Roman Gushchin <[email protected]> wrote:
> # Why do we need this?
>
> We've noticed that the number of dying cgroups is steadily growing on most
> of our hosts in production. The following investigation revealed an issue
> in userspace memory reclaim code [1], accounting of kernel stacks [2],
> and also the mainreason: slab objects.
>
> The underlying problem is quite simple: any page charged
> to a cgroup holds a reference to it, so the cgroup can't be reclaimed unless
> all charged pages are gone. If a slab object is actively used by other cgroups,
> it won't be reclaimed, and will prevent the origin cgroup from being reclaimed.
>
> Slab objects, and first of all vfs cache, is shared between cgroups, which are
> using the same underlying fs, and what's even more important, it's shared
> between multiple generations of the same workload. So if something is running
> periodically every time in a new cgroup (like how systemd works), we do
> accumulate multiple dying cgroups.
>
> Strictly speaking pagecache isn't different here, but there is a key difference:
> we disable protection and apply some extra pressure on LRUs of dying cgroups,
> and these LRUs contain all charged pages.
> My experiments show that with the disabled kernel memory accounting the number
> of dying cgroups stabilizes at a relatively small number (~100, depends on
> memory pressure and cgroup creation rate), and with kernel memory accounting
> it grows pretty steadily up to several thousands.
>
> Memory cgroups are quite complex and big objects (mostly due to percpu stats),
> so it leads to noticeable memory losses. Memory occupied by dying cgroups
> is measured in hundreds of megabytes. I've even seen a host with more than 100Gb
> of memory wasted for dying cgroups. It leads to a degradation of performance
> with the uptime, and generally limits the usage of cgroups.
>
> My previous attempt [3] to fix the problem by applying extra pressure on slab
> shrinker lists caused a regressions with xfs and ext4, and has been reverted [4].
> The following attempts to find the right balance [5, 6] were not successful.
>
> So instead of trying to find a maybe non-existing balance, let's do reparent
> the accounted slabs to the parent cgroup on cgroup removal.
>
>
> # Implementation approach
>
> There is however a significant problem with reparenting of slab memory:
> there is no list of charged pages. Some of them are in shrinker lists,
> but not all. Introducing of a new list is really not an option.
>
> But fortunately there is a way forward: every slab page has a stable pointer
> to the corresponding kmem_cache. So the idea is to reparent kmem_caches
> instead of slab pages.
>
> It's actually simpler and cheaper, but requires some underlying changes:
> 1) Make kmem_caches to hold a single reference to the memory cgroup,
> instead of a separate reference per every slab page.
> 2) Stop setting page->mem_cgroup pointer for memcg slab pages and use
> page->kmem_cache->memcg indirection instead. It's used only on
> slab page release, so it shouldn't be a big issue.
> 3) Introduce a refcounter for non-root slab caches. It's required to
> be able to destroy kmem_caches when they become empty and release
> the associated memory cgroup.
>
> There is a bonus: currently we do release empty kmem_caches on cgroup
> removal, however all other are waiting for the releasing of the memory cgroup.
> These refactorings allow kmem_caches to be released as soon as they
> become inactive and free.
>
> Some additional implementation details are provided in corresponding
> commit messages.
>
> # Results
>
> Below is the average number of dying cgroups on two groups of our production
> hosts. They do run some sort of web frontend workload, the memory pressure
> is moderate. As we can see, with the kernel memory reparenting the number
> stabilizes in 60s range; however with the original version it grows almost
> linearly and doesn't show any signs of plateauing. The difference in slab
> and percpu usage between patched and unpatched versions also grows linearly.
> In 7 days it exceeded 200Mb.
>
> day 0 1 2 3 4 5 6 7
> original 56 362 628 752 1070 1250 1490 1560
> patched 23 46 51 55 60 57 67 69
> mem diff(Mb) 22 74 123 152 164 182 214 241
No objection to the idea, but a question...
