public inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v46 2/7] Add conditional lock feature to dshash
3+ messages / 3 participants
[nested] [flat]

* [PATCH v46 2/7] Add conditional lock feature to dshash
@ 2020-03-13 07:58 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 3+ messages in thread

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

Dshash currently waits for lock unconditionally. It is inconvenient
when we want to avoid being blocked by other processes. This commit
adds alternative functions of dshash_find and dshash_find_or_insert
that allows immediate return on lock failure.
---
 src/backend/lib/dshash.c | 98 +++++++++++++++++++++-------------------
 src/include/lib/dshash.h |  3 ++
 2 files changed, 55 insertions(+), 46 deletions(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 520bfa0979..853d78b528 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -383,6 +383,10 @@ dshash_get_hash_table_handle(dshash_table *hash_table)
  * the caller must take care to ensure that the entry is not left corrupted.
  * The lock mode is either shared or exclusive depending on 'exclusive'.
  *
+ * If found is not NULL, *found is set to true if the key is found in the hash
+ * table. If the key is not found, *found is set to false and a pointer to a
+ * newly created entry is returned.
+ *
  * The caller must not lock a lock already.
  *
  * Note that the lock held is in fact an LWLock, so interrupts will be held on
@@ -392,36 +396,7 @@ dshash_get_hash_table_handle(dshash_table *hash_table)
 void *
 dshash_find(dshash_table *hash_table, const void *key, bool exclusive)
 {
-	dshash_hash hash;
-	size_t		partition;
-	dshash_table_item *item;
-
-	hash = hash_key(hash_table, key);
-	partition = PARTITION_FOR_HASH(hash);
-
-	Assert(hash_table->control->magic == DSHASH_MAGIC);
-	Assert(!hash_table->find_locked);
-
-	LWLockAcquire(PARTITION_LOCK(hash_table, partition),
-				  exclusive ? LW_EXCLUSIVE : LW_SHARED);
-	ensure_valid_bucket_pointers(hash_table);
-
-	/* Search the active bucket. */
-	item = find_in_bucket(hash_table, key, BUCKET_FOR_HASH(hash_table, hash));
-
-	if (!item)
-	{
-		/* Not found. */
-		LWLockRelease(PARTITION_LOCK(hash_table, partition));
-		return NULL;
-	}
-	else
-	{
-		/* The caller will free the lock by calling dshash_release_lock. */
-		hash_table->find_locked = true;
-		hash_table->find_exclusively_locked = exclusive;
-		return ENTRY_FROM_ITEM(item);
-	}
+	return dshash_find_extended(hash_table, key, exclusive, false, false, NULL);
 }
 
 /*
@@ -439,31 +414,60 @@ dshash_find_or_insert(dshash_table *hash_table,
 					  const void *key,
 					  bool *found)
 {
-	dshash_hash hash;
-	size_t		partition_index;
-	dshash_partition *partition;
+	return dshash_find_extended(hash_table, key, true, false, true, found);
+}
+
+
+/*
+ * Find the key in the hash table.
+ *
+ * "exclusive" is the lock mode in which the partition for the returned item
+ * is locked.  If "nowait" is true, the function immediately returns if
+ * required lock was not acquired.  "insert" indicates insert mode. In this
+ * mode new entry is inserted and set *found to false. *found is set to true if
+ * found. "found" must be non-null in this mode.
+ */
+void *
+dshash_find_extended(dshash_table *hash_table, const void *key,
+					 bool exclusive, bool nowait, bool insert, bool *found)
+{
+	dshash_hash hash = hash_key(hash_table, key);
+	size_t		partidx = PARTITION_FOR_HASH(hash);
+	dshash_partition *partition = &hash_table->control->partitions[partidx];
+	LWLockMode  lockmode = exclusive ? LW_EXCLUSIVE : LW_SHARED;
 	dshash_table_item *item;
 
