Home » Mailing lists » Devel » [RFC][PATCH 0/7] Resource controllers based on process containers
Re: [RFC][PATCH 2/7] RSS controller core [message #10914 is a reply to message #10909] |
Wed, 07 March 2007 07:25 |
xemul
Messages: 248 Registered: November 2005
|
Senior Member |
|
|
Balbir Singh wrote:
> Pavel Emelianov wrote:
>> This includes setup of RSS container within generic
>> process containers, all the declarations used in RSS
>> accounting, and core code responsible for accounting.
>>
>>
>> ------------------------------------------------------------ ------------
>>
>> diff -upr linux-2.6.20.orig/include/linux/rss_container.h
>> linux-2.6.20-0/include/linux/rss_container.h
>> --- linux-2.6.20.orig/include/linux/rss_container.h 2007-03-06
>> 13:39:17.000000000 +0300
>> +++ linux-2.6.20-0/include/linux/rss_container.h 2007-03-06
>> 13:33:28.000000000 +0300
>> @@ -0,0 +1,68 @@
>> +#ifndef __RSS_CONTAINER_H__
>> +#define __RSS_CONTAINER_H__
>> +/*
>> + * RSS container
>> + *
>> + * Copyright 2007 OpenVZ SWsoft Inc
>> + *
>> + * Author: Pavel Emelianov <xemul@openvz.org>
>> + *
>> + */
>> +
>> +struct page_container;
>> +struct rss_container;
>> +
>> +#ifdef CONFIG_RSS_CONTAINER
>> +int container_rss_prepare(struct page *, struct vm_area_struct *vma,
>> + struct page_container **);
>> +
>> +void container_rss_add(struct page_container *);
>> +void container_rss_del(struct page_container *);
>> +void container_rss_release(struct page_container *);
>> +
>> +int mm_init_container(struct mm_struct *mm, struct task_struct *tsk);
>> +void mm_free_container(struct mm_struct *mm);
>> +
>> +unsigned long container_isolate_pages(unsigned long nr_to_scan,
>> + struct rss_container *rss, struct list_head *dst,
>> + int active, unsigned long *scanned);
>> +unsigned long container_nr_physpages(struct rss_container *rss);
>> +
>> +unsigned long container_try_to_free_pages(struct rss_container *);
>> +void container_out_of_memory(struct rss_container *);
>> +
>> +void container_rss_init_early(void);
>> +#else
>> +static inline int container_rss_prepare(struct page *pg,
>> + struct vm_area_struct *vma, struct page_container **pc)
>> +{
>> + *pc = NULL; /* to make gcc happy */
>> + return 0;
>> +}
>> +
>> +static inline void container_rss_add(struct page_container *pc)
>> +{
>> +}
>> +
>> +static inline void container_rss_del(struct page_container *pc)
>> +{
>> +}
>> +
>> +static inline void container_rss_release(struct page_container *pc)
>> +{
>> +}
>> +
>> +static inline int mm_init_container(struct mm_struct *mm, struct
>> task_struct *t)
>> +{
>> + return 0;
>> +}
>> +
>> +static inline void mm_free_container(struct mm_struct *mm)
>> +{
>> +}
>> +
>> +static inline void container_rss_init_early(void)
>> +{
>> +}
>> +#endif
>> +#endif
>> diff -upr linux-2.6.20.orig/init/Kconfig linux-2.6.20-0/init/Kconfig
>> --- linux-2.6.20.orig/init/Kconfig 2007-03-06 13:33:28.000000000 +0300
>> +++ linux-2.6.20-0/init/Kconfig 2007-03-06 13:33:28.000000000 +0300
>> @@ -265,6 +265,13 @@ config CPUSETS
>> bool
>> select CONTAINERS
>>
>> +config RSS_CONTAINER
>> + bool "RSS accounting container"
>> + select RESOURCE_COUNTERS
>> + help
>> + Provides a simple Resource Controller for monitoring and
>> + controlling the total Resident Set Size of the tasks in a
>> container
>> +
>
> The wording looks very familiar :-). It would be useful to add
> "The reclaim logic is now container aware, when the container goes
> overlimit
> the page reclaimer reclaims pages belonging to this container. If we are
> unable to reclaim enough pages to satisfy the request, the process is
> killed with an out of memory warning"
OK. Thanks.
