agora inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v24 1/5] sequential scan for dshash
230+ messages / 3 participants
[nested] [flat]

* [PATCH 1/5] sequential scan for dshash
@ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw)

Add sequential scan feature to dshash.
---
 src/backend/lib/dshash.c | 185 +++++++++++++++++++++++++++++++++++++--
 src/include/lib/dshash.h |  22 ++++-
 2 files changed, 201 insertions(+), 6 deletions(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index fbdd941325..7675370058 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -112,6 +112,7 @@ struct dshash_table
 	size_t		size_log2;		/* log2(number of buckets) */
 	bool		find_locked;	/* Is any partition lock held by 'find'? */
 	bool		find_exclusively_locked;	/* ... exclusively? */
+	bool		seqscan_running;/* now under sequential scan */
 };
 
 /* Given a pointer to an item, find the entry (user data) it holds. */
@@ -127,6 +128,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +158,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg)
 
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
+	hash_table->seqscan_running = false;
 
 	/*
 	 * Set up the initial array of buckets.  Our initial size is the same as
@@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params,
 	hash_table->control = dsa_get_address(area, control);
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
+	hash_table->seqscan_running = false;
 	Assert(hash_table->control->magic == DSHASH_MAGIC);
 
 	/*
@@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry)
 								LW_EXCLUSIVE));
 
 	delete_item(hash_table, item);
-	hash_table->find_locked = false;
-	hash_table->find_exclusively_locked = false;
-	LWLockRelease(PARTITION_LOCK(hash_table, partition));
+
+	/* We need to keep partition lock while sequential scan */
+	if (!hash_table->seqscan_running)
+	{
+		hash_table->find_locked = false;
+		hash_table->find_exclusively_locked = false;
+		LWLockRelease(PARTITION_LOCK(hash_table, partition));
+	}
 }
 
 /*
@@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry)
 	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index),
 								hash_table->find_exclusively_locked
 								? LW_EXCLUSIVE : LW_SHARED));
+	/* lock is under control of sequential scan */
+	Assert(!hash_table->seqscan_running);
 
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
@@ -592,6 +610,164 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan trhough dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should be called for incomplete scans and otherwise
+ * shoudln't. Finished scans are cleaned up automatically.
+ *
+ * Returned elements are locked as is the case with dshash_find.  However, the
+ * caller must not release the lock.
+ *
+ * Same as dynanash, the caller may delete returned elements midst of a scan.
+ *
+ * If consistent is set for dshash_seq_init, the all hash table partitions are
+ * locked in the requested mode (as determined by the exclusive flag) during
+ * the scan.  Otherwise partitions are locked in one-at-a-time way during the
+ * scan.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool consistent, bool exclusive)
+{
+	/* allowed at most one scan at once */
+	Assert(!hash_table->seqscan_running);
+
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->consistent = consistent;
+	status->exclusive = exclusive;
+	hash_table->seqscan_running = true;
+
+	/*
+	 * Protect all partitions from modification if the caller wants a
+	 * consistent result.
+	 */
+	if (consistent)
+	{
+		int i;
+
+		for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i)
+		{
+			Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i)));
+
+			LWLockAcquire(PARTITION_LOCK(hash_table, i),
+						  exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		}
+		ensure_valid_bucket_pointers(hash_table);
+	}
+}
+
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	Assert(status->hash_table->seqscan_running);
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert (status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		if (!status->consistent)
+		{
+			partition =
+				PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+										   status->hash_table->size_log2);
+			LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			status->curpartition = partition;
+
+			/* resize doesn't happen from now until seq scan ends */
+			status->nbuckets =
+				NUM_BUCKETS(status->hash_table->control->size_log2);
+			ensure_valid_bucket_pointers(status->hash_table);
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finsih. */
+			dshash_seq_term(status);
+			return NULL;
+		}
+
+		/* Also move parititon lock if needed */
+		if (!status->consistent)
+		{
+			int next_partition =
+				PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+										   status->hash_table->size_log2);
+
+			/* Move lock along with partition for the bucket */
+			if (status->curpartition != next_partition)
+			{
+				/*
+				 * Lock the next partition then release the current, not in the
+				 * reverse order to to avoid concurrent resizing. Partitions
+				 * are locked in the same order with resize() so dead locks
+				 * won't happen.
+				 */
+				LWLockAcquire(PARTITION_LOCK(status->hash_table,
+											 next_partition),
+							  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+				LWLockRelease(PARTITION_LOCK(status->hash_table,
+											 status->curpartition));
+				status->curpartition = next_partition;
+			}
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	Assert(status->hash_table->seqscan_running);
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+	status->hash_table->seqscan_running = false;
+
+	if (status->consistent)
+	{
+		int i;
+
+		for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i)
+			LWLockRelease(PARTITION_LOCK(status->hash_table, i));
+	}
+	else if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
@@ -673,7 +849,6 @@ delete_item(dshash_table *hash_table, dshash_table_item *item)
 /*
  * Grow the hash table if necessary to the requested number of buckets.  The
  * requested size must be double some previously observed size.
- *
  * Must be called without any partition lock held.
  */
 static void
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..ad88f32cdd 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,22 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;
+	int					curbucket;
+	int					nbuckets;
+	dshash_table_item  *curitem;
+	dsa_pointer			pnextitem;
+	int					curpartition;
+	bool				consistent;
+	bool				exclusive;
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -70,7 +86,6 @@ extern dshash_table *dshash_attach(dsa_area *area,
 extern void dshash_detach(dshash_table *hash_table);
 extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table);
 extern void dshash_destroy(dshash_table *hash_table);
-
 /* Finding, creating, deleting entries. */
 extern void *dshash_find(dshash_table *hash_table,
 						 const void *key, bool exclusive);
@@ -80,6 +95,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool consistent, bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.23.0


----Next_Part(Wed_Jan_22_17_24_04_2020_620)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v24 1/5] sequential scan for dshash
@ 2018-06-29 07:41 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2018-06-29 07:41 UTC (permalink / raw)

Add sequential scan feature to dshash.
---
 src/backend/lib/dshash.c | 188 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  23 ++++-
 2 files changed, 206 insertions(+), 5 deletions(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 350f8c0a66..4f0c7ec840 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -112,6 +112,7 @@ struct dshash_table
 	size_t		size_log2;		/* log2(number of buckets) */
 	bool		find_locked;	/* Is any partition lock held by 'find'? */
 	bool		find_exclusively_locked;	/* ... exclusively? */
+	bool		seqscan_running;/* now under sequential scan */
 };
 