-	hash = hash_key(hash_table, key);
-	partition_index = PARTITION_FOR_HASH(hash);
-	partition = &hash_table->control->partitions[partition_index];
-
-	Assert(hash_table->control->magic == DSHASH_MAGIC);
-	Assert(!hash_table->find_locked);
+	/* must be exclusive when insert allowed */
+	Assert(!insert || (exclusive && found != NULL));
 
 restart:
-	LWLockAcquire(PARTITION_LOCK(hash_table, partition_index),
-				  LW_EXCLUSIVE);
+	if (!nowait)
+		LWLockAcquire(PARTITION_LOCK(hash_table, partidx), lockmode);
+	else if (!LWLockConditionalAcquire(PARTITION_LOCK(hash_table, partidx),
+									   lockmode))
+		return NULL;
+
 	ensure_valid_bucket_pointers(hash_table);
 
 	/* Search the active bucket. */
 	item = find_in_bucket(hash_table, key, BUCKET_FOR_HASH(hash_table, hash));
 
 	if (item)
-		*found = true;
+	{
+		if (found)
+			*found = true;
+	}
 	else
 	{
-		*found = false;
+		if (found)
+			*found = false;
+
+		if (!insert)
+		{
+			/* The caller didn't told to add a new entry. */
+			LWLockRelease(PARTITION_LOCK(hash_table, partidx));
+			return NULL;
+		}
 
 		/* Check if we are getting too full. */
 		if (partition->count > MAX_COUNT_PER_PARTITION(hash_table))
@@ -479,7 +483,8 @@ restart:
 			 * Give up our existing lock first, because resizing needs to
 			 * reacquire all the locks in the right order to avoid deadlocks.
 			 */
-			LWLockRelease(PARTITION_LOCK(hash_table, partition_index));
+			LWLockRelease(PARTITION_LOCK(hash_table, partidx));
+
 			resize(hash_table, hash_table->size_log2 + 1);
 
 			goto restart;
@@ -493,12 +498,13 @@ restart:
 		++partition->count;
 	}
 
-	/* The caller must release the lock with dshash_release_lock. */
+	/* The caller will free the lock by calling dshash_release_lock. */
 	hash_table->find_locked = true;
-	hash_table->find_exclusively_locked = true;
+	hash_table->find_exclusively_locked = exclusive;
 	return ENTRY_FROM_ITEM(item);
 }
 
+
 /*
  * Remove an entry by key.  Returns true if the key was found and the
  * corresponding entry was removed.
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index a6ea377173..5b8114d041 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -91,6 +91,9 @@ extern void *dshash_find(dshash_table *hash_table,
 						 const void *key, bool exclusive);
 extern void *dshash_find_or_insert(dshash_table *hash_table,
 								   const void *key, bool *found);
+extern void *dshash_find_extended(dshash_table *hash_table, const void *key,
+								  bool exclusive, bool nowait, bool insert,
+								  bool *found);
 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);
-- 
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="v46-0003-Make-archiver-process-an-auxiliary-process.patch"



^ permalink  raw  reply  [nested|flat] 3+ messages in thread

* pg_waldump vs. all-zeros WAL files; server creation of such files
@ 2023-08-13 03:15 Noah Misch <[email protected]>
  2023-08-14 01:37 ` Re: pg_waldump vs. all-zeros WAL files; server creation of such files Michael Paquier <[email protected]>
  0 siblings, 1 reply; 3+ messages in thread

From: Noah Misch @ 2023-08-13 03:15 UTC (permalink / raw)
  To: pgsql-hackers

The attached 010_zero.pl, when run as part of the pg_waldump test suite, fails
at today's master (c36b636) and v15 (1bc19df).  It passes at v14 (5a32af3).
Command "pg_waldump --start 0/01000000 --end 0/01000100" fails as follows:

  pg_waldump: error: WAL segment size must be a power of two between 1 MB and 1 GB, but the WAL file "000000010000000000000002" header specifies 0 bytes

Where it fails, the server has created an all-zeros WAL file under that name.
Where it succeeds, that file doesn't exist at all.  Two decisions to make:

- Should a clean server shutdown ever leave an all-zeros WAL file?  I think
  yes, it's okay to let that happen.
- Should "pg_waldump --start $X --end $Y" open files not needed for the
  requested range?  I think no.

