* [PATCH 0/3] ceph: persistent caching with fscache
@ 2013-08-07 23:15 Milosz Tanski
2013-08-07 23:15 ` [PATCH 1/3] new cachefiles interface to check cache consistency Hongyi Jia
` (2 more replies)
0 siblings, 3 replies; 6+ messages in thread
From: Milosz Tanski @ 2013-08-07 23:15 UTC (permalink / raw)
To: ceph-devel
Cc: linux-cachefs, linux-fsdevel, sage, zheng.z.yan, dhowells, jiayisuse
This is a new and reworked patchset. I would greatly appreciate another review
of patch.
Since my last patchset I rethought how implement fscache in Ceph. Originally, I
started taking queues largely from the NFS and CIFS code. The code in those
filesystems as implemented is racy and I ended up wit the same kind of problems.
This was exasperated by how Ceph handles cache caps.
Previously I would create the fscache cookie every time we gained a cache cap
and remove it when we lost it.
The current approach is to create the cache cookie the first time we reference
the inode by a file. After that we don't get rid of the cookie till we dispose
of the inode. I like this approach a lot more then creating and destroying
fscache cookies every time we gain/loose a cache cap. And it avoids the need
for locking everywhere in the read, write, invalidate page code. It's not race
prone and simple. Finally, I don't have to worry about delaying a bunch of
work till later due to having the cap being in the inode spinlock.
The only piece of serialization now if taking out the i_mutex when creating the
cookie to prevent multiple open() race.
The cache is invalidated every time we open the file for write, size changes.
Every time we gain a cache cap we schedule a cookie re-validation to a work
queue (with the exception of the first one, as fscache already invokes
validation). The cache is ignored till the re-validation work runs and changes
the re-validation sequence number (sometimes invalidating it if needed).
In order to use this you need need kenel 3.11 rc3 or greater. 3.11 contains a
big number of core fscache fixes. Otherwise you'll quickly run into oops on a
high concurrent workload.
The first two patches I included were not written by me but were written by
Hongyi Jia. He implemented the cookie re-validation scheme into fscache core.
Hongyi Jia (2):
new cachefiles interface to check cache consistency
new fscache interface to check cache consistency
Milosz Tanski (1):
ceph: use fscache as a local presisent cache
fs/cachefiles/interface.c | 19 +++
fs/cachefiles/internal.h | 1 +
fs/cachefiles/xattr.c | 39 ++++++
fs/ceph/Kconfig | 9 ++
fs/ceph/Makefile | 2 +
fs/ceph/addr.c | 70 +++++++---
fs/ceph/cache.c | 306 ++++++++++++++++++++++++++++++++++++++++++
fs/ceph/cache.h | 117 ++++++++++++++++
fs/ceph/caps.c | 19 ++-
fs/ceph/file.c | 17 +++
fs/ceph/inode.c | 69 +++++++++-
fs/ceph/super.c | 48 ++++++-
fs/ceph/super.h | 17 +++
fs/fscache/cookie.c | 22 +++
include/linux/fscache-cache.h | 4 +
include/linux/fscache.h | 17 +++
16 files changed, 748 insertions(+), 28 deletions(-)
create mode 100644 fs/ceph/cache.c
create mode 100644 fs/ceph/cache.h
--
1.8.1.2
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH 1/3] new cachefiles interface to check cache consistency
2013-08-07 23:15 [PATCH 0/3] ceph: persistent caching with fscache Milosz Tanski
@ 2013-08-07 23:15 ` Hongyi Jia
2013-08-07 23:15 ` [PATCH 2/3] new fscache " Hongyi Jia
2013-08-07 23:16 ` [PATCH 3/3] ceph: use fscache as a local presisent cache Milosz Tanski
2 siblings, 0 replies; 6+ messages in thread
From: Hongyi Jia @ 2013-08-07 23:15 UTC (permalink / raw)
To: ceph-devel
Cc: linux-cachefs, linux-fsdevel, sage, zheng.z.yan, dhowells, jiayisuse
Signed-off-by: Hongyi Jia <jiayisuse@gmail.com>
Signed-off-by: Milosz Tanski <milosz@adfin.com>
---
fs/cachefiles/interface.c | 19 +++++++++++++++++++
fs/cachefiles/internal.h | 1 +
fs/cachefiles/xattr.c | 39 +++++++++++++++++++++++++++++++++++++++
3 files changed, 59 insertions(+)
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index d4c1206..0805f23 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -378,6 +378,24 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache)
}
/*
+ * check if the backing cache is updated to FS-Cache
+ * - called by FS-Cache when evaluates if need to invalidate the cache
+ */
+static bool cachefiles_check_consistency(struct fscache_object *_object)
+{
+ struct cachefiles_object *object;
+ int ret;
+
+ _enter("{OBJ%x}", _object->debug_id);
+
+ object = container_of(_object, struct cachefiles_object, fscache);
+ ret = cachefiles_check_auxdata(object);
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
* notification the attributes on an object have changed
* - called with reads/writes excluded by FS-Cache
*/
@@ -522,4 +540,5 @@ const struct fscache_cache_ops cachefiles_cache_ops = {
.write_page = cachefiles_write_page,
.uncache_page = cachefiles_uncache_page,
.dissociate_pages = cachefiles_dissociate_pages,
+ .check_consistency = cachefiles_check_consistency,
};
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 4938251..e102d22 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -239,6 +239,7 @@ extern int cachefiles_check_object_xattr(struct cachefiles_object *object,
struct cachefiles_xattr *auxdata);
extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
struct dentry *dentry);
+extern bool cachefiles_check_auxdata(struct cachefiles_object *object);
/*
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index 2476e51..aafaac3 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -157,6 +157,45 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object,
}
/*
+ * check the consistency between the backing cache and the FS-Cache cookie
+ */
+bool cachefiles_check_auxdata(struct cachefiles_object *object)
+{
+ struct cachefiles_xattr *auxbuf;
+ struct dentry *dentry = object->dentry;
+ unsigned int dlen;
+ int ret;
+
+ ASSERT(dentry);
+ ASSERT(dentry->d_inode);
+
+ auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL);
+ if (!auxbuf)
+ return false;
+
+ auxbuf->len = vfs_getxattr(dentry, cachefiles_xattr_cache,
+ &auxbuf->type, 512 + 1);
+ if (auxbuf->len < 1)
+ return false;
+
+ if (auxbuf->type != object->fscache.cookie->def->type)
+ return false;
+
+ if (!object->fscache.cookie->def->check_aux)
+ return false;
+
+ dlen = auxbuf->len - 1;
+ ret = fscache_check_aux(&object->fscache,
+ &auxbuf->data, dlen);
+
+ kfree(auxbuf);
+ if (ret == FSCACHE_CHECKAUX_OKAY)
+ return true;
+ else
+ return false;
+}
+
+/*
* check the state xattr on a cache file
* - return -ESTALE if the object should be deleted
*/
--
1.8.1.2
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH 2/3] new fscache interface to check cache consistency
2013-08-07 23:15 [PATCH 0/3] ceph: persistent caching with fscache Milosz Tanski
2013-08-07 23:15 ` [PATCH 1/3] new cachefiles interface to check cache consistency Hongyi Jia
@ 2013-08-07 23:15 ` Hongyi Jia
2013-08-07 23:16 ` [PATCH 3/3] ceph: use fscache as a local presisent cache Milosz Tanski
2 siblings, 0 replies; 6+ messages in thread
From: Hongyi Jia @ 2013-08-07 23:15 UTC (permalink / raw)
To: ceph-devel; +Cc: sage, zheng.z.yan, linux-cachefs, linux-fsdevel
Signed-off-by: Hongyi Jia <jiayisuse@gmail.com>
Signed-off-by: Milosz Tanski <milosz@adfin.com>
---
fs/fscache/cookie.c | 22 ++++++++++++++++++++++
include/linux/fscache-cache.h | 4 ++++
include/linux/fscache.h | 17 +++++++++++++++++
3 files changed, 43 insertions(+)
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 0e91a3c..bfa1d3b 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -533,6 +533,28 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
EXPORT_SYMBOL(__fscache_relinquish_cookie);
/*
+ * check the consistency between the netfs inode and the backing cache
+ *
+ * NOTE: it only serves no-index type
+ */
+bool __fscache_check_consistency(struct fscache_cookie *cookie)
+{
+ struct fscache_object *object;
+
+ if (cookie->def->type != FSCACHE_COOKIE_TYPE_DATAFILE)
+ return false;
+
+ if (hlist_empty(&cookie->backing_objects))
+ return false;
+
+ object = hlist_entry(cookie->backing_objects.first,
+ struct fscache_object, cookie_link);
+
+ return object->cache->ops->check_consistency(object);
+}
+EXPORT_SYMBOL(__fscache_check_consistency);
+
+/*
* destroy a cookie
*/
void __fscache_cookie_put(struct fscache_cookie *cookie)
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index a9ff9a3..5513342 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -302,6 +302,10 @@ struct fscache_cache_ops {
/* dissociate a cache from all the pages it was backing */
void (*dissociate_pages)(struct fscache_cache *cache);
+
+ /* check the consistency between the backing cache and the FS-Cache
+ * cookie */
+ bool (*check_consistency)(struct fscache_object *object);
};
/*
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 7a08623..7a49e8f 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -183,6 +183,7 @@ extern struct fscache_cookie *__fscache_acquire_cookie(
const struct fscache_cookie_def *,
void *);
extern void __fscache_relinquish_cookie(struct fscache_cookie *, int);
+extern bool __fscache_check_consistency(struct fscache_cookie *);
extern void __fscache_update_cookie(struct fscache_cookie *);
extern int __fscache_attr_changed(struct fscache_cookie *);
extern void __fscache_invalidate(struct fscache_cookie *);
@@ -326,6 +327,22 @@ void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
}
/**
+ * fscache_check_consistency - Request that if the cache is updated
+ * @cookie: The cookie representing the cache object
+ *
+ * Request an consistency check from fscache, which resorts to backing
+ * cache.
+ */
+static inline
+bool fscache_check_consistency(struct fscache_cookie *cookie)
+{
+ if (fscache_cookie_valid(cookie))
+ return __fscache_check_consistency(cookie);
+ else
+ return false;
+}
+
+/**
* fscache_update_cookie - Request that a cache object be updated
* @cookie: The cookie representing the cache object
*
--
1.8.1.2
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH 3/3] ceph: use fscache as a local presisent cache
2013-08-07 23:15 [PATCH 0/3] ceph: persistent caching with fscache Milosz Tanski
2013-08-07 23:15 ` [PATCH 1/3] new cachefiles interface to check cache consistency Hongyi Jia
2013-08-07 23:15 ` [PATCH 2/3] new fscache " Hongyi Jia
@ 2013-08-07 23:16 ` Milosz Tanski
2013-08-09 4:16 ` Sage Weil
2 siblings, 1 reply; 6+ messages in thread
From: Milosz Tanski @ 2013-08-07 23:16 UTC (permalink / raw)
To: ceph-devel
Cc: linux-cachefs, linux-fsdevel, sage, zheng.z.yan, dhowells, jiayisuse
Adding support for fscache to the Ceph filesystem. This would bring it to on
par with some of the other network filesystems in Linux (like NFS, AFS, etc...)
In order to mount the filesystem with fscache the 'fsc' mount option must be
passed.
Signed-off-by: Milosz Tanski <milosz@adfin.com>
---
fs/ceph/Kconfig | 9 ++
fs/ceph/Makefile | 2 +
fs/ceph/addr.c | 70 +++++++++----
fs/ceph/cache.c | 306 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/ceph/cache.h | 117 +++++++++++++++++++++
fs/ceph/caps.c | 19 +++-
fs/ceph/file.c | 17 ++++
fs/ceph/inode.c | 69 ++++++++++++-
fs/ceph/super.c | 48 ++++++++-
fs/ceph/super.h | 17 ++++
10 files changed, 646 insertions(+), 28 deletions(-)
create mode 100644 fs/ceph/cache.c
create mode 100644 fs/ceph/cache.h
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 49bc782..ac9a2ef 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -16,3 +16,12 @@ config CEPH_FS
If unsure, say N.
+if CEPH_FS
+config CEPH_FSCACHE
+ bool "Enable Ceph client caching support"
+ depends on CEPH_FS=m && FSCACHE || CEPH_FS=y && FSCACHE=y
+ help
+ Choose Y here to enable persistent, read-only local
+ caching support for Ceph clients using FS-Cache
+
+endif
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index bd35212..0af0678 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -9,3 +9,5 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
mds_client.o mdsmap.o strings.o ceph_frag.o \
debugfs.o
+ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
+
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index afb2fc2..de6de0e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -11,6 +11,7 @@
#include "super.h"
#include "mds_client.h"
+#include "cache.h"
#include <linux/ceph/osd_client.h>
/*
@@ -149,11 +150,23 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc = page_snap_context(page);
- BUG_ON(!PageLocked(page));
- BUG_ON(!PagePrivate(page));
BUG_ON(!page->mapping);
inode = page->mapping->host;
+ ci = ceph_inode(inode);
+
+ if (offset != 0) {
+ dout("%p invalidatepage %p idx %lu partial dirty page\n",
+ inode, page, page->index);
+ return;
+ }
+
+ ceph_invalidate_fscache_page(inode, page);
+
+ if (!PagePrivate(page))
+ return;
+
+ BUG_ON(!PageLocked(page));
/*
* We can get non-dirty pages here due to races between
@@ -163,31 +176,28 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
if (!PageDirty(page))
pr_err("%p invalidatepage %p page not dirty\n", inode, page);
- if (offset == 0)
- ClearPageChecked(page);
+ ClearPageChecked(page);
- ci = ceph_inode(inode);
- if (offset == 0) {
- dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
- inode, page, page->index, offset);
- ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
- ceph_put_snap_context(snapc);
- page->private = 0;
- ClearPagePrivate(page);
- } else {
- dout("%p invalidatepage %p idx %lu partial dirty page\n",
- inode, page, page->index);
- }
+ dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
+ inode, page, page->index, offset);
+
+ ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+ ceph_put_snap_context(snapc);
+ page->private = 0;
+ ClearPagePrivate(page);
}
-/* just a sanity check */
static int ceph_releasepage(struct page *page, gfp_t g)
{
struct inode *inode = page->mapping ? page->mapping->host : NULL;
dout("%p releasepage %p idx %lu\n", inode, page, page->index);
WARN_ON(PageDirty(page));
- WARN_ON(PagePrivate(page));
- return 0;
+
+ /* Can we release the page from the cache? */
+ if (!ceph_release_fscache_page(page, g))
+ return 0;
+
+ return !PagePrivate(page);
}
/*
@@ -197,11 +207,16 @@ static int readpage_nounlock(struct file *filp, struct page *page)
{
struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_osd_client *osdc =
+ struct ceph_osd_client *osdc =
&ceph_inode_to_client(inode)->client->osdc;
int err = 0;
u64 len = PAGE_CACHE_SIZE;
+ err = ceph_readpage_from_fscache(inode, page);
+
+ if (err == 0)
+ goto out;
+
dout("readpage inode %p file %p page %p index %lu\n",
inode, filp, page, page->index);
err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
@@ -219,6 +234,9 @@ static int readpage_nounlock(struct file *filp, struct page *page)
}
SetPageUptodate(page);
+ if (err == 0)
+ ceph_readpage_to_fscache(inode, page);
+
out:
return err < 0 ? err : 0;
}
@@ -261,6 +279,7 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
page->index);
flush_dcache_page(page);
SetPageUptodate(page);
+ ceph_readpage_to_fscache(inode, page);
unlock_page(page);
page_cache_release(page);
bytes -= PAGE_CACHE_SIZE;
@@ -330,7 +349,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
page = list_entry(page_list->prev, struct page, lru);
BUG_ON(PageLocked(page));
list_del(&page->lru);
-
+
dout("start_read %p adding %p idx %lu\n", inode, page,
page->index);
if (add_to_page_cache_lru(page, &inode->i_data, page->index,
@@ -377,6 +396,12 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
int rc = 0;
int max = 0;
+ rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list,
+ &nr_pages);
+
+ if (rc == 0)
+ goto out;
+
if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
>> PAGE_SHIFT;
@@ -496,6 +521,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
+ ceph_readpage_to_fscache(inode, page);
+
set_page_writeback(page);
err = ceph_osdc_writepages(osdc, ceph_vino(inode),
&ci->i_layout, snapc,
@@ -551,7 +578,6 @@ static void ceph_release_pages(struct page **pages, int num)
pagevec_release(&pvec);
}
-
/*
* async writeback completion handler.
