linux/fs/nfs/fscache.c

538 lines
14 KiB
C
Raw Normal View History

/* NFS filesystem cache interface
*
* Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_fs_sb.h>
#include <linux/in6.h>
#include <linux/seq_file.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_FSCACHE
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 15:42:42 +00:00
static struct rb_root nfs_fscache_keys = RB_ROOT;
static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
/*
* Get the per-client index cookie for an NFS client if the appropriate mount
* flag was set
* - We always try and get an index cookie for the client, but get filehandle
* cookies on a per-superblock basis, depending on the mount flags
*/
void nfs_fscache_get_client_cookie(struct nfs_client *clp)
{
/* create a cache index for looking up filehandles */
clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index,
&nfs_fscache_server_index_def,
clp);
dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n",
clp, clp->fscache);
}
/*
* Dispose of a per-client cookie
*/
void nfs_fscache_release_client_cookie(struct nfs_client *clp)
{
dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n",
clp, clp->fscache);
fscache_relinquish_cookie(clp->fscache, 0);
clp->fscache = NULL;
}
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 15:42:42 +00:00
/*
* Get the cache cookie for an NFS superblock. We have to handle
* uniquification here because the cache doesn't do it for us.
*
* The default uniquifier is just an empty string, but it may be overridden
* either by the 'fsc=xxx' option to mount, or by inheriting it from the parent
* superblock across an automount point of some nature.
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 15:42:42 +00:00
*/
void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq,
struct nfs_clone_mount *mntdata)
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 15:42:42 +00:00
{
struct nfs_fscache_key *key, *xkey;
struct nfs_server *nfss = NFS_SB(sb);
struct rb_node **p, *parent;
int diff, ulen;
if (uniq) {
ulen = strlen(uniq);
} else if (mntdata) {
struct nfs_server *mnt_s = NFS_SB(mntdata->sb);
if (mnt_s->fscache_key) {
uniq = mnt_s->fscache_key->key.uniquifier;
ulen = mnt_s->fscache_key->key.uniq_len;
}
}
if (!uniq) {
uniq = "";
ulen = 1;
}
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 15:42:42 +00:00
key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
if (!key)
return;
key->nfs_client = nfss->nfs_client;
key->key.super.s_flags = sb->s_flags & NFS_MS_MASK;
key->key.nfs_server.flags = nfss->flags;
key->key.nfs_server.rsize = nfss->rsize;
key->key.nfs_server.wsize = nfss->wsize;
key->key.nfs_server.acregmin = nfss->acregmin;
key->key.nfs_server.acregmax = nfss->acregmax;
key->key.nfs_server.acdirmin = nfss->acdirmin;
key->key.nfs_server.acdirmax = nfss->acdirmax;
key->key.nfs_server.fsid = nfss->fsid;
key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor;
key->key.uniq_len = ulen;
memcpy(key->key.uniquifier, uniq, ulen);
spin_lock(&nfs_fscache_keys_lock);
p = &nfs_fscache_keys.rb_node;
parent = NULL;
while (*p) {
parent = *p;
xkey = rb_entry(parent, struct nfs_fscache_key, node);
if (key->nfs_client < xkey->nfs_client)
goto go_left;
if (key->nfs_client > xkey->nfs_client)
goto go_right;
diff = memcmp(&key->key, &xkey->key, sizeof(key->key));
if (diff < 0)
goto go_left;
if (diff > 0)
goto go_right;
if (key->key.uniq_len == 0)
goto non_unique;
diff = memcmp(key->key.uniquifier,
xkey->key.uniquifier,
key->key.uniq_len);
if (diff < 0)
goto go_left;
if (diff > 0)
goto go_right;
goto non_unique;
go_left:
p = &(*p)->rb_left;
continue;
go_right:
p = &(*p)->rb_right;
}
rb_link_node(&key->node, parent, p);
rb_insert_color(&key->node, &nfs_fscache_keys);
spin_unlock(&nfs_fscache_keys_lock);
nfss->fscache_key = key;
/* create a cache index for looking up filehandles */
nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
&nfs_fscache_super_index_def,
nfss);
dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
nfss, nfss->fscache);
return;
non_unique:
spin_unlock(&nfs_fscache_keys_lock);
kfree(key);
nfss->fscache_key = NULL;
nfss->fscache = NULL;
printk(KERN_WARNING "NFS:"
" Cache request denied due to non-unique superblock keys\n");
}
/*
* release a per-superblock cookie
*/
void nfs_fscache_release_super_cookie(struct super_block *sb)
{
struct nfs_server *nfss = NFS_SB(sb);
dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n",
nfss, nfss->fscache);
fscache_relinquish_cookie(nfss->fscache, 0);
nfss->fscache = NULL;
if (nfss->fscache_key) {
spin_lock(&nfs_fscache_keys_lock);
rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys);
spin_unlock(&nfs_fscache_keys_lock);
kfree(nfss->fscache_key);
nfss->fscache_key = NULL;
}
}
/*
* Initialise the per-inode cache cookie pointer for an NFS inode.