 /* Given a pointer to an item, find the entry (user data) it holds. */
@@ -127,6 +128,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +158,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg)
 
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
+	hash_table->seqscan_running = false;
 
 	/*
 	 * Set up the initial array of buckets.  Our initial size is the same as
@@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params,
 	hash_table->control = dsa_get_address(area, control);
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
+	hash_table->seqscan_running = false;
 	Assert(hash_table->control->magic == DSHASH_MAGIC);
 
 	/*
@@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -549,9 +560,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry)
 								LW_EXCLUSIVE));
 
 	delete_item(hash_table, item);
-	hash_table->find_locked = false;
-	hash_table->find_exclusively_locked = false;
-	LWLockRelease(PARTITION_LOCK(hash_table, partition));
+
+	/* We need to keep partition lock while sequential scan */
+	if (!hash_table->seqscan_running)
+	{
+		hash_table->find_locked = false;
+		hash_table->find_exclusively_locked = false;
+		LWLockRelease(PARTITION_LOCK(hash_table, partition));
+	}
 }
 
 /*
@@ -568,6 +584,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry)
 	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index),
 								hash_table->find_exclusively_locked
 								? LW_EXCLUSIVE : LW_SHARED));
+	/* lock is under control of sequential scan */
+	Assert(!hash_table->seqscan_running);
 
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
@@ -592,6 +610,168 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan trhough dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should be called if and only if the scan is abandoned
+ * before completion; if dshash_seq_next returns NULL then it has already done
+ * the end-of-scan cleanup.
+ *
+ * On returning element, it is locked as is the case with dshash_find.
+ * However, the caller must not release the lock. The lock is released as
+ * necessary in continued scan.
+ *
+ * As opposed to the equivalent for dynanash, the caller is not supposed to
+ * delete the returned element before continuing the scan.
+ *
+ * If consistent is set for dshash_seq_init, the whole hash table is
+ * non-exclusively locked. Otherwise a part of the hash table is locked in the
+ * same mode (partition lock).
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool consistent, bool exclusive)
+{
+	/* allowed at most one scan at once */
+	Assert(!hash_table->seqscan_running);
+
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->consistent = consistent;
+	status->exclusive = exclusive;
+	hash_table->seqscan_running = true;
+
+	/*
+	 * Protect all partitions from modification if the caller wants a
+	 * consistent result.
+	 */
+	if (consistent)
+	{
+		int i;
+
+		for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i)
+		{
+			Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i)));
+
+			LWLockAcquire(PARTITION_LOCK(hash_table, i),
+						  exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		}
+		ensure_valid_bucket_pointers(hash_table);
+	}
+}
+
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	Assert(status->hash_table->seqscan_running);
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert (status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		if (!status->consistent)
+		{
+			partition =
+				PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+										   status->hash_table->size_log2);
+			LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			status->curpartition = partition;
+
+			/* resize doesn't happen from now until seq scan ends */
+			status->nbuckets =
+				NUM_BUCKETS(status->hash_table->control->size_log2);
+			ensure_valid_bucket_pointers(status->hash_table);
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finsih. */
+			dshash_seq_term(status);
+			return NULL;
+		}
+
+		/* Also move parititon lock if needed */
+		if (!status->consistent)
+		{
+			int next_partition =
+				PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+										   status->hash_table->size_log2);
+
+			/* Move lock along with partition for the bucket */
+			if (status->curpartition != next_partition)
+			{
+				/*
+				 * Take lock on the next partition then release the current,
+				 * not in the reverse order. This is required to avoid
+				 * resizing from happening during a sequential scan. Locks are
+				 * taken in partition order so no dead lock happen with other
+				 * seq scans or resizing.
+				 */
+				LWLockAcquire(PARTITION_LOCK(status->hash_table,
+											 next_partition),
+							  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+				LWLockRelease(PARTITION_LOCK(status->hash_table,
+											 status->curpartition));
+				status->curpartition = next_partition;
+			}
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * This item can be deleted by the caller. Store the next item for the
+	 * next iteration for the occasion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	Assert(status->hash_table->seqscan_running);
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+	status->hash_table->seqscan_running = false;
+
+	if (status->consistent)
+	{
+		int i;
+
+		for (i = 0; i < DSHASH_NUM_PARTITIONS; ++i)
+			LWLockRelease(PARTITION_LOCK(status->hash_table, i));
+	}
+	else if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index fa2e28ff3e..79698a6ad6 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,23 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state of dshash. The detail is exposed since the storage
+ * size should be known to users but it should be considered as an opaque
+ * type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;
+	int					curbucket;
+	int					nbuckets;
+	dshash_table_item  *curitem;
+	dsa_pointer			pnextitem;
+	int					curpartition;
+	bool				consistent;
+	bool				exclusive;
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -70,7 +87,6 @@ extern dshash_table *dshash_attach(dsa_area *area,
 extern void dshash_detach(dshash_table *hash_table);
 extern dshash_table_handle dshash_get_hash_table_handle(dshash_table *hash_table);
 extern void dshash_destroy(dshash_table *hash_table);
-
 /* Finding, creating, deleting entries. */
 extern void *dshash_find(dshash_table *hash_table,
 						 const void *key, bool exclusive);
@@ -80,6 +96,11 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool consistent, bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.23.0


----Next_Part(Tue_Dec__3_17_27_59_2019_887)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v24-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v27 9/9] Add documentations about Incremental View Maintenance
@ 2019-12-20 01:25 Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:25 UTC (permalink / raw)

