mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Glauber Costa](/assets/img/avatar_default.png)
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 <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Chinner <dchinner@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
204 lines
7.9 KiB
C
204 lines
7.9 KiB
C
#ifndef _UAPI_LINUX_FS_H
|
|
#define _UAPI_LINUX_FS_H
|
|
|
|
/*
|
|
* This file has definitions for some important file table
|
|
* structures etc.
|
|
*/
|
|
|
|
#include <linux/limits.h>
|
|
#include <linux/ioctl.h>
|
|
#include <linux/types.h>
|
|
|
|
/*
|
|
* It's silly to have NR_OPEN bigger than NR_FILE, but you can change
|
|
* the file limit at runtime and only root can increase the per-process
|
|
* nr_file rlimit, so it's safe to set up a ridiculously high absolute
|
|
* upper limit on files-per-process.
|
|
*
|
|
* Some programs (notably those using select()) may have to be
|
|
* recompiled to take full advantage of the new limits..
|
|
*/
|
|
|
|
/* Fixed constants first: */
|
|
#undef NR_OPEN
|
|
#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */
|
|
#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */
|
|
|
|
#define BLOCK_SIZE_BITS 10
|
|
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
|
|
|
|
#define SEEK_SET 0 /* seek relative to beginning of file */
|
|
#define SEEK_CUR 1 /* seek relative to current file position */
|
|
#define SEEK_END 2 /* seek relative to end of file */
|
|
#define SEEK_DATA 3 /* seek to the next data */
|
|
#define SEEK_HOLE 4 /* seek to the next hole */
|
|
#define SEEK_MAX SEEK_HOLE
|
|
|
|
struct fstrim_range {
|
|
__u64 start;
|
|
__u64 len;
|
|
__u64 minlen;
|
|
};
|
|
|
|
/* And dynamically-tunable limits and defaults: */
|
|
struct files_stat_struct {
|
|
unsigned long nr_files; /* read only */
|
|
unsigned long nr_free_files; /* read only */
|
|
unsigned long max_files; /* tunable */
|
|
};
|
|
|
|
struct inodes_stat_t {
|
|
long nr_inodes;
|
|
long nr_unused;
|
|
long dummy[5]; /* padding for sysctl ABI compatibility */
|
|
};
|
|
|
|
|
|
#define NR_FILE 8192 /* this can well be larger on a larger system */
|
|
|
|
|
|
/*
|
|
* These are the fs-independent mount-flags: up to 32 flags are supported
|
|
*/
|
|
#define MS_RDONLY 1 /* Mount read-only */
|
|
#define MS_NOSUID 2 /* Ignore suid and sgid bits */
|
|
#define MS_NODEV 4 /* Disallow access to device special files */
|
|
#define MS_NOEXEC 8 /* Disallow program execution */
|
|
#define MS_SYNCHRONOUS 16 /* Writes are synced at once */
|
|
#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
|
|
#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
|
|
#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
|
|
#define MS_NOATIME 1024 /* Do not update access times. */
|
|
#define MS_NODIRATIME 2048 /* Do not update directory access times */
|
|
#define MS_BIND 4096
|
|
#define MS_MOVE 8192
|
|
#define MS_REC 16384
|
|
#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence.
|
|
MS_VERBOSE is deprecated. */
|
|
#define MS_SILENT 32768
|
|
#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */
|
|
#define MS_UNBINDABLE (1<<17) /* change to unbindable */
|
|
#define MS_PRIVATE (1<<18) /* change to private */
|
|
#define MS_SLAVE (1<<19) /* change to slave */
|
|
#define MS_SHARED (1<<20) /* change to shared */
|
|
#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
|
|
#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
|
|
#define MS_I_VERSION (1<<23) /* Update inode I_version field */
|
|
#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
|
|
|
|
/* These sb flags are internal to the kernel */
|
|
#define MS_NOSEC (1<<28)
|
|
#define MS_BORN (1<<29)
|
|
#define MS_ACTIVE (1<<30)
|
|
#define MS_NOUSER (1<<31)
|
|
|
|
/*
|
|
* Superblock flags that can be altered by MS_REMOUNT
|
|
*/
|
|
#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
|
|
|
|
/*
|
|
* Old magic mount flag and mask
|
|
*/
|
|
#define MS_MGC_VAL 0xC0ED0000
|
|
#define MS_MGC_MSK 0xffff0000
|
|
|
|
/* the read-only stuff doesn't really belong here, but any other place is
|
|
probably as bad and I don't want to create yet another include file. */
|
|
|
|
#define BLKROSET _IO(0x12,93) /* set device read-only (0 = read-write) */
|
|
#define BLKROGET _IO(0x12,94) /* get read-only status (0 = read_write) */
|
|
#define BLKRRPART _IO(0x12,95) /* re-read partition table */
