/*
* StrategyInitialize -- initialize the buffer cache replacement
* strategy.
*
* Assumes: All of the buffers are already built into a linked list.
* Only called by postmaster and only during initialization.
*/
void
StrategyInitialize(bool init)
{
bool found;
/*
* Initialize the shared buffer lookup hashtable.
*
* Since we can't tolerate running out of lookup table entries, we must be
* sure to specify an adequate table size here. The maximum steady-state
* usage is of course NBuffers entries, but BufferAlloc() tries to insert
* a new___ entry before deleting the old. In principle this could be
* happening in each partition concurrently, so we could need as many as
* NBuffers + NUM_BUFFER_PARTITIONS entries.
*/
InitBufTable(NBuffers + NUM_BUFFER_PARTITIONS);
/*
* Get or create the shared strategy control block
*/
StrategyControl = (BufferStrategyControl *)
ShmemInitStruct("Buffer Strategy Status",
sizeof(BufferStrategyControl),
&found);
if (!found)
{
/*
* Only done once, usually in postmaster
*/
Assert(init);
SpinLockInit(&StrategyControl->buffer_strategy_lock);
/*
* Grab the whole linked list of free buffers for our strategy. We
* assume it was previously set up by InitBufferPool().
*/
StrategyControl->firstFreeBuffer = 0;
StrategyControl->lastFreeBuffer = NBuffers - 1;
/* Initialize the clock sweep pointer */
pg_atomic_init_u32(&StrategyControl->nextVictimBuffer, 0);
/* Clear statistics */
StrategyControl->completePasses = 0;
pg_atomic_init_u32(&StrategyControl->numBufferAllocs, 0);
/* No pending notification */
StrategyControl->bgwprocno = -1;
}
else
Assert(!init);
}
/*
* Initialize shared buffer pool
*
* This is called once during shared-memory initialization (either in the
* postmaster, or in a standalone backend).
*/
void
InitBufferPool(void)
{
bool foundBufs,
foundDescs,
foundIOLocks,
foundBufCkpt;
/* Align descriptors to a cacheline boundary. */
BufferDescriptors = (BufferDescPadded *)
ShmemInitStruct("Buffer Descriptors",
NBuffers * sizeof(BufferDescPadded),
&foundDescs);
BufferBlocks = (char *)
ShmemInitStruct("Buffer Blocks",
NBuffers * (Size) BLCKSZ, &foundBufs);
/* Align lwlocks to cacheline boundary */
BufferIOLWLockArray = (LWLockMinimallyPadded *)
ShmemInitStruct("Buffer IO Locks",
NBuffers * (Size) sizeof(LWLockMinimallyPadded),
&foundIOLocks);
LWLockRegisterTranche(LWTRANCHE_BUFFER_IO_IN_PROGRESS, "buffer_io");
LWLockRegisterTranche(LWTRANCHE_BUFFER_CONTENT, "buffer_content");
/*
* The array used to sort to-be-checkpointed buffer ids is located in
* shared memory, to avoid having to allocate significant amounts of
* memory at runtime. As that'd be in the middle of a checkpoint, or when
* the checkpointer is restarted, memory allocation failures would be
* painful.
*/
CkptBufferIds = (CkptSortItem *)
ShmemInitStruct("Checkpoint BufferIds",
NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
if (foundDescs || foundBufs || foundIOLocks || foundBufCkpt)
{
/* should find all of these, or none of them */
Assert(foundDescs && foundBufs && foundIOLocks && foundBufCkpt);
/* note: this path is only taken in EXEC_BACKEND case */
}
else
{
int i;
/*
* Initialize all the buffer headers.
*/
for (i = 0; i < NBuffers; i++)
{
BufferDesc *buf = GetBufferDescriptor(i);
CLEAR_BUFFERTAG(buf->tag);
pg_atomic_init_u32(&buf->state, 0);
buf->wait_backend_pid = 0;
buf->buf_id = i;
/*
* Initially link all the buffers together as unused. Subsequent
* management of this list is done by freelist.c.
