Hello, all.
I thought about patch simplification, and tested version
without BufTable and dynahash api change at all.
It performs suprisingly well. It is just a bit worse
than v1 since there is more contention around dynahash's
freelist, but most of improvement remains.
I'll finish benchmarking and will attach graphs with
next message. Patch is attached here.
------
regards,
Yura Sokolov
Postgres Professional
y.soko...@postgrespro.ru
funny.fal...@gmail.com
From 7f430bdaa748456ed6b59f16f32ac0ea55644a66 Mon Sep 17 00:00:00 2001
From: Yura Sokolov <y.soko...@postgrespro.ru>
Date: Fri, 14 Jan 2022 02:28:36 +0300
Subject: [PATCH v2] 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 lock 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 | 179 +++++++++++++---------------
1 file changed, 82 insertions(+), 97 deletions(-)
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index b4532948d3f..abb916938a7 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -1288,93 +1288,16 @@ 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.
*/
@@ -1391,31 +1314,100 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
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.
+ * Clear out the buffer's tag and flags. We must do this to ensure that
+ * linear scans of the buffer array don't think the buffer is valid. We
+ * also reset the usage_count since any recency of use of the old content
+ * is no longer relevant.
*
- * 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.)
+ * Since we are single pinner, there should no be PIN_COUNT_WAITER or
+ * IO_IN_PROGRESS (flags that were not cleared in previous code).
+ */
+ Assert((oldFlags & (BM_PIN_COUNT_WAITER | BM_IO_IN_PROGRESS)) == 0);
+ CLEAR_BUFFERTAG(buf->tag);
+ buf_state &= ~(BUF_FLAG_MASK | BUF_USAGECOUNT_MASK);
+ UnlockBufHdr(buf, buf_state);
+
+ 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. 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
+ * 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;
+ }
+
+ /*
+ * Okay, it's finally safe to rename the buffer.
*
* 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
@@ -1423,13 +1415,6 @@ 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
