Re: [PATCH] swap: Add percpu cluster_next to reduce lock contention on swap cache
From: Daniel Jordan
Date: Mon May 18 2020 - 21:41:21 EST
On Mon, May 18, 2020 at 02:37:15PM +0800, Huang, Ying wrote:
> Daniel Jordan <daniel.m.jordan@xxxxxxxxxx> writes:
> > On Thu, May 14, 2020 at 03:04:24PM +0800, Huang Ying wrote:
> >> And the pmbench score increases 15.9%.
> >
> > What metric is that, and how long did you run the benchmark for?
>
> I run the benchmark for 1800s. The metric comes from the following
> output of the pmbench,
>
> [1] Benchmark done - took 1800.088 sec for 122910000 page access
>
> That is, the throughput is 122910000 / 1800.088 = 68280.0 (accesses/s).
> Then we sum the values from the different processes.
Ok.
> > It's just a nit but SWP_SOLIDSTATE and 'if (si->cluster_info)' are two ways to
> > check the same thing and I'd stick with the one that's already there.
>
> Yes. In effect, (si->flags & SWP_SOLIDSTATE) and (si->cluster_info)
> always has same value at least for now. But I don't think they are
> exactly same in semantics. So I would rather to use their exact
> semantics.
Oh, but I thought the swap clusters were for scaling the locking for fast
devices, so that both checks have the same semantics now, and presumably would
in the future.
It's a minor point, I'm fine either way.
> The first swap slot is the swap partition header, you cand find the
> corresponding code in syscall swapon function, below comments "Read the
Aha, thanks.