| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 18 Aug 2011 00:04:21 -0700
From: Greg Thelen <gthelen@...gle.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
containers@...ts.osdl.org, linux-fsdevel@...r.kernel.org,
Balbir Singh <bsingharora@...il.com>,
Daisuke Nishimura <nishimura@....nes.nec.co.jp>,
Minchan Kim <minchan.kim@...il.com>,
Johannes Weiner <hannes@...xchg.org>,
Wu Fengguang <fengguang.wu@...el.com>,
Dave Chinner <david@...morbit.com>,
Vivek Goyal <vgoyal@...hat.com>,
Andrea Righi <andrea@...terlinux.com>,
Ciju Rajan K <ciju@...ux.vnet.ibm.com>,
David Rientjes <rientjes@...gle.com>
Subject: Re: [PATCH v9 08/13] memcg: dirty page accounting support routines
KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com> writes:
> On Wed, 17 Aug 2011 09:15:00 -0700
> Greg Thelen <gthelen@...gle.com> wrote:
>
>> Added memcg dirty page accounting support routines. These routines are
>> used by later changes to provide memcg aware writeback and dirty page
>> limiting. A mem_cgroup_dirty_info() tracepoint is is also included to
>> allow for easier understanding of memcg writeback operation.
>>
>> Signed-off-by: Greg Thelen <gthelen@...gle.com>
>
> I have small comments.
>
>> ---
>> Changelog since v8:
>> - Use 'memcg' rather than 'mem' for local variables and parameters.
>> This is consistent with other memory controller code.
>>
>> include/linux/memcontrol.h | 9 ++
>> include/trace/events/memcontrol.h | 34 +++++++++
>> mm/memcontrol.c | 147 +++++++++++++++++++++++++++++++++++++
>> 3 files changed, 190 insertions(+), 0 deletions(-)
>>
>> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
>> index 630d3fa..9cc8841 100644
>> --- a/include/linux/memcontrol.h
>> +++ b/include/linux/memcontrol.h
>> @@ -36,6 +36,15 @@ enum mem_cgroup_page_stat_item {
>> MEMCG_NR_FILE_DIRTY, /* # of dirty pages in page cache */
>> MEMCG_NR_FILE_WRITEBACK, /* # of pages under writeback */
>> MEMCG_NR_FILE_UNSTABLE_NFS, /* # of NFS unstable pages */
>> + MEMCG_NR_DIRTYABLE_PAGES, /* # of pages that could be dirty */
>> +};
>> +
>> +struct dirty_info {
>> + unsigned long dirty_thresh;
>> + unsigned long background_thresh;
>> + unsigned long nr_file_dirty;
>> + unsigned long nr_writeback;
>> + unsigned long nr_unstable_nfs;
>> };
>>
>> extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
>> diff --git a/include/trace/events/memcontrol.h b/include/trace/events/memcontrol.h
>> index 781ef9fc..abf1306 100644
>> --- a/include/trace/events/memcontrol.h
>> +++ b/include/trace/events/memcontrol.h
>> @@ -26,6 +26,40 @@ TRACE_EVENT(mem_cgroup_mark_inode_dirty,
>> TP_printk("ino=%ld css_id=%d", __entry->ino, __entry->css_id)
>> )
>>
>> +TRACE_EVENT(mem_cgroup_dirty_info,
>> + TP_PROTO(unsigned short css_id,
>> + struct dirty_info *dirty_info),
>> +
>> + TP_ARGS(css_id, dirty_info),
>> +
>> + TP_STRUCT__entry(
>> + __field(unsigned short, css_id)
>> + __field(unsigned long, dirty_thresh)
>> + __field(unsigned long, background_thresh)
>> + __field(unsigned long, nr_file_dirty)
>> + __field(unsigned long, nr_writeback)
>> + __field(unsigned long, nr_unstable_nfs)
>> + ),
>> +
>> + TP_fast_assign(
>> + __entry->css_id = css_id;
>> + __entry->dirty_thresh = dirty_info->dirty_thresh;
>> + __entry->background_thresh = dirty_info->background_thresh;
>> + __entry->nr_file_dirty = dirty_info->nr_file_dirty;
>> + __entry->nr_writeback = dirty_info->nr_writeback;
>> + __entry->nr_unstable_nfs = dirty_info->nr_unstable_nfs;
>> + ),
>> +
>> + TP_printk("css_id=%d thresh=%ld bg_thresh=%ld dirty=%ld wb=%ld "
>> + "unstable_nfs=%ld",
>> + __entry->css_id,
>> + __entry->dirty_thresh,
>> + __entry->background_thresh,
>> + __entry->nr_file_dirty,
>> + __entry->nr_writeback,
>> + __entry->nr_unstable_nfs)
>> +)
>> +
>> #endif /* _TRACE_MEMCONTROL_H */
>>
>> /* This part must be outside protection */
>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
>> index 4e01699..d54adf4 100644
>> --- a/mm/memcontrol.c
>> +++ b/mm/memcontrol.c
>> @@ -1366,6 +1366,11 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg)
>> return memcg->swappiness;
>> }
>>
>> +static unsigned long dirty_info_reclaimable(struct dirty_info *info)
>> +{
>> + return info->nr_file_dirty + info->nr_unstable_nfs;
>> +}
>> +
>> /*
>> * Return true if the current memory cgroup has local dirty memory settings.
