OpenCloudOS-Kernel/fs/xfs/xfs_sysctl.h

104 lines
3.2 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2001-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_SYSCTL_H__
#define __XFS_SYSCTL_H__
#include <linux/sysctl.h>
/*
* Tunable xfs parameters
*/
typedef struct xfs_sysctl_val {
int min;
int val;
int max;
} xfs_sysctl_val_t;
typedef struct xfs_param {
xfs_sysctl_val_t sgid_inherit; /* Inherit S_ISGID if process' GID is
* not a member of parent dir GID. */
xfs_sysctl_val_t symlink_mode; /* Link creat mode affected by umask */
xfs_sysctl_val_t panic_mask; /* bitmask to cause panic on errors. */
xfs_sysctl_val_t error_level; /* Degree of reporting for problems */
xfs_sysctl_val_t syncd_timer; /* Interval between xfssyncd wakeups */
xfs_sysctl_val_t stats_clear; /* Reset all XFS statistics to zero. */
xfs_sysctl_val_t inherit_sync; /* Inherit the "sync" inode flag. */
xfs_sysctl_val_t inherit_nodump;/* Inherit the "nodump" inode flag. */
xfs_sysctl_val_t inherit_noatim;/* Inherit the "noatime" inode flag. */
xfs_sysctl_val_t xfs_buf_timer; /* Interval between xfsbufd wakeups. */
xfs_sysctl_val_t xfs_buf_age; /* Metadata buffer age before flush. */
xfs_sysctl_val_t inherit_nosym; /* Inherit the "nosymlinks" flag. */
xfs_sysctl_val_t rotorstep; /* inode32 AG rotoring control knob */
xfs_sysctl_val_t inherit_nodfrg;/* Inherit the "nodefrag" inode flag. */
[XFS] Concurrent Multi-File Data Streams In media spaces, video is often stored in a frame-per-file format. When dealing with uncompressed realtime HD video streams in this format, it is crucial that files do not get fragmented and that multiple files a placed contiguously on disk. When multiple streams are being ingested and played out at the same time, it is critical that the filesystem does not cross the streams and interleave them together as this creates seek and readahead cache miss latency and prevents both ingest and playout from meeting frame rate targets. This patch set creates a "stream of files" concept into the allocator to place all the data from a single stream contiguously on disk so that RAID array readahead can be used effectively. Each additional stream gets placed in different allocation groups within the filesystem, thereby ensuring that we don't cross any streams. When an AG fills up, we select a new AG for the stream that is not in use. The core of the functionality is the stream tracking - each inode that we create in a directory needs to be associated with the directories' stream. Hence every time we create a file, we look up the directories' stream object and associate the new file with that object. Once we have a stream object for a file, we use the AG that the stream object point to for allocations. If we can't allocate in that AG (e.g. it is full) we move the entire stream to another AG. Other inodes in the same stream are moved to the new AG on their next allocation (i.e. lazy update). Stream objects are kept in a cache and hold a reference on the inode. Hence the inode cannot be reclaimed while there is an outstanding stream reference. This means that on unlink we need to remove the stream association and we also need to flush all the associations on certain events that want to reclaim all unreferenced inodes (e.g. filesystem freeze). SGI-PV: 964469 SGI-Modid: xfs-linux-melb:xfs-kern:29096a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Barry Naujok <bnaujok@sgi.com> Signed-off-by: Donald Douwsma <donaldd@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com> Signed-off-by: Vlad Apostolov <vapo@sgi.com>
2007-07-11 09:09:12 +08:00
xfs_sysctl_val_t fstrm_timer; /* Filestream dir-AG assoc'n timeout. */
xfs_sysctl_val_t eofb_timer; /* Interval between eofb scan wakeups */
xfs_sysctl_val_t cowb_timer; /* Interval between cowb scan wakeups */
} xfs_param_t;
/*
* xfs_error_level:
*
* How much error reporting will be done when internal problems are
* encountered. These problems normally return an EFSCORRUPTED to their
* caller, with no other information reported.