>
>> config SYSFS_DEPRECATED
>> bool "Create deprecated sysfs files"
>> default y
>> diff -upr linux-2.6.20.orig/mm/Makefile linux-2.6.20-0/mm/Makefile
>> --- linux-2.6.20.orig/mm/Makefile 2007-02-04 21:44:54.000000000 +0300
>> +++ linux-2.6.20-0/mm/Makefile 2007-03-06 13:33:28.000000000 +0300
>> @@ -29,3 +29,5 @@ obj-$(CONFIG_MEMORY_HOTPLUG) += memory_h
>> obj-$(CONFIG_FS_XIP) += filemap_xip.o
>> obj-$(CONFIG_MIGRATION) += migrate.o
>> obj-$(CONFIG_SMP) += allocpercpu.o
>> +
>> +obj-$(CONFIG_RSS_CONTAINER) += rss_container.o
>> diff -upr linux-2.6.20.orig/mm/rss_container.c
>> linux-2.6.20-0/mm/rss_container.c
>> --- linux-2.6.20.orig/mm/rss_container.c 2007-03-06
>> 13:39:17.000000000 +0300
>> +++ linux-2.6.20-0/mm/rss_container.c 2007-03-06 13:33:28.000000000
>> +0300
>> @@ -0,0 +1,307 @@
>> +/*
>> + * RSS accounting container
>> + *
>> + * Copyright 2007 OpenVZ SWsoft Inc
>> + *
>> + * Author: Pavel Emelianov <xemul@openvz.org>
>> + *
>> + */
>> +
>> +#include <linux/list.h>
>> +#include <linux/sched.h>
>> +#include <linux/mm.h>
>> +#include <linux/res_counter.h>
>> +#include <linux/rss_container.h>
>> +
>> +static struct container_subsys rss_subsys;
>> +
>> +struct rss_container {
>> + struct res_counter res;
>> + struct list_head page_list;
>> + struct container_subsys_state css;
>> +};
>> +
>> +struct page_container {
>> + struct page *page;
>> + struct rss_container *cnt;
>> + struct list_head list;
>> +};
>> +
>
> Yes, this is what I was planning to get to -- a per container LRU list.
> But you have just one list, don't you need active and inactive lists?
> When the global LRU is manipulated, shouldn't this list be updated as
> well, so that reclaim will pick the best pages.
>
>> +static inline struct rss_container *rss_from_cont(struct container *cnt)
>> +{
>> + return container_of(container_subsys_state(cnt, &rss_subsys),
>> + struct rss_container, css);
>> +}
>> +
>> +int mm_init_container(struct mm_struct *mm, struct task_struct *tsk)
>> +{
>> + struct rss_container *cnt;
>> +
>> + cnt = rss_from_cont(task_container(tsk, &rss_subsys));
>> + if (css_get(&cnt->css))
>> + return -EBUSY;
>> +
>> + mm->rss_container = cnt;
>> + return 0;
>> +}
>> +
>> +void mm_free_container(struct mm_struct *mm)
>> +{
>> + css_put(&mm->rss_container->css);
>> +}
>> +
>> +int container_rss_prepare(struct page *page, struct vm_area_struct *vma,
>> + struct page_container **ppc)
>> +{
>> + struct rss_container *rss;
>> + struct page_container *pc;
>> +
>> + rcu_read_lock();
>> + rss = rcu_dereference(vma->vm_mm->rss_container);
>> + css_get_current(&rss->css);
>> + rcu_read_unlock();
>> +
>> + pc = kmalloc(sizeof(struct page_container), GFP_KERNEL);
>> + if (pc == NULL)
>> + goto out_nomem;
>> +
>> + while (res_counter_charge(&rss->res, 1)) {
>> + if (container_try_to_free_pages(rss))
>> + continue;
>> +
>
> The return codes of the functions is a bit confusing, ideally
> container_try_to_free_pages() should return 0 on success. Also
This returns exactly what try_to_free_pages() does.
> res_counter_charge() has a WARN_ON(1) if the limit is exceeded.
Nope - res_counter_uncharge() has - this is an absolutely
sane check that we haven't over-uncharged resources.
> The system administrator can figure out the details from failcnt,
> I suspect when the container is running close to it's limit,
> dmesg will have too many WARNING messages.