>> * There is an allowed race between the current task migrating in-to/out-of the
>> @@ -1396,6 +1401,148 @@ static void mem_cgroup_dirty_param(struct vm_dirty_param *param,
>> }
>> }
>>
>> +static inline bool mem_cgroup_can_swap(struct mem_cgroup *memcg)
>> +{
>> + if (!do_swap_account)
>> + return nr_swap_pages > 0;
>> + return !memcg->memsw_is_minimum &&
>> + (res_counter_read_u64(&memcg->memsw, RES_LIMIT) > 0);
>> +}
>
> I think
>
> if (nr_swap_pages == 0)
> return false;
> if (!do_swap_account)
> return true;
> if (memcg->memsw_is_mininum)
> return false;
> if (res_counter_margin(&memcg->memsw) == 0)
> return false;
>
> is a correct check.
Ok. I'll update to use your logic.
>> +
>> +static s64 mem_cgroup_local_page_stat(struct mem_cgroup *memcg,
>> + enum mem_cgroup_page_stat_item item)
>> +{
>> + s64 ret;
>> +
>> + switch (item) {
>> + case MEMCG_NR_FILE_DIRTY:
>> + ret = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_FILE_DIRTY);
>> + break;
>> + case MEMCG_NR_FILE_WRITEBACK:
>> + ret = mem_cgroup_read_stat(memcg,
>> + MEM_CGROUP_STAT_FILE_WRITEBACK);
>> + break;
>> + case MEMCG_NR_FILE_UNSTABLE_NFS:
>> + ret = mem_cgroup_read_stat(memcg,
>> + MEM_CGROUP_STAT_FILE_UNSTABLE_NFS);
>> + break;
>> + case MEMCG_NR_DIRTYABLE_PAGES:
>> + ret = mem_cgroup_read_stat(memcg, LRU_ACTIVE_FILE) +
>> + mem_cgroup_read_stat(memcg, LRU_INACTIVE_FILE);
>> + if (mem_cgroup_can_swap(memcg))
>> + ret += mem_cgroup_read_stat(memcg, LRU_ACTIVE_ANON) +
>> + mem_cgroup_read_stat(memcg, LRU_INACTIVE_ANON);
>> + break;
>> + default:
>> + BUG();
>> + break;
>> + }
>> + return ret;
>> +}
>> +
>> +/*
>> + * Return the number of additional pages that the @memcg cgroup could allocate.
>> + * If use_hierarchy is set, then this involves checking parent mem cgroups to
>> + * find the cgroup with the smallest free space.
>> + */
>> +static unsigned long
>> +mem_cgroup_hierarchical_free_pages(struct mem_cgroup *memcg)
>> +{
>> + u64 free;
>> + unsigned long min_free;
>> +
>> + min_free = global_page_state(NR_FREE_PAGES);
>> +
>> + while (memcg) {
>> + free = (res_counter_read_u64(&memcg->res, RES_LIMIT) -
>> + res_counter_read_u64(&memcg->res, RES_USAGE)) >>
>> + PAGE_SHIFT;
>
> How about
> free = mem_cgroup_margin(&mem->res);
> ?
>
> Thanks,
> -Kame
Sounds good. I'll update to:
while (memcg) {
free = res_counter_margin(&memcg->res) >> PAGE_SHIFT;
min_free = min_t(u64, min_free, free);
memcg = parent_mem_cgroup(memcg);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists