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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Wed, 11 Dec 2013 23:44:32 +0800
From:	Zhi Yong Wu <zwu.kernel@...il.com>
To:	Al Viro <viro@...iv.linux.org.uk>
Cc:	"linux-fsdevel@...r.kernel.org" <linux-fsdevel@...r.kernel.org>,
	linux-kernel mlist <linux-kernel@...r.kernel.org>,
	Zhi Yong Wu <wuzhy@...ux.vnet.ibm.com>,
	Ric Wheeler <rwheeler@...hat.com>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	Paul McKenney <paulmck@...ux.vnet.ibm.com>
Subject: Re: [PATCH v6 07/11] VFS hot tracking: Add a /proc interface to
 control memory usage

Ping ^ 7....

On Wed, Nov 6, 2013 at 9:45 PM, Zhi Yong Wu <zwu.kernel@...il.com> wrote:
> From: Zhi Yong Wu <wuzhy@...ux.vnet.ibm.com>
>
> Introduce a /proc interface hot-mem-high-thresh and
> to cap the memory which is consumed by hot_inode_item
> and hot_range_item, and they will be in the unit of
> 1M bytes.
>
> Signed-off-by: Chandra Seetharaman <sekharan@...ibm.com>
> Signed-off-by: Zhi Yong Wu <wuzhy@...ux.vnet.ibm.com>
> ---
>  fs/hot_tracking.c            | 29 +++++++++++++++++++++++++++++
>  fs/hot_tracking.h            | 23 +++++++++++++++++++++++
>  include/linux/hot_tracking.h |  3 +++
>  kernel/sysctl.c              |  7 +++++++
>  4 files changed, 62 insertions(+)
>
> diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
> index 7a9bd4f..2c5a7fd 100644
> --- a/fs/hot_tracking.c
> +++ b/fs/hot_tracking.c
> @@ -15,6 +15,7 @@
>  #include <linux/sched.h>
>  #include "hot_tracking.h"
>
> +int sysctl_hot_mem_high_thresh __read_mostly = 0;
>  int sysctl_hot_update_interval __read_mostly = 150;
>
>  /* kmem_cache pointers for slab caches */
> @@ -32,6 +33,7 @@ static void hot_range_item_init(struct hot_range_item *hr,
>         hr->len = 1 << RANGE_BITS;
>         hr->hot_inode = he;
>         atomic_long_inc(&he->hot_root->hot_cnt);
> +       hot_mem_limit_add(he->hot_root, sizeof(struct hot_range_item));
>  }
>
>  static void hot_range_item_free_cb(struct rcu_head *head)
> @@ -55,6 +57,7 @@ static void hot_range_item_free(struct kref *kref)
>         spin_unlock(&root->m_lock);
>
>         atomic_long_dec(&root->hot_cnt);
> +       hot_mem_limit_sub(root, sizeof(struct hot_range_item));
>         call_rcu(&hr->rcu, hot_range_item_free_cb);
>  }
>
> @@ -103,6 +106,8 @@ redo:
>                                  * newly allocated item.
>                                  */
>                                 atomic_long_dec(&he->hot_root->hot_cnt);
> +                               hot_mem_limit_sub(he->hot_root,
> +                                               sizeof(struct hot_range_item));
>                                 kmem_cache_free(hot_range_item_cachep, hr_new);
>                         }
>                         spin_unlock(&he->i_lock);
> @@ -205,6 +210,7 @@ static void hot_inode_item_init(struct hot_inode_item *he,
>         he->hot_root = root;
>         spin_lock_init(&he->i_lock);
>         atomic_long_inc(&root->hot_cnt);
> +       hot_mem_limit_add(root, sizeof(struct hot_inode_item));
>  }
>
>  static void hot_inode_item_free_cb(struct rcu_head *head)
> @@ -226,6 +232,7 @@ static void hot_inode_item_free(struct kref *kref)
>         hot_range_tree_free(he);
>
>         atomic_long_dec(&he->hot_root->hot_cnt);
> +       hot_mem_limit_sub(he->hot_root, sizeof(struct hot_inode_item));
>         call_rcu(&he->rcu, hot_inode_item_free_cb);
>  }
>
> @@ -272,6 +279,8 @@ redo:
>                                  * newly allocated item.
>                                  */
>                                 atomic_long_dec(&root->hot_cnt);
> +                               hot_mem_limit_sub(root,
> +                                               sizeof(struct hot_inode_item));
>                                 kmem_cache_free(hot_inode_item_cachep, he_new);
>                         }
