victim.
*
* Returns true if buffer manager should ask for a new victim, and false
* if this buffer should be written and re-used.
*/
bool
StrategyRejectBuffer(BufferAccessStrategy strategy, volatile BufferDesc *buf)
{
/* We only do this in bulkread mode */
if (strategy->btype != BAS_BULKREAD)
return false;
/* Don't muck with behavior of normal buffer-replacement strategy */
if (!strategy->current_was_in_ring ||
strategy->buffers[strategy->current] != BufferDescriptorGetBuffer(buf))
return false;
/*
* Remove the dirty buffer from the ring; necessary to prevent infinite
* loop if all ring members are dirty.
*/
strategy->buffers[strategy->current] = InvalidBuffer;
return true;
}
/*
* AddBufferToRing -- add a buffer to the buffer ring
*
* Caller must hold the buffer header spinlock on the buffer. Since this
* is called with the spinlock held, it had better be quite cheap.
*/
static void
AddBufferToRing(BufferAccessStrategy strategy, volatile BufferDesc *buf)
{
strategy->buffers[strategy->current] = BufferDescriptorGetBuffer(buf);
}
/*
* LocalBufferAlloc -
* Find or create a local buffer for the given page of the given relation.
*
* API is similar to bufmgr.c's BufferAlloc, except that we do not need
* to do any locking since this is all local. Also, IO_IN_PROGRESS
* does not get set. Lastly, we support only default access strategy
* (hence, usage_count is always advanced).
*/
BufferDesc *
LocalBufferAlloc(SMgrRelation smgr, ForkNumber forkNum, BlockNumber blockNum,
bool *foundPtr)
{
BufferTag newTag; /* identity of requested block */
LocalBufferLookupEnt *hresult;
BufferDesc *bufHdr;
int b;
int trycounter;
bool found;
INIT_BUFFERTAG(newTag, smgr->smgr_rnode.node, forkNum, blockNum);
/* Initialize local buffers if first request in this session */
if (LocalBufHash == NULL)
InitLocalBuffers();
/* See if the desired buffer already exists */
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, (void *) &newTag, HASH_FIND, NULL);
if (hresult)
{
b = hresult->id;
bufHdr = &LocalBufferDescriptors[b];
Assert(BUFFERTAGS_EQUAL(bufHdr->tag, newTag));
#ifdef LBDEBUG
fprintf(stderr, "LB ALLOC (%u,%d,%d) %d\n",
smgr->smgr_rnode.node.relNode, forkNum, blockNum, -b - 1);
#endif
/* this part is equivalent to PinBuffer for a shared buffer */
if (LocalRefCount[b] == 0)
{
if (bufHdr->usage_count < BM_MAX_USAGE_COUNT)
bufHdr->usage_count++;
}
LocalRefCount[b]++;
ResourceOwnerRememberBuffer(CurrentResourceOwner,
BufferDescriptorGetBuffer(bufHdr));
if (bufHdr->flags & BM_VALID)
*foundPtr = TRUE;
else
{
/* Previous read attempt must have failed; try again */
*foundPtr = FALSE;
}
return bufHdr;
}
#ifdef LBDEBUG
fprintf(stderr, "LB ALLOC (%u,%d,%d) %d\n",
smgr->smgr_rnode.node.relNode, forkNum, blockNum,
-nextFreeLocalBuf - 1);
#endif
/*
* Need to get a new buffer. We use a clock sweep algorithm (essentially
* the same as what freelist.c does now...)
*/
trycounter = NLocBuffer;
for (;;)
{
b = nextFreeLocalBuf;
if (++nextFreeLocalBuf >= NLocBuffer)
nextFreeLocalBuf = 0;
bufHdr = &LocalBufferDescriptors[b];
if (LocalRefCount[b] == 0)
{
if (bufHdr->usage_count > 0)
{
bufHdr->usage_count--;
trycounter = NLocBuffer;
}
else
{
/* Found a usable buffer */
LocalRefCount[b]++;
ResourceOwnerRememberBuffer(CurrentResourceOwner,
BufferDescriptorGetBuffer(bufHdr));
break;
}
}
else if (--trycounter == 0)
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_RESOURCES),
errmsg("no empty local buffer available")));
}
/*
* this buffer is not referenced but it might still be dirty. if that's
* the case, write it out before reusing it!
