Commit 3d14c5d2 authored by Yehuda Sadeh's avatar Yehuda Sadeh Committed by Sage Weil
Browse files

ceph: factor out libceph from Ceph file system 



This factors out protocol and low-level storage parts of ceph into a
separate libceph module living in net/ceph and include/linux/ceph.  This
is mostly a matter of moving files around.  However, a few key pieces
of the interface change as well:

 - ceph_client becomes ceph_fs_client and ceph_client, where the latter
   captures the mon and osd clients, and the fs_client gets the mds client
   and file system specific pieces.
 - Mount option parsing and debugfs setup is correspondingly broken into
   two pieces.
 - The mon client gets a generic handler callback for otherwise unknown
   messages (mds map, in this case).
 - The basic supported/required feature bits can be expanded (and are by
   ceph_fs_client).

No functional change, aside from some subtle error handling cases that got
cleaned up in the refactoring process.

Signed-off-by: default avatarSage Weil <sage@newdream.net>
parent ae1533b6

MAINTAINERS

+2 −0
Original line number Diff line number Diff line
@@ -1527,6 +1527,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git 
S:	Supported

F:	Documentation/filesystems/ceph.txt

F:	fs/ceph

F:	net/ceph

F:	include/linux/ceph



CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:

M:	David Vrabel <david.vrabel@csr.com>

fs/ceph/Kconfig

+2 −12
Original line number Diff line number Diff line 
config CEPH_FS

        tristate "Ceph distributed file system (EXPERIMENTAL)"

	depends on INET && EXPERIMENTAL

	select CEPH_LIB

	select LIBCRC32C

	select CRYPTO_AES

	select CRYPTO

	default n

	help

	  Choose Y or M here to include support for mounting the

	  experimental Ceph distributed file system.  Ceph is an extremely
@@ -14,15 +16,3 @@ config CEPH_FS 


	  If unsure, say N.

config CEPH_FS_PRETTYDEBUG

	bool "Include file:line in ceph debug output"

	depends on CEPH_FS

	default n

	help

	  If you say Y here, debug output will include a filename and

	  line to aid debugging.  This icnreases kernel size and slows

	  execution slightly when debug call sites are enabled (e.g.,

	  via CONFIG_DYNAMIC_DEBUG).



	  If unsure, say N.

fs/ceph/Makefile

+2 −9
Original line number Diff line number Diff line
@@ -8,15 +8,8 @@ obj-$(CONFIG_CEPH_FS) += ceph.o 


ceph-objs := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \

	export.o caps.o snap.o xattr.o \

	messenger.o msgpool.o buffer.o pagelist.o \

	mds_client.o mdsmap.o \

	mon_client.o \

	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \

	debugfs.o \

	auth.o auth_none.o \

	crypto.o armor.o \

	auth_x.o \

	ceph_fs.o ceph_strings.o ceph_hash.o ceph_frag.o

	mds_client.o mdsmap.o strings.o ceph_frag.o \

	debugfs.o



else

#Otherwise we were called directly from the command

fs/ceph/README

deleted100644 → 0
+0 −20
Original line number Diff line number Diff line 
#

# The following files are shared by (and manually synchronized

# between) the Ceph userland and kernel client.

#

# userland                  kernel

src/include/ceph_fs.h	    fs/ceph/ceph_fs.h

src/include/ceph_fs.cc	    fs/ceph/ceph_fs.c

src/include/msgr.h	    fs/ceph/msgr.h

src/include/rados.h	    fs/ceph/rados.h

src/include/ceph_strings.cc fs/ceph/ceph_strings.c

src/include/ceph_frag.h	    fs/ceph/ceph_frag.h

src/include/ceph_frag.cc    fs/ceph/ceph_frag.c

src/include/ceph_hash.h	    fs/ceph/ceph_hash.h

src/include/ceph_hash.cc    fs/ceph/ceph_hash.c

src/crush/crush.c	    fs/ceph/crush/crush.c

src/crush/crush.h	    fs/ceph/crush/crush.h

src/crush/mapper.c	    fs/ceph/crush/mapper.c

src/crush/mapper.h	    fs/ceph/crush/mapper.h

src/crush/hash.h	    fs/ceph/crush/hash.h

src/crush/hash.c	    fs/ceph/crush/hash.c

fs/ceph/addr.c

+34 −31
Original line number Diff line number Diff line 
#include "ceph_debug.h"