*/
void nfs_fscache_init_inode_cookie(struct inode *inode)
{
NFS_I(inode)->fscache = NULL;
if (S_ISREG(inode->i_mode))
set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
}
/*
* Get the per-inode cache cookie for an NFS inode.
*/
static void nfs_fscache_enable_inode_cookie(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
struct nfs_inode *nfsi = NFS_I(inode);
if (nfsi->fscache || !NFS_FSCACHE(inode))
return;
if ((NFS_SB(sb)->options & NFS_OPTION_FSCACHE)) {
nfsi->fscache = fscache_acquire_cookie(
NFS_SB(sb)->fscache,
&nfs_fscache_inode_object_def,
nfsi);
dfprintk(FSCACHE, "NFS: get FH cookie (0x%p/0x%p/0x%p)\n",
sb, nfsi, nfsi->fscache);
}
}
/*
* Release a per-inode cookie.
*/
void nfs_fscache_release_inode_cookie(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n",
nfsi, nfsi->fscache);
fscache_relinquish_cookie(nfsi->fscache, 0);
nfsi->fscache = NULL;
}
/*
* Retire a per-inode cookie, destroying the data attached to it.
*/
void nfs_fscache_zap_inode_cookie(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
dfprintk(FSCACHE, "NFS: zapping cookie (0x%p/0x%p)\n",
nfsi, nfsi->fscache);
fscache_relinquish_cookie(nfsi->fscache, 1);
nfsi->fscache = NULL;
}
/*
* Turn off the cache with regard to a per-inode cookie if opened for writing,
* invalidating all the pages in the page cache relating to the associated
* inode to clear the per-page caching.
*/
static void nfs_fscache_disable_inode_cookie(struct inode *inode)
{
clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
if (NFS_I(inode)->fscache) {
dfprintk(FSCACHE,
"NFS: nfsi 0x%p turning cache off\n", NFS_I(inode));
/* Need to invalidate any mapped pages that were read in before
* turning off the cache.
*/
if (inode->i_mapping && inode->i_mapping->nrpages)
invalidate_inode_pages2(inode->i_mapping);
nfs_fscache_zap_inode_cookie(inode);
}
}
/*
* wait_on_bit() sleep function for uninterruptible waiting
*/
static int nfs_fscache_wait_bit(void *flags)
{
schedule();
return 0;
}
/*
* Lock against someone else trying to also acquire or relinquish a cookie
*/
static inline void nfs_fscache_inode_lock(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
while (test_and_set_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags))
wait_on_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK,
nfs_fscache_wait_bit, TASK_UNINTERRUPTIBLE);
}
/*
* Unlock cookie management lock
*/
static inline void nfs_fscache_inode_unlock(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
smp_mb__before_clear_bit();
clear_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags);
smp_mb__after_clear_bit();
wake_up_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK);
}
/*
* Decide if we should enable or disable local caching for this inode.
* - For now, with NFS, only regular files that are open read-only will be able
* to use the cache.
* - May be invoked multiple times in parallel by parallel nfs_open() functions.
*/
void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
{
if (NFS_FSCACHE(inode)) {
nfs_fscache_inode_lock(inode);
if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
nfs_fscache_disable_inode_cookie(inode);
else
nfs_fscache_enable_inode_cookie(inode);
nfs_fscache_inode_unlock(inode);
}
}
/*
* Replace a per-inode cookie due to revalidation detecting a file having
* changed on the server.
*/
void nfs_fscache_reset_inode_cookie(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_server *nfss = NFS_SERVER(inode);
struct fscache_cookie *old = nfsi->fscache;
nfs_fscache_inode_lock(inode);
if (nfsi->fscache) {
/* retire the current fscache cache and get a new one */
fscache_relinquish_cookie(nfsi->fscache, 1);
nfsi->fscache = fscache_acquire_cookie(
nfss->nfs_client->fscache,
&nfs_fscache_inode_object_def,
nfsi);
dfprintk(FSCACHE,
"NFS: revalidation new cookie (0x%p/0x%p/0x%p/0x%p)\n",
nfss, nfsi, old, nfsi->fscache);
}
nfs_fscache_inode_unlock(inode);
}
/*
* Release the caching state associated with a page, if the page isn't busy
* interacting with the cache.
* - Returns true (can release page) or false (page busy).