*
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
new file mode 100644
index 0000000..fa49bf7
--- /dev/null
+++ b/fs/ceph/cache.c
@@ -0,0 +1,306 @@
+/*
+ * Ceph cache definitions.
+ *
+ * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
+ * Written by Milosz Tanski (milosz@adfin.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to:
+ * Free Software Foundation
+ * 51 Franklin Street, Fifth Floor
+ * Boston, MA 02111-1301 USA
+ *
+ */
+
+#include "super.h"
+#include "cache.h"
+
+struct ceph_aux_inode {
+ struct timespec mtime;
+ loff_t size;
+};
+
+struct fscache_netfs ceph_cache_netfs = {
+ .name = "ceph",
+ .version = 0,
+};
+
+static uint16_t ceph_fscache_session_get_key(const void *cookie_netfs_data,
+ void *buffer, uint16_t maxbuf)
+{
+ const struct ceph_fs_client *fsc = cookie_netfs_data;
+ uint16_t klen;
+
+ klen = sizeof(fsc->client->fsid);
+ if (klen > maxbuf)
+ return 0;
+
+ memcpy(buffer, &fsc->client->fsid, klen);
+ return klen;
+}
+
+static const struct fscache_cookie_def ceph_fscache_fsid_object_def = {
+ .name = "CEPH.fsid",
+ .type = FSCACHE_COOKIE_TYPE_INDEX,
+ .get_key = ceph_fscache_session_get_key,
+};
+
+void ceph_fscache_register_fsid_cookie(struct ceph_fs_client *fsc)
+{
+ fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
+ &ceph_fscache_fsid_object_def,
+ fsc);
+}
+
+void ceph_fscache_unregister_fsid_cookie(struct ceph_fs_client *fsc)
+{
+ fscache_relinquish_cookie(fsc->fscache, 0);
+ fsc->fscache = NULL;
+}
+
+static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data,
+ void *buffer, uint16_t maxbuf)
+{
+ const struct ceph_inode_info *ci = cookie_netfs_data;
+ uint16_t klen;
+
+ /* use ceph virtual inode (id + snaphot) */
+ klen = sizeof(ci->i_vino);
+ if (klen > maxbuf)
+ return 0;
+
+ memcpy(buffer, &ci->i_vino, klen);
+ return klen;
+}
+
+static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data,
+ void *buffer, uint16_t bufmax)
+{
+ struct ceph_aux_inode aux;
+ const struct ceph_inode_info *ci = cookie_netfs_data;
+ const struct inode *inode = &ci->vfs_inode;
+
+ memset(&aux, 0, sizeof(aux));
+ aux.mtime = inode->i_mtime;
+ aux.size = inode->i_size;
+
+ memcpy(buffer, &aux, sizeof(aux));
+
+ return sizeof(aux);
+}
+
+static void ceph_fscache_inode_get_attr(const void *cookie_netfs_data,
+ uint64_t *size)
+{
+ const struct ceph_inode_info *ci = cookie_netfs_data;
+ const struct inode *inode = &ci->vfs_inode;
+
+ *size = inode->i_size;
+}
+
+static enum fscache_checkaux ceph_fscache_inode_check_aux(
+ void *cookie_netfs_data, const void *data, uint16_t dlen)
+{
+ struct ceph_aux_inode aux;
+ struct ceph_inode_info *ci = cookie_netfs_data;
+ struct inode *inode = &ci->vfs_inode;
+
+ if (dlen != sizeof(aux))
+ return FSCACHE_CHECKAUX_OBSOLETE;
+
+ memset(&aux, 0, sizeof(aux));
+ aux.mtime = inode->i_mtime;
+ aux.size = inode->i_size;
+
+ if (memcmp(data, &aux, sizeof(aux)) != 0)
+ return FSCACHE_CHECKAUX_OBSOLETE;
+
+ dout("ceph inode 0x%p cached okay", ci);
+ return FSCACHE_CHECKAUX_OKAY;
+}
+
+static void ceph_fscache_inode_now_uncached(void *cookie_netfs_data)
+{
+ struct ceph_inode_info *ci = cookie_netfs_data;
+ struct pagevec pvec;
+ pgoff_t first;
+ int loop, nr_pages;
+
+ pagevec_init(&pvec, 0);
+ first = 0;
+
+ dout("ceph inode 0x%p now uncached", ci);
+
+ while (1) {
+ nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first,
+ PAGEVEC_SIZE - pagevec_count(&pvec));
+
+ if (!nr_pages)
+ break;
+
+ for (loop = 0; loop < nr_pages; loop++)
+ ClearPageFsCache(pvec.pages[loop]);
+
+ first = pvec.pages[nr_pages - 1]->index + 1;
+
+ pvec.nr = nr_pages;
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+}
+
+static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
+ .name = "CEPH.inode",
+ .type = FSCACHE_COOKIE_TYPE_DATAFILE,
+ .get_key = ceph_fscache_inode_get_key,
+ .get_attr = ceph_fscache_inode_get_attr,
+ .get_aux = ceph_fscache_inode_get_aux,
+ .check_aux = ceph_fscache_inode_check_aux,
+ .now_uncached = ceph_fscache_inode_now_uncached,
+};
+
+void ceph_fscache_register_inode_cookie(struct ceph_fs_client *fsc,
+ struct ceph_inode_info *ci)
+{
+ struct inode *inode = &ci->vfs_inode;
+
+ /* No caching for filesystem */
+ if (fsc->fscache == NULL)
+ return;
+
+ /* Only cache for regular files that are read only */
+ if ((ci->vfs_inode.i_mode & S_IFREG) == 0)
+ return;
+
+ /* Avoid multiple racing open requests */
+ mutex_lock(&inode->i_mutex);
+
+ if (ci->fscache)
+ goto done;
+
+ ci->fscache = fscache_acquire_cookie(fsc->fscache,
+ &ceph_fscache_inode_object_def,
+ ci);
+done:
+ mutex_unlock(&inode->i_mutex);
+
+}
+
+void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci)
+{
+ fscache_uncache_all_inode_pages(ci->fscache, &ci->vfs_inode);
+ fscache_relinquish_cookie(ci->fscache, 0);
+ ci->fscache = NULL;
+}
+
+static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
+{
+ if (!error)
+ SetPageUptodate(page);
+}
+
+static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data,
+ int error)
+{
+ if (!error)
+ SetPageUptodate(page);
+
+ unlock_page(page);
+}
+
+static inline int cache_valid(struct ceph_inode_info *ci)
+{
+ return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) &&
+ (ci->i_fscache_gen == ci->i_rdcache_gen));
+}
+
+
+/* Atempt to read from the fscache,
+ *
+ * This function is called from the readpage_nounlock context. DO NOT attempt to
+ * unlock the page here (or in the callback).
+ */
+int __ceph_readpage_from_fscache(struct inode *inode, struct page *page)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ int ret;
+
+ if (!cache_valid(ci))
+ return -ENOBUFS;
+
+ ret = fscache_read_or_alloc_page(ci->fscache, page,
+ ceph_vfs_readpage_complete, NULL,
+ GFP_KERNEL);
+
+ switch (ret) {
+ case 0: /* Page found */
+ dout("page read submitted\n");
+ return 0;
+ case -ENOBUFS: /* Pages were not found, and can't be */
+ case -ENODATA: /* Pages were not found */
+ dout("page/inode not in cache\n");
+ return ret;
+ default:
+ dout("%s: unknown error ret = %i\n", __func__, ret);
+ return ret;
+ }
+}
+
+int __ceph_readpages_from_fscache(struct inode *inode,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ int ret;
+
+ if (!cache_valid(ci))
+ return -ENOBUFS;
+
+ ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
+ ceph_vfs_readpage_complete_unlock,
+ NULL, mapping_gfp_mask(mapping));
+
+ switch (ret) {
+ case 0: /* All pages found */
+ dout("all-page read submitted\n");
+ return 0;
+ case -ENOBUFS: /* Some pages were not found, and can't be */
+ case -ENODATA: /* some pages were not found */
+ dout("page/inode not in cache\n");
+ return ret;
+ default:
+ dout("%s: unknown error ret = %i\n", __func__, ret);
+ return ret;
+ }
+}
+
+void __ceph_readpage_to_fscache(struct inode *inode, struct page *page)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ int ret;
+
+ if (!cache_valid(ci))
+ return;
+
+ ret = fscache_write_page(ci->fscache, page, GFP_KERNEL);
+ if (ret)
+ fscache_uncache_page(ci->fscache, page);
+}
+
+void __ceph_invalidate_fscache_page(struct inode *inode, struct page *page)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+
+ fscache_wait_on_page_write(ci->fscache, page);
+ fscache_uncache_page(ci->fscache, page);
+}
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
new file mode 100644
index 0000000..23ce336
--- /dev/null
+++ b/fs/ceph/cache.h
@@ -0,0 +1,117 @@
+/*
+ * Ceph cache definitions.
+ *
+ * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
+ * Written by Milosz Tanski (milosz@adfin.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to:
+ * Free Software Foundation
+ * 51 Franklin Street, Fifth Floor
+ * Boston, MA 02111-1301 USA
+ *
+ */
+
+#ifndef _CEPH_CACHE_H
+#define _CEPH_CACHE_H
+
+#include <linux/fscache.h>
+
+
+extern struct fscache_netfs ceph_cache_netfs;
+
+
+void ceph_fscache_register_fsid_cookie(struct ceph_fs_client *fsc);
+void ceph_fscache_unregister_fsid_cookie(struct ceph_fs_client *fsc);
+void ceph_fscache_register_inode_cookie(struct ceph_fs_client *parent_fsc,
+ struct ceph_inode_info *ci);
+void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci);
+
+int __ceph_readpage_from_fscache(struct inode *inode, struct page *page);
+int __ceph_readpages_from_fscache(struct inode *inode,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages);
+void __ceph_readpage_to_fscache(struct inode *inode, struct page *page);
+void __ceph_invalidate_fscache_page(struct inode *inode, struct page *page);
+
+#ifdef CONFIG_CEPH_FSCACHE
+
+
+static inline int ceph_readpage_from_fscache(struct inode *inode,
+ struct page *page)
+{
+ return __ceph_readpage_from_fscache(inode, page);
+}
+
+static inline int ceph_readpages_from_fscache(struct inode *inode,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages)
+{
+ return __ceph_readpages_from_fscache(inode, mapping, pages,
+ nr_pages);
+}
+
+static inline void ceph_readpage_to_fscache(struct inode *inode,
+ struct page *page)
+{
+ return __ceph_readpage_to_fscache(inode, page);
+}
+
+static inline void ceph_invalidate_fscache_page(struct inode *inode,
+ struct page *page)
+{
+ return __ceph_invalidate_fscache_page(inode, page);
+}
+
+static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
+{
+ struct inode *inode = page->mapping->host;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ return fscache_maybe_release_page(ci->fscache, page, gfp);
+}
+
+#else
+
+static inline int ceph_readpage_from_fscache(struct inode *inode,
+ struct page *page)
+{
+ return -ENOBUFS;
+}
+
+static inline int ceph_readpages_from_fscache(struct inode *inode,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages)
+{
+ return -ENOBUFS;
+}
+
+static inline void ceph_readpage_to_fscache(struct inode *inode,
+ struct page *page)
+{
+}
+
+static inline void ceph_invalidate_fscache_page(struct inode *inode,
+ struct page *page)
+{
+}
+
+static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
+{
+ return 1;
+}
+
+#endif
+
+#endif
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 430121a..32ce13d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -10,6 +10,7 @@
#include "super.h"
#include "mds_client.h"
+#include "cache.h"
#include <linux/ceph/decode.h>
#include <linux/ceph/messenger.h>
@@ -479,8 +480,9 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
* i_rdcache_gen.
