From 3942c07ccf98e66b8893f396dca98f5b076f905f Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:17:53 +1000 Subject: [PATCH] fs: bump inode and dentry counters to long MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa Cc: Dave Chinner Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: Dave Chinner Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- fs/dcache.c | 8 ++++---- fs/inode.c | 18 +++++++++--------- fs/internal.h | 2 +- include/linux/dcache.h | 10 +++++----- include/linux/fs.h | 4 ++-- include/uapi/linux/fs.h | 6 +++--- kernel/sysctl.c | 6 +++--- 7 files changed, 27 insertions(+), 27 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index 4d9df3c940e6..6ef1c2e1bbc4 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -146,13 +146,13 @@ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; -static DEFINE_PER_CPU(unsigned int, nr_dentry); +static DEFINE_PER_CPU(long, nr_dentry); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) -static int get_nr_dentry(void) +static long get_nr_dentry(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; @@ -162,7 +162,7 @@ int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif diff --git a/fs/inode.c b/fs/inode.c index 93a0625b46e4..2a3c37ea823d 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -70,33 +70,33 @@ EXPORT_SYMBOL(empty_aops); */ struct inodes_stat_t inodes_stat; -static DEFINE_PER_CPU(unsigned int, nr_inodes); -static DEFINE_PER_CPU(unsigned int, nr_unused); +static DEFINE_PER_CPU(unsigned long, nr_inodes); +static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __read_mostly; -static int get_nr_inodes(void) +static long get_nr_inodes(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } -static inline int get_nr_inodes_unused(void) +static inline long get_nr_inodes_unused(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } -int get_nr_dirty_inodes(void) +long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ - int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); + long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } @@ -109,7 +109,7 @@ int proc_nr_inodes(ctl_table *table, int write, { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif diff --git a/fs/internal.h b/fs/internal.h index 2be46ea5dd0b..b6495659d6e8 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -121,7 +121,7 @@ extern void inode_add_lru(struct inode *inode); */ extern void inode_wb_list_del(struct inode *inode); -extern int get_nr_dirty_inodes(void); +extern long get_nr_dirty_inodes(void); extern void evict_inodes(struct super_block *); extern int invalidate_inodes(struct super_block *, bool); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index feaa8d88eef7..844a1ef387e4 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -55,11 +55,11 @@ struct qstr { #define hashlen_len(hashlen) ((u32)((hashlen) >> 32)) struct dentry_stat_t { - int nr_dentry; - int nr_unused; - int age_limit; /* age in seconds */ - int want_pages; /* pages requested by system */ - int dummy[2]; + long nr_dentry; + long nr_unused; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long dummy[2]; }; extern struct dentry_stat_t dentry_stat; diff --git a/include/linux/fs.h b/include/linux/fs.h index 49e71b0f0e9f..3b3edac75df2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1271,12 +1271,12 @@ struct super_block { struct list_head s_mounts; /* list of mounts; _not_ for fs use */ /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ struct list_head s_dentry_lru; /* unused dentry lru */ - int s_nr_dentry_unused; /* # of dentry on lru */ + long s_nr_dentry_unused; /* # of dentry on lru */ /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp; struct list_head s_inode_lru; /* unused inode lru */ - int s_nr_inodes_unused; /* # of inodes on lru */ + long s_nr_inodes_unused; /* # of inodes on lru */ struct block_device *s_bdev; struct backing_dev_info *s_bdi; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index a4ed56cf0eac..6c28b61bb690 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -49,9 +49,9 @@ struct files_stat_struct { }; struct inodes_stat_t { - int nr_inodes; - int nr_unused; - int dummy[5]; /* padding for sysctl ABI compatibility */ + long nr_inodes; + long nr_unused; + long dummy[5]; /* padding for sysctl ABI compatibility */ }; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 07f6fc468e17..7822cd88a95c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1471,14 +1471,14 @@ static struct ctl_table fs_table[] = { { .procname = "inode-nr", .data = &inodes_stat, - .maxlen = 2*sizeof(int), + .maxlen = 2*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, - .maxlen = 7*sizeof(int), + .maxlen = 7*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, @@ -1508,7 +1508,7 @@ static struct ctl_table fs_table[] = { { .procname = "dentry-state", .data = &dentry_stat, - .maxlen = 6*sizeof(int), + .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, -- 2.20.1