*/
buf->freeNext = i + 1;
LWLockInitialize(BufferDescriptorGetContentLock(buf),
LWTRANCHE_BUFFER_CONTENT);
LWLockInitialize(BufferDescriptorGetIOLock(buf),
LWTRANCHE_BUFFER_IO_IN_PROGRESS);
}
/* Correct last entry of linked list */
GetBufferDescriptor(NBuffers - 1)->freeNext = FREENEXT_END_OF_LIST;
}
/* Init other shared buffer-management stuff */
StrategyInitialize(!foundDescs);
/* Initialize per-backend file flush context */
WritebackContextInit(&BackendWritebackContext,
&backend_flush_after);
}
static void
test_atomic_uint32(void)
{
pg_atomic_uint32 var;
uint32 expected;
int i;
pg_atomic_init_u32(&var, 0);
if (pg_atomic_read_u32(&var) != 0)
elog(ERROR, "atomic_read_u32() #1 wrong");
pg_atomic_write_u32(&var, 3);
if (pg_atomic_read_u32(&var) != 3)
elog(ERROR, "atomic_read_u32() #2 wrong");
if (pg_atomic_fetch_add_u32(&var, 1) != 3)
elog(ERROR, "atomic_fetch_add_u32() #1 wrong");
if (pg_atomic_fetch_sub_u32(&var, 1) != 4)
elog(ERROR, "atomic_fetch_sub_u32() #1 wrong");
if (pg_atomic_sub_fetch_u32(&var, 3) != 0)
elog(ERROR, "atomic_sub_fetch_u32() #1 wrong");
if (pg_atomic_add_fetch_u32(&var, 10) != 10)
elog(ERROR, "atomic_add_fetch_u32() #1 wrong");
if (pg_atomic_exchange_u32(&var, 5) != 10)
elog(ERROR, "pg_atomic_exchange_u32() #1 wrong");
if (pg_atomic_exchange_u32(&var, 0) != 5)
elog(ERROR, "pg_atomic_exchange_u32() #0 wrong");
/* test around numerical limits */
if (pg_atomic_fetch_add_u32(&var, INT_MAX) != 0)
elog(ERROR, "pg_atomic_fetch_add_u32() #2 wrong");
if (pg_atomic_fetch_add_u32(&var, INT_MAX) != INT_MAX)
elog(ERROR, "pg_atomic_add_fetch_u32() #3 wrong");
pg_atomic_fetch_add_u32(&var, 1); /* top up to UINT_MAX */
if (pg_atomic_read_u32(&var) != UINT_MAX)
elog(ERROR, "atomic_read_u32() #2 wrong");
if (pg_atomic_fetch_sub_u32(&var, INT_MAX) != UINT_MAX)
elog(ERROR, "pg_atomic_fetch_sub_u32() #2 wrong");
if (pg_atomic_read_u32(&var) != (uint32) INT_MAX + 1)
elog(ERROR, "atomic_read_u32() #3 wrong: %u", pg_atomic_read_u32(&var));
expected = pg_atomic_sub_fetch_u32(&var, INT_MAX);
if (expected != 1)
elog(ERROR, "pg_atomic_sub_fetch_u32() #3 wrong: %u", expected);
pg_atomic_sub_fetch_u32(&var, 1);
/* fail exchange because of old expected */
expected = 10;
if (pg_atomic_compare_exchange_u32(&var, &expected, 1))
elog(ERROR, "atomic_compare_exchange_u32() changed value spuriously");
/* CAS is allowed to fail due to interrupts, try a couple of times */
for (i = 0; i < 1000; i++)
{
expected = 0;
if (!pg_atomic_compare_exchange_u32(&var, &expected, 1))
break;
}
if (i == 1000)
elog(ERROR, "atomic_compare_exchange_u32() never succeeded");
if (pg_atomic_read_u32(&var) != 1)
elog(ERROR, "atomic_compare_exchange_u32() didn't set value properly");
pg_atomic_write_u32(&var, 0);
/* try setting flagbits */
if (pg_atomic_fetch_or_u32(&var, 1) & 1)
elog(ERROR, "pg_atomic_fetch_or_u32() #1 wrong");
