OpenVZ Forum


Home » Mailing lists » Devel » Re: [RFC/PATCH] cgroup swap subsystem
Re: [RFC/PATCH] cgroup swap subsystem [message #27995] Wed, 05 March 2008 08:33 Go to previous message
Pavel Emelianov is currently offline  Pavel Emelianov
Messages: 1149
Registered: September 2006
Senior Member
Daisuke Nishimura wrote:
> Hi.
> 
> Even if limiting memory usage by cgroup memory subsystem
> or isolating memory by cpuset, swap space is shared, so
> resource isolation is not enough. If one group uses up all the
> swap space, it can affect other groups.
> 
> I try making a patch of swap subsystem based on memory
> subsystem, which limits swap usage per cgroup.
> It can now charge and limit the swap usage.
> 
> I implemented this feature as a new subsystem,
> not as a part of memory subsystem, because I don't want to
> make big change to memcontrol.c, and even if implemented
> as other subsystem, users can manage memory and swap on
> the same cgroup directory if mount them together.
> 
> Basic idea of my implementation:
>   - what will be charged ?
>     the number of swap entries.

This is a very obscure thing "a swap entry" for the end user. People
would prefer accounting bytes.

>   - when to charge/uncharge ?
>     charge at get_swap_entry(), and uncharge at swap_entry_free().
> 
>   - to what group charge the swap entry ?
>     To determine to what swap_cgroup (corresponding to mem_cgroup in
>     memory subsystem) the swap entry should be charged,
>     I added a pointer to mm_struct to page_cgroup(pc->pc_mm), and
>     changed the argument of get_swap_entry() from (void) to
>     (struct page *). As a result, get_swap_entry() can determine
>     to what swap_cgroup it should charge the swap entry
>     by referring to page->page_cgroup->mm_struct->swap_cgroup.
> 
>   - from what group uncharge the swap entry ?
>     I added to swap_info_struct a member 'struct swap_cgroup **',
>     array of pointer to which swap_cgroup the swap entry is
>     charged.
> 
> Todo:
>   - rebase new kernel, and split into some patches.
>   - Merge with memory subsystem (if it would be better), or
>     remove dependency on CONFIG_CGROUP_MEM_CONT if possible
>     (needs to make page_cgroup more generic one).

Merge is a must IMHO. I can hardly imagine a situation in which
someone would need these two separately.

>   - More tests, cleanups, and feartures   :-)  
> 
> 
> Any comments or discussions would be appreciated.
> 
> Thanks,
> Daisuke Nishimura
> 
> 
> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
> 
> ---
> diff -uprN linux-2.6.24-mm1/include/linux/cgroup_subsys.h linux-2.6.24-mm1-swaplimit/include/linux/cgroup_subsys.h
> --- linux-2.6.24-mm1/include/linux/cgroup_subsys.h	2008-02-04 14:34:24.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/include/linux/cgroup_subsys.h	2008-03-03 10:56:56.000000000 +0900
> @@ -42,3 +42,9 @@ SUBSYS(mem_cgroup)
>  #endif
>  
>  /* */
> +
> +#ifdef CONFIG_CGROUP_SWAP_LIMIT
> +SUBSYS(swap)
> +#endif
> +
> +/* */
> diff -uprN linux-2.6.24-mm1/include/linux/memcontrol.h linux-2.6.24-mm1-swaplimit/include/linux/memcontrol.h
> --- linux-2.6.24-mm1/include/linux/memcontrol.h	2008-02-04 14:34:24.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/include/linux/memcontrol.h	2008-03-03 10:56:56.000000000 +0900
> @@ -29,6 +29,21 @@ struct page;
>  struct mm_struct;
>  
>  #ifdef CONFIG_CGROUP_MEM_CONT
> +/*
> + * A page_cgroup page is associated with every page descriptor. The
> + * page_cgroup helps us identify information about the cgroup
> + */
> +struct page_cgroup {
> +	struct list_head lru;		/* per cgroup LRU list */
> +	struct page *page;
> +	struct mem_cgroup *mem_cgroup;
> +#ifdef CONFIG_CGROUP_SWAP_LIMIT
> +	struct mm_struct *pc_mm;
> +#endif

Try not to add new entries here.

