/*
* ClockSweepTick - Helper routine for StrategyGetBuffer()
*
* Move the clock hand one buffer ahead of its current position and return the
* id of the buffer now under the hand.
*/
static inline uint32
ClockSweepTick(void)
{
uint32 victim;
/*
* Atomically move hand ahead one buffer - if there's several processes
* doing this, this can lead to buffers being returned slightly out of
* apparent order.
*/
victim =
pg_atomic_fetch_add_u32(&StrategyControl->nextVictimBuffer, 1);
if (victim >= NBuffers)
{
uint32 originalVictim = victim;
/* always wrap what we look up in BufferDescriptors */
victim = victim % NBuffers;
/*
* If we're the one that just caused a wraparound, force
* completePasses to be incremented while holding the spinlock. We
* need the spinlock so StrategySyncStart() can return a consistent
* value consisting of nextVictimBuffer and completePasses.
*/
if (victim == 0)
{
uint32 expected;
uint32 wrapped;
bool success = false;
expected = originalVictim + 1;
while (!success)
{
/*
* Acquire the spinlock while increasing completePasses. That
* allows other readers to read nextVictimBuffer and
* completePasses in a consistent manner which is required for
* StrategySyncStart(). In theory delaying the increment
* could lead to an overflow of nextVictimBuffers, but that's
* highly unlikely and wouldn't be particularly harmful.
*/
SpinLockAcquire(&StrategyControl->buffer_strategy_lock);
wrapped = expected % NBuffers;
success = pg_atomic_compare_exchange_u32(&StrategyControl->nextVictimBuffer,
&expected, wrapped);
if (success)
StrategyControl->completePasses++;
SpinLockRelease(&StrategyControl->buffer_strategy_lock);
}
}
}
return victim;
}
void cfs_lock_file(FileMap* map, char const* file_path)
{
long delay = CFS_LOCK_MIN_TIMEOUT;
while (true) {
uint64 count = pg_atomic_fetch_add_u32(&map->lock, 1);
if (count < CFS_GC_LOCK) {
break;
}
if (InRecovery) {
/* Uhhh... looks like last GC was interrupted.
* Try to recover file
*/
char* map_bck_path = psprintf("%s.map.bck", file_path);
char* file_bck_path = psprintf("%s.bck", file_path);
if (access(file_bck_path, R_OK) != 0) {
/* There is no backup file: new map should be constructed */
int md2 = open(map_bck_path, O_RDWR|PG_BINARY, 0);
if (md2 >= 0) {
/* Recover map */
if (!cfs_read_file(md2, map, sizeof(FileMap))) {
elog(LOG, "Failed to read file %s: %m", map_bck_path);
}
close(md2);
}
} else {
/* Presence of backup file means that we still have unchanged data and map files.
* Just remove backup files, grab lock and continue processing
*/
unlink(file_bck_path);
unlink(map_bck_path);
}
pfree(file_bck_path);
pfree(map_bck_path);
break;
}
pg_atomic_fetch_sub_u32(&map->lock, 1);
pg_usleep(delay);
if (delay < CFS_LOCK_MAX_TIMEOUT) {
delay *= 2;
}
}
if (IsUnderPostmaster && cfs_gc_workers != 0 && pg_atomic_test_set_flag(&cfs_state->gc_started))
{
cfs_start_background_gc();
}
}
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");
}
/*
* Get position for storing updated page
*/
uint32 cfs_alloc_page(FileMap* map, uint32 oldSize, uint32 newSize)
{
pg_atomic_fetch_add_u32(&map->usedSize, newSize - oldSize);
return pg_atomic_fetch_add_u32(&map->physSize, newSize);
}
/*
* StrategyGetBuffer
*
* Called by the bufmgr to get the next candidate buffer to use in
* BufferAlloc(). The only hard requirement BufferAlloc() has is that
* the selected buffer must not currently be pinned by anyone.
*
* strategy is a BufferAccessStrategy object, or NULL for default strategy.
*
* To ensure that no one else can pin the buffer before we do, we must
* return the buffer with the buffer header spinlock still held.
*/
volatile BufferDesc *
StrategyGetBuffer(BufferAccessStrategy strategy)
{
volatile BufferDesc *buf;
int bgwprocno;
int trycounter;
/*
* If given a strategy object, see whether it can select a buffer. We
* assume strategy objects don't need buffer_strategy_lock.
