Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751959Ab3IPWU7 (ORCPT ); Mon, 16 Sep 2013 18:20:59 -0400 Received: from e39.co.us.ibm.com ([32.97.110.160]:49542 "EHLO e39.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751889Ab3IPWUw (ORCPT ); Mon, 16 Sep 2013 18:20:52 -0400 From: zwu.kernel@gmail.com To: viro@zeniv.linux.org.uk Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, Zhi Yong Wu , Chandra Seetharaman Subject: [PATCH v5 07/10] VFS hot tracking: Add a /proc interface to control memory usage Date: Tue, 17 Sep 2013 06:17:52 +0800 Message-Id: <1379369875-5123-8-git-send-email-zwu.kernel@gmail.com> X-Mailer: git-send-email 1.7.11.7 In-Reply-To: <1379369875-5123-1-git-send-email-zwu.kernel@gmail.com> References: <1379369875-5123-1-git-send-email-zwu.kernel@gmail.com> X-TM-AS-MML: No X-Content-Scanned: Fidelis XPS MAILER x-cbid: 13091622-9332-0000-0000-0000016FFDE2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5822 Lines: 197 From: Zhi Yong Wu 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 Signed-off-by: Zhi Yong Wu --- fs/hot_tracking.c | 31 +++++++++++++++++++++++++++++++ fs/hot_tracking.h | 23 +++++++++++++++++++++++ include/linux/hot_tracking.h | 3 +++ kernel/sysctl.c | 7 +++++++ 4 files changed, 64 insertions(+) diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c index 8c7e403..0047252 100644 --- a/fs/hot_tracking.c +++ b/fs/hot_tracking.c @@ -15,6 +15,9 @@ #include #include "hot_tracking.h" +int sysctl_hot_mem_high_thresh __read_mostly = 0; +EXPORT_SYMBOL_GPL(sysctl_hot_mem_high_thresh); + int sysctl_hot_update_interval __read_mostly = 150; EXPORT_SYMBOL_GPL(sysctl_hot_update_interval); @@ -33,6 +36,7 @@ static void hot_range_item_init(struct hot_range_item *hr, hr->len = hot_bit_shift(1, RANGE_BITS, true); 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) @@ -56,6 +60,7 @@ 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); } @@ -106,6 +111,8 @@ 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); @@ -213,6 +220,7 @@ 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) @@ -234,6 +242,7 @@ 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); } @@ -282,6 +291,8 @@ 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); @@ -528,6 +539,23 @@ 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 @@ -540,6 +568,8 @@ 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) { @@ -748,6 +778,7 @@ int hot_track_init(struct super_block *sb) goto err; } + hot_mem_limit_init(root); sb->s_hot_root = root; printk(KERN_INFO "VFS: Turning on hot tracking\n"); diff --git a/fs/hot_tracking.h b/fs/hot_tracking.h index 23b1339..c9efa5b 100644 --- a/fs/hot_tracking.h +++ b/fs/hot_tracking.h @@ -40,4 +40,27 @@ #define AVW_DIVIDER_POWER 40 /* AVW - average delta between recent writes(ns) */ #define AVW_COEFF_POWER 0 +/* 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 6923771..3f50c39 100644 --- a/include/linux/hot_tracking.h +++ b/include/linux/hot_tracking.h @@ -99,10 +99,13 @@ 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@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/