#include <linux/ceph/ceph_debug.h>



#include <linux/backing-dev.h>

#include <linux/fs.h>
@@ -10,7 +10,8 @@ 
#include <linux/task_io_accounting_ops.h>



#include "super.h"

#include "osd_client.h"

#include "mds_client.h"

#include <linux/ceph/osd_client.h>



/*

 * Ceph address space ops.
@@ -193,7 +194,8 @@ static int readpage_nounlock(struct file *filp, struct page *page) 
{

	struct inode *inode = filp->f_dentry->d_inode;

	struct ceph_inode_info *ci = ceph_inode(inode);

	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;

	struct ceph_osd_client *osdc = 

		&ceph_inode_to_client(inode)->client->osdc;

	int err = 0;

	u64 len = PAGE_CACHE_SIZE;
@@ -265,7 +267,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, 
{

	struct inode *inode = file->f_dentry->d_inode;

	struct ceph_inode_info *ci = ceph_inode(inode);

	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;

	struct ceph_osd_client *osdc =

		&ceph_inode_to_client(inode)->client->osdc;

	int rc = 0;

	struct page **pages;

	loff_t offset;
@@ -365,7 +368,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) 
{

	struct inode *inode;

	struct ceph_inode_info *ci;

	struct ceph_client *client;

	struct ceph_fs_client *fsc;

	struct ceph_osd_client *osdc;

	loff_t page_off = page->index << PAGE_CACHE_SHIFT;

	int len = PAGE_CACHE_SIZE;
@@ -383,8 +386,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) 
	}

	inode = page->mapping->host;

	ci = ceph_inode(inode);

	client = ceph_inode_to_client(inode);

	osdc = &client->osdc;

	fsc = ceph_inode_to_client(inode);

	osdc = &fsc->client->osdc;



	/* verify this is a writeable snap context */

	snapc = (void *)page->private;
@@ -414,10 +417,10 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) 
	dout("writepage %p page %p index %lu on %llu~%u snapc %p\n",

	     inode, page, page->index, page_off, len, snapc);



	writeback_stat = atomic_long_inc_return(&client->writeback_count);

	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);

	if (writeback_stat >

	    CONGESTION_ON_THRESH(client->mount_args->congestion_kb))

		set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC);

	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))

		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);



	set_page_writeback(page);

	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -496,7 +499,7 @@ static void writepages_finish(struct ceph_osd_request *req, 
	struct address_space *mapping = inode->i_mapping;

	__s32 rc = -EIO;

	u64 bytes = 0;

	struct ceph_client *client = ceph_inode_to_client(inode);

	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);

	long writeback_stat;

	unsigned issued = ceph_caps_issued(ci);
@@ -529,10 +532,10 @@ static void writepages_finish(struct ceph_osd_request *req, 
		WARN_ON(!PageUptodate(page));



		writeback_stat =

			atomic_long_dec_return(&client->writeback_count);

			atomic_long_dec_return(&fsc->writeback_count);

		if (writeback_stat <

		    CONGESTION_OFF_THRESH(client->mount_args->congestion_kb))

			clear_bdi_congested(&client->backing_dev_info,

		    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))

			clear_bdi_congested(&fsc->backing_dev_info,

					    BLK_RW_ASYNC);



		ceph_put_snap_context((void *)page->private);
@@ -569,13 +572,13 @@ static void writepages_finish(struct ceph_osd_request *req, 
 * mempool.  we avoid the mempool if we can because req->r_num_pages

 * may be less than the maximum write size.

