linux/fs/afs/file.c
David Howells 201a15428b 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

368 lines
8.2 KiB
C

/* AFS filesystem file handling
*
* Copyright (C) 2002, 2007 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 License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include "internal.h"
static int afs_readpage(struct file *file, struct page *page);
static void afs_invalidatepage(struct page *page, unsigned long offset);
static int afs_releasepage(struct page *page, gfp_t gfp_flags);
static int afs_launder_page(struct page *page);
static int afs_readpages(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages);
const struct file_operations afs_file_operations = {
.open = afs_open,
.release = afs_release,
.llseek = generic_file_llseek,
.read = do_sync_read,
.write = do_sync_write,
.aio_read = generic_file_aio_read,
.aio_write = afs_file_write,
.mmap = generic_file_readonly_mmap,
.splice_read = generic_file_splice_read,
.fsync = afs_fsync,
.lock = afs_lock,
.flock = afs_flock,
};
const struct inode_operations afs_file_inode_operations = {
.getattr = afs_getattr,
.setattr = afs_setattr,
.permission = afs_permission,
};
const struct address_space_operations afs_fs_aops = {
.readpage = afs_readpage,
.readpages = afs_readpages,
.set_page_dirty = afs_set_page_dirty,
.launder_page = afs_launder_page,
.releasepage = afs_releasepage,
.invalidatepage = afs_invalidatepage,
.write_begin = afs_write_begin,
.write_end = afs_write_end,
.writepage = afs_writepage,
.writepages = afs_writepages,
};
/*
* open an AFS file or directory and attach a key to it
*/
int afs_open(struct inode *inode, struct file *file)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
struct key *key;
int ret;
_enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
key = afs_request_key(vnode->volume->cell);
if (IS_ERR(key)) {
_leave(" = %ld [key]", PTR_ERR(key));
return PTR_ERR(key);
}
ret = afs_validate(vnode, key);
if (ret < 0) {
_leave(" = %d [val]", ret);
return ret;
}
file->private_data = key;
_leave(" = 0");
return 0;
}
/*
* release an AFS file or directory and discard its key
*/
int afs_release(struct inode *inode, struct file *file)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
_enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
key_put(file->private_data);
_leave(" = 0");
return 0;
}
#ifdef CONFIG_AFS_FSCACHE
/*
* deal with notification that a page was read from the cache
*/
static void afs_file_readpage_read_complete(struct page *page,
void *data,
int error)
{
_enter("%p,%p,%d", page, data, 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);
}
#endif
/*
* AFS read page from file, directory or symlink
*/
static int afs_readpage(struct file *file, struct page *page)
{
struct afs_vnode *vnode;
struct inode *inode;
struct key *key;
size_t len;
off_t offset;
int ret;
inode = page->mapping->host;
if (file) {
key = file->private_data;
ASSERT(key != NULL);
} else {
key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
if (IS_ERR(key)) {
ret = PTR_ERR(key);
goto error_nokey;
}
}
_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
vnode = AFS_FS_I(inode);
BUG_ON(!PageLocked(page));
ret = -ESTALE;
if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
goto error;
/* is it cached? */
#ifdef CONFIG_AFS_FSCACHE
ret = fscache_read_or_alloc_page(vnode->cache,
page,
afs_file_readpage_read_complete,
NULL,
GFP_KERNEL);
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* read BIO submitted (page in cache) */
case 0:
break;
/* page not yet cached */
case -ENODATA:
_debug("cache said ENODATA");
goto go_on;
/* page will not be cached */
case -ENOBUFS:
_debug("cache said ENOBUFS");
default:
go_on:
offset = page->index << PAGE_CACHE_SHIFT;
len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
/* read the contents of the file from the server into the
* page */
ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
if (ret < 0) {
if (ret == -ENOENT) {
_debug("got NOENT from server"
" - marking file deleted and stale");
set_bit(AFS_VNODE_DELETED, &vnode->flags);
ret = -ESTALE;
}
#ifdef CONFIG_AFS_FSCACHE
fscache_uncache_page(vnode->cache, page);
#endif
BUG_ON(PageFsCache(page));
goto error;
}
SetPageUptodate(page);
/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page) &&
fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
fscache_uncache_page(vnode->cache, page);
BUG_ON(PageFsCache(page));
}
#endif
unlock_page(page);
}
if (!file)
key_put(key);
_leave(" = 0");
return 0;
error:
SetPageError(page);
unlock_page(page);
if (!file)
key_put(key);
error_nokey:
_leave(" = %d", ret);
return ret;
}
/*
* read a set of pages
*/
static int afs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct afs_vnode *vnode;
int ret = 0;
_enter(",{%lu},,%d", mapping->host->i_ino, nr_pages);
vnode = AFS_FS_I(mapping->host);
if (vnode->flags & AFS_VNODE_DELETED) {
_leave(" = -ESTALE");
return -ESTALE;
}
/* attempt to read as many of the pages as possible */
#ifdef CONFIG_AFS_FSCACHE
ret = fscache_read_or_alloc_pages(vnode->cache,
mapping,
pages,
&nr_pages,
afs_file_readpage_read_complete,
NULL,
mapping_gfp_mask(mapping));
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* all pages are being read from the cache */
case 0:
BUG_ON(!list_empty(pages));
BUG_ON(nr_pages != 0);
_leave(" = 0 [reading all]");
return 0;
/* there were pages that couldn't be read from the cache */
case -ENODATA:
case -ENOBUFS:
break;
/* other error */
default:
_leave(" = %d", ret);
return ret;
}
/* load the missing pages from the network */
ret = read_cache_pages(mapping, pages, (void *) afs_readpage, file);
_leave(" = %d [netting]", ret);
return ret;
}
/*
* write back a dirty page
*/
static int afs_launder_page(struct page *page)
{
_enter("{%lu}", page->index);
return 0;
}
/*
* invalidate part or all of a page
* - release a page and clean up its private data if offset is 0 (indicating
* the entire page)
*/
static void afs_invalidatepage(struct page *page, unsigned long offset)
{
struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
_enter("{%lu},%lu", page->index, offset);
BUG_ON(!PageLocked(page));
/* we clean up only if the entire page is being invalidated */
if (offset == 0) {
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
fscache_wait_on_page_write(vnode->cache, page);
fscache_uncache_page(vnode->cache, page);
}
#endif
if (PagePrivate(page)) {
if (wb && !PageWriteback(page)) {
set_page_private(page, 0);
afs_put_writeback(wb);
}
if (!page_private(page))
ClearPagePrivate(page);
}
}
_leave("");
}
/*
* release a page and clean up its private state if it's not busy
* - return true if the page can now be released, false if not
*/
static int afs_releasepage(struct page *page, gfp_t gfp_flags)
{
struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
_enter("{{%x:%u}[%lu],%lx},%x",
vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
gfp_flags);
/* deny if page is being written to the cache and the caller hasn't
* elected to wait */
#ifdef CONFIG_AFS_FSCACHE
if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) {
_leave(" = F [cache busy]");
return 0;
}
#endif
if (PagePrivate(page)) {
if (wb) {
set_page_private(page, 0);
afs_put_writeback(wb);
}
ClearPagePrivate(page);
}
/* indicate that the page can be released */
_leave(" = T");
return 1;
}