hashtable->nbuckets = pstate->nbuckets;
hashtable->log2_nbuckets = my_log2(hashtable->nbuckets);
hashtable->totalTuples = pstate->total_tuples;
- ExecParallelHashEnsureBatchAccessors(hashtable);
+
+ /*
+ * Unless we're completely done and the batch state has been freed, make
+ * sure we have accessors.
+ */
+ if (BarrierPhase(build_barrier) < PHJ_BUILD_DONE)
+ ExecParallelHashEnsureBatchAccessors(hashtable);
/*
* The next synchronization point is in ExecHashJoin's HJ_BUILD_HASHTABLE
- * case, which will bring the build phase to PHJ_BUILD_DONE (if it isn't
+ * case, which will bring the build phase to PHJ_BUILD_RUNNING (if it isn't
* there already).
*/
Assert(BarrierPhase(build_barrier) == PHJ_BUILD_HASHING_OUTER ||
+ BarrierPhase(build_barrier) == PHJ_BUILD_RUNNING ||
BarrierPhase(build_barrier) == PHJ_BUILD_DONE);
}
/*
* The next Parallel Hash synchronization point is in
* MultiExecParallelHash(), which will progress it all the way to
- * PHJ_BUILD_DONE. The caller must not return control from this
+ * PHJ_BUILD_RUNNING. The caller must not return control from this
* executor node between now and then.
*/
}
}
/*
- * It's possible for a backend to start up very late so that the whole
- * join is finished and the shm state for tracking batches has already
- * been freed by ExecHashTableDetach(). In that case we'll just leave
- * hashtable->batches as NULL so that ExecParallelHashJoinNewBatch() gives
- * up early.
+ * We should never see a state where the batch-tracking array is freed,
+ * because we should have given up sooner if we join when the build barrier
+ * has reached the PHJ_BUILD_DONE phase.
*/
- if (!DsaPointerIsValid(pstate->batches))
- return;
+ Assert(DsaPointerIsValid(pstate->batches));
/* Use hash join memory context. */
oldcxt = MemoryContextSwitchTo(hashtable->hashCxt);
void
ExecHashTableDetach(HashJoinTable hashtable)
{
- if (hashtable->parallel_state)
+ ParallelHashJoinState *pstate = hashtable->parallel_state;
+
+ /*
+ * If we're involved in a parallel query, we must either have got all the
+ * way to PHJ_BUILD_RUNNING, or joined too late and be in PHJ_BUILD_DONE.
+ */
+ Assert(!pstate ||
+ BarrierPhase(&pstate->build_barrier) >= PHJ_BUILD_RUNNING);
+
+ if (pstate && BarrierPhase(&pstate->build_barrier) == PHJ_BUILD_RUNNING)
{
- ParallelHashJoinState *pstate = hashtable->parallel_state;
int i;
/* Make sure any temporary files are closed. */
}
/* If we're last to detach, clean up shared memory. */
- if (BarrierDetach(&pstate->build_barrier))
+ if (BarrierArriveAndDetach(&pstate->build_barrier))
{
+ /*
+ * Late joining processes will see this state and give up
+ * immediately.
+ */
+ Assert(BarrierPhase(&pstate->build_barrier) == PHJ_BUILD_DONE);
+
if (DsaPointerIsValid(pstate->batches))
{
dsa_free(hashtable->area, pstate->batches);
pstate->batches = InvalidDsaPointer;
}
}
-
- hashtable->parallel_state = NULL;
}
+ hashtable->parallel_state = NULL;
}
/*
* PHJ_BUILD_ALLOCATING -- one sets up the batches and table 0
* PHJ_BUILD_HASHING_INNER -- all hash the inner rel
* PHJ_BUILD_HASHING_OUTER -- (multi-batch only) all hash the outer
- * PHJ_BUILD_DONE -- building done, probing can begin
+ * PHJ_BUILD_RUNNING -- building done, probing can begin
+ * PHJ_BUILD_DONE -- all work complete, one frees batches
*
* While in the phase PHJ_BUILD_HASHING_INNER a separate pair of barriers may
* be used repeatedly as required to coordinate expansions in the number of
* batches whenever it encounters them while scanning and probing, which it
* can do because it processes batches in serial order.
*
- * Once PHJ_BUILD_DONE is reached, backends then split up and process
+ * Once PHJ_BUILD_RUNNING is reached, backends then split up and process
* different batches, or gang up and work together on probing batches if there
* aren't enough to go around. For each batch there is a separate barrier
* with the following phases:
*
* To avoid deadlocks, we never wait for any barrier unless it is known that
* all other backends attached to it are actively executing the node or have
- * already arrived. Practically, that means that we never return a tuple
- * while attached to a barrier, unless the barrier has reached its final
- * state. In the slightly special case of the per-batch barrier, we return
- * tuples while in PHJ_BATCH_PROBING phase, but that's OK because we use
- * BarrierArriveAndDetach() to advance it to PHJ_BATCH_DONE without waiting.
+ * finished. Practically, that means that we never emit a tuple while attached
+ * to a barrier, unless the barrier has reached a phase that means that no
+ * process will wait on it again. We emit tuples while attached to the build
+ * barrier in phase PHJ_BUILD_RUNNING, and to a per-batch barrier in phase
+ * PHJ_BATCH_PROBING. These are advanced to PHJ_BUILD_DONE and PHJ_BATCH_DONE
+ * respectively without waiting, using BarrierArriveAndDetach(). The last to
+ * detach receives a different return value so that it knows that it's safe to
+ * clean up. Any straggler process that attaches after that phase is reached
+ * will see that it's too late to participate or access the relevant shared
+ * memory objects.
*
*-------------------------------------------------------------------------
*/
build_barrier = ¶llel_state->build_barrier;
Assert(BarrierPhase(build_barrier) == PHJ_BUILD_HASHING_OUTER ||
+ BarrierPhase(build_barrier) == PHJ_BUILD_RUNNING ||
BarrierPhase(build_barrier) == PHJ_BUILD_DONE);
if (BarrierPhase(build_barrier) == PHJ_BUILD_HASHING_OUTER)
{
BarrierArriveAndWait(build_barrier,
WAIT_EVENT_HASH_BUILD_HASH_OUTER);
}
- Assert(BarrierPhase(build_barrier) == PHJ_BUILD_DONE);
+ else if (BarrierPhase(build_barrier) == PHJ_BUILD_DONE)
+ {
+ /*
+ * If we attached so late that the job is finished and
+ * the batch state has been freed, we can return
+ * immediately.
+ */
+ return NULL;
+ }
/* Each backend should now select a batch to work on. */
+ Assert(BarrierPhase(build_barrier) == PHJ_BUILD_RUNNING);
hashtable->curbatch = -1;
node->hj_JoinState = HJ_NEED_NEW_BATCH;
int start_batchno;
int batchno;
- /*
- * If we started up so late that the batch tracking array has been freed
- * already by ExecHashTableDetach(), then we are finished. See also
- * ExecParallelHashEnsureBatchAccessors().
- */
- if (hashtable->batches == NULL)
- return false;
-
/*
* If we were already attached to a batch, remember not to bother checking
* it again, and detach from it (possibly freeing the hash table if we are
projects / postgresql.git / commitdiff