Re: [PATCH 7/8] mm: vmscan: report vmpressure at the level of reclaim activity

From	Michal Hocko <mhocko@kernel.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH 7/8] mm: vmscan: report vmpressure at the level of reclaim activity
Date	2015-10-23 16:00 +0200
Message-ID	<qmL2W-3e7-13@gated-at.bofh.it> (permalink)
References	<qmfFL-87d-1@gated-at.bofh.it> <qmfFM-87d-13@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Thu 22-10-15 00:21:35, Johannes Weiner wrote:
> The vmpressure metric is based on reclaim efficiency, which in turn is
> an attribute of the LRU. However, vmpressure events are currently
> reported at the source of pressure rather than at the reclaim level.
> 
> Switch the reporting to the reclaim level to allow finer-grained
> analysis of which memcg is having trouble reclaiming its pages.

I can see how this can be useful.

> As far as memory.pressure_level interface semantics go, events are
> escalated up the hierarchy until a listener is found, so this won't
> affect existing users that listen at higher levels.

This is true but the parent will not see cumulative events anymore.
One memcg might be fighting and barely reclaim anything so it would
report high pressure while other would be doing just fine. The parent
will just see conflicting events in a short time period and cannot match
them the source memcg. This sounds really confusing. Even more confusing
than the current semantic which allows the same behavior under certain
configurations.

I dunno, have to think about it some more. Maybe we need to rethink the
way how the pressure is signaled. If we want the breakdown of the
particular memcgs then we should be able to identify them for this to be
useful.

[...]
-- 
Michal Hocko
SUSE Labs
--
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/

Thread

[PATCH 0/8] mm: memcontrol: account socket memory in unified hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
  [PATCH 1/8] mm: page_counter: let page_counter_try_charge() return bool Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 1/8] mm: page_counter: let page_counter_try_charge()  return bool Michal Hocko <mhocko@kernel.org> - 2015-10-23 13:40 +0200
  [PATCH 6/8] mm: vmscan: simplify memcg vs. global shrinker invocation Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 6/8] mm: vmscan: simplify memcg vs. global shrinker  invocation Michal Hocko <mhocko@kernel.org> - 2015-10-23 15:30 +0200
  [PATCH 4/8] mm: memcontrol: prepare for unified hierarchy socket accounting Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 4/8] mm: memcontrol: prepare for unified hierarchy socket  accounting Michal Hocko <mhocko@kernel.org> - 2015-10-23 14:40 +0200
  [PATCH 5/8] mm: memcontrol: account socket memory on unified hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-22 20:50 +0200
    Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Michal Hocko <mhocko@kernel.org> - 2015-10-23 15:30 +0200
      Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy David Miller <davem@davemloft.net> - 2015-10-23 15:50 +0200
        Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-26 18:00 +0100
          Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Michal Hocko <mhocko@kernel.org> - 2015-10-27 13:30 +0100
            Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy David Miller <davem@davemloft.net> - 2015-10-27 14:40 +0100
            Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-27 16:50 +0100
              Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Michal Hocko <mhocko@kernel.org> - 2015-10-27 17:20 +0100
                Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-27 17:50 +0100
                Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy David Miller <davem@davemloft.net> - 2015-10-28 01:30 +0100
                Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-28 04:10 +0100
                Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Michal Hocko <mhocko@kernel.org> - 2015-10-29 16:30 +0100
                Re: [PATCH 5/8] mm: memcontrol: account socket memory on unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-29 17:20 +0100
  [PATCH 2/8] mm: memcontrol: export root_mem_cgroup Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 2/8] mm: memcontrol: export root_mem_cgroup Michal Hocko <mhocko@kernel.org> - 2015-10-23 13:40 +0200
  [PATCH 7/8] mm: vmscan: report vmpressure at the level of reclaim activity Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 7/8] mm: vmscan: report vmpressure at the level of  reclaim activity Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-22 20:50 +0200
    Re: [PATCH 7/8] mm: vmscan: report vmpressure at the level of  reclaim activity Michal Hocko <mhocko@kernel.org> - 2015-10-23 16:00 +0200
  [PATCH 8/8] mm: memcontrol: hook up vmpressure to socket pressure Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 8/8] mm: memcontrol: hook up vmpressure to socket pressure Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-22 21:00 +0200
  [PATCH 3/8] net: consolidate memcg socket buffer tracking and accounting Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 06:30 +0200
    Re: [PATCH 3/8] net: consolidate memcg socket buffer tracking and  accounting Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-22 20:50 +0200
      Re: [PATCH 3/8] net: consolidate memcg socket buffer tracking and  accounting Johannes Weiner <hannes@cmpxchg.org> - 2015-10-22 21:20 +0200
        Re: [PATCH 3/8] net: consolidate memcg socket buffer tracking and  accounting Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-23 15:50 +0200
    Re: [PATCH 3/8] net: consolidate memcg socket buffer tracking and  accounting Michal Hocko <mhocko@kernel.org> - 2015-10-23 14:40 +0200
  Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-22 20:50 +0200
    Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-26 18:30 +0100
      Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-27 09:50 +0100
        Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-27 17:10 +0100
          Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-28 09:30 +0100
            Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-28 20:00 +0100
              Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Vladimir Davydov <vdavydov@virtuozzo.com> - 2015-10-29 10:30 +0100
                Re: [PATCH 0/8] mm: memcontrol: account socket memory in unified  hierarchy Johannes Weiner <hannes@cmpxchg.org> - 2015-10-29 19:00 +0100

csiph-web