|
|
#define BLKGETSIZE _IO(0x12,96) /* return device size /512 (long *arg) */
|
|
#define BLKFLSBUF _IO(0x12,97) /* flush buffer cache */
|
|
#define BLKRASET _IO(0x12,98) /* set read ahead for block device */
|
|
#define BLKRAGET _IO(0x12,99) /* get current read ahead setting */
|
|
#define BLKFRASET _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
|
|
#define BLKFRAGET _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
|
|
#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
|
|
#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
|
|
#define BLKSSZGET _IO(0x12,104)/* get block device sector size */
|
|
#if 0
|
|
#define BLKPG _IO(0x12,105)/* See blkpg.h */
|
|
|
|
/* Some people are morons. Do not use sizeof! */
|
|
|
|
#define BLKELVGET _IOR(0x12,106,size_t)/* elevator get */
|
|
#define BLKELVSET _IOW(0x12,107,size_t)/* elevator set */
|
|
/* This was here just to show that the number is taken -
|
|
probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
|
|
#endif
|
|
/* A jump here: 108-111 have been used for various private purposes. */
|
|
#define BLKBSZGET _IOR(0x12,112,size_t)
|
|
#define BLKBSZSET _IOW(0x12,113,size_t)
|
|
#define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */
|
|
#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
|
|
#define BLKTRACESTART _IO(0x12,116)
|
|
#define BLKTRACESTOP _IO(0x12,117)
|
|
#define BLKTRACETEARDOWN _IO(0x12,118)
|
|
#define BLKDISCARD _IO(0x12,119)
|
|
#define BLKIOMIN _IO(0x12,120)
|
|
#define BLKIOOPT _IO(0x12,121)
|
|
#define BLKALIGNOFF _IO(0x12,122)
|
|
#define BLKPBSZGET _IO(0x12,123)
|
|
#define BLKDISCARDZEROES _IO(0x12,124)
|
|
#define BLKSECDISCARD _IO(0x12,125)
|
|
#define BLKROTATIONAL _IO(0x12,126)
|
|
#define BLKZEROOUT _IO(0x12,127)
|
|
|
|
#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
|
|
#define FIBMAP _IO(0x00,1) /* bmap access */
|
|
#define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */
|
|
#define FIFREEZE _IOWR('X', 119, int) /* Freeze */
|
|
#define FITHAW _IOWR('X', 120, int) /* Thaw */
|
|
#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */
|
|
|
|
#define FS_IOC_GETFLAGS _IOR('f', 1, long)
|
|
#define FS_IOC_SETFLAGS _IOW('f', 2, long)
|
|
#define FS_IOC_GETVERSION _IOR('v', 1, long)
|
|
#define FS_IOC_SETVERSION _IOW('v', 2, long)
|
|
#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap)
|
|
#define FS_IOC32_GETFLAGS _IOR('f', 1, int)
|
|
#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
|
|
#define FS_IOC32_GETVERSION _IOR('v', 1, int)
|
|
#define FS_IOC32_SETVERSION _IOW('v', 2, int)
|
|
|
|
/*
|
|
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
|
|
*/
|
|
#define FS_SECRM_FL 0x00000001 /* Secure deletion */
|
|
#define FS_UNRM_FL 0x00000002 /* Undelete */
|
|
#define FS_COMPR_FL 0x00000004 /* Compress file */
|
|
#define FS_SYNC_FL 0x00000008 /* Synchronous updates */
|
|
#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
|
|
#define FS_APPEND_FL 0x00000020 /* writes to file may only append */
|
|
#define FS_NODUMP_FL 0x00000040 /* do not dump file */
|
|
#define FS_NOATIME_FL 0x00000080 /* do not update atime */
|
|
/* Reserved for compression usage... */
|
|
#define FS_DIRTY_FL 0x00000100
|
|
#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
|
|
#define FS_NOCOMP_FL 0x00000400 /* Don't compress */
|
|
#define FS_ECOMPR_FL 0x00000800 /* Compression error */
|
|
/* End compression flags --- maybe not all used */
|
|
#define FS_BTREE_FL 0x00001000 /* btree format dir */
|
|
#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */
|
|
#define FS_IMAGIC_FL 0x00002000 /* AFS directory */
|
|
#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */
|
|
#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
|
|
#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
|
|
#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
|
|
#define FS_EXTENT_FL 0x00080000 /* Extents */
|
|
#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */
|
|
#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
|
|
#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */
|
|
|
|
#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
|
|
#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
|
|
|
|
|
|
#define SYNC_FILE_RANGE_WAIT_BEFORE 1
|
|
#define SYNC_FILE_RANGE_WRITE 2
|
|
#define SYNC_FILE_RANGE_WAIT_AFTER 4
|
|
|
|
#endif /* _UAPI_LINUX_FS_H */
|