*
* 0 No error reports
* 1 Report EFSCORRUPTED errors that will cause a filesystem shutdown
* 5 Report all EFSCORRUPTED errors (all of the above errors, plus any
* additional errors that are known to not cause shutdowns)
*
* xfs_panic_mask bit 0x8 turns the error reports into panics
*/
enum {
/* XFS_REFCACHE_SIZE = 1 */
/* XFS_REFCACHE_PURGE = 2 */
/* XFS_RESTRICT_CHOWN = 3 */
XFS_SGID_INHERIT = 4,
XFS_SYMLINK_MODE = 5,
XFS_PANIC_MASK = 6,
XFS_ERRLEVEL = 7,
XFS_SYNCD_TIMER = 8,
/* XFS_PROBE_DMAPI = 9 */
/* XFS_PROBE_IOOPS = 10 */
/* XFS_PROBE_QUOTA = 11 */
XFS_STATS_CLEAR = 12,
XFS_INHERIT_SYNC = 13,
XFS_INHERIT_NODUMP = 14,
XFS_INHERIT_NOATIME = 15,
XFS_BUF_TIMER = 16,
XFS_BUF_AGE = 17,
/* XFS_IO_BYPASS = 18 */
XFS_INHERIT_NOSYM = 19,
XFS_ROTORSTEP = 20,
XFS_INHERIT_NODFRG = 21,
[XFS] Concurrent Multi-File Data Streams In media spaces, video is often stored in a frame-per-file format. When dealing with uncompressed realtime HD video streams in this format, it is crucial that files do not get fragmented and that multiple files a placed contiguously on disk. When multiple streams are being ingested and played out at the same time, it is critical that the filesystem does not cross the streams and interleave them together as this creates seek and readahead cache miss latency and prevents both ingest and playout from meeting frame rate targets. This patch set creates a "stream of files" concept into the allocator to place all the data from a single stream contiguously on disk so that RAID array readahead can be used effectively. Each additional stream gets placed in different allocation groups within the filesystem, thereby ensuring that we don't cross any streams. When an AG fills up, we select a new AG for the stream that is not in use. The core of the functionality is the stream tracking - each inode that we create in a directory needs to be associated with the directories' stream. Hence every time we create a file, we look up the directories' stream object and associate the new file with that object. Once we have a stream object for a file, we use the AG that the stream object point to for allocations. If we can't allocate in that AG (e.g. it is full) we move the entire stream to another AG. Other inodes in the same stream are moved to the new AG on their next allocation (i.e. lazy update). Stream objects are kept in a cache and hold a reference on the inode. Hence the inode cannot be reclaimed while there is an outstanding stream reference. This means that on unlink we need to remove the stream association and we also need to flush all the associations on certain events that want to reclaim all unreferenced inodes (e.g. filesystem freeze). SGI-PV: 964469 SGI-Modid: xfs-linux-melb:xfs-kern:29096a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Barry Naujok <bnaujok@sgi.com> Signed-off-by: Donald Douwsma <donaldd@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com> Signed-off-by: Vlad Apostolov <vapo@sgi.com>
2007-07-11 09:09:12 +08:00
XFS_FILESTREAM_TIMER = 22,
};
extern xfs_param_t xfs_params;
xfs: export log_recovery_delay to delay mount time log recovery XFS log recovery has been discovered to have race conditions with buffers when I/O errors occur. External tools are available to simulate I/O errors to XFS, but this alone is not sufficient for testing log recovery. XFS unconditionally resets the inactive region of the log prior to log recovery to avoid confusion over processing any partially written log records that might have been written before an unclean shutdown. Therefore, unconditional write I/O failures at mount time are caught by the reset sequence rather than log recovery and hinder the ability to test the latter. The device-mapper dm-flakey module uses an up/down timer to define a cycle for when to fail I/Os. Create a pre log recovery delay tunable that can be used to coordinate XFS log recovery with I/O errors simulated by dm-flakey. This facilitates coordination in userspace that allows the reset of stale log blocks to succeed and writes due to log recovery to fail. For example, define a dm-flakey instance with an uptime long enough to allow log reset to succeed and a log recovery delay long enough to allow the dm-flakey uptime to expire. The 'log_recovery_delay' sysfs tunable is exported under /sys/fs/xfs/debug and is only enabled for kernels compiled in XFS debug mode. The value is exported in units of seconds and allows for a delay of up to 60 seconds. Note that this is for XFS debug and test instrumentation purposes only and should not be used by applications. No delay is enabled by default. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-09-09 09:56:13 +08:00
