"Heikki Linnakangas" <heikki@enterprisedb.com> writes:
> If you look at the callgraph, you'll see that those
> LWLockAcquire/Release calls are coming from HeapTupleSatisfiesVacuum ->
> TransactionIdIsInProgress, which keeps trashing the ProcArrayLock. A
> "if(TransactionIdIsCurrentTransactionId(xid)) return true;" check in
> TransactionIdIsInProgress would speed that up, but I wonder if there's a
> more general solution to make HeapTupleSatisfiesVacuum cheaper. For
> example, we could cache the in-progress status of tuples.
Dunno about "more general", but your idea reduces the runtime of this
example by about 50% (22.2s to 10.5s) for me. I'm worried though that
it would be a net negative in more typical situations, especially if
you've got a lot of open subtransactions.
regards, tom lane
*** src/backend/storage/ipc/procarray.c.orig Sat Sep 8 16:31:15 2007
--- src/backend/storage/ipc/procarray.c Fri Sep 21 11:08:34 2007
***************
*** 341,346 ****
--- 341,353 ---- return false; }
+ /*
+ * Also, we can detect our own transaction without any access to shared
+ * memory.
+ */
+ if (TransactionIdIsCurrentTransactionId(xid))
+ return true;
+ /* Get workspace to remember main XIDs in */ xids = (TransactionId *) palloc(sizeof(TransactionId) *
arrayP->maxProcs);