>
> How much memory do you try to reclaim in container_try_to_free_pages()?
At least one page. This is enough to make one page charge.
That's the difference from general try_to_free_pages() that
returns success if it freed swap_cluster_max pages at least.
> With my patches, I was planning to export this knob to userspace with
> a default value. This will help the administrator decide how much
> of the working set/container LRU should be freed on reaching the limit.
> I cannot find the definition of container_try_to_free_pages() in
> this patch.
This is in patch #5.
Sorry for such a bad split - I'll make it cleaner next time :)
>
>
>> + container_out_of_memory(rss);
>> + if (test_thread_flag(TIF_MEMDIE))
>> + goto out_charge;
>> + }
>> +
>> + pc->page = page;
>> + pc->cnt = rss;
>> + *ppc = pc;
>> + return 0;
>> +
>> +out_charge:
>> + kfree(pc);
>> +out_nomem:
>> + css_put(&rss->css);
>> + return -ENOMEM;
>> +}
>> +
>> +void container_rss_release(struct page_container *pc)
>> +{
>> + struct rss_container *rss;
>> +
>> + rss = pc->cnt;
>> + res_counter_uncharge(&rss->res, 1);
>> + css_put(&rss->css);
>> + kfree(pc);
>> +}
>> +
>> +void container_rss_add(struct page_container *pc)
>> +{
>> + struct page *pg;
>> + struct rss_container *rss;
>> +
>> + pg = pc->page;
>> + rss = pc->cnt;
>> +
>> + spin_lock(&r
...
|
|
|
|
|
[RFC][PATCH 0/7] Resource controllers based on process containers
By: xemul on Tue, 06 March 2007 14:42
|
|
|
[RFC][PATCH 1/7] Resource counters
By: xemul on Tue, 06 March 2007 14:47
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: xemul on Wed, 07 March 2007 07:17
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: xemul on Sun, 11 March 2007 09:01
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: ebiederm on Sun, 11 March 2007 19:00
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: ebiederm on Tue, 13 March 2007 09:09
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: xemul on Tue, 13 March 2007 09:27
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: xemul on Tue, 13 March 2007 15:41
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: xemul on Wed, 14 March 2007 07:12
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
By: ebiederm on Thu, 15 March 2007 16:51
|
|
|
Re: Re: [RFC][PATCH 1/7] Resource counters
By: dev on Tue, 13 March 2007 09:36
|
|
|
Re: [RFC][PATCH 1/7] Resource counters
|
|
|
[RFC][PATCH 2/7] RSS controller core
By: xemul on Tue, 06 March 2007 14:53
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: dev on Sun, 11 March 2007 12:13
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: ebiederm on Sun, 11 March 2007 19:34
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: xemul on Mon, 12 March 2007 09:02
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: xemul on Tue, 13 March 2007 07:17
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: xemul on Tue, 13 March 2007 15:32
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: dev on Tue, 13 March 2007 15:10
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
By: ebiederm on Tue, 13 March 2007 09:26
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
By: dev on Tue, 13 March 2007 15:30
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
By: dev on Tue, 13 March 2007 10:06
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: mel on Wed, 14 March 2007 15:38
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: Re: [RFC][PATCH 2/7] RSS controller core
By: ebiederm on Mon, 19 March 2007 17:41
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: xemul on Sun, 11 March 2007 09:08
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: xemul on Sun, 11 March 2007 15:04
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: xemul on Mon, 12 March 2007 08:31
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: xemul on Wed, 07 March 2007 07:25
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: ebiederm on Sun, 18 March 2007 16:58
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: akpm on Tue, 13 March 2007 06:04
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: Alan Cox on Tue, 13 March 2007 19:09
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: ebiederm on Fri, 16 March 2007 00:55
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: ebiederm on Fri, 16 March 2007 18:54