 */

static void alloc_page_vec(struct ceph_client *client,

static void alloc_page_vec(struct ceph_fs_client *fsc,

			   struct ceph_osd_request *req)

{

	req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages,

			       GFP_NOFS);

	if (!req->r_pages) {

		req->r_pages = mempool_alloc(client->wb_pagevec_pool, GFP_NOFS);

		req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS);

		req->r_pages_from_pool = 1;

		WARN_ON(!req->r_pages);

	}
@@ -590,7 +593,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
	struct inode *inode = mapping->host;

	struct backing_dev_info *bdi = mapping->backing_dev_info;

	struct ceph_inode_info *ci = ceph_inode(inode);

	struct ceph_client *client;

	struct ceph_fs_client *fsc;

	pgoff_t index, start, end;

	int range_whole = 0;

	int should_loop = 1;
@@ -617,13 +620,13 @@ static int ceph_writepages_start(struct address_space *mapping, 
	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :

	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));



	client = ceph_inode_to_client(inode);

	if (client->mount_state == CEPH_MOUNT_SHUTDOWN) {

	fsc = ceph_inode_to_client(inode);

	if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {

		pr_warning("writepage_start %p on forced umount\n", inode);

		return -EIO; /* we're in a forced umount, don't write! */

	}

	if (client->mount_args->wsize && client->mount_args->wsize < wsize)

		wsize = client->mount_args->wsize;

	if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)

		wsize = fsc->mount_options->wsize;

	if (wsize < PAGE_CACHE_SIZE)

		wsize = PAGE_CACHE_SIZE;

	max_pages_ever = wsize >> PAGE_CACHE_SHIFT;
@@ -769,7 +772,7 @@ get_more_pages: 
				offset = (unsigned long long)page->index

					<< PAGE_CACHE_SHIFT;

				len = wsize;

				req = ceph_osdc_new_request(&client->osdc,

				req = ceph_osdc_new_request(&fsc->client->osdc,

					    &ci->i_layout,

					    ceph_vino(inode),

					    offset, &len,
@@ -782,7 +785,7 @@ get_more_pages: 
					    &inode->i_mtime, true, 1);

				max_pages = req->r_num_pages;



				alloc_page_vec(client, req);

				alloc_page_vec(fsc, req);

				req->r_callback = writepages_finish;

				req->r_inode = inode;

			}
@@ -794,10 +797,10 @@ get_more_pages: 
			     inode, page, page->index);



			writeback_stat =

			       atomic_long_inc_return(&client->writeback_count);

			       atomic_long_inc_return(&fsc->writeback_count);

			if (writeback_stat > CONGESTION_ON_THRESH(

				    client->mount_args->congestion_kb)) {

				set_bdi_congested(&client->backing_dev_info,

				    fsc->mount_options->congestion_kb)) {

				set_bdi_congested(&fsc->backing_dev_info,

						  BLK_RW_ASYNC);

			}
@@ -846,7 +849,7 @@ get_more_pages: 
		op->payload_len = cpu_to_le32(len);

		req->r_request->hdr.data_len = cpu_to_le32(len);



		ceph_osdc_start_request(&client->osdc, req, true);

		ceph_osdc_start_request(&fsc->client->osdc, req, true);

		req = NULL;



		/* continue? */
@@ -915,7 +918,7 @@ static int ceph_update_writeable_page(struct file *file, 
{

	struct inode *inode = file->f_dentry->d_inode;

	struct ceph_inode_info *ci = ceph_inode(inode);

	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;

	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;

	loff_t page_off = pos & PAGE_CACHE_MASK;

	int pos_in_page = pos & ~PAGE_CACHE_MASK;

	int end_in_page = pos_in_page + len;
@@ -1053,8 +1056,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, 
			  struct page *page, void *fsdata)

{

	struct inode *inode = file->f_dentry->d_inode;

	struct ceph_client *client = ceph_inode_to_client(inode);

	struct ceph_mds_client *mdsc = &client->mdsc;

	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);

	struct ceph_mds_client *mdsc = fsc->mdsc;

	unsigned from = pos & (PAGE_CACHE_SIZE - 1);

	int check_cap = 0;
@@ -1123,7 +1126,7 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) 
{

	struct inode *inode = vma->vm_file->f_dentry->d_inode;

	struct page *page = vmf->page;

	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;

	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;

	loff_t off = page->index << PAGE_CACHE_SHIFT;

	loff_t size, len;

	int ret;

CRA Git | Maintained and supported by SUSTech CRA and CCSE