On 11/08/2020 03:41, Andres Freund wrote:
> On 2020-08-10 18:27:17 -0400, Robert Haas wrote:
>> On Tue, Jun 2, 2020 at 8:25 AM Drouvot, Bertrand <bdrouvot@amazon.com> wrote:
>>> the patch adds into the LWLock struct:
>>>
>>> last_holding_pid: last pid owner of the lock
>>> last_mode: last holding mode of the last pid owner of the lock
>>> nholders: number of holders (could be >1 in case of LW_SHARED)
>>
>> There's been significant work done over the years to get the size of
>> an LWLock down; I'm not very enthusiastic about making it bigger
>> again. See for example commit 6150a1b08a9fe7ead2b25240be46dddeae9d98e1
>> which embeds one of the LWLocks associated with a BufferDesc into the
>> structure to reduce the number of cache lines associated with common
>> buffer operations. I'm not sure whether this patch would increase the
>> space usage of a BufferDesc to more than one cache line again, but at
>> the very least it would make it a lot tighter, since it looks like it
>> adds 12 bytes to the size of each one.
>
> +many. If anything I would like to make them *smaller*. We should strive
> to make locking more and more granular, and that requires the space
> overhead to be small. I'm unhappy enough about the tranche being in
> there, and requiring padding etc.
>
> I spent a *LOT* of sweat getting where we are, I'd be unhappy to regress
> on size or efficiency.
That seems to be the consensus, so I'm marking this as Returned with
Feeback in the commitfest.
- Heikki