*/
if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
- (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
+ (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) {
ci->i_rdcache_gen++;
+ }
/*
* if we are newly issued FILE_SHARED, mark dir not complete; we
@@ -2396,6 +2398,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
int revoked_rdcache = 0;
int queue_invalidate = 0;
int deleted_inode = 0;
+ int queue_revalidate = 0;
dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2420,6 +2423,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
ci->i_rdcache_revoking = ci->i_rdcache_gen;
}
}
+
+ fscache_invalidate(ci->fscache);
}
/* side effects now are allowed */
@@ -2461,6 +2466,11 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
}
}
+ /* Do we need to revalidate our fscache cookie. Don't bother on the
+ * first cache cap as we already validate at cookie creation time. */
+ if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
+ queue_revalidate = 1;
+
/* size/ctime/mtime/atime? */
ceph_fill_file_size(inode, issued,
le32_to_cpu(grant->truncate_seq),
@@ -2545,6 +2555,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
BUG_ON(cap->issued & ~cap->implemented);
spin_unlock(&ci->i_ceph_lock);
+
if (writeback)
/*
* queue inode for writeback: we can't actually call
@@ -2556,6 +2567,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
ceph_queue_invalidate(inode);
if (deleted_inode)
invalidate_aliases(inode);
+ if (queue_revalidate)
+ ceph_queue_revalidate(inode);
if (wake)
wake_up_all(&ci->i_cap_wq);
@@ -2712,8 +2725,10 @@ static void handle_cap_trunc(struct inode *inode,
truncate_seq, truncate_size, size);
spin_unlock(&ci->i_ceph_lock);
- if (queue_trunc)
+ if (queue_trunc) {
ceph_queue_vmtruncate(inode);
+ fscache_invalidate(ci->fscache);
+ }
}
/*
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 63ec830..ff35aa4 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -11,6 +11,7 @@
#include "super.h"
#include "mds_client.h"
+#include "cache.h"
/*
* Ceph file operations
@@ -68,9 +69,23 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
{
struct ceph_file_info *cf;
int ret = 0;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+ struct ceph_mds_client *mdsc = fsc->mdsc;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
+ /* First file open request creates the cookie, we want to keep
+ * this cookie around for the filetime of the inode as not to
+ * have to worry about fscache register / revoke / operation
+ * races.
+ *
+ * Also, if we know the operation is going to invalidate data
+ * (non readonly) just nuke the cache right away.
+ */
+ ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
+ if ((fmode & CEPH_FILE_MODE_WR))
+ fscache_invalidate(ci->fscache);
case S_IFDIR:
dout("init_file %p %p 0%o (regular)\n", inode, file,
inode->i_mode);
@@ -181,6 +196,7 @@ int ceph_open(struct inode *inode, struct file *file)
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
+
spin_unlock(&ci->i_ceph_lock);
dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
@@ -191,6 +207,7 @@ int ceph_open(struct inode *inode, struct file *file)
}
req->r_inode = inode;
ihold(inode);
+
req->r_num_caps = 1;
if (flags & (O_CREAT|O_TRUNC))
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 3b0abed..d85c977 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -12,6 +12,7 @@
#include "super.h"
#include "mds_client.h"
+#include "cache.h"
#include <linux/ceph/decode.h>
/*
@@ -31,6 +32,7 @@ static const struct inode_operations ceph_symlink_iops;
static void ceph_invalidate_work(struct work_struct *work);
static void ceph_writeback_work(struct work_struct *work);
static void ceph_vmtruncate_work(struct work_struct *work);
+static void ceph_revalidate_work(struct work_struct *work);
/*
* find or create an inode, given the ceph ino number
@@ -385,6 +387,13 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work);
+#ifdef CONFIG_CEPH_FSCACHE
+ ci->fscache = NULL;
+ /* The first load is verifed cookie open time */
+ ci->i_fscache_gen = 1;
+ INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work);
+#endif
+
return &ci->vfs_inode;
}
@@ -404,6 +413,8 @@ void ceph_destroy_inode(struct inode *inode)
dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
+ ceph_fscache_unregister_inode_cookie(ci);
+
ceph_queue_caps_release(inode);
/*
@@ -438,7 +449,6 @@ void ceph_destroy_inode(struct inode *inode)
call_rcu(&inode->i_rcu, ceph_i_callback);
}
-
/*
* Helpers to fill in size, ctime, mtime, and atime. We have to be
* careful because either the client or MDS may have more up to date
@@ -486,6 +496,10 @@ int ceph_fill_file_size(struct inode *inode, int issued,
truncate_size);
ci->i_truncate_size = truncate_size;
}
+
+ if (queue_trunc)
+ fscache_invalidate(ci->fscache);
+
return queue_trunc;
}
@@ -1074,7 +1088,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
* complete.
*/
ceph_set_dentry_offset(req->r_old_dentry);
- dout("dn %p gets new offset %lld\n", req->r_old_dentry,
+ dout("dn %p gets new offset %lld\n", req->r_old_dentry,
ceph_dentry(req->r_old_dentry)->offset);
dn = req->r_old_dentry; /* use old_dentry */
@@ -1495,6 +1509,7 @@ void ceph_queue_vmtruncate(struct inode *inode)
struct ceph_inode_info *ci = ceph_inode(inode);
ihold(inode);
+
if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
&ci->i_vmtruncate_work)) {
dout("ceph_queue_vmtruncate %p\n", inode);
@@ -1559,6 +1574,56 @@ retry:
wake_up_all(&ci->i_cap_wq);
}
+static void ceph_revalidate_work(struct work_struct *work)
+{
+ int issued;
+ u32 orig_gen;
+ struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
+ i_revalidate_work);
+ struct inode *inode = &ci->vfs_inode;
+
+ spin_lock(&ci->i_ceph_lock);
+ issued = __ceph_caps_issued(ci, NULL);
+ orig_gen = ci->i_rdcache_gen;
+ spin_unlock(&ci->i_ceph_lock);
+
+ if (!(issued & CEPH_CAP_FILE_CACHE)) {
+ dout("revalidate_work lost cache before validation %p\n",
+ inode);
+ goto out;
+ }
+
+ if (!fscache_check_consistency(ci->fscache))
+ fscache_invalidate(ci->fscache);
+
+ spin_lock(&ci->i_ceph_lock);
+ /* Update the new valid generation (backwards sanity check too) */
+ if (orig_gen > ci->i_fscache_gen) {
+ ci->i_fscache_gen = orig_gen;
+ } else {
+ pr_warn("revalidate_work raced cache validation %p\n",
+ inode);
+ }
+ spin_unlock(&ci->i_ceph_lock);
+
+out:
+ iput(&ci->vfs_inode);
+}
+
+void ceph_queue_revalidate(struct inode *inode)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+
+ ihold(inode);
+
+ if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq,
+ &ci->i_revalidate_work)) {
+ dout("ceph_queue_revalidate %p\n", inode);
+ } else {
+ dout("ceph_queue_revalidate %p failed\n)", inode);
+ iput(inode);
+ }
+}
/*
* symlinks
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 6627b26..d88808c 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -17,6 +17,7 @@
#include "super.h"
#include "mds_client.h"
+#include "cache.h"
#include <linux/ceph/ceph_features.h>
#include <linux/ceph/decode.h>
@@ -142,6 +143,8 @@ enum {
Opt_nodcache,
Opt_ino32,
Opt_noino32,
+ Opt_fscache,
+ Opt_nofscache
};
static match_table_t fsopt_tokens = {
@@ -167,6 +170,8 @@ static match_table_t fsopt_tokens = {
{Opt_nodcache, "nodcache"},
{Opt_ino32, "ino32"},
{Opt_noino32, "noino32"},
+ {Opt_fscache, "fsc"},
+ {Opt_nofscache, "nofsc"},
{-1, NULL}
};
@@ -260,6 +265,12 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_noino32:
fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
break;
+ case Opt_fscache:
+ fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
+ break;
+ case Opt_nofscache:
+ fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
+ break;
default:
BUG_ON(token);
}
@@ -422,6 +433,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",dcache");
else
seq_puts(m, ",nodcache");
+ if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE)
+ seq_puts(m, ",fsc");
+ else
+ seq_puts(m, ",nofsc");
if (fsopt->wsize)
seq_printf(m, ",wsize=%d", fsopt->wsize);
@@ -530,11 +545,24 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
if (!fsc->wb_pagevec_pool)
goto fail_trunc_wq;
+#ifdef CONFIG_CEPH_FSCACHE
+ if ((fsopt->flags & CEPH_MOUNT_OPT_FSCACHE))
+ ceph_fscache_register_fsid_cookie(fsc);
+
+ fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1);
+ if (fsc->revalidate_wq == NULL)
+ goto fail_fscache;
+#endif
+
/* caps */
fsc->min_caps = fsopt->max_readdir;
return fsc;
+#ifdef CONFIG_CEPH_FSCACHE
+fail_fscache:
+ ceph_fscache_unregister_fsid_cookie(fsc);
+#endif
fail_trunc_wq:
destroy_workqueue(fsc->trunc_wq);
fail_pg_inv_wq:
@@ -554,6 +582,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
{
dout("destroy_fs_client %p\n", fsc);
+#ifdef CONFIG_CEPH_FSCACHE
+ ceph_fscache_unregister_fsid_cookie(fsc);
+#endif
+
destroy_workqueue(fsc->wb_wq);
destroy_workqueue(fsc->pg_inv_wq);
destroy_workqueue(fsc->trunc_wq);
@@ -588,6 +620,8 @@ static void ceph_inode_init_once(void *foo)
static int __init init_caches(void)
{
+ int error = -ENOMEM;
+
ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
sizeof(struct ceph_inode_info),
__alignof__(struct ceph_inode_info),
@@ -611,15 +645,20 @@ static int __init init_caches(void)
if (ceph_file_cachep == NULL)
goto bad_file;
- return 0;
+#ifdef CONFIG_CEPH_FSCACHE
+ error = fscache_register_netfs(&ceph_cache_netfs);
+ if (error)
+ goto bad_file;
+#endif
+ return 0;
bad_file:
kmem_cache_destroy(ceph_dentry_cachep);
bad_dentry:
kmem_cache_destroy(ceph_cap_cachep);
bad_cap:
kmem_cache_destroy(ceph_inode_cachep);
- return -ENOMEM;
+ return error;
}
static void destroy_caches(void)
@@ -629,10 +668,15 @@ static void destroy_caches(void)
* destroy cache.
*/
rcu_barrier();
+
kmem_cache_destroy(ceph_inode_cachep);
kmem_cache_destroy(ceph_cap_cachep);
kmem_cache_destroy(ceph_dentry_cachep);
kmem_cache_destroy(ceph_file_cachep);
+
+#ifdef CONFIG_CEPH_FSCACHE
+ fscache_unregister_netfs(&ceph_cache_netfs);
+#endif
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index afcd62a..8bcac51 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -16,6 +16,10 @@
#include <linux/ceph/libceph.h>
+#ifdef CONFIG_CEPH_FSCACHE
+#include <linux/fscache.h>
+#endif
+
/* f_type in struct statfs */
#define CEPH_SUPER_MAGIC 0x00c36400
@@ -29,6 +33,7 @@
#define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */
#define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */
#define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */
+#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */
#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES)
@@ -90,6 +95,11 @@ struct ceph_fs_client {
struct dentry *debugfs_bdi;
struct dentry *debugfs_mdsc, *debugfs_mdsmap;
#endif
+
+#ifdef CONFIG_CEPH_FSCACHE
+ struct fscache_cookie *fscache;
+ struct workqueue_struct *revalidate_wq;
+#endif
};
@@ -319,6 +329,12 @@ struct ceph_inode_info {
struct work_struct i_vmtruncate_work;
+#ifdef CONFIG_CEPH_FSCACHE
+ struct fscache_cookie *fscache;
+ u32 i_fscache_gen; /* sequence, for delayed fscache validate */
+ struct work_struct i_revalidate_work;
+#endif
+
struct inode vfs_inode; /* at end */
};
@@ -699,6 +715,7 @@ extern void ceph_queue_vmtruncate(struct inode *inode);
extern void ceph_queue_invalidate(struct inode *inode);
extern void ceph_queue_writeback(struct inode *inode);
+extern void ceph_queue_revalidate(struct inode *inode);
extern int ceph_do_getattr(struct inode *inode, int mask);
extern int ceph_permission(struct inode *inode, int mask);
--
1.8.1.2
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH 3/3] ceph: use fscache as a local presisent cache
2013-08-07 23:16 ` [PATCH 3/3] ceph: use fscache as a local presisent cache Milosz Tanski
@ 2013-08-09 4:16 ` Sage Weil
2013-08-09 16:24 ` Milosz Tanski
0 siblings, 1 reply; 6+ messages in thread
From: Sage Weil @ 2013-08-09 4:16 UTC (permalink / raw)
To: Milosz Tanski
Cc: ceph-devel, linux-cachefs, linux-fsdevel, zheng.z.yan, dhowells,
jiayisuse
Hi Milosz!
I have a few comments below on invalidate_page:
On Wed, 7 Aug 2013, Milosz Tanski wrote:
> Adding support for fscache to the Ceph filesystem. This would bring it to on
> par with some of the other network filesystems in Linux (like NFS, AFS, etc...)
>
> In order to mount the filesystem with fscache the 'fsc' mount option must be
> passed.
>
> Signed-off-by: Milosz Tanski <milosz@adfin.com>
> ---
> fs/ceph/Kconfig | 9 ++
> fs/ceph/Makefile | 2 +
> fs/ceph/addr.c | 70 +++++++++----
> fs/ceph/cache.c | 306 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
> fs/ceph/cache.h | 117 +++++++++++++++++++++
> fs/ceph/caps.c | 19 +++-
> fs/ceph/file.c | 17 ++++
> fs/ceph/inode.c | 69 ++++++++++++-
> fs/ceph/super.c | 48 ++++++++-
> fs/ceph/super.h | 17 ++++
> 10 files changed, 646 insertions(+), 28 deletions(-)
> create mode 100644 fs/ceph/cache.c
> create mode 100644 fs/ceph/cache.h
>
> diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
> index 49bc782..ac9a2ef 100644
> --- a/fs/ceph/Kconfig
> +++ b/fs/ceph/Kconfig
> @@ -16,3 +16,12 @@ config CEPH_FS
>
> If unsure, say N.
>
> +if CEPH_FS
> +config CEPH_FSCACHE
> + bool "Enable Ceph client caching support"
> + depends on CEPH_FS=m && FSCACHE || CEPH_FS=y && FSCACHE=y
> + help
> + Choose Y here to enable persistent, read-only local
> + caching support for Ceph clients using FS-Cache
> +
> +endif
> diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
> index bd35212..0af0678 100644
> --- a/fs/ceph/Makefile
> +++ b/fs/ceph/Makefile
> @@ -9,3 +9,5 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
> mds_client.o mdsmap.o strings.o ceph_frag.o \
> debugfs.o
>
> +ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
> +
> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
> index afb2fc2..de6de0e 100644
> --- a/fs/ceph/addr.c
> +++ b/fs/ceph/addr.c
> @@ -11,6 +11,7 @@
>
> #include "super.h"
> #include "mds_client.h"
> +#include "cache.h"
> #include <linux/ceph/osd_client.h>
>
> /*
> @@ -149,11 +150,23 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
> struct ceph_inode_info *ci;
> struct ceph_snap_context *snapc = page_snap_context(page);
>
> - BUG_ON(!PageLocked(page));
> - BUG_ON(!PagePrivate(page));
Do these go away because of the fscache change? Or were they incorrect to
begin with?
