Re: [PATCH v2] pack-objects: Use packing_data lock instead of read_mutex

From: Jeff King <peff@peff.net>
Date: Jan 22, 2019, 07:28 UTC
Message-ID: <20190122072809.GA28975@sigill.intra.peff.net>
In-Reply-To: <CACsJy8AWCP+enBVVVga7jJZ-gxD=fxcushrk0D+xGSRAcZw_qg@mail.gmail.com>

On Mon, Jan 21, 2019 at 05:02:33PM +0700, Duy Nguyen wrote:

Show 12 quoted lines

> > As I mentioned in the prior thread I think that it will be simpler
> > to simply use the existing lock in packing_data instead of moving
> > read_mutex. I can go back to simply moving read_mutex to the
> > packing_data struct if that that is preferable, though.
> 
> In early iterations of these changes, I think we hit high contention
> when sharing the mutex [1]. I don't know if we will hit the same
> performance problem again with this patch. It would be great if Elijah
> with his zillion core machine could test this out. Otherwise it may be
> just safer to keep the two mutexes separate.
> 
> [1] http://public-inbox.org/git/20180720052829.GA3852@sigill.intra.peff.net/

I haven't been following this thread closely, but I still have access to a 40-core machine if you'd like me to time anything.

It sounds like _this_ patch is the more fine-grained one. Is the more coarse-grained one already written?

-Peff