> +	atomic_t ref_cnt;		/* Helpful when pages move b/w  */
> +					/* mapped and cached states     */
> +	int	 flags;
> +};
>  
>  extern void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p);
>  extern void mm_free_cgroup(struct mm_struct *mm);
> diff -uprN linux-2.6.24-mm1/include/linux/mm_types.h linux-2.6.24-mm1-swaplimit/include/linux/mm_types.h
> --- linux-2.6.24-mm1/include/linux/mm_types.h	2008-02-04 14:34:24.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/include/linux/mm_types.h	2008-03-03 10:56:56.000000000 +0900
> @@ -233,6 +233,9 @@ struct mm_struct {
>  #ifdef CONFIG_CGROUP_MEM_CONT
>  	struct mem_cgroup *mem_cgroup;
>  #endif
> +#ifdef CONFIG_CGROUP_SWAP_LIMIT
> +	struct swap_cgroup *swap_cgroup;
> +#endif
>  };
>  
>  #endif /* _LINUX_MM_TYPES_H */
> diff -uprN linux-2.6.24-mm1/include/linux/swap.h linux-2.6.24-mm1-swaplimit/include/linux/swap.h
> --- linux-2.6.24-mm1/include/linux/swap.h	2008-02-04 14:34:24.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/include/linux/swap.h	2008-03-03 10:56:56.000000000 +0900
> @@ -7,6 +7,7 @@
>  #include <linux/list.h>
>  #include <linux/memcontrol.h>
>  #include <linux/sched.h>
> +#include <linux/swap_limit.h>
>  
>  #include <asm/atomic.h>
>  #include <asm/page.h>
> @@ -141,6 +142,9 @@ struct swap_info_struct {
>  	struct swap_extent *curr_swap_extent;
>  	unsigned old_block_size;
>  	unsigned short * swap_map;
> +#ifdef CONFIG_CGROUP_SWAP_LIMIT
> +	struct swap_cgroup **swap_cgroup;
> +#endif
>  	unsigned int lowest_bit;
>  	unsigned int highest_bit;
>  	unsigned int cluster_next;
> @@ -239,7 +243,7 @@ extern struct page *swapin_readahead(swp
>  extern long total_swap_pages;
>  extern unsigned int nr_swapfiles;
>  extern void si_swapinfo(struct sysinfo *);
> -extern swp_entry_t get_swap_page(void);
> +extern swp_entry_t get_swap_page(struct page *);
>  extern swp_entry_t get_swap_page_of_type(int);
>  extern int swap_duplicate(swp_entry_t);
>  extern int valid_swaphandles(swp_entry_t, unsigned long *);
> @@ -342,7 +346,7 @@ static inline int remove_exclusive_swap_
>  	return 0;
>  }
>  
> -static inline swp_entry_t get_swap_page(void)
> +static inline swp_entry_t get_swap_page(struct page *page)
>  {
>  	swp_entry_t entry;
>  	entry.val = 0;
> diff -uprN linux-2.6.24-mm1/include/linux/swap_limit.h linux-2.6.24-mm1-swaplimit/include/linux/swap_limit.h
> --- linux-2.6.24-mm1/include/linux/swap_limit.h	1970-01-01 09:00:00.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/include/linux/swap_limit.h	2008-03-03 10:56:56.000000000 +0900
> @@ -0,0 +1,65 @@
> +/*
> + * swap_limit.h
> + *
> + */
> +#ifndef _LINUX_SWAP_LIMIT_H
> +#define _LINUX_SWAP_LIMIT_H
> +
> +#include <linux/swap.h>
> +#include <linux/cgroup.h>
> +#include <linux/res_counter.h>
> +
> +struct swap_cgroup;
> +struct swap_info_struct;
> +
> +#ifdef CONFIG_CGROUP_SWAP_LIMIT
> +struct swap_cgroup {
> +	struct cgroup_subsys_state css;
> +	struct res_counter res;
> +};
> +