> BUG_ON(!page->mapping);
>
> inode = page->mapping->host;
> + ci = ceph_inode(inode);
> +
> + if (offset != 0) {
> + dout("%p invalidatepage %p idx %lu partial dirty page\n",
> + inode, page, page->index);
> + return;
> + }
It would be nice to factor out the offset != 0 short circuit into a
separate patch. Under what circumstances does it actually happen?
> +
> + ceph_invalidate_fscache_page(inode, page);
> +
> + if (!PagePrivate(page))
> + return;
> +
> + BUG_ON(!PageLocked(page));
>
> /*
> * We can get non-dirty pages here due to races between
> @@ -163,31 +176,28 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
> if (!PageDirty(page))
> pr_err("%p invalidatepage %p page not dirty\n", inode, page);
>
> - if (offset == 0)
> - ClearPageChecked(page);
> + ClearPageChecked(page);
>
> - ci = ceph_inode(inode);
> - if (offset == 0) {
> - dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
> - inode, page, page->index, offset);
> - ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
> - ceph_put_snap_context(snapc);
> - page->private = 0;
> - ClearPagePrivate(page);
> - } else {
> - dout("%p invalidatepage %p idx %lu partial dirty page\n",
> - inode, page, page->index);
> - }
Again, having this code movement in a separate patch from fscache will
make it easier to review and test.
Thanks!
sage
> + dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
> + inode, page, page->index, offset);
> +
> + ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
> + ceph_put_snap_context(snapc);
> + page->private = 0;
> + ClearPagePrivate(page);
> }
>
> -/* just a sanity check */
> static int ceph_releasepage(struct page *page, gfp_t g)
> {
> struct inode *inode = page->mapping ? page->mapping->host : NULL;
> dout("%p releasepage %p idx %lu\n", inode, page, page->index);
> WARN_ON(PageDirty(page));
> - WARN_ON(PagePrivate(page));
> - return 0;
> +
> + /* Can we release the page from the cache? */
> + if (!ceph_release_fscache_page(page, g))
> + return 0;
> +
> + return !PagePrivate(page);
> }
>
> /*
> @@ -197,11 +207,16 @@ static int readpage_nounlock(struct file *filp, struct page *page)
> {
> struct inode *inode = file_inode(filp);
> struct ceph_inode_info *ci = ceph_inode(inode);
> - struct ceph_osd_client *osdc =
> + struct ceph_osd_client *osdc =
> &ceph_inode_to_client(inode)->client->osdc;
> int err = 0;
> u64 len = PAGE_CACHE_SIZE;
>
> + err = ceph_readpage_from_fscache(inode, page);
> +
> + if (err == 0)
> + goto out;
> +
> dout("readpage inode %p file %p page %p index %lu\n",
> inode, filp, page, page->index);
> err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
> @@ -219,6 +234,9 @@ static int readpage_nounlock(struct file *filp, struct page *page)
> }
> SetPageUptodate(page);
>
> + if (err == 0)
> + ceph_readpage_to_fscache(inode, page);
> +
> out:
> return err < 0 ? err : 0;
> }
> @@ -261,6 +279,7 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
> page->index);
> flush_dcache_page(page);
> SetPageUptodate(page);
> + ceph_readpage_to_fscache(inode, page);
> unlock_page(page);
> page_cache_release(page);
> bytes -= PAGE_CACHE_SIZE;
> @@ -330,7 +349,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
> page = list_entry(page_list->prev, struct page, lru);
> BUG_ON(PageLocked(page));
> list_del(&page->lru);
> -
> +
> dout("start_read %p adding %p idx %lu\n", inode, page,
> page->index);
> if (add_to_page_cache_lru(page, &inode->i_data, page->index,
> @@ -377,6 +396,12 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
> int rc = 0;
> int max = 0;
>
> + rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list,
> + &nr_pages);
> +
> + if (rc == 0)
> + goto out;
> +
> if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
> max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
> >> PAGE_SHIFT;
> @@ -496,6 +521,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
> CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
> set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
>
> + ceph_readpage_to_fscache(inode, page);
> +
> set_page_writeback(page);
> err = ceph_osdc_writepages(osdc, ceph_vino(inode),
> &ci->i_layout, snapc,
> @@ -551,7 +578,6 @@ static void ceph_release_pages(struct page **pages, int num)
> pagevec_release(&pvec);
> }
>
> -
> /*
> * async writeback completion handler.
> *
> diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
> new file mode 100644
> index 0000000..fa49bf7
> --- /dev/null
> +++ b/fs/ceph/cache.c
> @@ -0,0 +1,306 @@
> +/*
> + * Ceph cache definitions.
> + *
> + * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
> + * Written by Milosz Tanski (milosz@adfin.com)
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2
> + * as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public License
> + * along with this program; if not, write to:
> + * Free Software Foundation
> + * 51 Franklin Street, Fifth Floor
> + * Boston, MA 02111-1301 USA
> + *
> + */
> +
> +#include "super.h"
> +#include "cache.h"
> +
> +struct ceph_aux_inode {
> + struct timespec mtime;
> + loff_t size;
> +};
> +
> +struct fscache_netfs ceph_cache_netfs = {
> + .name = "ceph",
> + .version = 0,
> +};
> +
> +static uint16_t ceph_fscache_session_get_key(const void *cookie_netfs_data,
> + void *buffer, uint16_t maxbuf)
> +{
> + const struct ceph_fs_client *fsc = cookie_netfs_data;
> + uint16_t klen;
> +
> + klen = sizeof(fsc->client->fsid);
> + if (klen > maxbuf)
> + return 0;
> +
> + memcpy(buffer, &fsc->client->fsid, klen);
> + return klen;
> +}
> +
> +static const struct fscache_cookie_def ceph_fscache_fsid_object_def = {
> + .name = "CEPH.fsid",
> + .type = FSCACHE_COOKIE_TYPE_INDEX,
> + .get_key = ceph_fscache_session_get_key,
> +};
> +
> +void ceph_fscache_register_fsid_cookie(struct ceph_fs_client *fsc)
> +{
> + fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
> + &ceph_fscache_fsid_object_def,
> + fsc);
> +}
> +
> +void ceph_fscache_unregister_fsid_cookie(struct ceph_fs_client *fsc)
> +{
> + fscache_relinquish_cookie(fsc->fscache, 0);
> + fsc->fscache = NULL;
> +}
> +
> +static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data,
> + void *buffer, uint16_t maxbuf)
> +{
> + const struct ceph_inode_info *ci = cookie_netfs_data;
> + uint16_t klen;
> +
> + /* use ceph virtual inode (id + snaphot) */
> + klen = sizeof(ci->i_vino);
> + if (klen > maxbuf)
> + return 0;
> +
> + memcpy(buffer, &ci->i_vino, klen);
> + return klen;
> +}
> +
> +static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data,
> + void *buffer, uint16_t bufmax)
> +{
> + struct ceph_aux_inode aux;
> + const struct ceph_inode_info *ci = cookie_netfs_data;
> + const struct inode *inode = &ci->vfs_inode;
> +
> + memset(&aux, 0, sizeof(aux));
> + aux.mtime = inode->i_mtime;
> + aux.size = inode->i_size;
> +
> + memcpy(buffer, &aux, sizeof(aux));
> +
> + return sizeof(aux);
> +}
> +
> +static void ceph_fscache_inode_get_attr(const void *cookie_netfs_data,
> + uint64_t *size)
> +{
> + const struct ceph_inode_info *ci = cookie_netfs_data;
> + const struct inode *inode = &ci->vfs_inode;
> +
> + *size = inode->i_size;
> +}
> +
> +static enum fscache_checkaux ceph_fscache_inode_check_aux(
> + void *cookie_netfs_data, const void *data, uint16_t dlen)
> +{
> + struct ceph_aux_inode aux;
> + struct ceph_inode_info *ci = cookie_netfs_data;
> + struct inode *inode = &ci->vfs_inode;
> +
> + if (dlen != sizeof(aux))
> + return FSCACHE_CHECKAUX_OBSOLETE;
> +
> + memset(&aux, 0, sizeof(aux));
> + aux.mtime = inode->i_mtime;
> + aux.size = inode->i_size;
> +
> + if (memcmp(data, &aux, sizeof(aux)) != 0)
> + return FSCACHE_CHECKAUX_OBSOLETE;
> +
> + dout("ceph inode 0x%p cached okay", ci);
> + return FSCACHE_CHECKAUX_OKAY;
> +}
> +
> +static void ceph_fscache_inode_now_uncached(void *cookie_netfs_data)
> +{
> + struct ceph_inode_info *ci = cookie_netfs_data;
> + struct pagevec pvec;
> + pgoff_t first;
> + int loop, nr_pages;
> +
> + pagevec_init(&pvec, 0);
> + first = 0;
> +
> + dout("ceph inode 0x%p now uncached", ci);
> +
> + while (1) {
> + nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first,
> + PAGEVEC_SIZE - pagevec_count(&pvec));
> +
> + if (!nr_pages)
> + break;
> +
> + for (loop = 0; loop < nr_pages; loop++)
> + ClearPageFsCache(pvec.pages[loop]);
> +
> + first = pvec.pages[nr_pages - 1]->index + 1;
> +
> + pvec.nr = nr_pages;
> + pagevec_release(&pvec);
> + cond_resched();
> + }
> +}
> +
> +static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
> + .name = "CEPH.inode",
> + .type = FSCACHE_COOKIE_TYPE_DATAFILE,
> + .get_key = ceph_fscache_inode_get_key,
> + .get_attr = ceph_fscache_inode_get_attr,
> + .get_aux = ceph_fscache_inode_get_aux,
> + .check_aux = ceph_fscache_inode_check_aux,
> + .now_uncached = ceph_fscache_inode_now_uncached,
> +};
> +
> +void ceph_fscache_register_inode_cookie(struct ceph_fs_client *fsc,
> + struct ceph_inode_info *ci)
> +{
> + struct inode *inode = &ci->vfs_inode;
> +
> + /* No caching for filesystem */
> + if (fsc->fscache == NULL)
> + return;
> +
> + /* Only cache for regular files that are read only */
> + if ((ci->vfs_inode.i_mode & S_IFREG) == 0)
> + return;
> +
> + /* Avoid multiple racing open requests */
> + mutex_lock(&inode->i_mutex);
> +
> + if (ci->fscache)
> + goto done;
> +
> + ci->fscache = fscache_acquire_cookie(fsc->fscache,
> + &ceph_fscache_inode_object_def,
> + ci);
> +done:
> + mutex_unlock(&inode->i_mutex);
> +
> +}
> +
> +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci)
> +{
> + fscache_uncache_all_inode_pages(ci->fscache, &ci->vfs_inode);
> + fscache_relinquish_cookie(ci->fscache, 0);
> + ci->fscache = NULL;
> +}
> +
> +static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
> +{
> + if (!error)
> + SetPageUptodate(page);
> +}
> +
> +static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data,
> + int error)
> +{
> + if (!error)
> + SetPageUptodate(page);
> +
> + unlock_page(page);
> +}
> +
> +static inline int cache_valid(struct ceph_inode_info *ci)
> +{
> + return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) &&
> + (ci->i_fscache_gen == ci->i_rdcache_gen));
> +}
> +
> +
> +/* Atempt to read from the fscache,
> + *
> + * This function is called from the readpage_nounlock context. DO NOT attempt to
> + * unlock the page here (or in the callback).
> + */
> +int __ceph_readpage_from_fscache(struct inode *inode, struct page *page)
> +{
> + struct ceph_inode_info *ci = ceph_inode(inode);
> + int ret;
> +
> + if (!cache_valid(ci))
> + return -ENOBUFS;
> +
> + ret = fscache_read_or_alloc_page(ci->fscache, page,
> + ceph_vfs_readpage_complete, NULL,
> + GFP_KERNEL);
> +
> + switch (ret) {
> + case 0: /* Page found */
> + dout("page read submitted\n");
> + return 0;
> + case -ENOBUFS: /* Pages were not found, and can't be */
> + case -ENODATA: /* Pages were not found */
> + dout("page/inode not in cache\n");
> + return ret;
> + default:
> + dout("%s: unknown error ret = %i\n", __func__, ret);
> + return ret;
> + }
> +}
> +
> +int __ceph_readpages_from_fscache(struct inode *inode,
> + struct address_space *mapping,
> + struct list_head *pages,
> + unsigned *nr_pages)
> +{
> + struct ceph_inode_info *ci = ceph_inode(inode);
> + int ret;
> +
> + if (!cache_valid(ci))
> + return -ENOBUFS;
> +
> + ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
> + ceph_vfs_readpage_complete_unlock,
> + NULL, mapping_gfp_mask(mapping));
> +
> + switch (ret) {
> + case 0: /* All pages found */
> + dout("all-page read submitted\n");
> + return 0;
> + case -ENOBUFS: /* Some pages were not found, and can't be */
> + case -ENODATA: /* some pages were not found */
> + dout("page/inode not in cache\n");
> + return ret;
> + default:
> + dout("%s: unknown error ret = %i\n", __func__, ret);
> + return ret;
> + }
> +}
> +
> +void __ceph_readpage_to_fscache(struct inode *inode, struct page *page)
> +{
> + struct ceph_inode_info *ci = ceph_inode(inode);
> + int ret;
> +
> + if (!cache_valid(ci))
> + return;
> +
> + ret = fscache_write_page(ci->fscache, page, GFP_KERNEL);
> + if (ret)
> + fscache_uncache_page(ci->fscache, page);
> +}
> +
> +void __ceph_invalidate_fscache_page(struct inode *inode, struct page *page)
> +{
> + struct ceph_inode_info *ci = ceph_inode(inode);
> +
> + fscache_wait_on_page_write(ci->fscache, page);
> + fscache_uncache_page(ci->fscache, page);
> +}
> diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
> new file mode 100644
> index 0000000..23ce336
> --- /dev/null
> +++ b/fs/ceph/cache.h
> @@ -0,0 +1,117 @@
> +/*
> + * Ceph cache definitions.