struct xfs_globals {
#ifdef DEBUG
int pwork_threads; /* parallel workqueue threads */
#endif
xfs: export log_recovery_delay to delay mount time log recovery XFS log recovery has been discovered to have race conditions with buffers when I/O errors occur. External tools are available to simulate I/O errors to XFS, but this alone is not sufficient for testing log recovery. XFS unconditionally resets the inactive region of the log prior to log recovery to avoid confusion over processing any partially written log records that might have been written before an unclean shutdown. Therefore, unconditional write I/O failures at mount time are caught by the reset sequence rather than log recovery and hinder the ability to test the latter. The device-mapper dm-flakey module uses an up/down timer to define a cycle for when to fail I/Os. Create a pre log recovery delay tunable that can be used to coordinate XFS log recovery with I/O errors simulated by dm-flakey. This facilitates coordination in userspace that allows the reset of stale log blocks to succeed and writes due to log recovery to fail. For example, define a dm-flakey instance with an uptime long enough to allow log reset to succeed and a log recovery delay long enough to allow the dm-flakey uptime to expire. The 'log_recovery_delay' sysfs tunable is exported under /sys/fs/xfs/debug and is only enabled for kernels compiled in XFS debug mode. The value is exported in units of seconds and allows for a delay of up to 60 seconds. Note that this is for XFS debug and test instrumentation purposes only and should not be used by applications. No delay is enabled by default. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-09-09 09:56:13 +08:00
int log_recovery_delay; /* log recovery delay (secs) */
xfs: add mount delay debug option Similar to log_recovery_delay, this delay occurs between the VFS superblock being initialised and the xfs_mount being fully initialised. It also poisons the per-ag radix tree node so that it can be used for triggering shrinker races during mount such as the following: <run memory pressure workload in background> $ cat dirty-mount.sh #! /bin/bash umount -f /dev/pmem0 mkfs.xfs -f /dev/pmem0 mount /dev/pmem0 /mnt/test rm -f /mnt/test/foo xfs_io -fxc "pwrite 0 4k" -c fsync -c "shutdown" /mnt/test/foo umount /dev/pmem0 # let's crash it now! echo 30 > /sys/fs/xfs/debug/mount_delay mount /dev/pmem0 /mnt/test echo 0 > /sys/fs/xfs/debug/mount_delay umount /dev/pmem0 $ sudo ./dirty-mount.sh ..... [ 60.378118] CPU: 3 PID: 3577 Comm: fs_mark Tainted: G D W 4.16.0-rc5-dgc #440 [ 60.378120] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 60.378124] RIP: 0010:radix_tree_next_chunk+0x76/0x320 [ 60.378127] RSP: 0018:ffffc9000276f4f8 EFLAGS: 00010282 [ 60.383670] RAX: a5a5a5a5a5a5a5a4 RBX: 0000000000000010 RCX: 000000000000001a [ 60.385277] RDX: 0000000000000000 RSI: ffffc9000276f540 RDI: 0000000000000000 [ 60.386554] RBP: 0000000000000000 R08: 0000000000000000 R09: a5a5a5a5a5a5a5a5 [ 60.388194] R10: 0000000000000006 R11: 0000000000000001 R12: ffffc9000276f598 [ 60.389288] R13: 0000000000000040 R14: 0000000000000228 R15: ffff880816cd6458 [ 60.390827] FS: 00007f5c124b9740(0000) GS:ffff88083fc00000(0000) knlGS:0000000000000000 [ 60.392253] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 60.393423] CR2: 00007f5c11bba0b8 CR3: 000000035580e001 CR4: 00000000000606e0 [ 60.394519] Call Trace: [ 60.395252] radix_tree_gang_lookup_tag+0xc4/0x130 [ 60.395948] xfs_perag_get_tag+0x37/0xf0 [ 60.396522] xfs_reclaim_inodes_count+0x32/0x40 [ 60.397178] xfs_fs_nr_cached_objects+0x11/0x20 [ 60.397837] super_cache_count+0x35/0xc0 [ 60.399159] shrink_slab.part.66+0xb1/0x370 [ 60.400194] shrink_node+0x7e/0x1a0 [ 60.401058] try_to_free_pages+0x199/0x470 [ 60.402081] __alloc_pages_slowpath+0x3a1/0xd20 [ 60.403729] __alloc_pages_nodemask+0x1c3/0x200 [ 60.404941] cache_grow_begin+0x20b/0x2e0 [ 60.406164] fallback_alloc+0x160/0x200 [ 60.407088] kmem_cache_alloc+0x111/0x4e0 [ 60.408038] ? xfs_buf_rele+0x61/0x430 [ 60.408925] kmem_zone_alloc+0x61/0xe0 [ 60.409965] xfs_inode_alloc+0x24/0x1d0 ..... Signed-Off-By: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-05-11 12:50:23 +08:00