if (!(pg_atomic_fetch_or_u32(&var, 2) & 1))
elog(ERROR, "pg_atomic_fetch_or_u32() #2 wrong");
if (pg_atomic_read_u32(&var) != 3)
elog(ERROR, "invalid result after pg_atomic_fetch_or_u32()");
/* try clearing flagbits */
if ((pg_atomic_fetch_and_u32(&var, ~2) & 3) != 3)
elog(ERROR, "pg_atomic_fetch_and_u32() #1 wrong");
if (pg_atomic_fetch_and_u32(&var, ~1) != 1)
elog(ERROR, "pg_atomic_fetch_and_u32() #2 wrong: is %u",
pg_atomic_read_u32(&var));
/* no bits set anymore */
if (pg_atomic_fetch_and_u32(&var, ~0) != 0)
elog(ERROR, "pg_atomic_fetch_and_u32() #3 wrong");
}
/*
* InitProcess -- initialize a per-process data structure for this backend
*/
void
InitProcess(void)
{
/* use volatile pointer to prevent code rearrangement */
volatile PROC_HDR *procglobal = ProcGlobal;
PGPROC * volatile * procgloballist;
/*
* ProcGlobal should be set up already (if we are a backend, we inherit
* this by fork() or EXEC_BACKEND mechanism from the postmaster).
*/
if (procglobal == NULL)
elog(PANIC, "proc header uninitialized");
if (MyProc != NULL)
elog(ERROR, "you already exist");
/* Decide which list should supply our PGPROC. */
if (IsAnyAutoVacuumProcess())
procgloballist = &procglobal->autovacFreeProcs;
else if (IsBackgroundWorker)
procgloballist = &procglobal->bgworkerFreeProcs;
else
procgloballist = &procglobal->freeProcs;
/*
* Try to get a proc struct from the appropriate free list. If this
* fails, we must be out of PGPROC structures (not to mention semaphores).
*
* While we are holding the ProcStructLock, also copy the current shared
* estimate of spins_per_delay to local storage.
*/
SpinLockAcquire(ProcStructLock);
set_spins_per_delay(procglobal->spins_per_delay);
MyProc = *procgloballist;
if (MyProc != NULL)
{
*procgloballist = (PGPROC *) MyProc->links.next;
SpinLockRelease(ProcStructLock);
}
else
{
/*
* If we reach here, all the PGPROCs are in use. This is one of the
* possible places to detect "too many backends", so give the standard
* error message. XXX do we need to give a different failure message
* in the autovacuum case?
*/
SpinLockRelease(ProcStructLock);
ereport(FATAL,
(errcode(ERRCODE_TOO_MANY_CONNECTIONS),
errmsg("sorry, too many clients already")));
}
MyPgXact = &ProcGlobal->allPgXact[MyProc->pgprocno];
/*
* Cross-check that the PGPROC is of the type we expect; if this were
* not the case, it would get returned to the wrong list.
*/
Assert(MyProc->procgloballist == procgloballist);
/*
* Now that we have a PGPROC, mark ourselves as an active postmaster
* child; this is so that the postmaster can detect it if we exit without
* cleaning up. (XXX autovac launcher currently doesn't participate in
* this; it probably should.)
*/
if (IsUnderPostmaster && !IsAutoVacuumLauncherProcess())
MarkPostmasterChildActive();
/*
* Initialize all fields of MyProc, except for those previously
* initialized by InitProcGlobal.
