Horton

Re: connection establishment versus parallel workers

Nathan Bossart <nathandbossart@gmail.com>

View thread View on postgr.es
From: Nathan Bossart <nathandbossart@gmail.com>
To: Thomas Munro <thomas.munro@gmail.com>
Cc: pgsql-hackers@postgresql.org
Date: 2024-12-12T22:00:19Z
Lists: pgsql-hackers 
On Fri, Dec 13, 2024 at 02:29:53AM +1300, Thomas Munro wrote:
> Here's an experimental patch to try changing that policy.  It improves
> the connection times on my small computer with your test, but I doubt
> I'm seeing the real issue.  But in theory, assuming a backlog of
> connections and workers to start, I think each server loop should be
> able to accept and fork one client backend, and fork up to 100
> (MAX_BGWORKERS_TO_LAUNCH) background workers.

Thanks for the quick response!  I'm taking a look at the patch...

-- 
nathan

Commits

  1. Fix latch event policy that hid socket events.

  2. Teach WaitEventSetWait() to report multiple events on Windows.

  3. Process pending postmaster work before connections.

  4. Use WaitEventSet API for postmaster's event loop.

  5. Replace buffer I/O locks with condition variables.