int mount_delay; /* mount setup delay (secs) */
bool bug_on_assert; /* BUG() the kernel on assert failure */
xfs: introduce an always_cow mode Add a mode where XFS never overwrites existing blocks in place. This is to aid debugging our COW code, and also put infatructure in place for things like possible future support for zoned block devices, which can't support overwrites. This mode is enabled globally by doing a: echo 1 > /sys/fs/xfs/debug/always_cow Note that the parameter is global to allow running all tests in xfstests easily in this mode, which would not easily be possible with a per-fs sysfs file. In always_cow mode persistent preallocations are disabled, and fallocate will fail when called with a 0 mode (with our without FALLOC_FL_KEEP_SIZE), and not create unwritten extent for zeroed space when called with FALLOC_FL_ZERO_RANGE or FALLOC_FL_UNSHARE_RANGE. There are a few interesting xfstests failures when run in always_cow mode: - generic/392 fails because the bytes used in the file used to test hole punch recovery are less after the log replay. This is because the blocks written and then punched out are only freed with a delay due to the logging mechanism. - xfs/170 will fail as the already fragile file streams mechanism doesn't seem to interact well with the COW allocator - xfs/180 xfs/182 xfs/192 xfs/198 xfs/204 and xfs/208 will claim the file system is badly fragmented, but there is not much we can do to avoid that when always writing out of place - xfs/205 fails because overwriting a file in always_cow mode will require new space allocation and the assumption in the test thus don't work anymore. - xfs/326 fails to modify the file at all in always_cow mode after injecting the refcount error, leading to an unexpected md5sum after the remount, but that again is expected Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-02-19 01:38:49 +08:00
bool always_cow; /* use COW fork for all overwrites */
xfs: export log_recovery_delay to delay mount time log recovery XFS log recovery has been discovered to have race conditions with buffers when I/O errors occur. External tools are available to simulate I/O errors to XFS, but this alone is not sufficient for testing log recovery. XFS unconditionally resets the inactive region of the log prior to log recovery to avoid confusion over processing any partially written log records that might have been written before an unclean shutdown. Therefore, unconditional write I/O failures at mount time are caught by the reset sequence rather than log recovery and hinder the ability to test the latter. The device-mapper dm-flakey module uses an up/down timer to define a cycle for when to fail I/Os. Create a pre log recovery delay tunable that can be used to coordinate XFS log recovery with I/O errors simulated by dm-flakey. This facilitates coordination in userspace that allows the reset of stale log blocks to succeed and writes due to log recovery to fail. For example, define a dm-flakey instance with an uptime long enough to allow log reset to succeed and a log recovery delay long enough to allow the dm-flakey uptime to expire. The 'log_recovery_delay' sysfs tunable is exported under /sys/fs/xfs/debug and is only enabled for kernels compiled in XFS debug mode. The value is exported in units of seconds and allows for a delay of up to 60 seconds. Note that this is for XFS debug and test instrumentation purposes only and should not be used by applications. No delay is enabled by default. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-09-09 09:56:13 +08:00
};
extern struct xfs_globals xfs_globals;
#ifdef CONFIG_SYSCTL
extern int xfs_sysctl_register(void);
extern void xfs_sysctl_unregister(void);
#else
# define xfs_sysctl_register() (0)
# define xfs_sysctl_unregister() do { } while (0)
#endif /* CONFIG_SYSCTL */
#endif /* __XFS_SYSCTL_H__ */