*/
SHMQueueElemInit(&(MyProc->links));
MyProc->waitStatus = STATUS_OK;
MyProc->lxid = InvalidLocalTransactionId;
MyProc->fpVXIDLock = false;
MyProc->fpLocalTransactionId = InvalidLocalTransactionId;
MyPgXact->xid = InvalidTransactionId;
MyPgXact->xmin = InvalidTransactionId;
MyProc->pid = MyProcPid;
/* backendId, databaseId and roleId will be filled in later */
MyProc->backendId = InvalidBackendId;
MyProc->databaseId = InvalidOid;
MyProc->roleId = InvalidOid;
MyPgXact->delayChkpt = false;
MyPgXact->vacuumFlags = 0;
/* NB -- autovac launcher intentionally does not set IS_AUTOVACUUM */
if (IsAutoVacuumWorkerProcess())
MyPgXact->vacuumFlags |= PROC_IS_AUTOVACUUM;
MyProc->lwWaiting = false;
MyProc->lwWaitMode = 0;
MyProc->waitLock = NULL;
MyProc->waitProcLock = NULL;
#ifdef USE_ASSERT_CHECKING
{
int i;
/* Last process should have released all locks. */
for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
Assert(SHMQueueEmpty(&(MyProc->myProcLocks[i])));
}
#endif
MyProc->recoveryConflictPending = false;
/* Initialize fields for sync rep */
MyProc->waitLSN = 0;
MyProc->syncRepState = SYNC_REP_NOT_WAITING;
SHMQueueElemInit(&(MyProc->syncRepLinks));
/* Initialize fields for group XID clearing. */
MyProc->backendLatestXid = InvalidTransactionId;
pg_atomic_init_u32(&MyProc->nextClearXidElem, INVALID_PGPROCNO);
/*
* Acquire ownership of the PGPROC's latch, so that we can use WaitLatch
* on it. That allows us to repoint the process latch, which so far
* points to process local one, to the shared one.
*/
OwnLatch(&MyProc->procLatch);
SwitchToSharedLatch();
/*
* We might be reusing a semaphore that belonged to a failed process. So
* be careful and reinitialize its value here. (This is not strictly
* necessary anymore, but seems like a good idea for cleanliness.)
*/
PGSemaphoreReset(&MyProc->sem);
/*
* Arrange to clean up at backend exit.
*/
on_shmem_exit(ProcKill, 0);
/*
* Now that we have a PGPROC, we could try to acquire locks, so initialize
* local state needed for LWLocks, and the deadlock checker.
*/
InitLWLockAccess();
InitDeadLockChecking();
}
/*
* InitProcGlobal -
* Initialize the global process table during postmaster or standalone
* backend startup.
*
* We also create all the per-process semaphores we will need to support
* the requested number of backends. We used to allocate semaphores
* only when backends were actually started up, but that is bad because
* it lets Postgres fail under load --- a lot of Unix systems are
* (mis)configured with small limits on the number of semaphores, and
* running out when trying to start another backend is a common failure.
* So, now we grab enough semaphores to support the desired max number
* of backends immediately at initialization --- if the sysadmin has set
* MaxConnections, max_worker_processes, or autovacuum_max_workers higher
* than his kernel will support, he'll find out sooner rather than later.
*
* Another reason for creating semaphores here is that the semaphore
* implementation typically requires us to create semaphores in the
* postmaster, not in backends.
*
* Note: this is NOT called by individual backends under a postmaster,
* not even in the EXEC_BACKEND case. The ProcGlobal and AuxiliaryProcs
* pointers must be propagated specially for EXEC_BACKEND operation.
*/
void
InitProcGlobal(void)
{
PGPROC *procs;
PGXACT *pgxacts;
int i,
j;
bool found;
uint32 TotalProcs = MaxBackends + NUM_AUXILIARY_PROCS + max_prepared_xacts;
/* Create the ProcGlobal shared structure */
ProcGlobal = (PROC_HDR *)
ShmemInitStruct("Proc Header", sizeof(PROC_HDR), &found);
Assert(!found);
/*
* Initialize the data structures.
*/
ProcGlobal->spins_per_delay = DEFAULT_SPINS_PER_DELAY;
ProcGlobal->freeProcs = NULL;
ProcGlobal->autovacFreeProcs = NULL;
ProcGlobal->bgworkerFreeProcs = NULL;
ProcGlobal->startupProc = NULL;
ProcGlobal->startupProcPid = 0;
ProcGlobal->startupBufferPinWaitBufId = -1;
ProcGlobal->walwriterLatch = NULL;
ProcGlobal->checkpointerLatch = NULL;
pg_atomic_init_u32(&ProcGlobal->nextClearXidElem, INVALID_PGPROCNO);
/*
* Create and initialize all the PGPROC structures we'll need. There are
* five separate consumers: (1) normal backends, (2) autovacuum workers
* and the autovacuum launcher, (3) background workers, (4) auxiliary
* processes, and (5) prepared transactions. Each PGPROC structure is
* dedicated to exactly one of these purposes, and they do not move
* between groups.
