[Devel] Re: [PATCH -mmotm 3/4] memcg: dirty pages accounting and limiting infrastructure

Andrea Righi arighi at develer.com
Mon Mar 8 16:06:20 PST 2010


On Mon, Mar 08, 2010 at 05:07:11PM +0900, Daisuke Nishimura wrote:
> On Mon, 8 Mar 2010 11:37:11 +0900, KAMEZAWA Hiroyuki <kamezawa.hiroyu at jp.fujitsu.com> wrote:
> > On Mon, 8 Mar 2010 11:17:24 +0900
> > Daisuke Nishimura <nishimura at mxp.nes.nec.co.jp> wrote:
> > 
> > > > But IIRC, clear_writeback is done under treelock.... No ?
> > > > 
> > > The place where NR_WRITEBACK is updated is out of tree_lock.
> > > 
> > >    1311 int test_clear_page_writeback(struct page *page)
> > >    1312 {
> > >    1313         struct address_space *mapping = page_mapping(page);
> > >    1314         int ret;
> > >    1315
> > >    1316         if (mapping) {
> > >    1317                 struct backing_dev_info *bdi = mapping->backing_dev_info;
> > >    1318                 unsigned long flags;
> > >    1319
> > >    1320                 spin_lock_irqsave(&mapping->tree_lock, flags);
> > >    1321                 ret = TestClearPageWriteback(page);
> > >    1322                 if (ret) {
> > >    1323                         radix_tree_tag_clear(&mapping->page_tree,
> > >    1324                                                 page_index(page),
> > >    1325                                                 PAGECACHE_TAG_WRITEBACK);
> > >    1326                         if (bdi_cap_account_writeback(bdi)) {
> > >    1327                                 __dec_bdi_stat(bdi, BDI_WRITEBACK);
> > >    1328                                 __bdi_writeout_inc(bdi);
> > >    1329                         }
> > >    1330                 }
> > >    1331                 spin_unlock_irqrestore(&mapping->tree_lock, flags);
> > >    1332         } else {
> > >    1333                 ret = TestClearPageWriteback(page);
> > >    1334         }
> > >    1335         if (ret)
> > >    1336                 dec_zone_page_state(page, NR_WRITEBACK);
> > >    1337         return ret;
> > >    1338 }
> > 
> > We can move this up to under tree_lock. Considering memcg, all our target has "mapping".
> > 
> > If we newly account bounce-buffers (for NILFS, FUSE, etc..), which has no ->mapping,
> > we need much more complex new charge/uncharge theory.
> > 
> > But yes, adding new lock scheme seems complicated. (Sorry Andrea.)
> > My concerns is performance. We may need somehing new re-implementation of
> > locks/migrate/charge/uncharge.
> > 
> I agree. Performance is my concern too.
> 
> I made a patch below and measured the time(average of 10 times) of kernel build
> on tmpfs(make -j8 on 8 CPU machine with 2.6.33 defconfig).
> 
> <before>
> - root cgroup: 190.47 sec
> - child cgroup: 192.81 sec
> 
> <after>
> - root cgroup: 191.06 sec
> - child cgroup: 193.06 sec
> 
> Hmm... about 0.3% slower for root, 0.1% slower for child.

Thanks Daisuke-san. This doesn't seem too bad, I'll repeat the test on
my machine and compare performance with my patch + your and Kame-san
fixes. Even if I agree that adding multiple locked/unlocked versions of
mem_cgroup_update_page_stat() it's just too bug-prone...