*/
if (bufHdr->flags & BM_DIRTY)
{
SMgrRelation oreln;
/* Find smgr relation for buffer */
oreln = smgropen(bufHdr->tag.rnode, MyBackendId);
/* And write... */
smgrwrite(oreln,
bufHdr->tag.forkNum,
bufHdr->tag.blockNum,
(char *) LocalBufHdrGetBlock(bufHdr),
false);
/* Mark not-dirty now in case we error out below */
bufHdr->flags &= ~BM_DIRTY;
pgBufferUsage.local_blks_written++;
}
/*
* lazy memory allocation: allocate space on first use of a buffer.
*/
if (LocalBufHdrGetBlock(bufHdr) == NULL)
{
/* Set pointer for use by BufferGetBlock() macro */
LocalBufHdrGetBlock(bufHdr) = GetLocalBufferStorage();
}
/*
* Update the hash table: remove old entry, if any, and make new one.
*/
if (bufHdr->flags & BM_TAG_VALID)
{
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, (void *) &bufHdr->tag,
HASH_REMOVE, NULL);
if (!hresult) /* shouldn't happen */
elog(ERROR, "local buffer hash table corrupted");
/* mark buffer invalid just in case hash insert fails */
CLEAR_BUFFERTAG(bufHdr->tag);
bufHdr->flags &= ~(BM_VALID | BM_TAG_VALID);
}
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, (void *) &newTag, HASH_ENTER, &found);
if (found) /* shouldn't happen */
elog(ERROR, "local buffer hash table corrupted");
hresult->id = b;
/*
* it's all ours now.
*/
bufHdr->tag = newTag;
bufHdr->flags &= ~(BM_VALID | BM_DIRTY | BM_JUST_DIRTIED | BM_IO_ERROR);
bufHdr->flags |= BM_TAG_VALID;
bufHdr->usage_count = 1;
*foundPtr = FALSE;
return bufHdr;
}
Datum
pg_buffercache_pages(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
Datum result;
MemoryContext oldcontext;
BufferCachePagesContext *fctx; /* User function context. */
TupleDesc tupledesc;
HeapTuple tuple;
if (SRF_IS_FIRSTCALL())
{
int i;
volatile BufferDesc *bufHdr;
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));
/* Construct a tuple descriptor for the result rows. */
tupledesc = CreateTemplateTupleDesc(NUM_BUFFERCACHE_PAGES_ELEM, false);
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);
fctx->tupdesc = BlessTupleDesc(tupledesc);
/* Allocate NBuffers worth of BufferCachePagesRec records. */
fctx->record = (BufferCachePagesRec *) palloc(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);
/*
* To get a consistent picture of the buffer state, we must lock all
* partitions of the buffer map. Needless to say, this is horrible
* for concurrency. Must grab locks in increasing order to avoid
* possible deadlocks.
*/
for (i = 0; i < NUM_BUFFER_PARTITIONS; i++)
LWLockAcquire(FirstBufMappingLock + i, LW_SHARED);
/*
* Scan though all the buffers, saving the relevant fields in the
* fctx->record structure.
*/
for (i = 0, bufHdr = BufferDescriptors; i < NBuffers; i++, bufHdr++)
{
/* Lock each buffer header before inspecting. */
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 = bufHdr->usage_count;
if (bufHdr->flags & BM_DIRTY)
fctx->record[i].isdirty = true;
else
fctx->record[i].isdirty = false;
/* Note if the buffer is valid, and has storage created */
if ((bufHdr->flags & BM_VALID) && (bufHdr->flags & BM_TAG_VALID))
fctx->record[i].isvalid = true;
else
fctx->record[i].isvalid = false;
UnlockBufHdr(bufHdr);
}
/*
* And release locks. We do this in reverse order for two reasons:
* (1) Anyone else who needs more than one of the locks will be trying
* to lock them in increasing order; we don't want to release the
* other process until it can get all the locks it needs. (2) This
* avoids O(N^2) behavior inside LWLockRelease.
*/
for (i = NUM_BUFFER_PARTITIONS; --i >= 0;)
LWLockRelease(FirstBufMappingLock + i);
}
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;
}
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;
}
/* 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);
}
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, false);
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);
}