*/
if (strategy != NULL)
{
buf = GetBufferFromRing(strategy);
if (buf != NULL)
return buf;
}
/*
* If asked, we need to waken the bgwriter. Since we don't want to rely on
* a spinlock for this we force a read from shared memory once, and then
* set the latch based on that value. We need to go through that length
* because otherwise bgprocno might be reset while/after we check because
* the compiler might just reread from memory.
*
* This can possibly set the latch of the wrong process if the bgwriter
* dies in the wrong moment. But since PGPROC->procLatch is never
* deallocated the worst consequence of that is that we set the latch of
* some arbitrary process.
*/
bgwprocno = INT_ACCESS_ONCE(StrategyControl->bgwprocno);
if (bgwprocno != -1)
{
/* reset bgwprocno first, before setting the latch */
StrategyControl->bgwprocno = -1;
/*
* Not acquiring ProcArrayLock here which is slightly icky. It's
* actually fine because procLatch isn't ever freed, so we just can
* potentially set the wrong process' (or no process') latch.
*/
SetLatch(&ProcGlobal->allProcs[bgwprocno].procLatch);
}
/*
* We count buffer allocation requests so that the bgwriter can estimate
* the rate of buffer consumption. Note that buffers recycled by a
* strategy object are intentionally not counted here.
*/
pg_atomic_fetch_add_u32(&StrategyControl->numBufferAllocs, 1);
/*
* First check, without acquiring the lock, whether there's buffers in the
* freelist. Since we otherwise don't require the spinlock in every
* StrategyGetBuffer() invocation, it'd be sad to acquire it here -
* uselessly in most cases. That obviously leaves a race where a buffer is
* put on the freelist but we don't see the store yet - but that's pretty
* harmless, it'll just get used during the next buffer acquisition.
*
* If there's buffers on the freelist, acquire the spinlock to pop one
* buffer of the freelist. Then check whether that buffer is usable and
* repeat if not.
*
* Note that the freeNext fields are considered to be protected by the
* buffer_strategy_lock not the individual buffer spinlocks, so it's OK to
* manipulate them without holding the spinlock.
*/
if (StrategyControl->firstFreeBuffer >= 0)
{
while (true)
{
/* Acquire the spinlock to remove element from the freelist */
SpinLockAcquire(&StrategyControl->buffer_strategy_lock);
if (StrategyControl->firstFreeBuffer < 0)
{
SpinLockRelease(&StrategyControl->buffer_strategy_lock);
break;
}
buf = GetBufferDescriptor(StrategyControl->firstFreeBuffer);
Assert(buf->freeNext != FREENEXT_NOT_IN_LIST);
/* Unconditionally remove buffer from freelist */
StrategyControl->firstFreeBuffer = buf->freeNext;
buf->freeNext = FREENEXT_NOT_IN_LIST;
/*
* Release the lock so someone else can access the freelist while
* we check out this buffer.
*/
SpinLockRelease(&StrategyControl->buffer_strategy_lock);
/*
* If the buffer is pinned or has a nonzero usage_count, we cannot
* use it; discard it and retry. (This can only happen if VACUUM
* put a valid buffer in the freelist and then someone else used
* it before we got to it. It's probably impossible altogether as
* of 8.3, but we'd better check anyway.)
*/
LockBufHdr(buf);
if (buf->refcount == 0 && buf->usage_count == 0)
{
if (strategy != NULL)
AddBufferToRing(strategy, buf);
return buf;
}
UnlockBufHdr(buf);
}
}
/* Nothing on the freelist, so run the "clock sweep" algorithm */
trycounter = NBuffers;
for (;;)
{
buf = GetBufferDescriptor(ClockSweepTick());
/*
* If the buffer is pinned or has a nonzero usage_count, we cannot use
* it; decrement the usage_count (unless pinned) and keep scanning.
*/
LockBufHdr(buf);
if (buf->refcount == 0)
{
if (buf->usage_count > 0)
{
buf->usage_count--;
trycounter = NBuffers;
}
else
{
/* Found a usable buffer */
if (strategy != NULL)
AddBufferToRing(strategy, buf);
return buf;
}
}
else if (--trycounter == 0)
{
/*
* We've scanned all the buffers without making any state changes,
* so all the buffers are pinned (or were when we looked at them).
* We could hope that someone will free one eventually, but it's
* probably better to fail than to risk getting stuck in an
* infinite loop.
*/
UnlockBufHdr(buf);
elog(ERROR, "no unpinned buffers available");
}
UnlockBufHdr(buf);
}
}
void MMReceiverStarted()
{
if (pg_atomic_fetch_add_u32(&dtm->nReceivers, 1) == dtm->nNodes-2) {
dtm->initialized = true;
}
}
