Re: [PATCH -next 2/3] md/raid10: convert resync_lock to use seqlock

[Yu Kuai]

Hi,

在 2022/09/02 18:16, Guoqing Jiang 写道:
> On 9/2/22 6:02 PM, Yu Kuai wrote:
> > Hi,
> >
> > 在 2022/09/02 17:42, Guoqing Jiang 写道:
> > > Hi,
> > >
> > > On 8/29/22 9:15 PM, Yu Kuai wrote:
> > > > +static bool wait_barrier_nolock(struct r10conf *conf)
> > > > +{
> > > > +    unsigned int seq = raw_read_seqcount(&conf->resync_lock.seqcount);
> > > > +
> > > > +    if (seq & 1)
> > > > +        return false;
> > > > +
> > > > +    if (READ_ONCE(conf->barrier))
> > > > +        return false;
> > > > +
> > > > +    atomic_inc(&conf->nr_pending);
> > > > +    if (!read_seqcount_retry(&conf->resync_lock.seqcount, seq))
> > >
> > > I think 'seq' is usually get from read_seqcount_begin.
> >
> > read_seqcount_begin will loop untill "req & 1" failed, I'm afraid this
> > will cause high cpu usage in come cases.
> >
> > What I try to do here is just try once, and fall back to hold lock and
> > wait if failed.
>
> Thanks for the explanation.
>
> I'd suggest to try with read_seqcount_begin/read_seqcount_retry pattern
> because it is a common usage in kernel I think, then check whether the
> performance drops or not.  Maybe it is related to lockdep issue, but I am
> not sure.

I can try read_seqcount_begin/read_seqcount_retry.

Please take a look at another thread, lockdep issue is due to
inconsistent usage of lock and seqcount inside seqlock:

wait_event() only release lock, seqcount is not released.

Thansk,
Kuai
> Thanks,
> Guoqing
> .