---
 doc/src/sgml/catalogs.sgml                    |  24 +-
 .../sgml/ref/create_materialized_view.sgml    | 131 +++++-
 .../sgml/ref/refresh_materialized_view.sgml   |   8 +-
 doc/src/sgml/rules.sgml                       | 443 ++++++++++++++++++
 4 files changed, 601 insertions(+), 5 deletions(-)

diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml
index a533a2153e..2561faa163 100644
--- a/doc/src/sgml/catalogs.sgml
+++ b/doc/src/sgml/catalogs.sgml
@@ -2193,6 +2193,15 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>relisivm</structfield> <type>bool</type>
+      </para>
+      <para>
+       True if materialized view enables incremental view maintenance
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>relrewrite</structfield> <type>oid</type>
@@ -3508,6 +3517,18 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
       </para>
      </listitem>
     </varlistentry>
+
+    <varlistentry>
+     <term><symbol>DEPENDENCY_IMMV</symbol> (<literal>m</literal>)</term>
+     <listitem>
+      <para>
+       The dependent object was created as part of creation of the Materialized
+       View with Incremental View Maintenance reference, and is really just a 
+       part of its internal implementation. The dependent object must not be
+       dropped unless the materialized view is also dropped.
+      </para>
+     </listitem>
+    </varlistentry>
    </variablelist>
 
    Other dependency flavors might be needed in future.
@@ -3891,7 +3912,8 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
        <structfield>extrelocatable</structfield> <type>bool</type>
       </para>
       <para>
-       True if extension can be relocated to another schema
+      True for materialized views which are enabled for incremental
+      view maintenance (IVM).
       </para></entry>
      </row>
 
diff --git a/doc/src/sgml/ref/create_materialized_view.sgml b/doc/src/sgml/ref/create_materialized_view.sgml
index 0d2fea2b97..52a4d206b1 100644
--- a/doc/src/sgml/ref/create_materialized_view.sgml
+++ b/doc/src/sgml/ref/create_materialized_view.sgml
@@ -21,7 +21,7 @@ PostgreSQL documentation
 
  <refsynopsisdiv>
 <synopsis>
-CREATE MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_name</replaceable>
+CREATE [ INCREMENTAL ] MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_name</replaceable>
     [ (<replaceable>column_name</replaceable> [, ...] ) ]
     [ USING <replaceable class="parameter">method</replaceable> ]
     [ WITH ( <replaceable class="parameter">storage_parameter</replaceable> [= <replaceable class="parameter">value</replaceable>] [, ... ] ) ]
@@ -60,6 +60,132 @@ CREATE MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_name</replaceable>
   <title>Parameters</title>
 
   <variablelist>
+   <varlistentry>
+    <term><literal>INCREMENTAL</literal></term>
+    <listitem>
+     <para>
+      If specified, some triggers are automatically created so that the rows
+      of the materialized view are immediately updated when base tables of the
+      materialized view are updated. In general, this allows faster update of
+      the materialized view at a price of slower update of the base tables
+      because the triggers will be invoked. We call this form of materialized
+      view as "Incrementally Maintainable Materialized View" (IMMV).
+     </para>
+     <para>
+      When <acronym>IMMV</acronym> is defined without using <command>WITH NO DATA</command>,
+      a unique index is created on the view automatically if possible.  If the view
+      definition query has a GROUP BY clause, a unique index is created on the columns
+      of GROUP BY expressions.  Also, if the view has DISTINCT clause, a unique index
+      is created on all columns in the target list.  Otherwise, if the view contains all
+      primary key attritubes of its base tables in the target list, a unique index is
+      created on these attritubes.  In other cases, no index is created.
+     </para>
+     <para>
+      There are restrictions of query definitions allowed to use this
+      option. The following are supported in query definitions for IMMV:
+      <itemizedlist>
+
+       <listitem>
+        <para>
+         Inner joins (including self-joins).
+        </para>
+       </listitem>
+
+       <listitem>
+        <para>
+         Some built-in aggregate functions (count, sum, avg, min, max) without a HAVING
+         clause. 
+        </para>
+        </listitem>
+      </itemizedlist>
+
+      Unsupported queries with this option include the following:
+
+      <itemizedlist>
+       <listitem>
+        <para>
+         Outer joins.
+        </para>
+       </listitem>
+
+       <listitem>
+        <para>
+         Sub-queries.
+        </para>
+       </listitem>
+
+       <listitem>
+        <para>
+         Aggregate functions other than built-in count, sum, avg, min and max.
+        </para>
+       </listitem>
+       <listitem>
+        <para>
+         Aggregate functions with a HAVING clause.
+        </para>
+       </listitem>
+       <listitem>
+        <para>
+         DISTINCT ON, WINDOW, VALUES, LIMIT and OFFSET clause.
+        </para>
+       </listitem>
+      </itemizedlist>
+
+      Other restrictions include:
+      <itemizedlist>
+
+       <listitem>
+        <para>
+         IMMVs must be based on simple base tables. It's not supported to
+         create them on top of views or materialized views.
+        </para>
+       </listitem>
+
+       <listitem>
+        <para>
+         When the TRUNCATE command is executed on a base table,
+         no changes are made to the materialized view.
+        </para>
+       </listitem>
+
+       <listitem>
+        <para>
+         It is not supported to include system columns in an IMMV.
+         <programlisting>
+CREATE INCREMENTAL MATERIALIZED VIEW  mv_ivm02 AS SELECT i,j FROM mv_base_a WHERE xmin = '610';
+ERROR:  system column is not supported with IVM
+         </programlisting>
+        </para>
+       </listitem>
+
+       <listitem>
+        <para>
+         Non-immutable functions are not supported.
+         <programlisting>
+CREATE INCREMENTAL MATERIALIZED VIEW  mv_ivm12 AS SELECT i,j FROM mv_base_a WHERE i = random()::int;
+ERROR:  functions in IMMV must be marked IMMUTABLE
+         </programlisting>
+        </para>
+        </listitem>
+
+       <listitem>
+        <para>
+         IMMVs do not support expressions that contains aggregates
+        </para>
+       </listitem>
+
+       <listitem>
+        <para>
+         Logical replication does not support IMMVs.
+        </para>
+       </listitem>
+
+      </itemizedlist>
+
+     </para>
+    </listitem>
+   </varlistentry>
+
    <varlistentry>
     <term><literal>IF NOT EXISTS</literal></term>
     <listitem>
@@ -155,7 +281,8 @@ CREATE MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_name</replaceable>
       This clause specifies whether or not the materialized view should be
       populated at creation time.  If not, the materialized view will be
       flagged as unscannable and cannot be queried until <command>REFRESH
-      MATERIALIZED VIEW</command> is used.
+      MATERIALIZED VIEW</command> is used.  Also, if the view is IMMV,
+      triggers for maintaining the view are not created.
      </para>
     </listitem>
    </varlistentry>
diff --git a/doc/src/sgml/ref/refresh_materialized_view.sgml b/doc/src/sgml/ref/refresh_materialized_view.sgml
index 675d6090f3..c29cfc19b6 100644
--- a/doc/src/sgml/ref/refresh_materialized_view.sgml
+++ b/doc/src/sgml/ref/refresh_materialized_view.sgml
@@ -35,9 +35,13 @@ REFRESH MATERIALIZED VIEW [ CONCURRENTLY ] <replaceable class="parameter">name</
    owner of the materialized view.  The old contents are discarded.  If
    <literal>WITH DATA</literal> is specified (or defaults) the backing query
    is executed to provide the new data, and the materialized view is left in a
-   scannable state.  If <literal>WITH NO DATA</literal> is specified no new
+   scannable state.  If the view is an incrementally maintainable materialized
+   view (IMMV) and was unpopulated, triggers for maintaining the view are
+   created. Also, a unique index is created for IMMV if it is possible and the
+   view doesn't have that yet.
+   If <literal>WITH NO DATA</literal> is specified no new
    data is generated and the materialized view is left in an unscannable
-   state.
+   state.  If the view is IMMV, the triggers are dropped.
   </para>
   <para>
    <literal>CONCURRENTLY</literal> and <literal>WITH NO DATA</literal> may not
diff --git a/doc/src/sgml/rules.sgml b/doc/src/sgml/rules.sgml
index 4b2ba5a4e6..71e10ef5a1 100644
--- a/doc/src/sgml/rules.sgml
+++ b/doc/src/sgml/rules.sgml
@@ -1090,6 +1090,449 @@ SELECT word FROM words ORDER BY word &lt;-&gt; 'caterpiler' LIMIT 10;
 
