Re: [PATCH v3] zram: Introduce an aged idle interface

[Brian Geffon]

Hi Minchan,
Thank you for taking a look. I'm happy to make that change, but I
personally cannot see why userspace would want to do something like
idle pages older than "0x3C seconds" or "0o250600 seconds," it just
seems like a strange way to represent seconds. What do you think?

Brian

On Wed, Sep 22, 2021 at 8:09 PM Minchan Kim <minchan@xxxxxxxxxx> wrote:
>
> On Tue, Sep 21, 2021 at 12:43:36PM -0700, Brian Geffon wrote:
> > This change introduces an aged idle interface to the existing
> > idle sysfs file for zram.
> >
> > When CONFIG_ZRAM_MEMORY_TRACKING is enabled the idle file
> > now also accepts an integer argument. This integer is the
> > age (in seconds) of pages to mark as idle. The idle file
> > still supports 'all' as it always has. This new approach
> > allows for much more control over which pages get marked
> > as idle.
> >
> >   v2 -> v3:
> >       - Correct unused variable warning when
> >         CONFIG_ZRAM_MEMORY_TRACKING is not enabled.
> >   v1 -> v2:
> >       - Switch to using existing idle file.
> >       - Dont compare ktime directly.
> >
> > Signed-off-by: Brian Geffon <bgeffon@xxxxxxxxxx>
> > ---
> >  Documentation/admin-guide/blockdev/zram.rst |  8 +++
> >  drivers/block/zram/zram_drv.c               | 60 +++++++++++++++------
> >  2 files changed, 52 insertions(+), 16 deletions(-)
> >
> > diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst
> > index 700329d25f57..8c8a92e5c00c 100644
> > --- a/Documentation/admin-guide/blockdev/zram.rst
> > +++ b/Documentation/admin-guide/blockdev/zram.rst
> > @@ -328,6 +328,14 @@ as idle::
> >  From now on, any pages on zram are idle pages. The idle mark
> >  will be removed until someone requests access of the block.
> >  IOW, unless there is access request, those pages are still idle pages.
> > +Additionally, when CONFIG_ZRAM_MEMORY_TRACKING is enabled pages can be
> > +marked as idle based on how long (in seconds) it's been since they were
> > +last accessed, in seconds::
> > +
> > +        echo 86400 > /sys/block/zramX/idle
> > +
> > +In this example all pages which haven't been accessed in more than 86400
> > +seconds (one day) will be marked idle.
> >
> >  Admin can request writeback of those idle pages at right timing via::
> >
> > diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
> > index fcaf2750f68f..2af5cdb8da1a 100644
> > --- a/drivers/block/zram/zram_drv.c
> > +++ b/drivers/block/zram/zram_drv.c
> > @@ -291,22 +291,16 @@ static ssize_t mem_used_max_store(struct device *dev,
> >       return len;
> >  }
> >
> > -static ssize_t idle_store(struct device *dev,
> > -             struct device_attribute *attr, const char *buf, size_t len)
> > +/*
> > + * Mark all pages which are older than or equal to cutoff as IDLE.
> > + * Callers should hold the zram init lock in read mode
> > + **/
> > +static void mark_idle(struct zram *zram, ktime_t cutoff)
> >  {
> > -     struct zram *zram = dev_to_zram(dev);
> > +     int is_idle = 1;
> >       unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
> >       int index;
> >
> > -     if (!sysfs_streq(buf, "all"))
> > -             return -EINVAL;
> > -
> > -     down_read(&zram->init_lock);
> > -     if (!init_done(zram)) {
> > -             up_read(&zram->init_lock);
> > -             return -EINVAL;
> > -     }
> > -
> >       for (index = 0; index < nr_pages; index++) {
> >               /*
> >                * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race.
> > @@ -314,14 +308,48 @@ static ssize_t idle_store(struct device *dev,
> >                */
> >               zram_slot_lock(zram, index);
> >               if (zram_allocated(zram, index) &&
> > -                             !zram_test_flag(zram, index, ZRAM_UNDER_WB))
> > -                     zram_set_flag(zram, index, ZRAM_IDLE);
> > +                             !zram_test_flag(zram, index, ZRAM_UNDER_WB)) {
> > +#ifdef CONFIG_ZRAM_MEMORY_TRACKING
> > +                     is_idle = (!cutoff || ktime_after(cutoff, zram->table[index].ac_time));
> > +#endif
> > +                     if (is_idle)
> > +                             zram_set_flag(zram, index, ZRAM_IDLE);
> > +             }
> >               zram_slot_unlock(zram, index);
> >       }
> > +}
> >
> > -     up_read(&zram->init_lock);
> > +static ssize_t idle_store(struct device *dev,
> > +             struct device_attribute *attr, const char *buf, size_t len)
> > +{
> > +     struct zram *zram = dev_to_zram(dev);
> > +     ktime_t cutoff_time = 0;
> > +     ssize_t rv = -EINVAL;
> >
> > -     return len;
> > +     if (!sysfs_streq(buf, "all")) {
> > +#ifdef CONFIG_ZRAM_MEMORY_TRACKING
> > +             u64 age_sec;
> > +             /* If it did not parse as 'all' try to treat it as an integer */
> > +             if (!kstrtoull(buf, 10, &age_sec))
>
> nit:
> Do we need such limit base which work with only 10 base?
> Passing 0 would give more flexibility.
>
> Otherwise, looks good to me.
>
> Thanks, Brian.
>
> > +                     cutoff_time = ktime_sub(ktime_get_boottime(),
> > +                                     ns_to_ktime(age_sec * NSEC_PER_SEC));
> > +             else
> > +#endif
> > +                     goto out;
> > +     }
> > +
> > +     down_read(&zram->init_lock);
> > +     if (!init_done(zram))
> > +             goto out_unlock;
> > +
> > +     /* A age_sec of 0 marks everything as idle, this is the "all" behavior */
> > +     mark_idle(zram, cutoff_time);
> > +     rv = len;
> > +
> > +out_unlock:
> > +     up_read(&zram->init_lock);
> > +out:
> > +     return rv;
> >  }
> >
> >  #ifdef CONFIG_ZRAM_WRITEBACK
> > --
> > 2.33.0.464.g1972c5931b-goog
> >