Thanks,
-Andrea

> 
> ===
> From: Daisuke Nishimura <nishimura at mxp.nes.nec.co.jp>
> 
> In current implementation, we don't have to disable irq at lock_page_cgroup()
> because the lock is never acquired in interrupt context.
> But we are going to do it in later patch, so this patch encloses all of
> lock_page_cgroup()/unlock_page_cgroup() with irq_disabled()/irq_enabled().
> 
> Signed-off-by: Daisuke Nishimura <nishimura at mxp.nes.nec.co.jp>
> ---
>  mm/memcontrol.c |   17 +++++++++++++++++
>  1 files changed, 17 insertions(+), 0 deletions(-)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 02ea959..e5ae1a1 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1359,6 +1359,7 @@ void mem_cgroup_update_file_mapped(struct page *page, int val)
>  	if (unlikely(!pc))
>  		return;
>  
> +	local_irq_disable();
>  	lock_page_cgroup(pc);
>  	mem = pc->mem_cgroup;
>  	if (!mem)
> @@ -1374,6 +1375,7 @@ void mem_cgroup_update_file_mapped(struct page *page, int val)
>  
>  done:
>  	unlock_page_cgroup(pc);
> +	local_irq_enable();
>  }
>  
>  /*
> @@ -1711,6 +1713,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
>  	VM_BUG_ON(!PageLocked(page));
>  
>  	pc = lookup_page_cgroup(page);
> +	local_irq_disable();
>  	lock_page_cgroup(pc);
>  	if (PageCgroupUsed(pc)) {
>  		mem = pc->mem_cgroup;
> @@ -1726,6 +1729,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
>  		rcu_read_unlock();
>  	}
>  	unlock_page_cgroup(pc);
> +	local_irq_enable();
>  	return mem;
>  }
>  
> @@ -1742,9 +1746,11 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
>  	if (!mem)
>  		return;
>  
> +	local_irq_disable();
>  	lock_page_cgroup(pc);
>  	if (unlikely(PageCgroupUsed(pc))) {
>  		unlock_page_cgroup(pc);
> +		local_irq_enable();
>  		mem_cgroup_cancel_charge(mem);
>  		return;
>  	}
> @@ -1775,6 +1781,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
>  	mem_cgroup_charge_statistics(mem, pc, true);
>  
>  	unlock_page_cgroup(pc);
> +	local_irq_enable();
>  	/*
>  	 * "charge_statistics" updated event counter. Then, check it.
>  	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
> @@ -1844,12 +1851,14 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
>  		struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge)
>  {
>  	int ret = -EINVAL;
> +	local_irq_disable();
>  	lock_page_cgroup(pc);
>  	if (PageCgroupUsed(pc) && pc->mem_cgroup == from) {
>  		__mem_cgroup_move_account(pc, from, to, uncharge);
>  		ret = 0;
>  	}
>  	unlock_page_cgroup(pc);
> +	local_irq_enable();
>  	/*
>  	 * check events
>  	 */
> @@ -1981,12 +1990,15 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
>  		pc = lookup_page_cgroup(page);
>  		if (!pc)
>  			return 0;
> +		local_irq_disable();
>  		lock_page_cgroup(pc);
>  		if (PageCgroupUsed(pc)) {
>  			unlock_page_cgroup(pc);
> +			local_irq_enable();
>  			return 0;
>  		}
>  		unlock_page_cgroup(pc);
> +		local_irq_enable();
>  	}
>  
>  	if (unlikely(!mm && !mem))
> @@ -2182,6 +2194,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
>  	if (unlikely(!pc || !PageCgroupUsed(pc)))
>  		return NULL;
>  
> +	local_irq_disable();
>  	lock_page_cgroup(pc);
>  
>  	mem = pc->mem_cgroup;
> @@ -2222,6 +2235,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
>  
>  	mz = page_cgroup_zoneinfo(pc);
>  	unlock_page_cgroup(pc);
> +	local_irq_enable();
>  
>  	memcg_check_events(mem, page);
>  	/* at swapout, this memcg will be accessed to record to swap */
> @@ -2232,6 +2246,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
>  
>  unlock_out:
>  	unlock_page_cgroup(pc);
> +	local_irq_enable();
>  	return NULL;
>  }
>  
> @@ -2424,12 +2439,14 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
>  		return 0;
>  
>  	pc = lookup_page_cgroup(page);
> +	local_irq_disable();
>  	lock_page_cgroup(pc);
>  	if (PageCgroupUsed(pc)) {
>  		mem = pc->mem_cgroup;
>  		css_get(&mem->css);
>  	}
>  	unlock_page_cgroup(pc);
> +	local_irq_enable();
>  
>  	if (mem) {
>  		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
> -- 
> 1.6.4
> 
_______________________________________________
Containers mailing list
Containers at lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers




More information about the Devel mailing list