> + *
> + * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
> + * Written by Milosz Tanski (milosz@adfin.com)
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2
> + * as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public License
> + * along with this program; if not, write to:
> + * Free Software Foundation
> + * 51 Franklin Street, Fifth Floor
> + * Boston, MA 02111-1301 USA
> + *
> + */
> +
> +#ifndef _CEPH_CACHE_H
> +#define _CEPH_CACHE_H
> +
> +#include <linux/fscache.h>
> +
> +
> +extern struct fscache_netfs ceph_cache_netfs;
> +
> +
> +void ceph_fscache_register_fsid_cookie(struct ceph_fs_client *fsc);
> +void ceph_fscache_unregister_fsid_cookie(struct ceph_fs_client *fsc);
> +void ceph_fscache_register_inode_cookie(struct ceph_fs_client *parent_fsc,
> + struct ceph_inode_info *ci);
> +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci);
> +
> +int __ceph_readpage_from_fscache(struct inode *inode, struct page *page);
> +int __ceph_readpages_from_fscache(struct inode *inode,
> + struct address_space *mapping,
> + struct list_head *pages,
> + unsigned *nr_pages);
> +void __ceph_readpage_to_fscache(struct inode *inode, struct page *page);
> +void __ceph_invalidate_fscache_page(struct inode *inode, struct page *page);
> +
> +#ifdef CONFIG_CEPH_FSCACHE
> +
> +
> +static inline int ceph_readpage_from_fscache(struct inode *inode,
> + struct page *page)
> +{
> + return __ceph_readpage_from_fscache(inode, page);
> +}
> +
> +static inline int ceph_readpages_from_fscache(struct inode *inode,
> + struct address_space *mapping,
> + struct list_head *pages,
> + unsigned *nr_pages)
> +{
> + return __ceph_readpages_from_fscache(inode, mapping, pages,
> + nr_pages);
> +}
> +
> +static inline void ceph_readpage_to_fscache(struct inode *inode,
> + struct page *page)
> +{
> + return __ceph_readpage_to_fscache(inode, page);
> +}
> +
> +static inline void ceph_invalidate_fscache_page(struct inode *inode,
> + struct page *page)
> +{
> + return __ceph_invalidate_fscache_page(inode, page);
> +}
> +
> +static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
> +{
> + struct inode *inode = page->mapping->host;
> + struct ceph_inode_info *ci = ceph_inode(inode);
> + return fscache_maybe_release_page(ci->fscache, page, gfp);
> +}
> +
> +#else
> +
> +static inline int ceph_readpage_from_fscache(struct inode *inode,
> + struct page *page)
> +{
> + return -ENOBUFS;
> +}
> +
> +static inline int ceph_readpages_from_fscache(struct inode *inode,
> + struct address_space *mapping,
> + struct list_head *pages,
> + unsigned *nr_pages)
> +{
> + return -ENOBUFS;
> +}
> +
> +static inline void ceph_readpage_to_fscache(struct inode *inode,
> + struct page *page)
> +{
> +}
> +
> +static inline void ceph_invalidate_fscache_page(struct inode *inode,
> + struct page *page)
> +{
> +}
> +
> +static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
> +{
> + return 1;
> +}
> +
> +#endif
> +
> +#endif
> diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
> index 430121a..32ce13d 100644
> --- a/fs/ceph/caps.c
> +++ b/fs/ceph/caps.c
> @@ -10,6 +10,7 @@
>
> #include "super.h"
> #include "mds_client.h"
> +#include "cache.h"
> #include <linux/ceph/decode.h>
> #include <linux/ceph/messenger.h>
>
> @@ -479,8 +480,9 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
> * i_rdcache_gen.
> */
> if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
> - (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
> + (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) {
> ci->i_rdcache_gen++;
> + }
>
> /*
> * if we are newly issued FILE_SHARED, mark dir not complete; we
> @@ -2396,6 +2398,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
> int revoked_rdcache = 0;
> int queue_invalidate = 0;
> int deleted_inode = 0;
> + int queue_revalidate = 0;
>
> dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
> inode, cap, mds, seq, ceph_cap_string(newcaps));
> @@ -2420,6 +2423,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
> ci->i_rdcache_revoking = ci->i_rdcache_gen;
> }
> }
> +
> + fscache_invalidate(ci->fscache);
> }
>
> /* side effects now are allowed */
> @@ -2461,6 +2466,11 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
> }
> }
>
> + /* Do we need to revalidate our fscache cookie. Don't bother on the
> + * first cache cap as we already validate at cookie creation time. */
> + if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
> + queue_revalidate = 1;
> +
> /* size/ctime/mtime/atime? */
> ceph_fill_file_size(inode, issued,
> le32_to_cpu(grant->truncate_seq),
> @@ -2545,6 +2555,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
> BUG_ON(cap->issued & ~cap->implemented);
>
> spin_unlock(&ci->i_ceph_lock);
> +
> if (writeback)
> /*
> * queue inode for writeback: we can't actually call
> @@ -2556,6 +2567,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
> ceph_queue_invalidate(inode);
> if (deleted_inode)
> invalidate_aliases(inode);
> + if (queue_revalidate)
> + ceph_queue_revalidate(inode);
> if (wake)
> wake_up_all(&ci->i_cap_wq);
>
> @@ -2712,8 +2725,10 @@ static void handle_cap_trunc(struct inode *inode,
> truncate_seq, truncate_size, size);
> spin_unlock(&ci->i_ceph_lock);
>
> - if (queue_trunc)
> + if (queue_trunc) {
> ceph_queue_vmtruncate(inode);
> + fscache_invalidate(ci->fscache);
> + }
> }
>
> /*
> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
> index 63ec830..ff35aa4 100644
> --- a/fs/ceph/file.c
> +++ b/fs/ceph/file.c
> @@ -11,6 +11,7 @@
>
> #include "super.h"
> #include "mds_client.h"
> +#include "cache.h"
>
> /*
> * Ceph file operations
> @@ -68,9 +69,23 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
> {
> struct ceph_file_info *cf;
> int ret = 0;
> + struct ceph_inode_info *ci = ceph_inode(inode);
> + struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
> + struct ceph_mds_client *mdsc = fsc->mdsc;
>
> switch (inode->i_mode & S_IFMT) {
> case S_IFREG:
> + /* First file open request creates the cookie, we want to keep
> + * this cookie around for the filetime of the inode as not to
> + * have to worry about fscache register / revoke / operation
> + * races.
> + *
> + * Also, if we know the operation is going to invalidate data
> + * (non readonly) just nuke the cache right away.
> + */
> + ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
> + if ((fmode & CEPH_FILE_MODE_WR))
> + fscache_invalidate(ci->fscache);
> case S_IFDIR:
> dout("init_file %p %p 0%o (regular)\n", inode, file,
> inode->i_mode);
> @@ -181,6 +196,7 @@ int ceph_open(struct inode *inode, struct file *file)
> spin_unlock(&ci->i_ceph_lock);
> return ceph_init_file(inode, file, fmode);
> }
> +
> spin_unlock(&ci->i_ceph_lock);
>
> dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
> @@ -191,6 +207,7 @@ int ceph_open(struct inode *inode, struct file *file)
> }
> req->r_inode = inode;
> ihold(inode);
> +
> req->r_num_caps = 1;
> if (flags & (O_CREAT|O_TRUNC))
> parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
> diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> index 3b0abed..d85c977 100644
> --- a/fs/ceph/inode.c
> +++ b/fs/ceph/inode.c
> @@ -12,6 +12,7 @@
>
> #include "super.h"
> #include "mds_client.h"
> +#include "cache.h"
> #include <linux/ceph/decode.h>
>
> /*
> @@ -31,6 +32,7 @@ static const struct inode_operations ceph_symlink_iops;
> static void ceph_invalidate_work(struct work_struct *work);
> static void ceph_writeback_work(struct work_struct *work);
> static void ceph_vmtruncate_work(struct work_struct *work);
> +static void ceph_revalidate_work(struct work_struct *work);
>
> /*
> * find or create an inode, given the ceph ino number
> @@ -385,6 +387,13 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
>
> INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work);
>
> +#ifdef CONFIG_CEPH_FSCACHE
> + ci->fscache = NULL;
> + /* The first load is verifed cookie open time */
> + ci->i_fscache_gen = 1;
> + INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work);
> +#endif
> +
> return &ci->vfs_inode;
> }
>
> @@ -404,6 +413,8 @@ void ceph_destroy_inode(struct inode *inode)
>
> dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
>
> + ceph_fscache_unregister_inode_cookie(ci);
> +
> ceph_queue_caps_release(inode);
>
> /*
> @@ -438,7 +449,6 @@ void ceph_destroy_inode(struct inode *inode)
> call_rcu(&inode->i_rcu, ceph_i_callback);
> }
>
> -
> /*
> * Helpers to fill in size, ctime, mtime, and atime. We have to be
> * careful because either the client or MDS may have more up to date
> @@ -486,6 +496,10 @@ int ceph_fill_file_size(struct inode *inode, int issued,
> truncate_size);
> ci->i_truncate_size = truncate_size;
> }
> +
> + if (queue_trunc)
> + fscache_invalidate(ci->fscache);
> +
> return queue_trunc;
> }
>
> @@ -1074,7 +1088,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
> * complete.
> */
> ceph_set_dentry_offset(req->r_old_dentry);
> - dout("dn %p gets new offset %lld\n", req->r_old_dentry,
> + dout("dn %p gets new offset %lld\n", req->r_old_dentry,
> ceph_dentry(req->r_old_dentry)->offset);
>
> dn = req->r_old_dentry; /* use old_dentry */
> @@ -1495,6 +1509,7 @@ void ceph_queue_vmtruncate(struct inode *inode)
> struct ceph_inode_info *ci = ceph_inode(inode);
>
> ihold(inode);
> +
> if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
> &ci->i_vmtruncate_work)) {
> dout("ceph_queue_vmtruncate %p\n", inode);
> @@ -1559,6 +1574,56 @@ retry:
> wake_up_all(&ci->i_cap_wq);
> }
>
> +static void ceph_revalidate_work(struct work_struct *work)
> +{
> + int issued;
> + u32 orig_gen;
> + struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
> + i_revalidate_work);
> + struct inode *inode = &ci->vfs_inode;
> +
> + spin_lock(&ci->i_ceph_lock);
> + issued = __ceph_caps_issued(ci, NULL);
> + orig_gen = ci->i_rdcache_gen;
> + spin_unlock(&ci->i_ceph_lock);
> +
> + if (!(issued & CEPH_CAP_FILE_CACHE)) {
> + dout("revalidate_work lost cache before validation %p\n",
> + inode);
> + goto out;
> + }
> +
> + if (!fscache_check_consistency(ci->fscache))
> + fscache_invalidate(ci->fscache);
> +
> + spin_lock(&ci->i_ceph_lock);
> + /* Update the new valid generation (backwards sanity check too) */
> + if (orig_gen > ci->i_fscache_gen) {
> + ci->i_fscache_gen = orig_gen;
> + } else {
> + pr_warn("revalidate_work raced cache validation %p\n",
> + inode);
> + }
> + spin_unlock(&ci->i_ceph_lock);
> +
> +out:
> + iput(&ci->vfs_inode);
> +}
> +
> +void ceph_queue_revalidate(struct inode *inode)
> +{
> + struct ceph_inode_info *ci = ceph_inode(inode);
> +
> + ihold(inode);
> +
> + if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq,
> + &ci->i_revalidate_work)) {
> + dout("ceph_queue_revalidate %p\n", inode);
> + } else {
> + dout("ceph_queue_revalidate %p failed\n)", inode);
> + iput(inode);
> + }
> +}
>
> /*
> * symlinks
> diff --git a/fs/ceph/super.c b/fs/ceph/super.c
> index 6627b26..d88808c 100644
> --- a/fs/ceph/super.c
> +++ b/fs/ceph/super.c
> @@ -17,6 +17,7 @@
>
> #include "super.h"
> #include "mds_client.h"
> +#include "cache.h"
>
> #include <linux/ceph/ceph_features.h>
> #include <linux/ceph/decode.h>
> @@ -142,6 +143,8 @@ enum {
> Opt_nodcache,
> Opt_ino32,
> Opt_noino32,
> + Opt_fscache,
> + Opt_nofscache
> };
>
> static match_table_t fsopt_tokens = {
> @@ -167,6 +170,8 @@ static match_table_t fsopt_tokens = {
> {Opt_nodcache, "nodcache"},
> {Opt_ino32, "ino32"},
> {Opt_noino32, "noino32"},
> + {Opt_fscache, "fsc"},
> + {Opt_nofscache, "nofsc"},
> {-1, NULL}
> };
>
> @@ -260,6 +265,12 @@ static int parse_fsopt_token(char *c, void *private)
> case Opt_noino32:
> fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
> break;
> + case Opt_fscache:
> + fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
> + break;
> + case Opt_nofscache:
> + fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
> + break;
> default:
> BUG_ON(token);
> }
> @@ -422,6 +433,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
> seq_puts(m, ",dcache");
> else
> seq_puts(m, ",nodcache");
> + if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE)
> + seq_puts(m, ",fsc");
> + else
> + seq_puts(m, ",nofsc");
>
> if (fsopt->wsize)
> seq_printf(m, ",wsize=%d", fsopt->wsize);
> @@ -530,11 +545,24 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
> if (!fsc->wb_pagevec_pool)
> goto fail_trunc_wq;
>
> +#ifdef CONFIG_CEPH_FSCACHE
> + if ((fsopt->flags & CEPH_MOUNT_OPT_FSCACHE))
> + ceph_fscache_register_fsid_cookie(fsc);
> +
> + fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1);
> + if (fsc->revalidate_wq == NULL)
> + goto fail_fscache;
> +#endif
> +
> /* caps */
> fsc->min_caps = fsopt->max_readdir;
>
> return fsc;
>
> +#ifdef CONFIG_CEPH_FSCACHE
> +fail_fscache:
> + ceph_fscache_unregister_fsid_cookie(fsc);
> +#endif
> fail_trunc_wq:
> destroy_workqueue(fsc->trunc_wq);
> fail_pg_inv_wq:
> @@ -554,6 +582,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
> {
> dout("destroy_fs_client %p\n", fsc);
>
> +#ifdef CONFIG_CEPH_FSCACHE
> + ceph_fscache_unregister_fsid_cookie(fsc);
> +#endif
> +
> destroy_workqueue(fsc->wb_wq);
> destroy_workqueue(fsc->pg_inv_wq);
> destroy_workqueue(fsc->trunc_wq);
> @@ -588,6 +620,8 @@ static void ceph_inode_init_once(void *foo)
>
> static int __init init_caches(void)
> {
> + int error = -ENOMEM;
> +
> ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
> sizeof(struct ceph_inode_info),
> __alignof__(struct ceph_inode_info),
> @@ -611,15 +645,20 @@ static int __init init_caches(void)
> if (ceph_file_cachep == NULL)
> goto bad_file;
>
> - return 0;
> +#ifdef CONFIG_CEPH_FSCACHE
> + error = fscache_register_netfs(&ceph_cache_netfs);
> + if (error)
> + goto bad_file;
> +#endif
>
> + return 0;
> bad_file:
> kmem_cache_destroy(ceph_dentry_cachep);
> bad_dentry:
> kmem_cache_destroy(ceph_cap_cachep);
> bad_cap:
> kmem_cache_destroy(ceph_inode_cachep);
> - return -ENOMEM;
> + return error;
> }
>
> static void destroy_caches(void)
> @@ -629,10 +668,15 @@ static void destroy_caches(void)
> * destroy cache.
> */
> rcu_barrier();
> +
> kmem_cache_destroy(ceph_inode_cachep);
> kmem_cache_destroy(ceph_cap_cachep);
> kmem_cache_destroy(ceph_dentry_cachep);
> kmem_cache_destroy(ceph_file_cachep);
> +
> +#ifdef CONFIG_CEPH_FSCACHE
> + fscache_unregister_netfs(&ceph_cache_netfs);
> +#endif
> }
>
>
> diff --git a/fs/ceph/super.h b/fs/ceph/super.h
> index afcd62a..8bcac51 100644
> --- a/fs/ceph/super.h
> +++ b/fs/ceph/super.h
> @@ -16,6 +16,10 @@
>
> #include <linux/ceph/libceph.h>
>
> +#ifdef CONFIG_CEPH_FSCACHE
> +#include <linux/fscache.h>
> +#endif
> +
> /* f_type in struct statfs */
> #define CEPH_SUPER_MAGIC 0x00c36400
>
> @@ -29,6 +33,7 @@
> #define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */
> #define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */
> #define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */
> +#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */
>
> #define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES)
>
> @@ -90,6 +95,11 @@ struct ceph_fs_client {
> struct dentry *debugfs_bdi;
> struct dentry *debugfs_mdsc, *debugfs_mdsmap;
> #endif
> +
> +#ifdef CONFIG_CEPH_FSCACHE
> + struct fscache_cookie *fscache;
> + struct workqueue_struct *revalidate_wq;
> +#endif
> };
>
>
> @@ -319,6 +329,12 @@ struct ceph_inode_info {
>
> struct work_struct i_vmtruncate_work;
>
> +#ifdef CONFIG_CEPH_FSCACHE
> + struct fscache_cookie *fscache;
> + u32 i_fscache_gen; /* sequence, for delayed fscache validate */
> + struct work_struct i_revalidate_work;
> +#endif
> +
> struct inode vfs_inode; /* at end */
> };
>
> @@ -699,6 +715,7 @@ extern void ceph_queue_vmtruncate(struct inode *inode);
>
> extern void ceph_queue_invalidate(struct inode *inode);
> extern void ceph_queue_writeback(struct inode *inode);
> +extern void ceph_queue_revalidate(struct inode *inode);
>
> extern int ceph_do_getattr(struct inode *inode, int mask);
> extern int ceph_permission(struct inode *inode, int mask);
> --
> 1.8.1.2
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH 3/3] ceph: use fscache as a local presisent cache
2013-08-09 4:16 ` Sage Weil
@ 2013-08-09 16:24 ` Milosz Tanski
0 siblings, 0 replies; 6+ messages in thread
From: Milosz Tanski @ 2013-08-09 16:24 UTC (permalink / raw)
To: Sage Weil
Cc: ceph-devel, linux-cachefs, linux-fsdevel, Yan, Zheng,
David Howells, Hongyi Jia
Sage,
I can spin some of this out into a another patch; In the things I've
been sending I've been squashing the changes just because I've done so
many less then smart things to get to this point.
After reviewing this one more time and going from memory... I believe
the invalidate page code is overly paranoid in some of it's checking
in the beginning of. Here's my nodes inline.
146 static void ceph_invalidatepage(struct page *page, unsigned long offset)
147 {
148 struct inode *inode;
149 struct ceph_inode_info *ci;
150 struct ceph_snap_context *snapc = page_snap_context(page);
151
152 BUG_ON(!PageLocked(page));
This check is bunk because the VMA locks the page for us as it calls
this. The documentation in Documentation/filesystems/Locking make the
guarantee.
153 BUG_ON(!PagePrivate(page));
invalidatepage is not going to be called unless there is a PagePrivate
flag on it (or PagePrivate2 which is baked into the VMA for fscache).
In the current code has no effect, when I added fscache support this
line must go (it could be PagePrivate2 without PagePrivate). I'm using
Documentation/filesystems/vfs.txt as documentation.
154 BUG_ON(!page->mapping);
I also think this check is bunk. I doubt the VMA layer would call
ceph_invalidatepage without it being pre-mapped.
-------------
Now to address the code movement I can also refactor it a different
patch. I did it mainly so I could sandwich the fscache invalidate in
there. But taking the fscache change away, it should still be
functionally the same and simplify the logic a bit by just bailing
early. Since all the code does logically is throw it's hands up if we
get a truncate with a non-zero offset.
Cheers,
- Milosz
On Fri, Aug 9, 2013 at 12:16 AM, Sage Weil <sage@inktank.com> wrote:
> Hi Milosz!
>
> I have a few comments below on invalidate_page:
>
> On Wed, 7 Aug 2013, Milosz Tanski wrote:
>> Adding support for fscache to the Ceph filesystem. This would bring it to on
>> par with some of the other network filesystems in Linux (like NFS, AFS, etc...)
>>
>> In order to mount the filesystem with fscache the 'fsc' mount option must be
>> passed.
>>
>> Signed-off-by: Milosz Tanski <milosz@adfin.com>
>> ---
>> fs/ceph/Kconfig | 9 ++
>> fs/ceph/Makefile | 2 +
>> fs/ceph/addr.c | 70 +++++++++----
>> fs/ceph/cache.c | 306 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
>> fs/ceph/cache.h | 117 +++++++++++++++++++++
>> fs/ceph/caps.c | 19 +++-
>> fs/ceph/file.c | 17 ++++
>> fs/ceph/inode.c | 69 ++++++++++++-
>> fs/ceph/super.c | 48 ++++++++-
>> fs/ceph/super.h | 17 ++++
>> 10 files changed, 646 insertions(+), 28 deletions(-)
>> create mode 100644 fs/ceph/cache.c
>> create mode 100644 fs/ceph/cache.h
>>
>> diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
>> index 49bc782..ac9a2ef 100644
>> --- a/fs/ceph/Kconfig
>> +++ b/fs/ceph/Kconfig
>> @@ -16,3 +16,12 @@ config CEPH_FS
>>
>> If unsure, say N.
>>
>> +if CEPH_FS
>> +config CEPH_FSCACHE
>> + bool "Enable Ceph client caching support"
>> + depends on CEPH_FS=m && FSCACHE || CEPH_FS=y && FSCACHE=y
>> + help
>> + Choose Y here to enable persistent, read-only local
>> + caching support for Ceph clients using FS-Cache
>> +
>> +endif
>> diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
>> index bd35212..0af0678 100644
>> --- a/fs/ceph/Makefile
>> +++ b/fs/ceph/Makefile
>> @@ -9,3 +9,5 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
>> mds_client.o mdsmap.o strings.o ceph_frag.o \
>> debugfs.o
>>
>> +ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
>> +
>> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
>> index afb2fc2..de6de0e 100644
>> --- a/fs/ceph/addr.c
>> +++ b/fs/ceph/addr.c
>> @@ -11,6 +11,7 @@
>>
>> #include "super.h"
>> #include "mds_client.h"
>> +#include "cache.h"
>> #include <linux/ceph/osd_client.h>
>>
>> /*
>> @@ -149,11 +150,23 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
>> struct ceph_inode_info *ci;
>> struct ceph_snap_context *snapc = page_snap_context(page);
>>
>> - BUG_ON(!PageLocked(page));
>> - BUG_ON(!PagePrivate(page));
>
> Do these go away because of the fscache change? Or were they incorrect to
> begin with?
>
>> BUG_ON(!page->mapping);
>>
>> inode = page->mapping->host;
>> + ci = ceph_inode(inode);
>> +
>> + if (offset != 0) {
>> + dout("%p invalidatepage %p idx %lu partial dirty page\n",
>> + inode, page, page->index);
>> + return;
>> + }
>
> It would be nice to factor out the offset != 0 short circuit into a
> separate patch. Under what circumstances does it actually happen?
>
>> +
>> + ceph_invalidate_fscache_page(inode, page);
>> +
>> + if (!PagePrivate(page))
>> + return;
>> +
>> + BUG_ON(!PageLocked(page));
>>
>> /*
>> * We can get non-dirty pages here due to races between
>> @@ -163,31 +176,28 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
>> if (!PageDirty(page))
>> pr_err("%p invalidatepage %p page not dirty\n", inode, page);
>>
>> - if (offset == 0)
>> - ClearPageChecked(page);
>> + ClearPageChecked(page);
>>
>> - ci = ceph_inode(inode);
>> - if (offset == 0) {
>> - dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
>> - inode, page, page->index, offset);
>> - ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
>> - ceph_put_snap_context(snapc);
>> - page->private = 0;
>> - ClearPagePrivate(page);
>> - } else {
>> - dout("%p invalidatepage %p idx %lu partial dirty page\n",
>> - inode, page, page->index);
>> - }
>
> Again, having this code movement in a separate patch from fscache will
> make it easier to review and test.
>
> Thanks!
> sage
>
>
>> + dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
>> + inode, page, page->index, offset);
>> +
>> + ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
>> + ceph_put_snap_context(snapc);
>> + page->private = 0;
>> + ClearPagePrivate(page);
>> }
>>
>> -/* just a sanity check */
>> static int ceph_releasepage(struct page *page, gfp_t g)
>> {
>> struct inode *inode = page->mapping ? page->mapping->host : NULL;
>> dout("%p releasepage %p idx %lu\n", inode, page, page->index);
>> WARN_ON(PageDirty(page));
>> - WARN_ON(PagePrivate(page));
>> - return 0;
>> +
>> + /* Can we release the page from the cache? */
>> + if (!ceph_release_fscache_page(page, g))
>> + return 0;
>> +
>> + return !PagePrivate(page);
>> }
>>
>> /*
>> @@ -197,11 +207,16 @@ static int readpage_nounlock(struct file *filp, struct page *page)
>> {
>> struct inode *inode = file_inode(filp);
>> struct ceph_inode_info *ci = ceph_inode(inode);
>> - struct ceph_osd_client *osdc =
>> + struct ceph_osd_client *osdc =
>> &ceph_inode_to_client(inode)->client->osdc;
>> int err = 0;
>> u64 len = PAGE_CACHE_SIZE;
>>
>> + err = ceph_readpage_from_fscache(inode, page);
>> +
>> + if (err == 0)
>> + goto out;
>> +
>> dout("readpage inode %p file %p page %p index %lu\n",
>> inode, filp, page, page->index);
>> err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
>> @@ -219,6 +234,9 @@ static int readpage_nounlock(struct file *filp, struct page *page)
>> }
>> SetPageUptodate(page);
>>
>> + if (err == 0)
>> + ceph_readpage_to_fscache(inode, page);
>> +
>> out:
>> return err < 0 ? err : 0;
>> }
>> @@ -261,6 +279,7 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
>> page->index);
>> flush_dcache_page(page);
>> SetPageUptodate(page);
>> + ceph_readpage_to_fscache(inode, page);
>> unlock_page(page);
>> page_cache_release(page);
>> bytes -= PAGE_CACHE_SIZE;
>> @@ -330,7 +349,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
>> page = list_entry(page_list->prev, struct page, lru);
>> BUG_ON(PageLocked(page));
>> list_del(&page->lru);
>> -
>> +
>> dout("start_read %p adding %p idx %lu\n", inode, page,
>> page->index);
>> if (add_to_page_cache_lru(page, &inode->i_data, page->index,
>> @@ -377,6 +396,12 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
>> int rc = 0;
>> int max = 0;
>>
>> + rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list,
>> + &nr_pages);
>> +
>> + if (rc == 0)
>> + goto out;
>> +
>> if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
>> max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
>> >> PAGE_SHIFT;
>> @@ -496,6 +521,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
>> CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
>> set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
>>
>> + ceph_readpage_to_fscache(inode, page);
>> +
>> set_page_writeback(page);
>> err = ceph_osdc_writepages(osdc, ceph_vino(inode),
>> &ci->i_layout, snapc,
>> @@ -551,7 +578,6 @@ static void ceph_release_pages(struct page **pages, int num)
>> pagevec_release(&pvec);
>> }
>>
>> -
>> /*
>> * async writeback completion handler.
>> *
>> diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
>> new file mode 100644
>> index 0000000..fa49bf7
>> --- /dev/null
>> +++ b/fs/ceph/cache.c
>> @@ -0,0 +1,306 @@
>> +/*
>> + * Ceph cache definitions.
>> + *
>> + * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
>> + * Written by Milosz Tanski (milosz@adfin.com)
>> + *
>> + * This program is free software; you can redistribute it and/or modify
>> + * it under the terms of the GNU General Public License version 2
>> + * as published by the Free Software Foundation.
>> + *
>> + * This program is distributed in the hope that it will be useful,
>> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
>> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
>> + * GNU General Public License for more details.
>> + *
>> + * You should have received a copy of the GNU General Public License
>> + * along with this program; if not, write to:
>> + * Free Software Foundation
>> + * 51 Franklin Street, Fifth Floor
>> + * Boston, MA 02111-1301 USA
>> + *
>> + */
>> +
>> +#include "super.h"
>> +#include "cache.h"
>> +
>> +struct ceph_aux_inode {
>> + struct timespec mtime;
>> + loff_t size;
>> +};
>> +
>> +struct fscache_netfs ceph_cache_netfs = {
>> + .name = "ceph",
>> + .version = 0,
>> +};
>> +
>> +static uint16_t ceph_fscache_session_get_key(const void *cookie_netfs_data,
>> + void *buffer, uint16_t maxbuf)
>> +{
>> + const struct ceph_fs_client *fsc = cookie_netfs_data;
>> + uint16_t klen;
>> +
>> + klen = sizeof(fsc->client->fsid);
>> + if (klen > maxbuf)
>> + return 0;
>> +
>> + memcpy(buffer, &fsc->client->fsid, klen);
>> + return klen;
>> +}
>> +
>> +static const struct fscache_cookie_def ceph_fscache_fsid_object_def = {
>> + .name = "CEPH.fsid",
>> + .type = FSCACHE_COOKIE_TYPE_INDEX,
>> + .get_key = ceph_fscache_session_get_key,
>> +};
>> +
>> +void ceph_fscache_register_fsid_cookie(struct ceph_fs_client *fsc)
>> +{
>> + fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
>> + &ceph_fscache_fsid_object_def,
>> + fsc);
>> +}
>> +
>> +void ceph_fscache_unregister_fsid_cookie(struct ceph_fs_client *fsc)
>> +{
>> + fscache_relinquish_cookie(fsc->fscache, 0);
>> + fsc->fscache = NULL;
>> +}
>> +
>> +static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data,
>> + void *buffer, uint16_t maxbuf)
>> +{
>> + const struct ceph_inode_info *ci = cookie_netfs_data;
>> + uint16_t klen;
>> +
>> + /* use ceph virtual inode (id + snaphot) */
>> + klen = sizeof(ci->i_vino);
>> + if (klen > maxbuf)
>> + return 0;
>> +
>> + memcpy(buffer, &ci->i_vino, klen);
>> + return klen;
>> +}
>> +
>> +static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data,
>> + void *buffer, uint16_t bufmax)
>> +{
>> + struct ceph_aux_inode aux;
>> + const struct ceph_inode_info *ci = cookie_netfs_data;
>> + const struct inode *inode = &ci->vfs_inode;
>> +
>> + memset(&aux, 0, sizeof(aux));
>> + aux.mtime = inode->i_mtime;
>> + aux.size = inode->i_size;
>> +
>> + memcpy(buffer, &aux, sizeof(aux));
>> +
>> + return sizeof(aux);
>> +}
>> +
>> +static void ceph_fscache_inode_get_attr(const void *cookie_netfs_data,
>> + uint64_t *size)
>> +{
>> + const struct ceph_inode_info *ci = cookie_netfs_data;
>> + const struct inode *inode = &ci->vfs_inode;
>> +
>> + *size = inode->i_size;
>> +}
>> +
>> +static enum fscache_checkaux ceph_fscache_inode_check_aux(
>> + void *cookie_netfs_data, const void *data, uint16_t dlen)
>> +{
>> + struct ceph_aux_inode aux;
>> + struct ceph_inode_info *ci = cookie_netfs_data;
>> + struct inode *inode = &ci->vfs_inode;
>> +
>> + if (dlen != sizeof(aux))
>> + return FSCACHE_CHECKAUX_OBSOLETE;
>> +
>> + memset(&aux, 0, sizeof(aux));
>> + aux.mtime = inode->i_mtime;
>> + aux.size = inode->i_size;
>> +
>> + if (memcmp(data, &aux, sizeof(aux)) != 0)
>> + return FSCACHE_CHECKAUX_OBSOLETE;
>> +
>> + dout("ceph inode 0x%p cached okay", ci);
>> + return FSCACHE_CHECKAUX_OKAY;
>> +}
>> +
>> +static void ceph_fscache_inode_now_uncached(void *cookie_netfs_data)
>> +{
>> + struct ceph_inode_info *ci = cookie_netfs_data;
>> + struct pagevec pvec;
>> + pgoff_t first;
>> + int loop, nr_pages;
>> +
>> + pagevec_init(&pvec, 0);
>> + first = 0;
>> +
>> + dout("ceph inode 0x%p now uncached", ci);
>> +
>> + while (1) {
>> + nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first,
>> + PAGEVEC_SIZE - pagevec_count(&pvec));
>> +
>> + if (!nr_pages)
>> + break;
>> +
>> + for (loop = 0; loop < nr_pages; loop++)
>> + ClearPageFsCache(pvec.pages[loop]);
>> +
>> + first = pvec.pages[nr_pages - 1]->index + 1;
>> +
>> + pvec.nr = nr_pages;
>> + pagevec_release(&pvec);
>> + cond_resched();
>> + }
>> +}
>> +
>> +static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
>> + .name = "CEPH.inode",
>> + .type = FSCACHE_COOKIE_TYPE_DATAFILE,
>> + .get_key = ceph_fscache_inode_get_key,
>> + .get_attr = ceph_fscache_inode_get_attr,
>> + .get_aux = ceph_fscache_inode_get_aux,
>> + .check_aux = ceph_fscache_inode_check_aux,
>> + .now_uncached = ceph_fscache_inode_now_uncached,
>> +};
>> +
>> +void ceph_fscache_register_inode_cookie(struct ceph_fs_client *fsc,
>> + struct ceph_inode_info *ci)
>> +{
>> + struct inode *inode = &ci->vfs_inode;
>> +
>> + /* No caching for filesystem */
>> + if (fsc->fscache == NULL)
>> + return;
>> +
>> + /* Only cache for regular files that are read only */
>> + if ((ci->vfs_inode.i_mode & S_IFREG) == 0)
>> + return;
>> +
>> + /* Avoid multiple racing open requests */
>> + mutex_lock(&inode->i_mutex);
>> +
>> + if (ci->fscache)
>> + goto done;
>> +
>> + ci->fscache = fscache_acquire_cookie(fsc->fscache,
>> + &ceph_fscache_inode_object_def,
>> + ci);
>> +done:
>> + mutex_unlock(&inode->i_mutex);
>> +
>> +}
>> +
>> +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci)
>> +{
>> + fscache_uncache_all_inode_pages(ci->fscache, &ci->vfs_inode);
>> + fscache_relinquish_cookie(ci->fscache, 0);
>> + ci->fscache = NULL;
>> +}
>> +
>> +static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
>> +{
>> + if (!error)
>> + SetPageUptodate(page);
>> +}
>> +
>> +static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data,
>> + int error)
>> +{
>> + if (!error)
>> + SetPageUptodate(page);
>> +
>> + unlock_page(page);
>> +}
>> +
>> +static inline int cache_valid(struct ceph_inode_info *ci)
>> +{
>> + return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) &&
>> + (ci->i_fscache_gen == ci->i_rdcache_gen));
>> +}
>> +
>> +
>> +/* Atempt to read from the fscache,
>> + *
>> + * This function is called from the readpage_nounlock context. DO NOT attempt to
>> + * unlock the page here (or in the callback).
>> + */
>> +int __ceph_readpage_from_fscache(struct inode *inode, struct page *page)
>> +{
>> + struct ceph_inode_info *ci = ceph_inode(inode);
>> + int ret;
>> +
>> + if (!cache_valid(ci))
>> + return -ENOBUFS;
>> +
>> + ret = fscache_read_or_alloc_page(ci->fscache, page,
>> + ceph_vfs_readpage_complete, NULL,
>> + GFP_KERNEL);
>> +
>> + switch (ret) {
>> + case 0: /* Page found */
>> + dout("page read submitted\n");
>> + return 0;
>> + case -ENOBUFS: /* Pages were not found, and can't be */
>> + case -ENODATA: /* Pages were not found */
>> + dout("page/inode not in cache\n");
>> + return ret;
>> + default:
>> + dout("%s: unknown error ret = %i\n", __func__, ret);
>> + return ret;
>> + }
>> +}
>> +
>> +int __ceph_readpages_from_fscache(struct inode *inode,
>> + struct address_space *mapping,
>> + struct list_head *pages,
>> + unsigned *nr_pages)
>> +{
>> + struct ceph_inode_info *ci = ceph_inode(inode);
>> + int ret;
>> +
>> + if (!cache_valid(ci))
>> + return -ENOBUFS;
>> +
>> + ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
>> + ceph_vfs_readpage_complete_unlock,
>> + NULL, mapping_gfp_mask(mapping));
>> +
>> + switch (ret) {
>> + case 0: /* All pages found */
>> + dout("all-page read submitted\n");
>> + return 0;
>> + case -ENOBUFS: /* Some pages were not found, and can't be */
>> + case -ENODATA: /* some pages were not found */
>> + dout("page/inode not in cache\n");
>> + return ret;
>> + default:
>> + dout("%s: unknown error ret = %i\n", __func__, ret);
>> + return ret;
>> + }
>> +}
>> +
>> +void __ceph_readpage_to_fscache(struct inode *inode, struct page *page)
>> +{
>> + struct ceph_inode_info *ci = ceph_inode(inode);
>> + int ret;
>> +
>> + if (!cache_valid(ci))
>> + return;
>> +
>> + ret = fscache_write_page(ci->fscache, page, GFP_KERNEL);
>> + if (ret)
>> + fscache_uncache_page(ci->fscache, page);
>> +}
>> +
>> +void __ceph_invalidate_fscache_page(struct inode *inode, struct page *page)
>> +{
>> + struct ceph_inode_info *ci = ceph_inode(inode);
>> +
>> + fscache_wait_on_page_write(ci->fscache, page);
>> + fscache_uncache_page(ci->fscache, page);
>> +}
>> diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
>> new file mode 100644
>> index 0000000..23ce336
>> --- /dev/null
>> +++ b/fs/ceph/cache.h
>> @@ -0,0 +1,117 @@
>> +/*
>> + * Ceph cache definitions.
>> + *
>> + * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
>> + * Written by Milosz Tanski (milosz@adfin.com)
>> + *
>> + * This program is free software; you can redistribute it and/or modify
>> + * it under the terms of the GNU General Public License version 2
>> + * as published by the Free Software Foundation.
>> + *
>> + * This program is distributed in the hope that it will be useful,
>> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
>> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
>> + * GNU General Public License for more details.
>> + *
>> + * You should have received a copy of the GNU General Public License
>> + * along with this program; if not, write to:
>> + * Free Software Foundation
>> + * 51 Franklin Street, Fifth Floor
>> + * Boston, MA 02111-1301 USA
>> + *
>> + */
>> +
>> +#ifndef _CEPH_CACHE_H
>> +#define _CEPH_CACHE_H
>> +
>> +#include <linux/fscache.h>
>> +
>> +
>> +extern struct fscache_netfs ceph_cache_netfs;
>> +
>> +
>> +void ceph_fscache_register_fsid_cookie(struct ceph_fs_client *fsc);
>> +void ceph_fscache_unregister_fsid_cookie(struct ceph_fs_client *fsc);
>> +void ceph_fscache_register_inode_cookie(struct ceph_fs_client *parent_fsc,
>> + struct ceph_inode_info *ci);
>> +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci);
>> +
>> +int __ceph_readpage_from_fscache(struct inode *inode, struct page *page);
>> +int __ceph_readpages_from_fscache(struct inode *inode,
>> + struct address_space *mapping,
>> + struct list_head *pages,
>> + unsigned *nr_pages);
>> +void __ceph_readpage_to_fscache(struct inode *inode, struct page *page);
>> +void __ceph_invalidate_fscache_page(struct inode *inode, struct page *page);
>> +
>> +#ifdef CONFIG_CEPH_FSCACHE
>> +
>> +
>> +static inline int ceph_readpage_from_fscache(struct inode *inode,
>> + struct page *page)
>> +{
>> + return __ceph_readpage_from_fscache(inode, page);
>> +}
>> +
>> +static inline int ceph_readpages_from_fscache(struct inode *inode,
>> + struct address_space *mapping,
>> + struct list_head *pages,
>> + unsigned *nr_pages)
>> +{
>> + return __ceph_readpages_from_fscache(inode, mapping, pages,
>> + nr_pages);
>> +}
>> +
>> +static inline void ceph_readpage_to_fscache(struct inode *inode,
>> + struct page *page)
>> +{
>> + return __ceph_readpage_to_fscache(inode, page);
>> +}
>> +
>> +static inline void ceph_invalidate_fscache_page(struct inode *inode,
>> + struct page *page)
>> +{
>> + return __ceph_invalidate_fscache_page(inode, page);
>> +}
>> +
>> +static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
>> +{
>> + struct inode *inode = page->mapping->host;
>> + struct ceph_inode_info *ci = ceph_inode(inode);
>> + return fscache_maybe_release_page(ci->fscache, page, gfp);
>> +}
>> +
>> +#else
>> +
>> +static inline int ceph_readpage_from_fscache(struct inode *inode,
>> + struct page *page)
>> +{
>> + return -ENOBUFS;
>> +}
>> +
>> +static inline int ceph_readpages_from_fscache(struct inode *inode,
>> + struct address_space *mapping,
>> + struct list_head *pages,
>> + unsigned *nr_pages)
>> +{
>> + return -ENOBUFS;
>> +}
>> +
>> +static inline void ceph_readpage_to_fscache(struct inode *inode,
>> + struct page *page)
>> +{
>> +}
>> +
>> +static inline void ceph_invalidate_fscache_page(struct inode *inode,
>> + struct page *page)
>> +{
>> +}
>> +
>> +static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
>> +{
>> + return 1;
>> +}
>> +
>> +#endif
>> +
>> +#endif
>> diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
>> index 430121a..32ce13d 100644
>> --- a/fs/ceph/caps.c
>> +++ b/fs/ceph/caps.c
>> @@ -10,6 +10,7 @@
>>
>> #include "super.h"
>> #include "mds_client.h"
>> +#include "cache.h"
>> #include <linux/ceph/decode.h>
>> #include <linux/ceph/messenger.h>
>>
>> @@ -479,8 +480,9 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
>> * i_rdcache_gen.
>> */
>> if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
>> - (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
>> + (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) {
>> ci->i_rdcache_gen++;
>> + }
>>
>> /*
>> * if we are newly issued FILE_SHARED, mark dir not complete; we
>> @@ -2396,6 +2398,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
>> int revoked_rdcache = 0;
>> int queue_invalidate = 0;
>> int deleted_inode = 0;
>> + int queue_revalidate = 0;
>>
>> dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
>> inode, cap, mds, seq, ceph_cap_string(newcaps));
>> @@ -2420,6 +2423,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
>> ci->i_rdcache_revoking = ci->i_rdcache_gen;
>> }
>> }
>> +
>> + fscache_invalidate(ci->fscache);
>> }
>>
>> /* side effects now are allowed */
>> @@ -2461,6 +2466,11 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
>> }
>> }
>>
>> + /* Do we need to revalidate our fscache cookie. Don't bother on the
>> + * first cache cap as we already validate at cookie creation time. */
>> + if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
>> + queue_revalidate = 1;
>> +
>> /* size/ctime/mtime/atime? */
>> ceph_fill_file_size(inode, issued,
>> le32_to_cpu(grant->truncate_seq),
>> @@ -2545,6 +2555,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
>> BUG_ON(cap->issued & ~cap->implemented);
>>
>> spin_unlock(&ci->i_ceph_lock);
>> +
>> if (writeback)
>> /*
>> * queue inode for writeback: we can't actually call
>> @@ -2556,6 +2567,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
>> ceph_queue_invalidate(inode);
>> if (deleted_inode)
>> invalidate_aliases(inode);
>> + if (queue_revalidate)
>> + ceph_queue_revalidate(inode);
>> if (wake)
>> wake_up_all(&ci->i_cap_wq);
>>
>> @@ -2712,8 +2725,10 @@ static void handle_cap_trunc(struct inode *inode,
>> truncate_seq, truncate_size, size);
>> spin_unlock(&ci->i_ceph_lock);
>>
>> - if (queue_trunc)
>> + if (queue_trunc) {
>> ceph_queue_vmtruncate(inode);
>> + fscache_invalidate(ci->fscache);
>> + }
>> }
>>
>> /*
>> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
>> index 63ec830..ff35aa4 100644
>> --- a/fs/ceph/file.c
>> +++ b/fs/ceph/file.c
>> @@ -11,6 +11,7 @@
>>
>> #include "super.h"
>> #include "mds_client.h"
>> +#include "cache.h"
>>
>> /*
>> * Ceph file operations
>> @@ -68,9 +69,23 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
>> {
>> struct ceph_file_info *cf;
>> int ret = 0;
>> + struct ceph_inode_info *ci = ceph_inode(inode);
>> + struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
>> + struct ceph_mds_client *mdsc = fsc->mdsc;
>>
>> switch (inode->i_mode & S_IFMT) {
>> case S_IFREG:
>> + /* First file open request creates the cookie, we want to keep
>> + * this cookie around for the filetime of the inode as not to
>> + * have to worry about fscache register / revoke / operation
>> + * races.