In patched kernel, does slabinfo (or similar) show the list reparented
slab caches? A pile of zombie kmem_caches is certainly better than a
pile of zombie mem_cgroup. But it still seems like it'll might cause
degradation - does cache_reap() walk an ever growing set of zombie
caches?
We've found it useful to add a slabinfo_full file which includes zombie
kmem_cache with their memcg_name. This can help hunt down zombies.
> # History
>
> v4:
> 1) removed excessive memcg != parent check in memcg_deactivate_kmem_caches()
> 2) fixed rcu_read_lock() usage in memcg_charge_slab()
> 3) fixed synchronization around dying flag in kmemcg_queue_cache_shutdown()
> 4) refreshed test results data
> 5) reworked PageTail() checks in memcg_from_slab_page()
> 6) added some comments in multiple places
>
> v3:
> 1) reworked memcg kmem_cache search on allocation path
> 2) fixed /proc/kpagecgroup interface
>
> v2:
> 1) switched to percpu kmem_cache refcounter
> 2) a reference to kmem_cache is held during the allocation
> 3) slabs stats are fixed for !MEMCG case (and the refactoring
> is separated into a standalone patch)
> 4) kmem_cache reparenting is performed from deactivatation context
>
> v1:
> https://lkml.org/lkml/2019/4/17/1095
>
>
> # Links
>
> [1]: commit 68600f623d69 ("mm: don't miss the last page because of
> round-off error")
> [2]: commit 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting")
> [3]: commit 172b06c32b94 ("mm: slowly shrink slabs with a relatively
> small number of objects")
> [4]: commit a9a238e83fbb ("Revert "mm: slowly shrink slabs
> with a relatively small number of objects")
> [5]: https://lkml.org/lkml/2019/1/28/1865
> [6]: https://marc.info/?l=linux-mm&m=155064763626437&w=2
>
>
> Roman Gushchin (7):
> mm: postpone kmem_cache memcg pointer initialization to
> memcg_link_cache()
> mm: generalize postponed non-root kmem_cache deactivation
> mm: introduce __memcg_kmem_uncharge_memcg()
> mm: unify SLAB and SLUB page accounting
> mm: rework non-root kmem_cache lifecycle management
> mm: reparent slab memory on cgroup removal
> mm: fix /proc/kpagecgroup interface for slab pages
>
> include/linux/memcontrol.h | 10 +++
> include/linux/slab.h | 13 +--
> mm/memcontrol.c | 101 ++++++++++++++++-------
> mm/slab.c | 25 ++----
> mm/slab.h | 137 ++++++++++++++++++++++++-------
> mm/slab_common.c | 162 +++++++++++++++++++++----------------
> mm/slub.c | 36 ++-------
> 7 files changed, 299 insertions(+), 185 deletions(-)
On Wed, Jun 05, 2019 at 12:39:24AM -0700, Greg Thelen wrote:
> Roman Gushchin <[email protected]> wrote:
>
> > # Why do we need this?
> >
> > We've noticed that the number of dying cgroups is steadily growing on most
> > of our hosts in production. The following investigation revealed an issue
> > in userspace memory reclaim code [1], accounting of kernel stacks [2],
> > and also the mainreason: slab objects.
> >
> > The underlying problem is quite simple: any page charged
> > to a cgroup holds a reference to it, so the cgroup can't be reclaimed unless
> > all charged pages are gone. If a slab object is actively used by other cgroups,
> > it won't be reclaimed, and will prevent the origin cgroup from being reclaimed.
> >
> > Slab objects, and first of all vfs cache, is shared between cgroups, which are
> > using the same underlying fs, and what's even more important, it's shared
> > between multiple generations of the same workload. So if something is running
> > periodically every time in a new cgroup (like how systemd works), we do
> > accumulate multiple dying cgroups.
> >
> > Strictly speaking pagecache isn't different here, but there is a key difference:
> > we disable protection and apply some extra pressure on LRUs of dying cgroups,
> > and these LRUs contain all charged pages.
