ceph: use fscache as a local presisent cache

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 <[email protected]> Signed-off-by: Sage Weil <[email protected]>
chewitt · Sep 6, 2013 · 99ccbd2 · 99ccbd2
1 parent cd0a2df
commit 99ccbd2
Show file tree

Hide file tree

Showing 10 changed files with 666 additions and 13 deletions.
diff --git 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
@@ -9,3 +9,4 @@ 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
@@ -11,6 +11,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "cache.h"
 #include <linux/ceph/osd_client.h>
 
 /*
@@ -144,6 +145,11 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 		return;
 	}
 
+	ceph_invalidate_fscache_page(inode, page);
+
+	if (!PagePrivate(page))
+		return;
+
 	/*
 	 * We can get non-dirty pages here due to races between
 	 * set_page_dirty and truncate_complete_page; just spit out a
@@ -163,14 +169,17 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 	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);
 }
 
 /*
@@ -180,11 +189,16 @@ 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,
@@ -202,6 +216,9 @@ 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;
 }
@@ -244,6 +261,7 @@ 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;
@@ -313,7 +331,7 @@ 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,
@@ -360,6 +378,12 @@ 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;
@@ -479,6 +503,8 @@ 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,
@@ -534,7 +560,6 @@ static void ceph_release_pages(struct page **pages, int num)
 	pagevec_release(&pvec);
 }
 
-
 /*
  * async writeback completion handler.
  *