public inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v52 1/7] sequential scan for dshash
2+ messages / 2 participants
[nested] [flat]

* [PATCH v52 1/7] sequential scan for dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 2+ 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] 2+ messages in thread

* Re: Refactor calculations to use instr_time
@ 2023-02-17 10:53 Nazir Bilal Yavuz <[email protected]>
  0 siblings, 0 replies; 2+ messages in thread

From: Nazir Bilal Yavuz @ 2023-02-17 10:53 UTC (permalink / raw)
  To: Andres Freund <[email protected]>; +Cc: pgsql-hackers

Hi,


On 2/16/23 19:13, Andres Freund wrote:
>> +#define WALSTAT_ACC(fld, var_to_add) \
>> + 	(stats_shmem->stats.fld += var_to_add.fld)
>> +#define WALLSTAT_ACC_INSTR_TIME_TYPE(fld) \
>> +	(stats_shmem->stats.fld += INSTR_TIME_GET_MICROSEC(PendingWalStats.fld))
>> +	WALSTAT_ACC(wal_records, diff);
>> +	WALSTAT_ACC(wal_fpi, diff);
>> +	WALSTAT_ACC(wal_bytes, diff);
>> +	WALSTAT_ACC(wal_buffers_full, PendingWalStats);
>> +	WALSTAT_ACC(wal_write, PendingWalStats);
>> +	WALSTAT_ACC(wal_sync, PendingWalStats);
>> +	WALLSTAT_ACC_INSTR_TIME_TYPE(wal_write_time);
>> +	WALLSTAT_ACC_INSTR_TIME_TYPE(wal_sync_time);
>>   #undef WALSTAT_ACC
>> -
>>   	LWLockRelease(&stats_shmem->lock);
> WALSTAT_ACC is undefined, but WALLSTAT_ACC_INSTR_TIME_TYPE isn't.
>
> I'd not remove the newline before LWLockRelease().
>
>
>>   	/*
>> diff --git a/src/include/pgstat.h b/src/include/pgstat.h
>> index db9675884f3..295c5eabf38 100644
>> --- a/src/include/pgstat.h
>> +++ b/src/include/pgstat.h
>> @@ -445,6 +445,21 @@ typedef struct PgStat_WalStats
>>   	TimestampTz stat_reset_timestamp;
>>   } PgStat_WalStats;
>>   
>> +/* Created for accumulating wal_write_time and wal_sync_time as a
>> instr_time
> Minor code-formatting point: In postgres we don't put code in the same line as
> a multi-line comment starting with the /*. So either
>
> /* single line comment */
> or
> /*
>   * multi line
>   * comment
>   */


Thanks for the review. I updated the patch.


Regards,
Nazir Bilal Yavuz
Microsoft




Attachments:

  [text/x-diff] v2-0001-Refactor-instr_time-calculations.patch (5.2K, ../../[email protected]/3-v2-0001-Refactor-instr_time-calculations.patch)
  download | inline diff:
From e3723aca8b79b07190834b0cfd1440dbbf706862 Mon Sep 17 00:00:00 2001
From: Nazir Bilal Yavuz <[email protected]>
Date: Thu, 2 Feb 2023 15:06:48 +0300
Subject: [PATCH v2] Refactor instr_time calculations

---
 src/backend/access/transam/xlog.c       |  6 ++----
 src/backend/storage/file/buffile.c      |  6 ++----
 src/backend/utils/activity/pgstat_wal.c | 27 +++++++++++++------------
 src/include/pgstat.h                    | 18 ++++++++++++++++-
 4 files changed, 35 insertions(+), 22 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index f9f0f6db8d1..3c35dc1ca23 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -2206,8 +2206,7 @@ XLogWrite(XLogwrtRqst WriteRqst, TimeLineID tli, bool flexible)
 					instr_time	duration;
 
 					INSTR_TIME_SET_CURRENT(duration);
-					INSTR_TIME_SUBTRACT(duration, start);
-					PendingWalStats.wal_write_time += INSTR_TIME_GET_MICROSEC(duration);
+					INSTR_TIME_ACCUM_DIFF(PendingWalStats.wal_write_time, duration, start);
 				}
 
 				PendingWalStats.wal_write++;
@@ -8201,8 +8200,7 @@ issue_xlog_fsync(int fd, XLogSegNo segno, TimeLineID tli)
 		instr_time	duration;
 
 		INSTR_TIME_SET_CURRENT(duration);
-		INSTR_TIME_SUBTRACT(duration, start);
-		PendingWalStats.wal_sync_time += INSTR_TIME_GET_MICROSEC(duration);
+		INSTR_TIME_ACCUM_DIFF(PendingWalStats.wal_sync_time, duration, start);
 	}
 
 	PendingWalStats.wal_sync++;
diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c
index 0a51624df3b..e55f86b675e 100644
--- a/src/backend/storage/file/buffile.c
+++ b/src/backend/storage/file/buffile.c
@@ -469,8 +469,7 @@ BufFileLoadBuffer(BufFile *file)
 	if (track_io_timing)
 	{
 		INSTR_TIME_SET_CURRENT(io_time);
-		INSTR_TIME_SUBTRACT(io_time, io_start);
-		INSTR_TIME_ADD(pgBufferUsage.temp_blk_read_time, io_time);
+		INSTR_TIME_ACCUM_DIFF(pgBufferUsage.temp_blk_read_time, io_time, io_start);
 	}
 
 	/* we choose not to advance curOffset here */
@@ -544,8 +543,7 @@ BufFileDumpBuffer(BufFile *file)
 		if (track_io_timing)
 		{
 			INSTR_TIME_SET_CURRENT(io_time);
-			INSTR_TIME_SUBTRACT(io_time, io_start);
-			INSTR_TIME_ADD(pgBufferUsage.temp_blk_write_time, io_time);
+			INSTR_TIME_ACCUM_DIFF(pgBufferUsage.temp_blk_write_time, io_time, io_start);
 		}
 
 		file->curOffset += bytestowrite;
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
index e8598b2f4e0..ab2869a0e24 100644
--- a/src/backend/utils/activity/pgstat_wal.c
+++ b/src/backend/utils/activity/pgstat_wal.c
@@ -21,7 +21,7 @@
 #include "executor/instrument.h"
 
 
-PgStat_WalStats PendingWalStats = {0};
+PgStat_PendingWalUsage PendingWalStats = {0};
 
 /*
  * WAL usage counters saved from pgWALUsage at the previous call to
@@ -89,24 +89,25 @@ pgstat_flush_wal(bool nowait)
 	 * previous counters from the current ones.
 	 */
 	WalUsageAccumDiff(&diff, &pgWalUsage, &prevWalUsage);
-	PendingWalStats.wal_records = diff.wal_records;
-	PendingWalStats.wal_fpi = diff.wal_fpi;
-	PendingWalStats.wal_bytes = diff.wal_bytes;
 
 	if (!nowait)
 		LWLockAcquire(&stats_shmem->lock, LW_EXCLUSIVE);
 	else if (!LWLockConditionalAcquire(&stats_shmem->lock, LW_EXCLUSIVE))
 		return true;
 
-#define WALSTAT_ACC(fld) stats_shmem->stats.fld += PendingWalStats.fld
-	WALSTAT_ACC(wal_records);
-	WALSTAT_ACC(wal_fpi);
-	WALSTAT_ACC(wal_bytes);
-	WALSTAT_ACC(wal_buffers_full);
-	WALSTAT_ACC(wal_write);
-	WALSTAT_ACC(wal_sync);
-	WALSTAT_ACC(wal_write_time);
-	WALSTAT_ACC(wal_sync_time);
+#define WALSTAT_ACC(fld, var_to_add) \
+ 	(stats_shmem->stats.fld += var_to_add.fld)
+#define WALLSTAT_ACC_INSTR_TIME_TYPE(fld) \
+	(stats_shmem->stats.fld += INSTR_TIME_GET_MICROSEC(PendingWalStats.fld))
+	WALSTAT_ACC(wal_records, diff);
+	WALSTAT_ACC(wal_fpi, diff);
+	WALSTAT_ACC(wal_bytes, diff);
+	WALSTAT_ACC(wal_buffers_full, PendingWalStats);
+	WALSTAT_ACC(wal_write, PendingWalStats);
+	WALSTAT_ACC(wal_sync, PendingWalStats);
+	WALLSTAT_ACC_INSTR_TIME_TYPE(wal_write_time);
+	WALLSTAT_ACC_INSTR_TIME_TYPE(wal_sync_time);
+#undef WALLSTAT_ACC_INSTR_TIME_TYPE
 #undef WALSTAT_ACC
 
 	LWLockRelease(&stats_shmem->lock);
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index db9675884f3..cc103df7d2e 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -445,6 +445,22 @@ typedef struct PgStat_WalStats
 	TimestampTz stat_reset_timestamp;
 } PgStat_WalStats;
 
+/*
+ * Created for accumulating wal_write_time and wal_sync_time as a instr_time
+ * but instr_time can't be used as a type where it ends up on-disk
+ * because its units may change. PgStat_WalStats type is used for
+ * in-memory/on-disk data. So, PgStat_PendingWalUsage is created for
+ * accumulating intervals as a instr_time.
+ */
+typedef struct PgStat_PendingWalUsage
+{
+	PgStat_Counter wal_buffers_full;
+	PgStat_Counter wal_write;
+	PgStat_Counter wal_sync;
+	instr_time wal_write_time;
+	instr_time wal_sync_time;
+} PgStat_PendingWalUsage;
+
 
 /*
  * Functions in pgstat.c
@@ -758,7 +774,7 @@ extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
  */
 
 /* updated directly by backends and background processes */
-extern PGDLLIMPORT PgStat_WalStats PendingWalStats;
+extern PGDLLIMPORT PgStat_PendingWalUsage PendingWalStats;
 
 
 #endif							/* PGSTAT_H */
-- 
2.39.1



^ permalink  raw  reply  [nested|flat] 2+ messages in thread


end of thread, other threads:[~2023-02-17 10:53 UTC | newest]

Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-03-13 07:58 [PATCH v52 1/7] sequential scan for dshash Kyotaro Horiguchi <[email protected]>
2023-02-17 10:53 Re: Refactor calculations to use instr_time Nazir Bilal Yavuz <[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