В Вс, 13/03/2022 в 07:05 -0700, Zhihong Yu пишет:
>
> Hi,
> In the description:
>
> There is no need to hold both lock simultaneously.
>
> both lock -> both locks
Thanks.
> + * We also reset the usage_count since any recency of use of the old
>
> recency of use -> recent use
Thanks.
> +BufTableDelete(BufferTag *tagPtr, uint32 hashcode, bool reuse)
>
> Later on, there is code:
>
> + reuse ? HASH_REUSE : HASH_REMOVE,
>
> Can flag (such as HASH_REUSE) be passed to BufTableDelete() instead of bool ?
> That way, flag can be used directly in the above place.
No.
BufTable* functions are created to abstract Buffer Table from dynahash.
Pass of HASH_REUSE directly will break abstraction.
> + long nalloced; /* number of entries initially allocated for
>
> nallocated isn't very long. I think it would be better to name the field
> nallocated 'nallocated'.
It is debatable.
Why not num_allocated? allocated_count? number_of_allocations?
Same points for nfree.
`nalloced` is recognizable and unambiguous. And there are a lot
of `*alloced` in the postgresql's source, so this one will not
be unusual.
I don't see the need to make it longer.
But if someone supports your point, I will not mind to changing
the name.
> + sum += hashp->hctl->freeList[i].nalloced;
> + sum -= hashp->hctl->freeList[i].nfree;
>
> I think it would be better to calculate the difference between nalloced and
> nfree first, then add the result to sum (to avoid overflow).
Doesn't really matter much, because calculation must be valid
even if all nfree==0.
I'd rather debate use of 'long' in dynahash at all: 'long' is
32bit on 64bit Windows. It is better to use 'Size' here.
But 'nelements' were 'long', so I didn't change things. I think
it is place for another patch.
(On the other hand, dynahash with 2**31 elements is at least
512GB RAM... we doubtfully trigger problem before OOM killer
came. Does Windows have an OOM killer?)
> Subject: [PATCH 3/3] reduce memory allocation for non-partitioned dynahash
>
> memory allocation -> memory allocations
For each dynahash instance single allocation were reduced.
I think, 'memory allocation' is correct.
Plural will be
reduce memory allocations for non-partitioned dynahashes
ie both 'allocations' and 'dynahashes'.
Am I wrong?
------
regards
Yura Sokolov
From 68800f6f02f062320e6d9fe42c986809a06a37cb Mon Sep 17 00:00:00 2001
From: Yura Sokolov <y.soko...@postgrespro.ru>
Date: Mon, 21 Feb 2022 08:49:03 +0300
Subject: [PATCH 1/3] bufmgr: do not acquire two partition locks.
Acquiring two partition locks leads to complex dependency chain that hurts
at high concurrency level.
There is no need to hold both locks simultaneously. Buffer is pinned so
other processes could not select it for eviction. If tag is cleared and
buffer removed from old partition other processes will not find it.
Therefore it is safe to release old partition lock before acquiring
new partition lock.
---
src/backend/storage/buffer/bufmgr.c | 198 ++++++++++++++--------------
1 file changed, 96 insertions(+), 102 deletions(-)
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index f5459c68f89..f7dbfc90aaa 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -1275,8 +1275,9 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
}
/*
- * To change the association of a valid buffer, we'll need to have
- * exclusive lock on both the old and new mapping partitions.
+ * To change the association of a valid buffer, we'll need to reset
+ * tag first, so we need to have exclusive lock on the old mapping
+ * partitions.
*/
if (oldFlags & BM_TAG_VALID)
{
@@ -1289,93 +1290,16 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
oldHash = BufTableHashCode(&oldTag);
oldPartitionLock = BufMappingPartitionLock(oldHash);
- /*
- * Must lock the lower-numbered partition first to avoid
- * deadlocks.
- */
- if (oldPartitionLock < newPartitionLock)
- {
- LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
- LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
- }
- else if (oldPartitionLock > newPartitionLock)
- {
- LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
- LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
- }
- else
- {
- /* only one partition, only one lock */
- LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
- }
+ LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
}
else
{
- /* if it wasn't valid, we need only the new partition */
- LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
/* remember we have no old-partition lock or tag */
oldPartitionLock = NULL;
/* keep the compiler quiet about uninitialized variables */
oldHash = 0;
}
- /*
- * Try to make a hashtable entry for the buffer under its new tag.
- * This could fail because while we were writing someone else
- * allocated another buffer for the same block we want to read in.
- * Note that we have not yet removed the hashtable entry for the old
- * tag.
- */
- buf_id = BufTableInsert(&newTag, newHash, buf->buf_id);
-
- if (buf_id >= 0)
- {
- /*
- * Got a collision. Someone has already done what we were about to
- * do. We'll just handle this as if it were found in the buffer
- * pool in the first place. First, give up the buffer we were
- * planning to use.
- */
- UnpinBuffer(buf, true);
-
- /* Can give up that buffer's mapping partition lock now */
- if (oldPartitionLock != NULL &&
- oldPartitionLock != newPartitionLock)
- LWLockRelease(oldPartitionLock);
-
- /* remaining code should match code at top of routine */
-
- buf = GetBufferDescriptor(buf_id);
-
- valid = PinBuffer(buf, strategy);
-
- /* Can release the mapping lock as soon as we've pinned it */
- LWLockRelease(newPartitionLock);
-
- *foundPtr = true;
-
- if (!valid)
- {
- /*
- * We can only get here if (a) someone else is still reading
- * in the page, or (b) a previous read attempt failed. We
- * have to wait for any active read attempt to finish, and
- * then set up our own read attempt if the page is still not
- * BM_VALID. StartBufferIO does it all.
- */
- if (StartBufferIO(buf, true))
- {
- /*
- * If we get here, previous attempts to read the buffer
- * must have failed ... but we shall bravely try again.
- */
- *foundPtr = false;
- }
- }
-
- return buf;
- }
-
/*
* Need to lock the buffer header too in order to change its tag.
*/
@@ -1383,40 +1307,117 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
/*
* Somebody could have pinned or re-dirtied the buffer while we were
- * doing the I/O and making the new hashtable entry. If so, we can't
- * recycle this buffer; we must undo everything we've done and start
- * over with a new victim buffer.
+ * doing the I/O. If so, we can't recycle this buffer; we must undo
+ * everything we've done and start over with a new victim buffer.
*/
oldFlags = buf_state & BUF_FLAG_MASK;
if (BUF_STATE_GET_REFCOUNT(buf_state) == 1 && !(oldFlags & BM_DIRTY))
break;
UnlockBufHdr(buf, buf_state);
- BufTableDelete(&newTag, newHash);
- if (oldPartitionLock != NULL &&
- oldPartitionLock != newPartitionLock)
+ if (oldPartitionLock != NULL)
LWLockRelease(oldPartitionLock);
- LWLockRelease(newPartitionLock);
UnpinBuffer(buf, true);
}
/*
- * Okay, it's finally safe to rename the buffer.
+ * We are single pinner, we hold buffer header lock and exclusive
+ * partition lock (if tag is valid). It means no other process can inspect
+ * it at the moment.
*
- * Clearing BM_VALID here is necessary, clearing the dirtybits is just
- * paranoia. We also reset the usage_count since any recency of use of
- * the old content is no longer relevant. (The usage_count starts out at
- * 1 so that the buffer can survive one clock-sweep pass.)
+ * But we will release partition lock and buffer header lock. We must be
+ * sure other backend will not use this buffer until we reuse it for new
+ * tag. Therefore, we clear out the buffer's tag and flags and remove it
+ * from buffer table. Also buffer remains pinned to ensure
+ * StrategyGetBuffer will not try to reuse the buffer concurrently.
+ *
+ * We also reset the usage_count since any recent use of the old
+ * content is no longer relevant.
+ */
+ CLEAR_BUFFERTAG(buf->tag);
+ buf_state &= ~(BUF_FLAG_MASK | BUF_USAGECOUNT_MASK);
+ UnlockBufHdr(buf, buf_state);
+
+ /* Delete old tag from hash table if it were valid. */
+ if (oldFlags & BM_TAG_VALID)
+ BufTableDelete(&oldTag, oldHash);
+
+ if (oldPartitionLock != newPartitionLock)
+ {
+ if (oldPartitionLock != NULL)
+ LWLockRelease(oldPartitionLock);
+ LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
+ }
+
+ /*
+ * Try to make a hashtable entry for the buffer under its new tag. This
+ * could fail because while we were writing someone else allocated another
+ * buffer for the same block we want to read in. In that case we will have
+ * to return our buffer to free list.
+ */
+ buf_id = BufTableInsert(&newTag, newHash, buf->buf_id);
+
+ if (buf_id >= 0)
+ {
+ /*
+ * Got a collision. Someone has already done what we were about to do.
+ * We'll just handle this as if it were found in the buffer pool in
+ * the first place.
+ */
+
+ /*
+ * First, give up the buffer we were planning to use and put it to
+ * free lists.
+ */
+ UnpinBuffer(buf, true);
+ StrategyFreeBuffer(buf);
+
+ /* remaining code should match code at top of routine */
+
+ buf = GetBufferDescriptor(buf_id);
+
+ valid = PinBuffer(buf, strategy);
+
+ /* Can release the mapping lock as soon as we've pinned it */
+ LWLockRelease(newPartitionLock);
+
+ *foundPtr = true;
+
+ if (!valid)
+ {
+ /*
+ * We can only get here if (a) someone else is still reading in
+ * the page, or (b) a previous read attempt failed. We have to
+ * wait for any active read attempt to finish, and then set up our
+ * own read attempt if the page is still not BM_VALID.
+ * StartBufferIO does it all.
+ */
+ if (StartBufferIO(buf, true))
+ {
+ /*
+ * If we get here, previous attempts to read the buffer must
+ * have failed ... but we shall bravely try again.
+ */
+ *foundPtr = false;
+ }
+ }
+
+ return buf;
+ }
+
+ /*
+ * Now reuse victim buffer for new tag.
*
* Make sure BM_PERMANENT is set for buffers that must be written at every
* checkpoint. Unlogged buffers only need to be written at shutdown
* checkpoints, except for their "init" forks, which need to be treated
* just like permanent relations.
+ *
+ * The usage_count starts out at 1 so that the buffer can survive one
+ * clock-sweep pass.
*/
+ buf_state = LockBufHdr(buf);
buf->tag = newTag;
- buf_state &= ~(BM_VALID | BM_DIRTY | BM_JUST_DIRTIED |
- BM_CHECKPOINT_NEEDED | BM_IO_ERROR | BM_PERMANENT |
- BUF_USAGECOUNT_MASK);
if (relpersistence == RELPERSISTENCE_PERMANENT || forkNum == INIT_FORKNUM)
buf_state |= BM_TAG_VALID | BM_PERMANENT | BUF_USAGECOUNT_ONE;
else
@@ -1424,13 +1425,6 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
UnlockBufHdr(buf, buf_state);
- if (oldPartitionLock != NULL)
- {
- BufTableDelete(&oldTag, oldHash);
- if (oldPartitionLock != newPartitionLock)
- LWLockRelease(oldPartitionLock);
- }
-
LWLockRelease(newPartitionLock);
/*
--
2.35.1
From 34b323bf5a26041cd2763a551a976ef043d152f8 Mon Sep 17 00:00:00 2001
From: Yura Sokolov <y.soko...@postgrespro.ru>
Date: Mon, 28 Feb 2022 12:19:17 +0300
Subject: [PATCH 2/3] Add HASH_REUSE and use it in BufTable.
Avoid dynahash's freelist locking when BufferAlloc reuses buffer for
different tag.
HASH_REUSE acts as HASH_REMOVE, but stores element to reuse in static
variable instead of freelist partition. And HASH_ENTER then may use the
element.
Unfortunately, FreeListData->nentries had to be manipulated even in this
case. So instead of manipulation with nentries, we replace nentries with
nfree - actual length of free list, and nalloced - initially allocated
entries for free list. This were suggested by Robert Haas in
https://postgr.es/m/CA%2BTgmoZkg-04rcNRURt%3DjAG0Cs5oPyB-qKxH4wqX09e-oXy-nw%40mail.gmail.com
---
src/backend/storage/buffer/buf_table.c | 7 +-
src/backend/storage/buffer/bufmgr.c | 4 +-
src/backend/utils/hash/dynahash.c | 126 ++++++++++++++++++++-----
src/include/storage/buf_internals.h | 2 +-
src/include/utils/hsearch.h | 3 +-
5 files changed, 113 insertions(+), 29 deletions(-)
diff --git a/src/backend/storage/buffer/buf_table.c b/src/backend/storage/buffer/buf_table.c
index dc439940faa..c189555751e 100644
--- a/src/backend/storage/buffer/buf_table.c
+++ b/src/backend/storage/buffer/buf_table.c
@@ -143,10 +143,13 @@ BufTableInsert(BufferTag *tagPtr, uint32 hashcode, int buf_id)
* BufTableDelete
* Delete the hashtable entry for given tag (which must exist)
*
+ * If reuse flag is true, deleted entry is cached for reuse, and caller
+ * must call BufTableInsert next.
+ *
* Caller must hold exclusive lock on BufMappingLock for tag's partition
*/
void
-BufTableDelete(BufferTag *tagPtr, uint32 hashcode)
+BufTableDelete(BufferTag *tagPtr, uint32 hashcode, bool reuse)
{
BufferLookupEnt *result;
@@ -154,7 +157,7 @@ BufTableDelete(BufferTag *tagPtr, uint32 hashcode)
hash_search_with_hash_value(SharedBufHash,
(void *) tagPtr,
hashcode,
- HASH_REMOVE,
+ reuse ? HASH_REUSE : HASH_REMOVE,
NULL);
if (!result) /* shouldn't happen */
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index f7dbfc90aaa..a16da37fe3d 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -1340,7 +1340,7 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
/* Delete old tag from hash table if it were valid. */
if (oldFlags & BM_TAG_VALID)
- BufTableDelete(&oldTag, oldHash);
+ BufTableDelete(&oldTag, oldHash, true);
if (oldPartitionLock != newPartitionLock)
{
@@ -1534,7 +1534,7 @@ retry:
* Remove the buffer from the lookup hashtable, if it was in there.
*/
if (oldFlags & BM_TAG_VALID)
- BufTableDelete(&oldTag, oldHash);
+ BufTableDelete(&oldTag, oldHash, false);
/*
* Done with mapping lock.
diff --git a/src/backend/utils/hash/dynahash.c b/src/backend/utils/hash/dynahash.c
index 3babde8d704..0cb35a0faf9 100644
--- a/src/backend/utils/hash/dynahash.c
+++ b/src/backend/utils/hash/dynahash.c
@@ -14,7 +14,7 @@
* a hash table in partitioned mode, the HASH_PARTITION flag must be given
* to hash_create. This prevents any attempt to split buckets on-the-fly.
* Therefore, each hash bucket chain operates independently, and no fields
- * of the hash header change after init except nentries and freeList.
+ * of the hash header change after init except nfree and freeList.
* (A partitioned table uses multiple copies of those fields, guarded by
* spinlocks, for additional concurrency.)
* This lets any subset of the hash buckets be treated as a separately
@@ -138,8 +138,9 @@ typedef HASHBUCKET *HASHSEGMENT;
*
* In a partitioned hash table, each freelist is associated with a specific
* set of hashcodes, as determined by the FREELIST_IDX() macro below.
- * nentries tracks the number of live hashtable entries having those hashcodes
- * (NOT the number of entries in the freelist, as you might expect).
+ * nalloced tracks the number of free hashtable entries initially allocated
+ * for the freelist.
+ * nfree tracks the actual number of free hashtable entries in the freelist.
*
* The coverage of a freelist might be more or less than one partition, so it
* needs its own lock rather than relying on caller locking. Relying on that
@@ -147,13 +148,15 @@ typedef HASHBUCKET *HASHSEGMENT;
* need to "borrow" entries from another freelist; see get_hash_entry().
*
* Using an array of FreeListData instead of separate arrays of mutexes,
- * nentries and freeLists helps to reduce sharing of cache lines between
+ * nfree and freeLists helps to reduce sharing of cache lines between
* different mutexes.
*/
typedef struct
{
slock_t mutex; /* spinlock for this freelist */
- long nentries; /* number of entries in associated buckets */
+ long nfree; /* number of free entries in the list */
+ long nalloced; /* number of entries initially allocated for
+ * the list */
HASHELEMENT *freeList; /* chain of free elements */
} FreeListData;
@@ -170,7 +173,7 @@ struct HASHHDR
/*
* The freelist can become a point of contention in high-concurrency hash
* tables, so we use an array of freelists, each with its own mutex and
- * nentries count, instead of just a single one. Although the freelists
+ * nfree count, instead of just a single one. Although the freelists
* normally operate independently, we will scavenge entries from freelists
* other than a hashcode's default freelist when necessary.
*
@@ -254,6 +257,15 @@ struct HTAB
*/
#define MOD(x,y) ((x) & ((y)-1))
+/*
+ * Struct for reuse element.
+ */
+struct HASHREUSE
+{
+ HTAB *hashp;
+ HASHBUCKET element;
+};
+
#ifdef HASH_STATISTICS
static long hash_accesses,
hash_collisions,
@@ -293,6 +305,12 @@ DynaHashAlloc(Size size)
}
+/*
+ * Support for HASH_REUSE + HASH_ASSIGN
+ */
+static struct HASHREUSE DynaHashReuse = {NULL, NULL};
+
+
/*
* HashCompareFunc for string keys
*
@@ -932,6 +950,8 @@ calc_bucket(HASHHDR *hctl, uint32 hash_val)
* HASH_ENTER: look up key in table, creating entry if not present
* HASH_ENTER_NULL: same, but return NULL if out of memory
* HASH_REMOVE: look up key in table, remove entry if present
+ * HASH_REUSE: same as HASH_REMOVE, but stores removed element in static
+ * variable instead of free list.
*
* Return value is a pointer to the element found/entered/removed if any,
* or NULL if no match was found. (NB: in the case of the REMOVE action,
@@ -943,6 +963,11 @@ calc_bucket(HASHHDR *hctl, uint32 hash_val)
* HASH_ENTER_NULL cannot be used with the default palloc-based allocator,
* since palloc internally ereports on out-of-memory.
*
+ * If HASH_REUSE were called then next dynahash operation must be HASH_ENTER
+ * on the same dynahash instance. Otherwise, assertion will be triggered.
+ * HASH_ENTER will reuse element stored with HASH_REUSE if no duplicate entry
+ * found.
+ *
* If foundPtr isn't NULL, then *foundPtr is set true if we found an
* existing entry in the table, false otherwise. This is needed in the
* HASH_ENTER case, but is redundant with the return value otherwise.
@@ -1000,7 +1025,9 @@ hash_search_with_hash_value(HTAB *hashp,
* Can't split if running in partitioned mode, nor if frozen, nor if
* table is the subject of any active hash_seq_search scans.
*/
- if (hctl->freeList[0].nentries > (long) hctl->max_bucket &&
+ long nentries = hctl->freeList[0].nalloced - hctl->freeList[0].nfree;
+
+ if (nentries > (long) hctl->max_bucket &&
!IS_PARTITIONED(hctl) && !hashp->frozen &&
!has_seq_scans(hashp))
(void) expand_table(hashp);
@@ -1044,6 +1071,11 @@ hash_search_with_hash_value(HTAB *hashp,
if (foundPtr)
*foundPtr = (bool) (currBucket != NULL);
+ /* Check there is no unfinished HASH_REUSE + HASH_ENTER pair */
+ Assert(action == HASH_ENTER || DynaHashReuse.element == NULL);
+ /* Check HASH_REUSE were called for same dynahash if were */
+ Assert(DynaHashReuse.element == NULL || DynaHashReuse.hashp == hashp);
+
/*
* OK, now what?
*/
@@ -1057,20 +1089,17 @@ hash_search_with_hash_value(HTAB *hashp,
case HASH_REMOVE:
if (currBucket != NULL)
{
- /* if partitioned, must lock to touch nentries and freeList */
+ /* if partitioned, must lock to touch nfree and freeList */
if (IS_PARTITIONED(hctl))
SpinLockAcquire(&(hctl->freeList[freelist_idx].mutex));
- /* delete the record from the appropriate nentries counter. */
- Assert(hctl->freeList[freelist_idx].nentries > 0);
- hctl->freeList[freelist_idx].nentries--;
-
/* remove record from hash bucket's chain. */
*prevBucketPtr = currBucket->link;
/* add the record to the appropriate freelist. */
currBucket->link = hctl->freeList[freelist_idx].freeList;
hctl->freeList[freelist_idx].freeList = currBucket;
+ hctl->freeList[freelist_idx].nfree++;
if (IS_PARTITIONED(hctl))
SpinLockRelease(&hctl->freeList[freelist_idx].mutex);
@@ -1084,6 +1113,21 @@ hash_search_with_hash_value(HTAB *hashp,
}
return NULL;
+ case HASH_REUSE:
+ if (currBucket != NULL)
+ {
+ /* remove record from hash bucket's chain. */
+ *prevBucketPtr = currBucket->link;
+
+ /* and store for HASH_ASSIGN */
+ DynaHashReuse.element = currBucket;
+ DynaHashReuse.hashp = hashp;
+
+ /* Caller should call HASH_ASSIGN as the very next step. */
+ return (void *) ELEMENTKEY(currBucket);
+ }
+ return NULL;
+
case HASH_ENTER_NULL:
/* ENTER_NULL does not work with palloc-based allocator */
Assert(hashp->alloc != DynaHashAlloc);
@@ -1092,14 +1136,44 @@ hash_search_with_hash_value(HTAB *hashp,
case HASH_ENTER:
/* Return existing element if found, else create one */
if (currBucket != NULL)
+ {
+ if (likely(DynaHashReuse.element == NULL))
+ return (void *) ELEMENTKEY(currBucket);
+
+ /* if partitioned, must lock to touch nfree and freeList */
+ if (IS_PARTITIONED(hctl))
+ SpinLockAcquire(&(hctl->freeList[freelist_idx].mutex));
+
+ /* add the record to the appropriate freelist. */
+ DynaHashReuse.element->link = hctl->freeList[freelist_idx].freeList;
+ hctl->freeList[freelist_idx].freeList = DynaHashReuse.element;
+ hctl->freeList[freelist_idx].nfree++;
+
+ if (IS_PARTITIONED(hctl))
+ SpinLockRelease(&hctl->freeList[freelist_idx].mutex);
+
+ DynaHashReuse.element = NULL;
+ DynaHashReuse.hashp = NULL;
+
return (void *) ELEMENTKEY(currBucket);
+ }
/* disallow inserts if frozen */
if (hashp->frozen)
elog(ERROR, "cannot insert into frozen hashtable \"%s\"",
hashp->tabname);
- currBucket = get_hash_entry(hashp, freelist_idx);
+ if (DynaHashReuse.element == NULL)
+ {
+ currBucket = get_hash_entry(hashp, freelist_idx);
+ }
+ else
+ {
+ currBucket = DynaHashReuse.element;
+ DynaHashReuse.element = NULL;
+ DynaHashReuse.hashp = NULL;
+ }
+
if (currBucket == NULL)
{
/* out of memory */
@@ -1301,7 +1375,7 @@ get_hash_entry(HTAB *hashp, int freelist_idx)
for (;;)
{
- /* if partitioned, must lock to touch nentries and freeList */
+ /* if partitioned, must lock to touch nfree and freeList */
if (IS_PARTITIONED(hctl))
SpinLockAcquire(&hctl->freeList[freelist_idx].mutex);
@@ -1346,14 +1420,11 @@ get_hash_entry(HTAB *hashp, int freelist_idx)
if (newElement != NULL)
{
+ Assert(hctl->freeList[borrow_from_idx].nfree > 0);
hctl->freeList[borrow_from_idx].freeList = newElement->link;
+ hctl->freeList[borrow_from_idx].nfree--;
SpinLockRelease(&(hctl->freeList[borrow_from_idx].mutex));
- /* careful: count the new element in its proper freelist */
- SpinLockAcquire(&hctl->freeList[freelist_idx].mutex);
- hctl->freeList[freelist_idx].nentries++;
- SpinLockRelease(&hctl->freeList[freelist_idx].mutex);
-
return newElement;
}
@@ -1365,9 +1436,10 @@ get_hash_entry(HTAB *hashp, int freelist_idx)
}
}
- /* remove entry from freelist, bump nentries */
+ /* remove entry from freelist, decrease nfree */
+ Assert(hctl->freeList[freelist_idx].nfree > 0);
hctl->freeList[freelist_idx].freeList = newElement->link;
- hctl->freeList[freelist_idx].nentries++;
+ hctl->freeList[freelist_idx].nfree--;
if (IS_PARTITIONED(hctl))
SpinLockRelease(&hctl->freeList[freelist_idx].mutex);
@@ -1382,7 +1454,10 @@ long
hash_get_num_entries(HTAB *hashp)
{
int i;
- long sum = hashp->hctl->freeList[0].nentries;
+ long sum = 0;
+
+ sum += hashp->hctl->freeList[0].nalloced;
+ sum -= hashp->hctl->freeList[0].nfree;
/*
* We currently don't bother with acquiring the mutexes; it's only
@@ -1392,7 +1467,10 @@ hash_get_num_entries(HTAB *hashp)
if (IS_PARTITIONED(hashp->hctl))
{
for (i = 1; i < NUM_FREELISTS; i++)
- sum += hashp->hctl->freeList[i].nentries;
+ {
+ sum += hashp->hctl->freeList[i].nalloced;
+ sum -= hashp->hctl->freeList[i].nfree;
+ }
}
return sum;
@@ -1739,6 +1817,8 @@ element_alloc(HTAB *hashp, int nelem, int freelist_idx)
/* freelist could be nonempty if two backends did this concurrently */
firstElement->link = hctl->freeList[freelist_idx].freeList;
hctl->freeList[freelist_idx].freeList = prevElement;
+ hctl->freeList[freelist_idx].nfree += nelem;
+ hctl->freeList[freelist_idx].nalloced += nelem;
if (IS_PARTITIONED(hctl))
SpinLockRelease(&hctl->freeList[freelist_idx].mutex);
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index b903d2bcaf0..2ffcde678a0 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -328,7 +328,7 @@ extern void InitBufTable(int size);
extern uint32 BufTableHashCode(BufferTag *tagPtr);
extern int BufTableLookup(BufferTag *tagPtr, uint32 hashcode);
extern int BufTableInsert(BufferTag *tagPtr, uint32 hashcode, int buf_id);
-extern void BufTableDelete(BufferTag *tagPtr, uint32 hashcode);
+extern void BufTableDelete(BufferTag *tagPtr, uint32 hashcode, bool reuse);
/* localbuf.c */
extern PrefetchBufferResult PrefetchLocalBuffer(SMgrRelation smgr,
diff --git a/src/include/utils/hsearch.h b/src/include/utils/hsearch.h
index 854c3312414..1ffb616d99e 100644
--- a/src/include/utils/hsearch.h
+++ b/src/include/utils/hsearch.h
@@ -113,7 +113,8 @@ typedef enum
HASH_FIND,
HASH_ENTER,
HASH_REMOVE,
- HASH_ENTER_NULL
+ HASH_ENTER_NULL,
+ HASH_REUSE
} HASHACTION;
/* hash_seq status (should be considered an opaque type by callers) */
--
2.35.1
From 552ade23c3790734c302c3d597eb53d18b92dd5c Mon Sep 17 00:00:00 2001
From: Yura Sokolov <y.soko...@postgrespro.ru>
Date: Thu, 3 Mar 2022 01:14:58 +0300
Subject: [PATCH 3/3] reduce memory allocation for non-partitioned
dynahash
Non-partitioned hash table doesn't use 32 partitions of HASHHDR->freeList.
Lets allocate just single free list.
---
src/backend/utils/hash/dynahash.c | 37 +++++++++++++++++--------------
1 file changed, 20 insertions(+), 17 deletions(-)
diff --git a/src/backend/utils/hash/dynahash.c b/src/backend/utils/hash/dynahash.c
index 0cb35a0faf9..0a172005059 100644
--- a/src/backend/utils/hash/dynahash.c
+++ b/src/backend/utils/hash/dynahash.c
@@ -170,18 +170,6 @@ typedef struct
*/
struct HASHHDR
{
- /*
- * The freelist can become a point of contention in high-concurrency hash
- * tables, so we use an array of freelists, each with its own mutex and
- * nfree count, instead of just a single one. Although the freelists
- * normally operate independently, we will scavenge entries from freelists
- * other than a hashcode's default freelist when necessary.
- *
- * If the hash table is not partitioned, only freeList[0] is used and its
- * spinlock is not used at all; callers' locking is assumed sufficient.
- */
- FreeListData freeList[NUM_FREELISTS];
-
/* These fields can change, but not in a partitioned table */
/* Also, dsize can't change in a shared table, even if unpartitioned */
long dsize; /* directory size */
@@ -208,6 +196,18 @@ struct HASHHDR
long accesses;
long collisions;
#endif
+
+ /*
+ * The freelist can become a point of contention in high-concurrency hash
+ * tables, so we use an array of freelists, each with its own mutex and
+ * nfree count, instead of just a single one. Although the freelists
+ * normally operate independently, we will scavenge entries from freelists
+ * other than a hashcode's default freelist when necessary.
+ *
+ * If the hash table is not partitioned, only freeList[0] is used and its
+ * spinlock is not used at all; callers' locking is assumed sufficient.
+ */
+ FreeListData freeList[NUM_FREELISTS];
};
#define IS_PARTITIONED(hctl) ((hctl)->num_partitions != 0)
@@ -281,7 +281,7 @@ static bool element_alloc(HTAB *hashp, int nelem, int freelist_idx);
static bool dir_realloc(HTAB *hashp);
static bool expand_table(HTAB *hashp);
static HASHBUCKET get_hash_entry(HTAB *hashp, int freelist_idx);
-static void hdefault(HTAB *hashp);
+static void hdefault(HTAB *hashp, bool partitioned);
static int choose_nelem_alloc(Size entrysize);
static bool init_htab(HTAB *hashp, long nelem);
static void hash_corrupted(HTAB *hashp);
@@ -524,7 +524,8 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags)
if (!hashp->hctl)
{
- hashp->hctl = (HASHHDR *) hashp->alloc(sizeof(HASHHDR));
+ Assert(!(flags & HASH_PARTITION));
+ hashp->hctl = (HASHHDR *) hashp->alloc(offsetof(HASHHDR, freeList[1]));
if (!hashp->hctl)
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -533,7 +534,7 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags)
hashp->frozen = false;
- hdefault(hashp);
+ hdefault(hashp, (flags & HASH_PARTITION) != 0);
hctl = hashp->hctl;
@@ -641,11 +642,13 @@ hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags)
* Set default HASHHDR parameters.
*/
static void
-hdefault(HTAB *hashp)
+hdefault(HTAB *hashp, bool partition)
{
HASHHDR *hctl = hashp->hctl;
- MemSet(hctl, 0, sizeof(HASHHDR));
+ MemSet(hctl, 0, partition ?
+ sizeof(HASHHDR) :
+ offsetof(HASHHDR, freeList[1]));
hctl->dsize = DEF_DIRSIZE;
hctl->nsegs = 0;
--
2.35.1