*/
int nfs_fscache_release_page(struct page *page, gfp_t gfp)
{
if (PageFsCache(page)) {
struct nfs_inode *nfsi = NFS_I(page->mapping->host);
struct fscache_cookie *cookie = nfsi->fscache;
BUG_ON(!cookie);
dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
cookie, page, nfsi);
FS-Cache: Handle pages pending storage that get evicted under OOM conditions Handle netfs pages that the vmscan algorithm wants to evict from the pagecache under OOM conditions, but that are waiting for write to the cache. Under these conditions, vmscan calls the releasepage() function of the netfs, asking if a page can be discarded. The problem is typified by the following trace of a stuck process: kslowd005 D 0000000000000000 0 4253 2 0x00000080 ffff88001b14f370 0000000000000046 ffff880020d0d000 0000000000000007 0000000000000006 0000000000000001 ffff88001b14ffd8 ffff880020d0d2a8 000000000000ddf0 00000000000118c0 00000000000118c0 ffff880020d0d2a8 Call Trace: [<ffffffffa00782d8>] __fscache_wait_on_page_write+0x8b/0xa7 [fscache] [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34 [<ffffffffa0078240>] ? __fscache_check_page_write+0x63/0x70 [fscache] [<ffffffffa00b671d>] nfs_fscache_release_page+0x4e/0xc4 [nfs] [<ffffffffa00927f0>] nfs_release_page+0x3c/0x41 [nfs] [<ffffffff810885d3>] try_to_release_page+0x32/0x3b [<ffffffff81093203>] shrink_page_list+0x316/0x4ac [<ffffffff8109372b>] shrink_inactive_list+0x392/0x67c [<ffffffff813532fa>] ? __mutex_unlock_slowpath+0x100/0x10b [<ffffffff81058df0>] ? trace_hardirqs_on_caller+0x10c/0x130 [<ffffffff8135330e>] ? mutex_unlock+0x9/0xb [<ffffffff81093aa2>] shrink_list+0x8d/0x8f [<ffffffff81093d1c>] shrink_zone+0x278/0x33c [<ffffffff81052d6c>] ? ktime_get_ts+0xad/0xba [<ffffffff81094b13>] try_to_free_pages+0x22e/0x392 [<ffffffff81091e24>] ? isolate_pages_global+0x0/0x212 [<ffffffff8108e743>] __alloc_pages_nodemask+0x3dc/0x5cf [<ffffffff81089529>] grab_cache_page_write_begin+0x65/0xaa [<ffffffff8110f8c0>] ext3_write_begin+0x78/0x1eb [<ffffffff81089ec5>] generic_file_buffered_write+0x109/0x28c [<ffffffff8103cb69>] ? current_fs_time+0x22/0x29 [<ffffffff8108a509>] __generic_file_aio_write+0x350/0x385 [<ffffffff8108a588>] ? generic_file_aio_write+0x4a/0xae [<ffffffff8108a59e>] generic_file_aio_write+0x60/0xae [<ffffffff810b2e82>] do_sync_write+0xe3/0x120 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34 [<ffffffff810b18e1>] ? __dentry_open+0x1a5/0x2b8 [<ffffffff810b1a76>] ? dentry_open+0x82/0x89 [<ffffffffa00e693c>] cachefiles_write_page+0x298/0x335 [cachefiles] [<ffffffffa0077147>] fscache_write_op+0x178/0x2c2 [fscache] [<ffffffffa0075656>] fscache_op_execute+0x7a/0xd1 [fscache] [<ffffffff81082093>] slow_work_execute+0x18f/0x2d1 [<ffffffff8108239a>] slow_work_thread+0x1c5/0x308 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34 [<ffffffff810821d5>] ? slow_work_thread+0x0/0x308 [<ffffffff8104be91>] kthread+0x7a/0x82 [<ffffffff8100beda>] child_rip+0xa/0x20 [<ffffffff8100b87c>] ? restore_args+0x0/0x30 [<ffffffff8102ef83>] ? tg_shares_up+0x171/0x227 [<ffffffff8104be17>] ? kthread+0x0/0x82 [<ffffffff8100bed0>] ? child_rip+0x0/0x20 In the above backtrace, the following is happening: (1) A page storage operation is being executed by a slow-work thread (fscache_write_op()). (2) FS-Cache farms the operation out to the cache to perform (cachefiles_write_page()). (3) CacheFiles is then calling Ext3 to perform the actual write, using Ext3's standard write (do_sync_write()) under KERNEL_DS directly from the netfs page. (4) However, for Ext3 to perform the write, it must allocate some memory, in particular, it must allocate at least one page cache page into which it can copy the data from the netfs page. (5) Under OOM conditions, the memory allocator can't immediately come up with a page, so it uses vmscan to find something to discard (try_to_free_pages()). (6) vmscan finds a clean netfs page it might be able to discard (possibly the one it's trying to write out). (7) The netfs is called to throw the page away (nfs_release_page()) - but it's called with __GFP_WAIT, so the netfs decides to wait for the store to complete (__fscache_wait_on_page_write()). (8) This blocks a slow-work processing thread - possibly against itself. The system ends up stuck because it can't write out any netfs pages to the cache without allocating more memory. To avoid this, we make FS-Cache cancel some writes that aren't in the middle of actually being performed. This means that some data won't make it into the cache this time. To support this, a new FS-Cache function is added fscache_maybe_release_page() that replaces what the netfs releasepage() functions used to do with respect to the cache. The decisions fscache_maybe_release_page() makes are counted and displayed through /proc/fs/fscache/stats on a line labelled "VmScan". There are four counters provided: "nos=N" - pages that weren't pending storage; "gon=N" - pages that were pending storage when we first looked, but weren't by the time we got the object lock; "bsy=N" - pages that we ignored as they were actively being written when we looked; and "can=N" - pages that we cancelled the storage of. What I'd really like to do is alter the behaviour of the cancellation heuristics, depending on how necessary it is to expel pages. If there are plenty of other pages that aren't waiting to be written to the cache that could be ejected first, then it would be nice to hold up on immediate cancellation of cache writes - but I don't see a way of doing that. Signed-off-by: David Howells <dhowells@redhat.com>
2009-11-19 18:11:35 +00:00
if (!fscache_maybe_release_page(cookie, page, gfp))
return 0;
nfs_add_fscache_stats(page->mapping->host,
NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
}
return 1;
}
/*
* Release the caching state associated with a page if undergoing complete page
* invalidation.
