[RFC][-mm] [2/2] Simple stats for memory resource controller - Kernel

This is a discussion on [RFC][-mm] [2/2] Simple stats for memory resource controller - Kernel ; This patch implements trivial statistics for the memory resource controller. Signed-off-by: Balaji Rao CC: Balbir Singh CC: Dhaval Giani diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a860765..ca98b21 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index { */ MEM_CGROUP_STAT_CACHE, /* ...

+ Reply to Thread
Results 1 to 8 of 8

Thread: [RFC][-mm] [2/2] Simple stats for memory resource controller

  1. [RFC][-mm] [2/2] Simple stats for memory resource controller

    This patch implements trivial statistics for the memory resource controller.

    Signed-off-by: Balaji Rao
    CC: Balbir Singh
    CC: Dhaval Giani

    diff --git a/mm/memcontrol.c b/mm/memcontrol.c
    index a860765..ca98b21 100644
    --- a/mm/memcontrol.c
    +++ b/mm/memcontrol.c
    @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index {
    */
    MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
    MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
    + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
    + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */

    MEM_CGROUP_STAT_NSTATS,
    };
    @@ -198,6 +200,13 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
    __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
    else
    __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
    +
    + if (charge)
    + __mem_cgroup_stat_add_safe(stat,
    + MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
    + else
    + __mem_cgroup_stat_add_safe(stat,
    + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
    }

    static struct mem_cgroup_per_zone *
    @@ -897,6 +906,8 @@ static const struct mem_cgroup_stat_desc {
    } mem_cgroup_stat_desc[] = {
    [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
    [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
    + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
    + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
    };

    static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,

    --
    regards,
    Balaji Rao
    Dept. of Mechanical Engineering,
    National Institute of Technology Karnataka, India
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  2. Re: [RFC][-mm] [2/2] Simple stats for memory resource controller

    Balaji Rao wrote:
    > This patch implements trivial statistics for the memory resource controller.
    >
    > Signed-off-by: Balaji Rao
    > CC: Balbir Singh
    > CC: Dhaval Giani
    >
    > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
    > index a860765..ca98b21 100644
    > --- a/mm/memcontrol.c
    > +++ b/mm/memcontrol.c
    > @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index {
    > */
    > MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
    > MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
    > + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
    > + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
    >
    > MEM_CGROUP_STAT_NSTATS,
    > };
    > @@ -198,6 +200,13 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
    > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
    > else
    > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
    > +
    > + if (charge)
    > + __mem_cgroup_stat_add_safe(stat,
    > + MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
    > + else
    > + __mem_cgroup_stat_add_safe(stat,
    > + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
    > }
    >
    > static struct mem_cgroup_per_zone *
    > @@ -897,6 +906,8 @@ static const struct mem_cgroup_stat_desc {
    > } mem_cgroup_stat_desc[] = {
    > [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
    > [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
    > + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
    > + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
    > };
    >
    > static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
    >


    Looks good to me. I wonder if pgpin/pggout per second will be a useful metric,
    to see how fast things are changing within the cgroup.

    Acked-by: Balbir Singh

    Let me test this patch right away.

    --
    Warm Regards,
    Balbir Singh
    Linux Technology Center
    IBM, ISTL
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  3. Re: [RFC][-mm] [2/2] Simple stats for memory resource controller

    Balaji Rao wrote:
    > This patch implements trivial statistics for the memory resource controller.
    >
    > Signed-off-by: Balaji Rao
    > CC: Balbir Singh
    > CC: Dhaval Giani
    >
    > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
    > index a860765..ca98b21 100644
    > --- a/mm/memcontrol.c
    > +++ b/mm/memcontrol.c
    > @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index {
    > */
    > MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
    > MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
    > + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
    > + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
    >
    > MEM_CGROUP_STAT_NSTATS,
    > };
    > @@ -198,6 +200,13 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
    > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
    > else
    > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
    > +
    > + if (charge)
    > + __mem_cgroup_stat_add_safe(stat,
    > + MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
    > + else
    > + __mem_cgroup_stat_add_safe(stat,
    > + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
    > }
    >
    > static struct mem_cgroup_per_zone *
    > @@ -897,6 +906,8 @@ static const struct mem_cgroup_stat_desc {
    > } mem_cgroup_stat_desc[] = {
    > [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
    > [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
    > + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
    > + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
    > };
    >
    > static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
    >


    Acked-by: Balbir Singh

    Hi, Andrew,

    Could you please include these statistics in -mm.