Bisect of master got:
30a53b7 Wed Mar 8 16:56:37 2023 +0100 Allow tailoring of ICU locales with custom rules
Doesn't fail at $(git merge-base REL_15_STABLE master).  Bisect of v15 got:
811203d Sat Aug 6 11:50:23 2022 -0400 Fix data-corruption hazard in WAL-logged CREATE DATABASE.

I suspect those are innocent.  They changed the exact WAL content, which I
expect somehow caused creation of segment 2.

Oddly, I find only one other report of this:
https://www.postgresql.org/message-id/CAJ6DU3HiJ5FHbqPua19jAD%3DwLgiXBTjuHfbmv1jCOaNOpB3cCQ%40mail.g...

Thanks,
nm


Attachments:

  [application/x-perl] 010_zero.pl (545B, ../../[email protected]/2-010_zero.pl)
  download

^ permalink  raw  reply  [nested|flat] 3+ messages in thread

* Re: pg_waldump vs. all-zeros WAL files; server creation of such files
  2023-08-13 03:15 pg_waldump vs. all-zeros WAL files; server creation of such files Noah Misch <[email protected]>
@ 2023-08-14 01:37 ` Michael Paquier <[email protected]>
  0 siblings, 0 replies; 3+ messages in thread

From: Michael Paquier @ 2023-08-14 01:37 UTC (permalink / raw)
  To: Noah Misch <[email protected]>; +Cc: pgsql-hackers

On Sat, Aug 12, 2023 at 08:15:31PM -0700, Noah Misch wrote:
> The attached 010_zero.pl, when run as part of the pg_waldump test suite, fails
> at today's master (c36b636) and v15 (1bc19df).  It passes at v14 (5a32af3).
> Command "pg_waldump --start 0/01000000 --end 0/01000100" fails as follows:
> 
>   pg_waldump: error: WAL segment size must be a power of two between
>   1 MB and 1 GB, but the WAL file "000000010000000000000002" header
>   specifies 0 bytes

So this depends on the ordering of the entries retrieved by readdir()
as much as the segments produced by the backend.

> Where it fails, the server has created an all-zeros WAL file under that name.
> Where it succeeds, that file doesn't exist at all.  Two decisions to make:
> 
> - Should a clean server shutdown ever leave an all-zeros WAL file?  I think
>   yes, it's okay to let that happen.

It doesn't hurt to leave that around.  On the contrary, it makes any
follow-up startup cheaper the bigger the segment size.

> - Should "pg_waldump --start $X --end $Y" open files not needed for the
>   requested range?  I think no.

So this is a case where identify_target_directory() is called with a
fname of NULL.  Agreed that search_directory could be smarter with the
files it should scan, especially if we have start and/or end LSNs at
hand to filter out what we'd like to be in the data folder.
--
Michael


Attachments:

  [application/pgp-signature] signature.asc (833B, ../../[email protected]/2-signature.asc)
  download

^ permalink  raw  reply  [nested|flat] 3+ messages in thread


end of thread, other threads:[~2023-08-14 01:37 UTC | newest]

Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-03-13 07:58 [PATCH v46 2/7] Add conditional lock feature to dshash Kyotaro Horiguchi <[email protected]>
2023-08-13 03:15 pg_waldump vs. all-zeros WAL files; server creation of such files Noah Misch <[email protected]>
2023-08-14 01:37 ` Re: pg_waldump vs. all-zeros WAL files; server creation of such files Michael Paquier <[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