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: mel on Wed, 14 March 2007 16:47
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: dev on Tue, 13 March 2007 15:54
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: mel on Tue, 20 March 2007 18:57
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
By: ebiederm on Sun, 18 March 2007 17:42
|
|
|
Re: [RFC][PATCH 2/7] RSS controller core
|
|
|
controlling mmap()'d vs read/write() pages
|
|
|
Re: controlling mmap()'d vs read/write() pages
By: ebiederm on Tue, 20 March 2007 21:19
|
|
|
Re: controlling mmap()'d vs read/write() pages
|
|
|
Re: controlling mmap()'d vs read/write() pages
|
|
|
Re: controlling mmap()'d vs read/write() pages
By: ebiederm on Fri, 23 March 2007 10:12
|
|
|
Re: controlling mmap()'d vs read/write() pages
|
|
|
Re: controlling mmap()'d vs read/write() pages
|
|
|
Re: controlling mmap()'d vs read/write() pages
|
|
|
Re: controlling mmap()'d vs read/write() pages
|
|
|
Re: controlling mmap()'d vs read/write() pages
By: ebiederm on Fri, 23 March 2007 12:21
|
|
|
Re: controlling mmap()'d vs read/write() pages
|
|
|
[RFC][PATCH 3/7] Data structures changes for RSS accounting
By: xemul on Tue, 06 March 2007 14:55
|
|
|
Re: [RFC][PATCH 3/7] Data structures changes for RSS accounting
By: ebiederm on Sun, 11 March 2007 19:13
|
|
|
Re: [RFC][PATCH 3/7] Data structures changes for RSS accounting
By: dev on Mon, 12 March 2007 16:16
|
|
|
Re: [RFC][PATCH 3/7] Data structures changes for RSS accounting
|
|
|
Re: [RFC][PATCH 3/7] Data structures changes for RSS accounting
By: xemul on Mon, 12 March 2007 17:19
|
|
|
Re: [RFC][PATCH 3/7] Data structures changes for RSS accounting
|
|
|
Re: [RFC][PATCH 3/7] Data structures changes for RSS accounting
|
|
|
Re: [RFC][PATCH 3/7] Data structures changes for RSS accounting
By: xemul on Tue, 13 March 2007 07:10
|
|
|
[RFC][PATCH 4/7] RSS accounting hooks over the code
By: xemul on Tue, 06 March 2007 14:57
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: xemul on Wed, 14 March 2007 15:43
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: ebiederm on Sun, 11 March 2007 19:14
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: dev on Mon, 12 March 2007 16:23
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: dev on Mon, 12 March 2007 17:07
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: ebiederm on Tue, 13 March 2007 09:58
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: ebiederm on Tue, 13 March 2007 09:43
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: ebiederm on Tue, 13 March 2007 16:01
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
By: dev on Wed, 14 March 2007 16:16
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
Re: [RFC][PATCH 4/7] RSS accounting hooks over the code
|
|
|
[RFC][PATCH 5/7] Per-container OOM killer and page reclamation
By: xemul on Tue, 06 March 2007 15:01
|
|
|
Re: [RFC][PATCH 5/7] Per-container OOM killer and page reclamation
|
|
|
Re: [RFC][PATCH 5/7] Per-container OOM killer and page reclamation
By: xemul on Sun, 11 March 2007 08:39
|
|
|
[RFC][PATCH 6/7] Account for the number of tasks within container
By: xemul on Tue, 06 March 2007 15:02
|
|
|
Re: [RFC][PATCH 6/7] Account for the number of tasks within container
|
|
|
Re: [RFC][PATCH 6/7] Account for the number of tasks within container
By: xemul on Wed, 07 March 2007 07:10
|
|
|
Re: [RFC][PATCH 6/7] Account for the number of tasks within container
|
|
|
Re: [RFC][PATCH 6/7] Account for the number of tasks within container
By: xemul on Sun, 11 March 2007 08:34
|
|
|
[RFC][PATCH 7/7] Account for the number of files opened within container
By: xemul on Tue, 06 March 2007 15:05
|
|
|
Re: [RFC][PATCH 0/7] Resource controllers based on process containers
|
|
|
Re: [RFC][PATCH 0/7] Resource controllers based on process containers
By: xemul on Wed, 07 March 2007 07:27
|
|
|
Re: [RFC][PATCH 0/7] Resource controllers based on process containers
|
|
|
Re: [RFC][PATCH 0/7] Resource controllers based on process containers
By: xemul on Wed, 07 March 2007 07:30
|
|
|
Re: [RFC][PATCH 0/7] Resource controllers based on process containers
By: dev on Wed, 07 March 2007 09:30
|
Goto Forum:
Current Time: Sun Dec 08 00:36:29 GMT 2024
Total time taken to generate the page: 0.02850 seconds
|