> > My experiments show that with the disabled kernel memory accounting the number
> > of dying cgroups stabilizes at a relatively small number (~100, depends on
> > memory pressure and cgroup creation rate), and with kernel memory accounting
> > it grows pretty steadily up to several thousands.
> >
> > Memory cgroups are quite complex and big objects (mostly due to percpu stats),
> > so it leads to noticeable memory losses. Memory occupied by dying cgroups
> > is measured in hundreds of megabytes. I've even seen a host with more than 100Gb
> > of memory wasted for dying cgroups. It leads to a degradation of performance
> > with the uptime, and generally limits the usage of cgroups.
> >
> > My previous attempt [3] to fix the problem by applying extra pressure on slab
> > shrinker lists caused a regressions with xfs and ext4, and has been reverted [4].
> > The following attempts to find the right balance [5, 6] were not successful.
> >
> > So instead of trying to find a maybe non-existing balance, let's do reparent
> > the accounted slabs to the parent cgroup on cgroup removal.
> >
> >
> > # Implementation approach
> >
> > There is however a significant problem with reparenting of slab memory:
> > there is no list of charged pages. Some of them are in shrinker lists,
> > but not all. Introducing of a new list is really not an option.
> >
> > But fortunately there is a way forward: every slab page has a stable pointer
> > to the corresponding kmem_cache. So the idea is to reparent kmem_caches
> > instead of slab pages.
> >
> > It's actually simpler and cheaper, but requires some underlying changes:
> > 1) Make kmem_caches to hold a single reference to the memory cgroup,
> > instead of a separate reference per every slab page.
> > 2) Stop setting page->mem_cgroup pointer for memcg slab pages and use
> > page->kmem_cache->memcg indirection instead. It's used only on
> > slab page release, so it shouldn't be a big issue.
> > 3) Introduce a refcounter for non-root slab caches. It's required to
> > be able to destroy kmem_caches when they become empty and release
> > the associated memory cgroup.
> >
> > There is a bonus: currently we do release empty kmem_caches on cgroup
> > removal, however all other are waiting for the releasing of the memory cgroup.
> > These refactorings allow kmem_caches to be released as soon as they
> > become inactive and free.
> >
> > Some additional implementation details are provided in corresponding
> > commit messages.
> >
> > # Results
> >
> > Below is the average number of dying cgroups on two groups of our production
> > hosts. They do run some sort of web frontend workload, the memory pressure
> > is moderate. As we can see, with the kernel memory reparenting the number
> > stabilizes in 60s range; however with the original version it grows almost
> > linearly and doesn't show any signs of plateauing. The difference in slab
> > and percpu usage between patched and unpatched versions also grows linearly.
> > In 7 days it exceeded 200Mb.
> >
> > day 0 1 2 3 4 5 6 7
> > original 56 362 628 752 1070 1250 1490 1560
> > patched 23 46 51 55 60 57 67 69
> > mem diff(Mb) 22 74 123 152 164 182 214 241
>
> No objection to the idea, but a question...
Hi Greg!
> In patched kernel, does slabinfo (or similar) show the list reparented
> slab caches? A pile of zombie kmem_caches is certainly better than a
> pile of zombie mem_cgroup. But it still seems like it'll might cause
> degradation - does cache_reap() walk an ever growing set of zombie
> caches?
It's not a pile of zombie kmem_caches vs a pile of zombie mem_cgroups.
It's a smaller pile of zombie kmem_caches vs a larger pile of zombie kmem_caches
*and* a pile of zombie mem_cgroups. The patchset makes the number of zombie
kmem_caches lower, not bigger.
Re slabinfo and other debug interfaces: I do not change anything here.
>
> We've found it useful to add a slabinfo_full file which includes zombie
> kmem_cache with their memcg_name. This can help hunt down zombies.
I'm not sure we need to add a permanent debug interface, because something like
drgn ( https://github.com/osandov/drgn ) can be used instead.
If you think that we lack some necessary debug interfaces, I'm totally open
here, but it's not a part of this patchset. Let's talk about them separately.
Thank you for looking into it!
Roman