 </sect1>
 
+<sect1 id="rules-ivm">
+<title>Incremental View Maintenance</title>
+
+<indexterm zone="rules-ivm">
+ <primary>incremental view maintenance</primary>
+</indexterm>
+
+<indexterm zone="rules-ivm">
+ <primary>materialized view</primary>
+ <secondary>incremental view maintenance</secondary>
+</indexterm>
+
+<indexterm zone="rules-ivm">
+ <primary>view</primary>
+ <secondary>incremental view maintenance</secondary>
+</indexterm>
+
+<sect2 id="rules-ivm-overview">
+<title>Overview</title>
+
+<para>
+    Incremental View Maintenance (<acronym>IVM</acronym>) is a way to make
+    materialized views up-to-date in which only incremental changes are computed
+    and applied on views rather than recomputing the contents from scratch as
+    <command>REFRESH MATERIALIZED VIEW</command> does.  <acronym>IVM</acronym>
+    can update materialized views more efficiently than recomputation when only
+    small parts of the view are changed.
+</para>
+
+<para>
+    There are two approaches with regard to timing of view maintenance:
+    immediate and deferred.  In immediate maintenance, views are updated in the
+    same transaction that its base table is modified.  In deferred maintenance,
+    views are updated after the transaction is committed, for example, when the
+    view is accessed, as a response to user command like <command>REFRESH
+    MATERIALIZED VIEW</command>, or periodically in background, and so on.
+    <productname>PostgreSQL</productname> currently implements only a kind of
+    immediate maintenance, in which materialized views are updated immediately
+    in AFTER triggers when a base table is modified.
+</para>
+
+<para>
+    To create materialized views supporting <acronym>IVM</acronym>, use the
+    <command>CREATE INCREMENTAL MATERIALIZED VIEW</command>, for example:
+<programlisting>
+CREATE <emphasis>INCREMENTAL</emphasis> MATERIALIZED VIEW mymatview AS SELECT * FROM mytab;
+</programlisting>
+    When a materialized view is created with the <literal>INCREMENTAL</literal>
+    keyword, some triggers are automatically created so that the view's contents are
+    immediately updated when its base tables are modified. We call this form
+    of materialized view an Incrementally Maintainable Materialized View
+    (<acronym>IMMV</acronym>).
+<programlisting>
+postgres=# CREATE INCREMENTAL MATERIALIZED VIEW m AS SELECT * FROM t0;
+NOTICE:  could not create an index on materialized view "m" automatically
+HINT:  Create an index on the materialized view for effcient incremental maintenance.
+SELECT 3
+postgres=# SELECT * FROM m;
+ i
+---
+ 1
+ 2
+ 3
+(3 rows)
+
+postgres=# INSERT INTO t0 VALUES (4);
+INSERT 0 1
+postgres=# SELECT * FROM m; -- automatically updated
+ i
+---
+ 1
+ 2
+ 3
+ 4
+(4 rows)
+</programlisting>
+</para>
+
+<para>
+    Some <acronym>IMMV</acronym>s have hidden columns which are added
+    automatically when a materialized view is created. Their name starts
+    with <literal>__ivm_</literal> and they contain information required
+    for maintaining the <acronym>IMMV</acronym>. Such columns are not visible
+    when the <acronym>IMMV</acronym> is accessed by <literal>SELECT *</literal>
+    but are visible if the column name is explicitly specified in the target
+    list. We can also see the hidden columns in <literal>\d</literal>
+    meta-commands of <command>psql</command> commands.
+</para>
+
+<para>
+    In general, <acronym>IMMV</acronym>s allow faster updates of materialized
+    views at the price of slower updates to their base tables. Updates of
+    <acronym>IMMV</acronym> is slower because triggers will be invoked and the
+    view is updated in triggers per modification statement.
+</para>
+
+<para>
+    For example, suppose a normal materialized view defined as below:
+
+<programlisting>
+test=# CREATE INCREMENTAL MATERIALIZED VIEW mv_ivm AS
+        SELECT a.aid, b.bid, a.abalance, b.bbalance
+        FROM pgbench_accounts a JOIN pgbench_branches b USING(bid);
+SELECT 10000000
+
+</programlisting>
+
+    Updating a tuple in a base table of this materialized view is rapid but the
+   <command>REFRESH MATERIALIZED VIEW</command> command on this view takes a long time:
+
+<programlisting>
+test=# UPDATE pgbench_accounts SET abalance = 1000 WHERE aid = 1;
+UPDATE 1
+Time: 0.990 ms
+
+test=# REFRESH MATERIALIZED VIEW mv_normal ;
+REFRESH MATERIALIZED VIEW
+Time: 33533.952 ms (00:33.534)
+</programlisting>
+</para>
+
+<para>
+    On the other hand, after creating <acronym>IMMV</acronym> with the same view
+    definition as below:
+
+<programlisting>
+test=# CREATE INCREMENTAL MATERIALIZED VIEW mv_ivm AS
+        SELECT a.aid, b.bid, a.abalance, b.bbalance
+        FROM pgbench_accounts a JOIN pgbench_branches b USING(bid);
+test=# UPDATE pgbench_accounts SET abalance = 1000 WHERE aid = 1;
+NOTICE:  created index "mv_ivm_index" on materialized view "mv_ivm"
+</programlisting>
+
+    updating a tuple in a base table takes more than the normal view,
+    but its content is updated automatically and this is faster than the
+    <command>REFRESH MATERIALIZED VIEW</command> command.
+
+<programlisting>
+test=# UPDATE pgbench_accounts SET abalance = 1000 WHERE aid = 1;
+UPDATE 1
+Time: 13.068 ms
+</programlisting>
+
+</para>
+
+<para>
+    Appropriate indexes on <acronym>IMMV</acronym>s are necessary for
+    efficient <acronym>IVM</acronym> because it looks for tuples to be
+    updated in <acronym>IMMV</acronym>.  If there are no indexes, it
+    will take a long time.
+</para>
+
+<para>
+    Therefore, when <acronym>IMMV</acronym> is defined, a unique index is created on the view
+    automatically if possible.  If the view definition query has a GROUP BY clause, a unique
+    index is created on the columns of GROUP BY expressions.  Also, if the view has DISTINCT
+    clause, a unique index is created on all columns in the target list. Otherwise, if the
+    view contains all primary key attritubes of its base tables in the target list, a unique
+    index is created on these attritubes.  In other cases, no index is created.
+</para>
+
+<para>
+    In the previous example, a unique index "mv_ivm_index" is created on aid and bid
+    columns of materialized view "mv_ivm", and this enables the rapid update of the view.
+    Dropping this index make updating the view take a loger time.
+<programlisting>
+test=# DROP INDEX mv_ivm_index;
+DROP INDEX
+Time: 67.081 ms
+
+test=# UPDATE pgbench_accounts SET abalance = 1000 WHERE aid = 1;
+UPDATE 1
+Time: 16386.245 ms (00:16.386)
+</programlisting>
+
+</para>
+
+<para>
+    <acronym>IVM</acronym> is effective when we want to keep a materialized
+    view up-to-date and small fraction of a base table is modified
+    infrequently.  Due to the overhead of immediate maintenance, <acronym>IVM</acronym>
+    is not effective when a base table is modified frequently.  Also, when a
+    large part of a base table is modified or large data is inserted into a
+    base table, <acronym>IVM</acronym> is not effective and the cost of
+    maintenance can be larger than the <command>REFRESH MATERIALIZED VIEW</command>
+    command. In such situation, we can use <command>REFRESH MATERIALIZED VIEW</command>
+    and specify <literal>WITH NO DATA</literal> to disable immediate
+    maintenance before modifying a base table. After a base table modification,
+    execute the <command>REFRESH MATERIALIZED VIEW</command> (with <literal>WITH DATA</literal>)
+    command to refresh the view data and enable immediate maintenance.
+</para>
+
+</sect2>
+
+<sect2>
+<title>Supported View Definitions and Restrictions</title>
+
+<para>
+    Currently, we can create <acronym>IMMV</acronym>s using inner joins, and some
+    aggregates. However, several restrictions apply to the definition of IMMV.
+</para>
+
+<sect3>
+<title>Joins</title>
+<para>
