[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20180802061146.GA48671@dennisz-mbp.dhcp.thefacebook.com>
Date: Wed, 1 Aug 2018 23:11:48 -0700
From: Dennis Zhou <dennisszhou@...il.com>
To: Tejun Heo <tj@...nel.org>
Cc: Jens Axboe <axboe@...nel.dk>, Josef Bacik <jbacik@...com>,
kernel-team@...com, linux-block@...r.kernel.org,
linux-kernel@...r.kernel.org, Johannes Weiner <hannes@...xchg.org>
Subject: Re: [PATCH v2] block: make iolatency avg_lat exponentially decay
Hi Tejun,
On Wed, Aug 01, 2018 at 09:10:11AM -0700, Tejun Heo wrote:
> On Wed, Aug 01, 2018 at 08:49:58AM -0700, Tejun Heo wrote:
> > Hello,
> >
> > On Tue, Jul 31, 2018 at 05:25:59PM -0700, Dennis Zhou wrote:
> > ...
> > > + /*
> > > + * CALC_LOAD takes in a number stored in fixed point representation.
> > > + * Because we are using this for IO time in ns, the values stored
> > > + * are significantly larger than the FIXED_1 denominator (2048).
> > > + * Therefore, rounding errors in the calculation are negligible and
> > > + * can be ignored.
> > > + */
> > > + exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1,
> > > + iolat->cur_win_nsec / BLKIOLATENCY_EXP_BUCKET_SIZE);
> >
> > Build bot is complaining about naked 64bit div. Should use one of the
> > div64*() helpers.
> >
> > Looks good to me. Once Johannes's concerns are addressed, please feel
> > free to add
>
> Ooh, one nitpick. total_lat_avg is a bit of a misnomer now. Maybe
> rename to lat_avg?
>
Yeah, that makes sense. I've renamed it to lat_avg and updated the
Documentation file as well.
Thanks,
Dennis
Powered by blists - more mailing lists