>                         spin_unlock(&root->t_lock);
> @@ -534,6 +543,23 @@ static unsigned long hot_item_evict(struct hot_info *root, unsigned long work,
>         return freed;
>  }
>
> +static void hot_mem_evict(struct hot_info *root)
> +{
> +       unsigned long sum, thresh;
> +
> +       if (sysctl_hot_mem_high_thresh == 0)
> +               return;
> +
> +       sum = hot_mem_limit_sum(root);
> +       /* Note: sysctl_** is in the unit of 1M bytes */
> +       thresh = sysctl_hot_mem_high_thresh;
> +       thresh *= 1024 * 1024;
> +       if (sum <= thresh)
> +               return;
> +
> +       hot_item_evict(root, sum - thresh, hot_mem_limit_sum);
> +}
> +
>  /*
>   * Every sync period we update temperatures for
>   * each hot inode item and hot range item for aging
> @@ -546,6 +572,8 @@ static void hot_update_worker(struct work_struct *work)
>         struct hot_inode_item *he;
>         struct rb_node *node;
>
> +       hot_mem_evict(root);
> +
>         rcu_read_lock();
>         node = root->hot_inode_tree.rb_node;
>         while (node) {
> @@ -753,6 +781,7 @@ int hot_track_init(struct super_block *sb)
>                 goto err;
>         }
>
> +       hot_mem_limit_init(root);
>         sb->s_hot_root = root;
>         sb->s_flags |= MS_HOTTRACK;
>
> diff --git a/fs/hot_tracking.h b/fs/hot_tracking.h
> index 6a6971e..4ee0b90 100644
> --- a/fs/hot_tracking.h
> +++ b/fs/hot_tracking.h
> @@ -46,4 +46,27 @@ struct hot_inode_item *hot_inode_item_lookup(struct hot_info *root, u64 ino);
>  void hot_inode_item_unlink(struct inode *inode);
>  u32 hot_temp_calc(struct hot_freq *freq);
>
> +/* Memory Tracking Functions. */
> +static inline unsigned long hot_mem_limit_sum(struct hot_info *root)
> +{
> +       return atomic_long_read(&root->mem);
> +}
> +
> +static inline void hot_mem_limit_sub(struct hot_info *root,
> +                               unsigned long count)
> +{
> +       atomic_long_sub(count, &root->mem);
> +}
> +
> +static inline void hot_mem_limit_add(struct hot_info *root,
> +                               unsigned long count)
> +{
> +       atomic_long_add(count, &root->mem);
> +}
> +
> +static inline void hot_mem_limit_init(struct hot_info *root)
> +{
> +       atomic_long_set(&root->mem, 0);
> +}
> +
>  #endif /* __HOT_TRACKING__ */
> diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h
> index 43df1b9..5c2c247 100644
> --- a/include/linux/hot_tracking.h
> +++ b/include/linux/hot_tracking.h
> @@ -83,10 +83,13 @@ struct hot_info {
>         struct workqueue_struct *update_wq;
>         struct delayed_work update_work;
>         struct shrinker hot_shrink;
> +       atomic_long_t mem;
>  };
>
>  /* set how often to update temperatures (seconds) */
>  extern int sysctl_hot_update_interval;
> +/* note: sysctl_** is in the unit of 1M bytes */
> +extern int sysctl_hot_mem_high_thresh;
>
>  /*
>   * Hot data tracking ioctls:
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index e0b062a..fde8bc2 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -1632,6 +1632,13 @@ static struct ctl_table fs_table[] = {
>                 .extra1         = &pipe_min_size,
>         },
>         {
> +               .procname       = "hot-mem-high-thresh",
> +               .data           = &sysctl_hot_mem_high_thresh,
> +               .maxlen         = sizeof(int),
> +               .mode           = 0644,
> +               .proc_handler   = proc_dointvec,
> +       },
> +       {
>                 .procname       = "hot-update-interval",
>                 .data           = &sysctl_hot_update_interval,
>                 .maxlen         = sizeof(int),
> --
> 1.7.11.7
>
> --
> 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/



-- 
Regards,

Zhi Yong Wu
--
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

Powered by Openwall GNU/*/Linux Powered by OpenVZ