+    Inner joins including self-join are supported. Outer joins are not supported.
+</para>
+</sect3>
+
+<sect3>
+<title>Aggregates</title>
+<para>
+    Supported aggregate functions are <function>count</function>, <function>sum</function>,
+    <function>avg</function>, <function>min</function>, and <function>max</function>.
+    Currently, only built-in aggregate functions are supported and user defined
+    aggregates cannot be used.  When a base table is modified, the new aggregated
+    values are incrementally calculated using the old aggregated values and values
+    of related hidden columns stored in <acronym>IMMV</acronym>.
+</para>
+
+<para>
+     Note that for <function>min</function> or <function>max</function>, the new values
+     could be re-calculated from base tables with regard to the affected groups when a
+     tuple containing the current minimal or maximal values are deleted from a base table.
+     Therefore, it can takes a long time to update an <acronym>IMMV</acronym> containing
+     these functions.
+</para>
+
+<para>
+    Also note that using <function>sum</function> or <function>avg</function> on
+    <type>real</type> (<type>float4</type>) type or <type>double precision</type>
+    (<type>float8</type>) type in <acronym>IMMV</acronym> is unsafe. This is
+    because aggregated values in <acronym>IMMV</acronym> can become different from
+    results calculated from base tables due to the limited precision of these types.
+    To avoid this problem, use the <type>numeric</type> type instead.
+</para>
+
+    <sect4>
+    <title>Restrictions on Aggregates</title>
+    <para>
+        There are the following restrictions:
+    <itemizedlist>
+        <listitem>
+        <para>
+            If we have a <literal>GROUP BY</literal> clause, expressions specified in
+               <literal>GROUP BY</literal> must appear in the target list.  This is
+               how tuples to be updated in the <acronym>IMMV</acronym> are identified.
+               These attributes are used as scan keys for searching tuples in the
+               <acronym>IMMV</acronym>, so indexes on them are required for efficient
+               <acronym>IVM</acronym>.
+        </para>
+        </listitem>
+
+        <listitem>
+        <para>
+            <literal>HAVING</literal> clause cannot be used.
+        </para>
+        </listitem>
+    </itemizedlist>
+    </para>
+    </sect4>
+</sect3>
+
+<sect3>
+<title>Other General Restrictions</title>
+<para>
+    There are other restrictions which generally apply to <acronym>IMMV</acronym>:
+    <itemizedlist>
+        <listitem>
+          <para>
+           Sub-queries cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+           CTEs cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+           Window functions cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <acronym>IMMV</acronym>s must be based on simple base tables.  It's not
+               supported to create them on top of views, materialized views, foreign tables, inhe.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            LIMIT and OFFSET clauses cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <acronym>IMMV</acronym>s cannot contain system columns.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <acronym>IMMV</acronym>s cannot contain non-immutable functions.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            UNION/INTERSECT/EXCEPT clauses cannnot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            DISTINCT ON clauses cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            TABLESAMPLE parameter cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            inheritance parent tables cannnot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            VALUES clause cannnot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <literal>GROUPING SETS</literal> and <literal>FILTER</literal> clauses cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            FOR UPDATE/SHARE cannot be used.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            targetlist cannot contain columns whose name start with <literal>__ivm_</literal>.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            targetlist cannot contain expressions which contain an aggregate in it.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+              Logical replication is not supported, that is, even when a base table
+               at a publisher node is modified, <acronym>IMMV</acronym>s at subscriber
+               nodes are not updated.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            When the <literal>TRUNCATE</literal> command is executed on a base table,
+               nothing is changed on the <acronym>IMMV</acronym>.
+          </para>
+        </listitem>
+
+    </itemizedlist>
+</para>
+</sect3>
+
+</sect2>
+
+<sect2>
+<title><literal>DISTINCT</literal></title>
+
+<para>
+    <productname>PostgreSQL</productname> supports <acronym>IMMV</acronym> with
+    <literal>DISTINCT</literal>.  For example, suppose a <acronym>IMMV</acronym>
+    defined with <literal>DISTINCT</literal> on a base table containing duplicate
+    tuples.  When tuples are deleted from the base table, a tuple in the view is
+    deleted if and only if the multiplicity of the tuple becomes zero.  Moreover,
+    when tuples are inserted into the base table, a tuple is inserted into the
+    view only if the same tuple doesn't already exist in it.
+</para>
+
+<para>
+    Physically, an <acronym>IMMV</acronym> defined with <literal>DISTINCT</literal>
+    contains tuples after eliminating duplicates, and the multiplicity of each tuple
+    is stored in a hidden column named <literal>__ivm_count__</literal>.
+</para>
+</sect2>
+
+<sect2>
+<title>Concurrent Transactions</title>
+<para>
+    Suppose an <acronym>IMMV</acronym> is defined on two base tables and each
+    table was modified in different a concurrent transaction simultaneously.
+    In the transaction which was committed first, <acronym>IMMV</acronym> can
+    be updated considering only the change which happened in this transaction.
+    On the other hand, in order to update the view correctly in the transaction
+    which was committed later, we need to know the changes occurred in
+    both transactions.  For this reason, <literal>ExclusiveLock</literal>
+    is held on an <acronym>IMMV</acronym> immediately after a base table is
+    modified in <literal>READ COMMITTED</literal> mode to make sure that
+    the <acronym>IMMV</acronym> is updated in the latter transaction after
+    the former transaction is committed.  In <literal>REPEATABLE READ</literal>
+    or <literal>SERIALIZABLE</literal> mode, an error is raised immediately
+    if lock acquisition fails because any changes which occurred in
+    other transactions are not be visible in these modes and
+    <acronym>IMMV</acronym> cannot be updated correctly in such situations.
+    However, as an exception if the view has only one base table, 
+    the lock held on thew view is <literal>RowExclusiveLock</literal>.
+</para>
+</sect2>
+
+<sect2>
+<title>Row Level Security</title>
+<para>
+    If some base tables have row level security policy, rows that are not visible
+    to the materialized view's owner are excluded from the result.  In addition, such
+    rows are excluded as well when views are incrementally maintained.  However, if a
+    new policy is defined or policies are changed after the materialized view was created,
+    the new policy will not be applied to the view contents.  To apply the new policy,
+    you need to refresh materialized views.
+</para>
+</sect2>
+
+</sect1>
+
 <sect1 id="rules-update">
 <title>Rules on <command>INSERT</command>, <command>UPDATE</command>, and <command>DELETE</command></title>
 
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_14_58_01_+0900_MN3L/o2YUVF2g4zw--





^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v32 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Tue_Apr__7_16_38_17_2020_299)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v32-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v40 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..b829167872 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..c337099061 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.4


----Next_Part(Wed_Nov__4_17_39_10_2020_208)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v40-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v36 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.4


----Next_Part(Tue_Sep__8_17_55_57_2020_197)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v36-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v41 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..b829167872 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..c337099061 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.4


----Next_Part(Fri_Nov__6_09_27_56_2020_738)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v41-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v30 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Wed_Apr__1_17_37_23_2020_570)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v30-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v37 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.4


----Next_Part(Fri_Sep_25_09_27_26_2020_419)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v37-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v43 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..b829167872 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..c337099061 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Dec_11_16_50_03_2020_915)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v43-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v44 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..b829167872 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..c337099061 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Mon_Dec_21_17_16_20_2020_608)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v44-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v38 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..b829167872 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..c337099061 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.4


----Next_Part(Thu_Oct__1_09_07_22_2020_252)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v38-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v33 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Thu_Apr_30_13_22_05_2020_409)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v33-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v57 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 1d1d5d2f0e..58ad2991a7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2961,6 +2961,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Thu_Mar_18_16_56_02_2021_947)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v57-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v29 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 150 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 170 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..fb7e23c4cb 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,146 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert (status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Also move parititon lock if needed */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		/* Move lock along with partition for the bucket */
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Lock the next partition then release the current, not in the
+			 * reverse order to avoid concurrent resizing. Partitions are
+			 * locked in the same order with resize() so dead locks won't
+			 * happen.
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..81a929b8d9 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;
+	int					curbucket;
+	int					nbuckets;
+	dshash_table_item  *curitem;
+	dsa_pointer			pnextitem;
+	int					curpartition;
+	bool				exclusive;
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Wed_Apr__1_15_15_11_2020_923)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v29-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v39 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..b829167872 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..c337099061 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.4


----Next_Part(Tue_Oct__6_10_06_44_2020_382)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v39-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v57 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 1d1d5d2f0e..58ad2991a7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2961,6 +2961,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Thu_Mar_18_16_56_02_2021_947)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v57-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v33 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Fri_May_15_17_30_36_2020_111)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v33-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v35 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Mon_Jun__8_17_32_04_2020_489)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v35-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v25 2/8] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 162 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 +++++
 2 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..2086bdbea9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -112,6 +112,7 @@ struct dshash_table
 	size_t		size_log2;		/* log2(number of buckets) */
 	bool		find_locked;	/* Is any partition lock held by 'find'? */
 	bool		find_exclusively_locked;	/* ... exclusively? */
+	bool		seqscan_running;/* now under sequential scan */
 };
 