> +static inline struct swap_cgroup *swap_cgroup_from_cgrp(struct cgroup *cgrp)
> +{
> +	return container_of(cgroup_subsys_state(cgrp, swap_subsys_id),
> +				struct swap_cgroup,
> +				css);
> +}
> +
> +static inline struct swap_cgroup *swap_cgroup_from_task(struct task_struct *p)
> +{
> +	return container_of(task_subsys_state(p, swap_subsys_id),
> +				struct swap_cgroup, css);
> +}
> +
> +extern int swap_cgroup_charge(struct page *page,
> +				struct swap_info_struct *si,
> +				unsigned long offset);
> +extern void swap_cgroup_uncharge(struct swap_info_struct *si,
> +				unsigned long offset);
> +
> +#else /* CONFIG_CGROUP_SWAP_LIMIT */
> +static inline struct swap_cgroup *swap_cgroup_from_cgrp(struct cgroup *cgrp)
> +{
> +	return NULL;
> +}
> +
> +static inline struct swap_cgroup *swap_cgroup_from_task(struct task_struct *p)
> +{
> +	return NULL;
> +}
> +
> +static inline int swap_cgroup_charge(struct page *page,
> +					struct swap_info_struct *si,
> +					unsigned long offset)
> +{
> +	return 0;
> +}
> +
> +static inline void swap_cgroup_uncharge(struct swap_info_struct *si,
> +					unsigned long offset)
> +{
> +}
> +
> +#endif
> +
> +#endif
> diff -uprN linux-2.6.24-mm1/init/Kconfig linux-2.6.24-mm1-swaplimit/init/Kconfig
> --- linux-2.6.24-mm1/init/Kconfig	2008-02-04 14:34:24.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/init/Kconfig	2008-03-03 10:56:56.000000000 +0900
> @@ -383,6 +383,12 @@ config CGROUP_MEM_CONT
>  	  Provides a memory controller that manages both page cache and
>  	  RSS memory.
>  
> +config CGROUP_SWAP_LIMIT
> +	bool "cgroup subsystem for swap"
> +	depends on CGROUP_MEM_CONT && SWAP
> +	help
> +	  Provides a swap controller that manages and limits swap usage.
> +
>  config PROC_PID_CPUSET
>  	bool "Include legacy /proc/<pid>/cpuset file"
>  	depends on CPUSETS
> diff -uprN linux-2.6.24-mm1/mm/Makefile linux-2.6.24-mm1-swaplimit/mm/Makefile
> --- linux-2.6.24-mm1/mm/Makefile	2008-02-04 14:34:24.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/mm/Makefile	2008-03-03 10:56:56.000000000 +0900
> @@ -32,4 +32,5 @@ obj-$(CONFIG_MIGRATION) += migrate.o
>  obj-$(CONFIG_SMP) += allocpercpu.o
>  obj-$(CONFIG_QUICKLIST) += quicklist.o
>  obj-$(CONFIG_CGROUP_MEM_CONT) += memcontrol.o
> +obj-$(CONFIG_CGROUP_SWAP_LIMIT) += swap_limit.o
>  
> diff -uprN linux-2.6.24-mm1/mm/memcontrol.c linux-2.6.24-mm1-swaplimit/mm/memcontrol.c
> --- linux-2.6.24-mm1/mm/memcontrol.c	2008-02-04 14:34:24.000000000 +0900
> +++ linux-2.6.24-mm1-swaplimit/mm/memcontrol.c	2008-03-03 10:56:56.000000000 +0900
> @@ -19,6 +19,7 @@
>  
>  #include <linux/res_counter.h>
>  #include <linux/memcontrol.h>
> +#include <linux/swap_limit.h>
>  #include <linux/cgr
...

 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: network namespace ipv6 perfs
Next Topic: Re: [RFC/PATCH] cgroup swap subsystem
Goto Forum:
  


Current Time: Fri Aug 16 13:24:41 GMT 2024

Total time taken to generate the page: 0.02935 seconds