    Balbir


    --
    Warm Regards,
    Balbir Singh
    Linux Technology Center
    IBM, ISTL
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  4. Re: [RFC][-mm] [2/2] Simple stats for memory resource controller

    Balbir Singh wrote:
    > Balaji Rao wrote:
    >> This patch implements trivial statistics for the memory resource controller.
    >>
    >> Signed-off-by: Balaji Rao
    >> CC: Balbir Singh
    >> CC: Dhaval Giani
    >>
    >> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
    >> index a860765..ca98b21 100644
    >> --- a/mm/memcontrol.c
    >> +++ b/mm/memcontrol.c
    >> @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index {
    >> */
    >> MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
    >> MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
    >> + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
    >> + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
    >>
    >> MEM_CGROUP_STAT_NSTATS,
    >> };
    >> @@ -198,6 +200,13 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
    >> __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
    >> else
    >> __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
    >> +
    >> + if (charge)
    >> + __mem_cgroup_stat_add_safe(stat,
    >> + MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
    >> + else
    >> + __mem_cgroup_stat_add_safe(stat,
    >> + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
    >> }
    >>
    >> static struct mem_cgroup_per_zone *
    >> @@ -897,6 +906,8 @@ static const struct mem_cgroup_stat_desc {
    >> } mem_cgroup_stat_desc[] = {
    >> [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
    >> [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
    >> + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
    >> + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
    >> };
    >>
    >> static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
    >>

    >
    > Acked-by: Balbir Singh
    >
    > Hi, Andrew,
    >
    > Could you please include these statistics in -mm.
    >
    > Balbir
    >
    >


    Andrew,

    This should have been addressed to you in the first place. Resending.

    --
    Warm Regards,
    Balbir Singh
    Linux Technology Center
    IBM, ISTL
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  5. Re: [RFC][-mm] [2/2] Simple stats for memory resource controller

    On Monday 14 April 2008 08:09:48 pm Balbir Singh wrote:
    > Balaji Rao wrote:
    > > This patch implements trivial statistics for the memory resource controller.
    > >
    > > Signed-off-by: Balaji Rao
    > > CC: Balbir Singh
    > > CC: Dhaval Giani
    > >
    > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
    > > index a860765..ca98b21 100644
    > > --- a/mm/memcontrol.c
    > > +++ b/mm/memcontrol.c
    > > @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index {
    > > */
    > > MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
    > > MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
    > > + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
    > > + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
    > >
    > > MEM_CGROUP_STAT_NSTATS,
    > > };
    > > @@ -198,6 +200,13 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
    > > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
    > > else
    > > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
    > > +
    > > + if (charge)
    > > + __mem_cgroup_stat_add_safe(stat,
    > > + MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
    > > + else
    > > + __mem_cgroup_stat_add_safe(stat,
    > > + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
    > > }
    > >
    > > static struct mem_cgroup_per_zone *
    > > @@ -897,6 +906,8 @@ static const struct mem_cgroup_stat_desc {
    > > } mem_cgroup_stat_desc[] = {
    > > [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
    > > [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
    > > + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
    > > + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
    > > };
    > >
    > > static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
    > >

    >
    > Acked-by: Balbir Singh
    >
    > Hi, Andrew,
    >
    > Could you please include these statistics in -mm.
    >
    > Balbir
    >
    >

    Hi Andrew,

    Now that Balbir Singh has ACKed it, could you please include it in -mm ?

    --
    Warm Regards,

    Balaji Rao
    Dept. of Mechanical Engineering
    NITK
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  6. Re: [RFC][-mm] [2/2] Simple stats for memory resource controller

    On Mon, 28 Apr 2008 21:30:29 +0530 Balaji Rao wrote:

    > On Monday 14 April 2008 08:09:48 pm Balbir Singh wrote:
    > > Balaji Rao wrote:
    > > > This patch implements trivial statistics for the memory resource controller.
    > > >
    > > > Signed-off-by: Balaji Rao
    > > > CC: Balbir Singh
    > > > CC: Dhaval Giani
    > > >
    > > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
    > > > index a860765..ca98b21 100644
    > > > --- a/mm/memcontrol.c
    > > > +++ b/mm/memcontrol.c
    > > > @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index {
    > > > */
    > > > MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
    > > > MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
    > > > + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
    > > > + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
    > > >
    > > > MEM_CGROUP_STAT_NSTATS,
    > > > };
    > > > @@ -198,6 +200,13 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
    > > > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
    > > > else
    > > > __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
    > > > +
    > > > + if (charge)
    > > > + __mem_cgroup_stat_add_safe(stat,
    > > > + MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
    > > > + else
    > > > + __mem_cgroup_stat_add_safe(stat,
    > > > + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
    > > > }
    > > >
    > > > static struct mem_cgroup_per_zone *
    > > > @@ -897,6 +906,8 @@ static const struct mem_cgroup_stat_desc {
    > > > } mem_cgroup_stat_desc[] = {
    > > > [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
    > > > [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
    > > > + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
    > > > + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
    > > > };
    > > >
    > > > static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
    > > >

    > >
    > > Acked-by: Balbir Singh
    > >
    > > Hi, Andrew,
    > >
    > > Could you please include these statistics in -mm.
    > >
    > > Balbir
    > >
    > >

    > Hi Andrew,
    >
    > Now that Balbir Singh has ACKed it, could you please include it in -mm ?




    I guess we can add this one, sure. But [patch 1/2] needs work.

    - The local_irq_save()-around-for_each_possible_cpu() locking doesn't
    make sense.

    - indenting is busted in account_user_time() and account_system_time()

    - The use of for_each_possible_cpu() can be grossly inefficient. It
    would be preferred to use for_each_possible_cpu() and add a cpu-hotplug
    notifier.