 /* Given a pointer to an item, find the entry (user data) it holds. */
@@ -127,6 +128,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +158,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -228,6 +237,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg)
 
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
+	hash_table->seqscan_running = false;
 
 	/*
 	 * Set up the initial array of buckets.  Our initial size is the same as
@@ -279,6 +289,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params,
 	hash_table->control = dsa_get_address(area, control);
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
+	hash_table->seqscan_running = false;
 	Assert(hash_table->control->magic == DSHASH_MAGIC);
 
 	/*
@@ -324,7 +335,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -568,6 +579,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry)
 	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index),
 								hash_table->find_exclusively_locked
 								? LW_EXCLUSIVE : LW_SHARED));
+	/* lock is under control of sequential scan */
+	Assert(!hash_table->seqscan_running);
 
 	hash_table->find_locked = false;
 	hash_table->find_exclusively_locked = false;
@@ -592,6 +605,153 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	/* allowed at most one scan at once */
+	Assert(!hash_table->seqscan_running);
+
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+	hash_table->seqscan_running = true;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	Assert(status->hash_table->seqscan_running);
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert (status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Also move parititon lock if needed */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		/* Move lock along with partition for the bucket */
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Lock the next partition then release the current, not in the
+			 * reverse order to avoid concurrent resizing. Partitions are
+			 * locked in the same order with resize() so dead locks won't
+			 * happen.
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	Assert(status->hash_table->seqscan_running);
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+	status->hash_table->seqscan_running = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..81a929b8d9 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;
+	int					curbucket;
+	int					nbuckets;
+	dshash_table_item  *curitem;
+	dsa_pointer			pnextitem;
+	int					curpartition;
+	bool				exclusive;
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Thu_Mar_19_20_30_04_2020_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v25-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v31 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Fri_Apr__3_17_31_17_2020_104)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v31-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v34 2/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 149 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  21 ++++++
 2 files changed, 169 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..1ef093e2e9 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,145 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..0ca9514021 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,12 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.2


----Next_Part(Mon_Jun__1_18_00_01_2020_089)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v34-0003-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e4d2debb3c..21fd98af66 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v51 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v42 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 78ccf03217..b829167872 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b86df68e77..c337099061 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.18.4


----Next_Part(Wed_Nov_11_10_07_22_2020_796)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v42-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v49 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v47 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v46 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v56 1/6] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This commit
adds the functionality.  The interface is similar but a bit different
both from that of dynahash and simple dshash search functions.  One of
the most significant differences is the sequential scan interface of
dshash always needs a call to dshash_seq_term when scan ends. Another
is locking.  Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a scan.
The seqscan interface allows entry deletion while a scan is in
progress. The in-scan deletion should be performed by
dshash_delete_current().
---
 src/backend/lib/dshash.c         | 161 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..29ad767618 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,157 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition PG_USED_FOR_ASSERTS_ONLY
+		= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 61cf4eae1f..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2958,6 +2958,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v45 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c | 160 ++++++++++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h |  22 ++++++
 2 files changed, 181 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v50 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread

* [PATCH v48 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 230+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:58 UTC (permalink / raw)

Dshash did not allow scan the all entries sequentially. This adds the
functionality. The interface is similar but a bit different both from
that of dynahash and simple dshash search functions. One of the most
significant differences is the sequential scan interface of dshash
always needs a call to dshash_seq_term when scan ends. Another is
locking. Dshash holds partition lock when returning an entry,
dshash_seq_next() also holds lock when returning an entry but callers
shouldn't release it, since the lock is essential to continue a
scan. The seqscan interface allows entry deletion while a scan. The
in-scan deletion should be performed by dshash_delete_current().
---
 src/backend/lib/dshash.c         | 160 ++++++++++++++++++++++++++++++-
 src/include/lib/dshash.h         |  22 +++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 182 insertions(+), 1 deletion(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index e0c763be32..520bfa0979 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -127,6 +127,10 @@ struct dshash_table
 #define NUM_SPLITS(size_log2)					\
 	(size_log2 - DSHASH_NUM_PARTITIONS_LOG2)
 
+/* How many buckets are there in a given size? */
+#define NUM_BUCKETS(size_log2)		\
+	(((size_t) 1) << (size_log2))
+
 /* How many buckets are there in each partition at a given size? */
 #define BUCKETS_PER_PARTITION(size_log2)		\
 	(((size_t) 1) << NUM_SPLITS(size_log2))
@@ -153,6 +157,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)	\
 	((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)				\
+	((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)								\
 	(hash_table->buckets[												\
@@ -324,7 +332,7 @@ dshash_destroy(dshash_table *hash_table)
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Free all the entries. */
-	size = ((size_t) 1) << hash_table->size_log2;
+	size = NUM_BUCKETS(hash_table->size_log2);
 	for (i = 0; i < size; ++i)
 	{
 		dsa_pointer item_pointer = hash_table->buckets[i];
@@ -592,6 +600,156 @@ dshash_memhash(const void *v, size_t size, void *arg)
 	return tag_hash(v, size);
 }
 
