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

From: Minchan Kim
Date: Thu Sep 23 2021 - 02:02:17 EST

Hey Brian,

On Wed, Sep 22, 2021 at 08:42:44PM -0400, Brian Geffon wrote:
> 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?

Kernel communty loves inline reply instead of top posting. ;-)

I am not strong opinion about mutiple base support. The question
just started from "what's the benefit with only 10-base support?"
if we can support multiple bases with almost zero maintainace
overhead.

>
> 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
> > >