*/
procs = (PGPROC *) ShmemAlloc(TotalProcs * sizeof(PGPROC));
ProcGlobal->allProcs = procs;
/* XXX allProcCount isn't really all of them; it excludes prepared xacts */
ProcGlobal->allProcCount = MaxBackends + NUM_AUXILIARY_PROCS;
if (!procs)
ereport(FATAL,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of shared memory")));
MemSet(procs, 0, TotalProcs * sizeof(PGPROC));
/*
* Also allocate a separate array of PGXACT structures. This is separate
* from the main PGPROC array so that the most heavily accessed data is
* stored contiguously in memory in as few cache lines as possible. This
* provides significant performance benefits, especially on a
* multiprocessor system. There is one PGXACT structure for every PGPROC
* structure.
*/
pgxacts = (PGXACT *) ShmemAlloc(TotalProcs * sizeof(PGXACT));
MemSet(pgxacts, 0, TotalProcs * sizeof(PGXACT));
ProcGlobal->allPgXact = pgxacts;
for (i = 0; i < TotalProcs; i++)
{
/* Common initialization for all PGPROCs, regardless of type. */
/*
* Set up per-PGPROC semaphore, latch, and backendLock. Prepared xact
* dummy PGPROCs don't need these though - they're never associated
* with a real process
*/
if (i < MaxBackends + NUM_AUXILIARY_PROCS)
{
PGSemaphoreCreate(&(procs[i].sem));
InitSharedLatch(&(procs[i].procLatch));
procs[i].backendLock = LWLockAssign();
}
procs[i].pgprocno = i;
/*
* Newly created PGPROCs for normal backends, autovacuum and bgworkers
* must be queued up on the appropriate free list. Because there can
* only ever be a small, fixed number of auxiliary processes, no free
* list is used in that case; InitAuxiliaryProcess() instead uses a
* linear search. PGPROCs for prepared transactions are added to a
* free list by TwoPhaseShmemInit().
*/
if (i < MaxConnections)
{
/* PGPROC for normal backend, add to freeProcs list */
procs[i].links.next = (SHM_QUEUE *) ProcGlobal->freeProcs;
ProcGlobal->freeProcs = &procs[i];
procs[i].procgloballist = &ProcGlobal->freeProcs;
}
else if (i < MaxConnections + autovacuum_max_workers + 1)
{
/* PGPROC for AV launcher/worker, add to autovacFreeProcs list */
procs[i].links.next = (SHM_QUEUE *) ProcGlobal->autovacFreeProcs;
ProcGlobal->autovacFreeProcs = &procs[i];
procs[i].procgloballist = &ProcGlobal->autovacFreeProcs;
}
else if (i < MaxBackends)
{
/* PGPROC for bgworker, add to bgworkerFreeProcs list */
procs[i].links.next = (SHM_QUEUE *) ProcGlobal->bgworkerFreeProcs;
ProcGlobal->bgworkerFreeProcs = &procs[i];
procs[i].procgloballist = &ProcGlobal->bgworkerFreeProcs;
}
/* Initialize myProcLocks[] shared memory queues. */
for (j = 0; j < NUM_LOCK_PARTITIONS; j++)
SHMQueueInit(&(procs[i].myProcLocks[j]));
}
/*
* Save pointers to the blocks of PGPROC structures reserved for auxiliary
* processes and prepared transactions.
*/
AuxiliaryProcs = &procs[MaxBackends];
PreparedXactProcs = &procs[MaxBackends + NUM_AUXILIARY_PROCS];
/* Create ProcStructLock spinlock, too */
ProcStructLock = (slock_t *) ShmemAlloc(sizeof(slock_t));
SpinLockInit(ProcStructLock);
}