+/*
+ * dshash_seq_init/_next/_term
+ *           Sequentially scan through dshash table and return all the
+ *           elements one by one, return NULL when no more.
+ *
+ * dshash_seq_term should always be called when a scan finished.
+ * The caller may delete returned elements midst of a scan by using
+ * dshash_delete_current(). exclusive must be true to delete elements.
+ */
+void
+dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+				bool exclusive)
+{
+	status->hash_table = hash_table;
+	status->curbucket = 0;
+	status->nbuckets = 0;
+	status->curitem = NULL;
+	status->pnextitem = InvalidDsaPointer;
+	status->curpartition = -1;
+	status->exclusive = exclusive;
+}
+
+/*
+ * Returns the next element.
+ *
+ * Returned elements are locked and the caller must not explicitly release
+ * it. It is released at the next call to dshash_next().
+ */
+void *
+dshash_seq_next(dshash_seq_status *status)
+{
+	dsa_pointer next_item_pointer;
+
+	if (status->curitem == NULL)
+	{
+		int partition;
+
+		Assert(status->curbucket == 0);
+		Assert(!status->hash_table->find_locked);
+
+		/* first shot. grab the first item. */
+		partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+		LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+					  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+		status->curpartition = partition;
+
+		/* resize doesn't happen from now until seq scan ends */
+		status->nbuckets =
+			NUM_BUCKETS(status->hash_table->control->size_log2);
+		ensure_valid_bucket_pointers(status->hash_table);
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+	else
+		next_item_pointer = status->pnextitem;
+
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(status->hash_table,
+											   status->curpartition),
+								status->exclusive ? LW_EXCLUSIVE : LW_SHARED));
+
+	/* Move to the next bucket if we finished the current bucket */
+	while (!DsaPointerIsValid(next_item_pointer))
+	{
+		int next_partition;
+
+		if (++status->curbucket >= status->nbuckets)
+		{
+			/* all buckets have been scanned. finish. */
+			return NULL;
+		}
+
+		/* Check if move to the next partition */
+		next_partition =
+			PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+									   status->hash_table->size_log2);
+
+		if (status->curpartition != next_partition)
+		{
+			/*
+			 * Move to the next partition. Lock the next partition then release
+			 * the current, not in the reverse order to avoid concurrent
+			 * resizing.  Avoid dead lock by taking lock in the same order
+			 * with resize().
+			 */
+			LWLockAcquire(PARTITION_LOCK(status->hash_table,
+										 next_partition),
+						  status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+			LWLockRelease(PARTITION_LOCK(status->hash_table,
+										 status->curpartition));
+			status->curpartition = next_partition;
+		}
+
+		next_item_pointer = status->hash_table->buckets[status->curbucket];
+	}
+
+	status->curitem =
+		dsa_get_address(status->hash_table->area, next_item_pointer);
+	status->hash_table->find_locked = true;
+	status->hash_table->find_exclusively_locked = status->exclusive;
+
+	/*
+	 * The caller may delete the item. Store the next item in case of deletion.
+	 */
+	status->pnextitem = status->curitem->next;
+
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
+/*
+ * Terminates the seqscan and release all locks.
+ *
+ * Should be always called when finishing or exiting a seqscan.
+ */
+void
+dshash_seq_term(dshash_seq_status *status)
+{
+	status->hash_table->find_locked = false;
+	status->hash_table->find_exclusively_locked = false;
+
+	if (status->curpartition >= 0)
+		LWLockRelease(PARTITION_LOCK(status->hash_table, status->curpartition));
+}
+
+/* Remove the current entry while a seq scan. */
+void
+dshash_delete_current(dshash_seq_status *status)
+{
+	dshash_table	   *hash_table	= status->hash_table;
+	dshash_table_item  *item		= status->curitem;
+	size_t				partition	= PARTITION_FOR_HASH(item->hash);
+
+	Assert(status->exclusive);
+	Assert(hash_table->control->magic == DSHASH_MAGIC);
+	Assert(hash_table->find_locked);
+	Assert(hash_table->find_exclusively_locked);
+	Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition),
+								LW_EXCLUSIVE));
+
+	delete_item(hash_table, item);
+}
+
+/* Get the current entry while a seq scan. */
+void *
+dshash_get_current(dshash_seq_status *status)
+{
+	return ENTRY_FROM_ITEM(status->curitem);
+}
+
 /*
  * Print debugging information about the internal state of the hash table to
  * stderr.  The caller must hold no partition locks.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index c069ec9de7..a6ea377173 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -59,6 +59,21 @@ typedef struct dshash_parameters
 struct dshash_table_item;
 typedef struct dshash_table_item dshash_table_item;
 
+/*
+ * Sequential scan state. The detail is exposed to let users know the storage
+ * size but it should be considered as an opaque type by callers.
+ */
+typedef struct dshash_seq_status
+{
+	dshash_table	   *hash_table;	/* dshash table working on */
+	int					curbucket;	/* bucket number we are at */
+	int					nbuckets;	/* total number of buckets in the dshash */
+	dshash_table_item  *curitem;	/* item we are currently at */
+	dsa_pointer			pnextitem;	/* dsa-pointer to the next item */
+	int					curpartition;	/* partition number we are at */
+	bool				exclusive;	/* locking mode */
+} dshash_seq_status;
+
 /* Creating, sharing and destroying from hash tables. */
 extern dshash_table *dshash_create(dsa_area *area,
 								   const dshash_parameters *params,
@@ -80,6 +95,13 @@ extern bool dshash_delete_key(dshash_table *hash_table, const void *key);
 extern void dshash_delete_entry(dshash_table *hash_table, void *entry);
 extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
+/* seq scan support */
+extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
+							bool exclusive);
+extern void *dshash_seq_next(dshash_seq_status *status);
+extern void dshash_seq_term(dshash_seq_status *status);
+extern void dshash_delete_current(dshash_seq_status *status);
+extern void *dshash_get_current(dshash_seq_status *status);
 /* Convenience hash and compare functions wrapping memcmp and tag_hash. */
 extern int	dshash_memcmp(const void *a, const void *b, size_t size, void *arg);
 extern dshash_hash dshash_memhash(const void *v, size_t size, void *arg);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8bd95aefa1..2b591e94e6 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2954,6 +2954,7 @@ dshash_hash
 dshash_hash_function
 dshash_parameters
 dshash_partition
+dshash_seq_status
 dshash_table
 dshash_table_control
 dshash_table_handle
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0002-Add-conditional-lock-feature-to-dshash.patch"



^ permalink  raw  reply  [nested|flat] 230+ messages in thread


end of thread, other threads:[~2020-03-13 07:58 UTC | newest]

Thread overview: 230+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2018-06-29 07:41 [PATCH 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2018-06-29 07:41 [PATCH v24 1/5] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2019-12-20 01:25 [PATCH v27 9/9] Add documentations about Incremental View Maintenance Yugo Nagata <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v32 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v40 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v36 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v41 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v30 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v37 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v43 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v44 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v38 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v33 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v57 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v29 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v39 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v57 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v33 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v35 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v25 2/8] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v31 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v34 2/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v51 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v42 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v49 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v47 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v46 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v56 1/6] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v45 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v50 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2020-03-13 07:58 [PATCH v48 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox