Re: Why are we waiting? - Mailing list pgsql-hackers

From Gregory Stark
Subject Re: Why are we waiting?
Date
Msg-id 87ir12uoa7.fsf@oxford.xeocode.com
Whole thread Raw
In response to Re: Why are we waiting?  (Staale Smedseng <Staale.Smedseng@Sun.COM>)
Responses Re: Why are we waiting?  (Staale Smedseng <Staale.Smedseng@Sun.COM>)
Re: Why are we waiting?  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
"Staale Smedseng" <Staale.Smedseng@Sun.COM> writes:

> The stack trace shows that the only time the lock is acquired
> exclusively is from the call to ProcArrayEndTransaction() in
> CommitTransaction().

I'm not sure but I think that's only true in 8.3. As I understood it in 8.2
transaction start also needed the exclusive lock.

> Also, an interesting observation is that the hot locks seem to have
> changed from v8.2 to v8.3, making the ProcArrayLock more contended. See
> the following outputs:
>
> PostgreSQL 8.2 (32-bit):
>...
> PostgreSQL 8.3 (64-bit):
>...

I'm not sure 32-bit and 64-bit cases are going to be directly comparable. We
could have a problem with cache line aliasing on only one or the other for
example.

But that is a pretty striking difference. Does the 8.3 run complete more
transactions in that time?

--  Gregory Stark EnterpriseDB          http://www.enterprisedb.com Ask me about EnterpriseDB's 24x7 Postgres support!


pgsql-hackers by date:

Previous
From: "Dave Page"
Date:
Subject: Re: PostgreSQL 8.4 development plan
Next
From: Simon Riggs
Date:
Subject: pg_dump additional options for performance