*/
void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct fscache_cookie *cookie = nfsi->fscache;
BUG_ON(!cookie);
dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n",
cookie, page, nfsi);
fscache_wait_on_page_write(cookie, page);
BUG_ON(!PageLocked(page));
fscache_uncache_page(cookie, page);
nfs_add_fscache_stats(page->mapping->host,
NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
}
/*
* Handle completion of a page being read from the cache.
* - Called in process (keventd) context.
*/
static void nfs_readpage_from_fscache_complete(struct page *page,
void *context,
int error)
{
dfprintk(FSCACHE,
"NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n",
page, context, error);
/* if the read completes with an error, we just unlock the page and let
* the VM reissue the readpage */
if (!error) {
SetPageUptodate(page);
unlock_page(page);
} else {
error = nfs_readpage_async(context, page->mapping->host, page);
if (error)
unlock_page(page);
}
}
/*
* Retrieve a page from fscache
*/
int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
struct inode *inode, struct page *page)
{
int ret;
dfprintk(FSCACHE,
"NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
NFS_I(inode)->fscache, page, page->index, page->flags, inode);
ret = fscache_read_or_alloc_page(NFS_I(inode)->fscache,
page,
nfs_readpage_from_fscache_complete,
ctx,
GFP_KERNEL);
switch (ret) {
case 0: /* read BIO submitted (page in fscache) */
dfprintk(FSCACHE,
"NFS: readpage_from_fscache: BIO submitted\n");
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, 1);
return ret;
case -ENOBUFS: /* inode not in cache */
case -ENODATA: /* page not in cache */
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
dfprintk(FSCACHE,
"NFS: readpage_from_fscache %d\n", ret);
return 1;
default:
dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret);
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
}
return ret;
}
/*
* Retrieve a set of pages from fscache
*/
int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages)
{
unsigned npages = *nr_pages;
int ret;
dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
NFS_I(inode)->fscache, npages, inode);
ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
mapping, pages, nr_pages,
nfs_readpage_from_fscache_complete,
ctx,
mapping_gfp_mask(mapping));
if (*nr_pages < npages)
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
npages);
if (*nr_pages > 0)
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
*nr_pages);
switch (ret) {
case 0: /* read submitted to the cache for all pages */
BUG_ON(!list_empty(pages));
BUG_ON(*nr_pages != 0);
dfprintk(FSCACHE,
"NFS: nfs_getpages_from_fscache: submitted\n");
return ret;
case -ENOBUFS: /* some pages aren't cached and can't be */
case -ENODATA: /* some pages aren't cached */
dfprintk(FSCACHE,
"NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
return 1;
default:
dfprintk(FSCACHE,
"NFS: nfs_getpages_from_fscache: ret %d\n", ret);
}
return ret;
}
/*
* Store a newly fetched page in fscache
* - PG_fscache must be set on the page
*/
void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
{
int ret;
dfprintk(FSCACHE,
"NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
NFS_I(inode)->fscache, page, page->index, page->flags, sync);
ret = fscache_write_page(NFS_I(inode)->fscache, page, GFP_KERNEL);
dfprintk(FSCACHE,
"NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
page, page->index, page->flags, ret);
if (ret != 0) {
fscache_uncache_page(NFS_I(inode)->fscache, page);
nfs_add_fscache_stats(inode,
NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, 1);
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
} else {
nfs_add_fscache_stats(inode,
NFSIOS_FSCACHE_PAGES_WRITTEN_OK, 1);
}
}