    - The proposed newly-added userspace interfaces are undocumented

    - The changelogs don't explain why we might want this feature in Linux.

    - Generally: there are a heck of a lot of different ways of accounting
    for things in core kernel and it's really sad to see yet another one
    being added.


    Actually, [patch 2/2] adds new kerenl->user interfaces and doesn't document
    them. But afaict the existing memcgroup stats are secret too.

    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  7. Re: [RFC][-mm] [2/2] Simple stats for memory resource controller

    Andrew Morton wrote:
    > On Mon, 28 Apr 2008 21:30:29 +0530 Balaji Rao wrote:
    >
    >> On Monday 14 April 2008 08:09:48 pm Balbir Singh wrote:
    >>> Balaji Rao wrote:
    >>>> This patch implements trivial statistics for the memory resource controller.
    >>>>
    >>>> Signed-off-by: Balaji Rao
    >>>> CC: Balbir Singh
    >>>> CC: Dhaval Giani
    >>>>
    >>>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
    >>>> index a860765..ca98b21 100644
    >>>> --- a/mm/memcontrol.c
    >>>> +++ b/mm/memcontrol.c
    >>>> @@ -47,6 +47,8 @@ enum mem_cgroup_stat_index {
    >>>> */
    >>>> MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
    >>>> MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
    >>>> + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
    >>>> + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
    >>>>
    >>>> MEM_CGROUP_STAT_NSTATS,
    >>>> };
    >>>> @@ -198,6 +200,13 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
    >>>> __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
    >>>> else
    >>>> __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
    >>>> +
    >>>> + if (charge)
    >>>> + __mem_cgroup_stat_add_safe(stat,
    >>>> + MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
    >>>> + else
    >>>> + __mem_cgroup_stat_add_safe(stat,
    >>>> + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
    >>>> }
    >>>>
    >>>> static struct mem_cgroup_per_zone *
    >>>> @@ -897,6 +906,8 @@ static const struct mem_cgroup_stat_desc {
    >>>> } mem_cgroup_stat_desc[] = {
    >>>> [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
    >>>> [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
    >>>> + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
    >>>> + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
    >>>> };
    >>>>
    >>>> static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
    >>>>
    >>> Acked-by: Balbir Singh
    >>>
    >>> Hi, Andrew,
    >>>
    >>> Could you please include these statistics in -mm.
    >>>
    >>> Balbir
    >>>
    >>>

    >> Hi Andrew,
    >>
    >> Now that Balbir Singh has ACKed it, could you please include it in -mm ?

    >
    >
    >
    > I guess we can add this one, sure. But [patch 1/2] needs work.
    >
    > - The local_irq_save()-around-for_each_possible_cpu() locking doesn't
    > make sense.
    >


    Yes, that needs re-work. Peter Zijlstra had detailed review comments for the patch

    > - indenting is busted in account_user_time() and account_system_time()
    >
    > - The use of for_each_possible_cpu() can be grossly inefficient. It
    > would be preferred to use for_each_possible_cpu() and add a cpu-hotplug
    > notifier.
    >
    > - The proposed newly-added userspace interfaces are undocumented
    >


    Yes, we need more documentation

    > - The changelogs don't explain why we might want this feature in Linux.
    >


    We need more accurate utime/stime per cgroup. Summing them in user space is
    insufficient, since tasks can move across groups and what we have is accumulated
    time per task.

    > - Generally: there are a heck of a lot of different ways of accounting
    > for things in core kernel and it's really sad to see yet another one
    > being added.
    >


    We thought of summing up stuff in user space, we've look harder. The plan is to
    finally send all the data using cgroupstats.

    >
    > Actually, [patch 2/2] adds new kerenl->user interfaces and doesn't document
    > them. But afaict the existing memcgroup stats are secret too.
    >


    The statistics was added as a part of git commit
    d52aa412d43827033a8e2ce4415ef6e8f8d53635. I'll go ahead and try to document
    them. These patches piggy back on the statistics patches and add pagein/pageout
    counts, which is a useful statistic for the memory controller.



    --
    Warm Regards,
    Balbir Singh
    Linux Technology Center
    IBM, ISTL
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  8. Re: [RFC][-mm] [2/2] Simple stats for memory resource controller

    On Mon, 28 Apr 2008 23:33:05 +0530
    Balbir Singh wrote:

    > The statistics was added as a part of git commit
    > d52aa412d43827033a8e2ce4415ef6e8f8d53635. I'll go ahead and try to document
    > them. These patches piggy back on the statistics patches and add pagein/pageout
    > counts, which is a useful statistic for the memory controller.
    >

    I'm sorry for lack of documentation.
    BTW, when you adds documentation on this pagein/pageout, please make it clear

    1. pagein means a new page is newly acconted to this cgrop, doesn't means
    a page is read from disk.
    2. pageout means a page is dropped from this cgroup, doesn't means a page
    is written into disk.

    So, pagein/pageout is a bit ambiguous. I'm happy if you find better names.


    Thanks,
    -Kame

    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

+ Reply to Thread