>> + *
>> + * Also, if we know the operation is going to invalidate data
>> + * (non readonly) just nuke the cache right away.
>> + */
>> + ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
>> + if ((fmode & CEPH_FILE_MODE_WR))
>> + fscache_invalidate(ci->fscache);
>> case S_IFDIR:
>> dout("init_file %p %p 0%o (regular)\n", inode, file,
>> inode->i_mode);
>> @@ -181,6 +196,7 @@ int ceph_open(struct inode *inode, struct file *file)
>> spin_unlock(&ci->i_ceph_lock);
>> return ceph_init_file(inode, file, fmode);
>> }
>> +
>> spin_unlock(&ci->i_ceph_lock);
>>
>> dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
>> @@ -191,6 +207,7 @@ int ceph_open(struct inode *inode, struct file *file)
>> }
>> req->r_inode = inode;
>> ihold(inode);
>> +
>> req->r_num_caps = 1;
>> if (flags & (O_CREAT|O_TRUNC))
>> parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
>> diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
>> index 3b0abed..d85c977 100644
>> --- a/fs/ceph/inode.c
>> +++ b/fs/ceph/inode.c
>> @@ -12,6 +12,7 @@
>>
>> #include "super.h"
>> #include "mds_client.h"
>> +#include "cache.h"
>> #include <linux/ceph/decode.h>
>>
>> /*
>> @@ -31,6 +32,7 @@ static const struct inode_operations ceph_symlink_iops;
>> static void ceph_invalidate_work(struct work_struct *work);
>> static void ceph_writeback_work(struct work_struct *work);
>> static void ceph_vmtruncate_work(struct work_struct *work);
>> +static void ceph_revalidate_work(struct work_struct *work);
>>
>> /*
>> * find or create an inode, given the ceph ino number
>> @@ -385,6 +387,13 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
>>
>> INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work);
>>
>> +#ifdef CONFIG_CEPH_FSCACHE
>> + ci->fscache = NULL;
>> + /* The first load is verifed cookie open time */
>> + ci->i_fscache_gen = 1;
>> + INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work);
>> +#endif
>> +
>> return &ci->vfs_inode;
>> }
>>
>> @@ -404,6 +413,8 @@ void ceph_destroy_inode(struct inode *inode)
>>
>> dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
>>
>> + ceph_fscache_unregister_inode_cookie(ci);
>> +
>> ceph_queue_caps_release(inode);
>>
>> /*
>> @@ -438,7 +449,6 @@ void ceph_destroy_inode(struct inode *inode)
>> call_rcu(&inode->i_rcu, ceph_i_callback);
>> }
>>
>> -
>> /*
>> * Helpers to fill in size, ctime, mtime, and atime. We have to be
>> * careful because either the client or MDS may have more up to date
>> @@ -486,6 +496,10 @@ int ceph_fill_file_size(struct inode *inode, int issued,
>> truncate_size);
>> ci->i_truncate_size = truncate_size;
>> }
>> +
>> + if (queue_trunc)
>> + fscache_invalidate(ci->fscache);
>> +
>> return queue_trunc;
>> }
>>
>> @@ -1074,7 +1088,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
>> * complete.
>> */
>> ceph_set_dentry_offset(req->r_old_dentry);
>> - dout("dn %p gets new offset %lld\n", req->r_old_dentry,
>> + dout("dn %p gets new offset %lld\n", req->r_old_dentry,
>> ceph_dentry(req->r_old_dentry)->offset);
>>
>> dn = req->r_old_dentry; /* use old_dentry */
>> @@ -1495,6 +1509,7 @@ void ceph_queue_vmtruncate(struct inode *inode)
>> struct ceph_inode_info *ci = ceph_inode(inode);
>>
>> ihold(inode);
>> +
>> if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
>> &ci->i_vmtruncate_work)) {
>> dout("ceph_queue_vmtruncate %p\n", inode);
>> @@ -1559,6 +1574,56 @@ retry:
>> wake_up_all(&ci->i_cap_wq);
>> }
>>
>> +static void ceph_revalidate_work(struct work_struct *work)
>> +{
>> + int issued;
>> + u32 orig_gen;
>> + struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
>> + i_revalidate_work);
>> + struct inode *inode = &ci->vfs_inode;
>> +
>> + spin_lock(&ci->i_ceph_lock);
>> + issued = __ceph_caps_issued(ci, NULL);
>> + orig_gen = ci->i_rdcache_gen;
>> + spin_unlock(&ci->i_ceph_lock);
>> +
>> + if (!(issued & CEPH_CAP_FILE_CACHE)) {
>> + dout("revalidate_work lost cache before validation %p\n",
>> + inode);
>> + goto out;
>> + }
>> +
>> + if (!fscache_check_consistency(ci->fscache))
>> + fscache_invalidate(ci->fscache);
>> +
>> + spin_lock(&ci->i_ceph_lock);
>> + /* Update the new valid generation (backwards sanity check too) */
>> + if (orig_gen > ci->i_fscache_gen) {
>> + ci->i_fscache_gen = orig_gen;
>> + } else {
>> + pr_warn("revalidate_work raced cache validation %p\n",
>> + inode);
>> + }
>> + spin_unlock(&ci->i_ceph_lock);
>> +
>> +out:
>> + iput(&ci->vfs_inode);
>> +}
>> +
>> +void ceph_queue_revalidate(struct inode *inode)
>> +{
>> + struct ceph_inode_info *ci = ceph_inode(inode);
>> +
>> + ihold(inode);
>> +
>> + if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq,
>> + &ci->i_revalidate_work)) {
>> + dout("ceph_queue_revalidate %p\n", inode);
>> + } else {
>> + dout("ceph_queue_revalidate %p failed\n)", inode);
>> + iput(inode);
>> + }
>> +}
>>
>> /*
>> * symlinks
>> diff --git a/fs/ceph/super.c b/fs/ceph/super.c
>> index 6627b26..d88808c 100644
>> --- a/fs/ceph/super.c
>> +++ b/fs/ceph/super.c
>> @@ -17,6 +17,7 @@
>>
>> #include "super.h"
>> #include "mds_client.h"
>> +#include "cache.h"
>>
>> #include <linux/ceph/ceph_features.h>
>> #include <linux/ceph/decode.h>
>> @@ -142,6 +143,8 @@ enum {
>> Opt_nodcache,
>> Opt_ino32,
>> Opt_noino32,
>> + Opt_fscache,
>> + Opt_nofscache
>> };
>>
>> static match_table_t fsopt_tokens = {
>> @@ -167,6 +170,8 @@ static match_table_t fsopt_tokens = {
>> {Opt_nodcache, "nodcache"},
>> {Opt_ino32, "ino32"},
>> {Opt_noino32, "noino32"},
>> + {Opt_fscache, "fsc"},
>> + {Opt_nofscache, "nofsc"},
>> {-1, NULL}
>> };
>>
>> @@ -260,6 +265,12 @@ static int parse_fsopt_token(char *c, void *private)
>> case Opt_noino32:
>> fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
>> break;
>> + case Opt_fscache:
>> + fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
>> + break;
>> + case Opt_nofscache:
>> + fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
>> + break;
>> default:
>> BUG_ON(token);
>> }
>> @@ -422,6 +433,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
>> seq_puts(m, ",dcache");
>> else
>> seq_puts(m, ",nodcache");
>> + if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE)
>> + seq_puts(m, ",fsc");
>> + else
>> + seq_puts(m, ",nofsc");
>>
>> if (fsopt->wsize)
>> seq_printf(m, ",wsize=%d", fsopt->wsize);
>> @@ -530,11 +545,24 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
>> if (!fsc->wb_pagevec_pool)
>> goto fail_trunc_wq;
>>
>> +#ifdef CONFIG_CEPH_FSCACHE
>> + if ((fsopt->flags & CEPH_MOUNT_OPT_FSCACHE))
>> + ceph_fscache_register_fsid_cookie(fsc);
>> +
>> + fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1);
>> + if (fsc->revalidate_wq == NULL)
>> + goto fail_fscache;
>> +#endif
>> +
>> /* caps */
>> fsc->min_caps = fsopt->max_readdir;
>>
>> return fsc;
>>
>> +#ifdef CONFIG_CEPH_FSCACHE
>> +fail_fscache:
>> + ceph_fscache_unregister_fsid_cookie(fsc);
>> +#endif
>> fail_trunc_wq:
>> destroy_workqueue(fsc->trunc_wq);
>> fail_pg_inv_wq:
>> @@ -554,6 +582,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
>> {
>> dout("destroy_fs_client %p\n", fsc);
>>
>> +#ifdef CONFIG_CEPH_FSCACHE
>> + ceph_fscache_unregister_fsid_cookie(fsc);
>> +#endif
>> +
>> destroy_workqueue(fsc->wb_wq);
>> destroy_workqueue(fsc->pg_inv_wq);
>> destroy_workqueue(fsc->trunc_wq);
>> @@ -588,6 +620,8 @@ static void ceph_inode_init_once(void *foo)
>>
>> static int __init init_caches(void)
>> {
>> + int error = -ENOMEM;
>> +
>> ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
>> sizeof(struct ceph_inode_info),
>> __alignof__(struct ceph_inode_info),
>> @@ -611,15 +645,20 @@ static int __init init_caches(void)
>> if (ceph_file_cachep == NULL)
>> goto bad_file;
>>
>> - return 0;
>> +#ifdef CONFIG_CEPH_FSCACHE
>> + error = fscache_register_netfs(&ceph_cache_netfs);
>> + if (error)
>> + goto bad_file;
>> +#endif
>>
>> + return 0;
>> bad_file:
>> kmem_cache_destroy(ceph_dentry_cachep);
>> bad_dentry:
>> kmem_cache_destroy(ceph_cap_cachep);
>> bad_cap:
>> kmem_cache_destroy(ceph_inode_cachep);
>> - return -ENOMEM;
>> + return error;
>> }
>>
>> static void destroy_caches(void)
>> @@ -629,10 +668,15 @@ static void destroy_caches(void)
>> * destroy cache.
>> */
>> rcu_barrier();
>> +
>> kmem_cache_destroy(ceph_inode_cachep);
>> kmem_cache_destroy(ceph_cap_cachep);
>> kmem_cache_destroy(ceph_dentry_cachep);
>> kmem_cache_destroy(ceph_file_cachep);
>> +
>> +#ifdef CONFIG_CEPH_FSCACHE
>> + fscache_unregister_netfs(&ceph_cache_netfs);
>> +#endif
>> }
>>
>>
>> diff --git a/fs/ceph/super.h b/fs/ceph/super.h
>> index afcd62a..8bcac51 100644
>> --- a/fs/ceph/super.h
>> +++ b/fs/ceph/super.h
>> @@ -16,6 +16,10 @@
>>
>> #include <linux/ceph/libceph.h>
>>
>> +#ifdef CONFIG_CEPH_FSCACHE
>> +#include <linux/fscache.h>
>> +#endif
>> +
>> /* f_type in struct statfs */
>> #define CEPH_SUPER_MAGIC 0x00c36400
>>
>> @@ -29,6 +33,7 @@
>> #define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */
>> #define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */
>> #define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */
>> +#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */
>>
>> #define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES)
>>
>> @@ -90,6 +95,11 @@ struct ceph_fs_client {
>> struct dentry *debugfs_bdi;
>> struct dentry *debugfs_mdsc, *debugfs_mdsmap;
>> #endif
>> +
>> +#ifdef CONFIG_CEPH_FSCACHE
>> + struct fscache_cookie *fscache;
>> + struct workqueue_struct *revalidate_wq;
>> +#endif
>> };
>>
>>
>> @@ -319,6 +329,12 @@ struct ceph_inode_info {
>>
>> struct work_struct i_vmtruncate_work;
>>
>> +#ifdef CONFIG_CEPH_FSCACHE
>> + struct fscache_cookie *fscache;
>> + u32 i_fscache_gen; /* sequence, for delayed fscache validate */
>> + struct work_struct i_revalidate_work;
>> +#endif
>> +
>> struct inode vfs_inode; /* at end */
>> };
>>
>> @@ -699,6 +715,7 @@ extern void ceph_queue_vmtruncate(struct inode *inode);
>>
>> extern void ceph_queue_invalidate(struct inode *inode);
>> extern void ceph_queue_writeback(struct inode *inode);
>> +extern void ceph_queue_revalidate(struct inode *inode);
>>
>> extern int ceph_do_getattr(struct inode *inode, int mask);
>> extern int ceph_permission(struct inode *inode, int mask);
>> --
>> 1.8.1.2
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>
>>
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2013-08-09 16:24 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-08-07 23:15 [PATCH 0/3] ceph: persistent caching with fscache Milosz Tanski
2013-08-07 23:15 ` [PATCH 1/3] new cachefiles interface to check cache consistency Hongyi Jia
2013-08-07 23:15 ` [PATCH 2/3] new fscache " Hongyi Jia
2013-08-07 23:16 ` [PATCH 3/3] ceph: use fscache as a local presisent cache Milosz Tanski
2013-08-09 4:16 ` Sage Weil
2013-08-09 16:24 ` Milosz Tanski
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.