Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit b284d4d5 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'ceph-for-4.17-rc1' of git://github.com/ceph/ceph-client 

Pull ceph updates from Ilya Dryomov:
 "The big ticket items are:

   - support for rbd "fancy" striping (myself).

     The striping feature bit is now fully implemented, allowing mapping
     v2 images with non-default striping patterns. This completes
     support for --image-format 2.

   - CephFS quota support (Luis Henriques and Zheng Yan).

     This set is based on the new SnapRealm code in the upcoming v13.y.z
     ("Mimic") release. Quota handling will be rejected on older
     filesystems.

   - memory usage improvements in CephFS (Chengguang Xu).

     Directory specific bits have been split out of ceph_file_info and
     some effort went into improving cap reservation code to avoid OOM
     crashes.

  Also included a bunch of assorted fixes all over the place from
  Chengguang and others"

* tag 'ceph-for-4.17-rc1' of git://github.com/ceph/ceph-client: (67 commits)
  ceph: quota: report root dir quota usage in statfs
  ceph: quota: add counter for snaprealms with quota
  ceph: quota: cache inode pointer in ceph_snap_realm
  ceph: fix root quota realm check
  ceph: don't check quota for snap inode
  ceph: quota: update MDS when max_bytes is approaching
  ceph: quota: support for ceph.quota.max_bytes
  ceph: quota: don't allow cross-quota renames
  ceph: quota: support for ceph.quota.max_files
  ceph: quota: add initial infrastructure to support cephfs quotas
  rbd: remove VLA usage
  rbd: fix spelling mistake: "reregisteration" -> "reregistration"
  ceph: rename function drop_leases() to a more descriptive name
  ceph: fix invalid point dereference for error case in mdsc destroy
  ceph: return proper bool type to caller instead of pointer
  ceph: optimize memory usage
  ceph: optimize mds session register
  libceph, ceph: add __init attribution to init funcitons
  ceph: filter out used flags when printing unused open flags
  ceph: don't wait on writeback when there is no more dirty pages
  ...
parents a7726f6b 9122eed5

Documentation/filesystems/ceph.txt

+16 −0
Original line number Diff line number Diff line
@@ -62,6 +62,18 @@ subdirectories, and a summation of all nested file sizes. This makes 
the identification of large disk space consumers relatively quick, as

no 'du' or similar recursive scan of the file system is required.



Finally, Ceph also allows quotas to be set on any directory in the system.

The quota can restrict the number of bytes or the number of files stored

beneath that point in the directory hierarchy.  Quotas can be set using

extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg:



 setfattr -n ceph.quota.max_bytes -v 100000000 /some/dir

 getfattr -n ceph.quota.max_bytes /some/dir



A limitation of the current quotas implementation is that it relies on the

cooperation of the client mounting the file system to stop writers when a

limit is reached.  A modified or adversarial client cannot be prevented

from writing as much data as it needs.



Mount Syntax

============
@@ -137,6 +149,10 @@ Mount Options 
  noasyncreaddir

	Do not use the dcache as above for readdir.



  noquotadf

        Report overall filesystem usage in statfs instead of using the root

        directory quota.



More Information

================

drivers/block/rbd.c

+980 −1472

File changed.

Preview size limit exceeded, changes collapsed.

fs/ceph/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -6,7 +6,7 @@ 
obj-$(CONFIG_CEPH_FS) += ceph.o



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

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

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

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

	debugfs.o

fs/ceph/addr.c

+32 −31
Original line number Diff line number Diff line
@@ -15,6 +15,7 @@ 
#include "mds_client.h"

#include "cache.h"

#include <linux/ceph/osd_client.h>

#include <linux/ceph/striper.h>



/*

 * Ceph address space ops.
@@ -438,7 +439,7 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, 
{

	struct inode *inode = file_inode(file);

	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);

	struct ceph_file_info *ci = file->private_data;

	struct ceph_file_info *fi = file->private_data;

	struct ceph_rw_context *rw_ctx;

	int rc = 0;

	int max = 0;
@@ -452,7 +453,7 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, 
	if (rc == 0)

		goto out;



	rw_ctx = ceph_find_rw_context(ci);

	rw_ctx = ceph_find_rw_context(fi);

	max = fsc->mount_options->rsize >> PAGE_SHIFT;

	dout("readpages %p file %p ctx %p nr_pages %d max %d\n",

	     inode, file, rw_ctx, nr_pages, max);
@@ -800,7 +801,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
	struct ceph_osd_request *req = NULL;

	struct ceph_writeback_ctl ceph_wbc;

	bool should_loop, range_whole = false;

	bool stop, done = false;

	bool done = false;



	dout("writepages_start %p (mode=%s)\n", inode,

	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
@@ -856,7 +857,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
		 * in that range can be associated with newer snapc.

		 * They are not writeable until we write all dirty pages

		 * associated with 'snapc' get written */

		if (index > 0 || wbc->sync_mode != WB_SYNC_NONE)

		if (index > 0)

			should_loop = true;

		dout(" non-head snapc, range whole\n");

	}
@@ -864,8 +865,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
	ceph_put_snap_context(last_snapc);

	last_snapc = snapc;



	stop = false;

	while (!stop && index <= end) {

	while (!done && index <= end) {

		int num_ops = 0, op_idx;

		unsigned i, pvec_pages, max_pages, locked_pages = 0;

		struct page **pages = NULL, **data_pages;
@@ -898,16 +898,30 @@ static int ceph_writepages_start(struct address_space *mapping, 
				unlock_page(page);

				continue;

			}

			if (strip_unit_end && (page->index > strip_unit_end)) {

				dout("end of strip unit %p\n", page);

			/* only if matching snap context */

			pgsnapc = page_snap_context(page);

			if (pgsnapc != snapc) {

				dout("page snapc %p %lld != oldest %p %lld\n",

				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);

				if (!should_loop &&

				    !ceph_wbc.head_snapc &&

				    wbc->sync_mode != WB_SYNC_NONE)

					should_loop = true;

				unlock_page(page);

				break;

				continue;

			}

			if (page_offset(page) >= ceph_wbc.i_size) {

				dout("%p page eof %llu\n",

				     page, ceph_wbc.i_size);

				/* not done if range_cyclic */

				stop = true;

				if (ceph_wbc.size_stable ||

				    page_offset(page) >= i_size_read(inode))

					mapping->a_ops->invalidatepage(page,

								0, PAGE_SIZE);

				unlock_page(page);

				continue;

			}

			if (strip_unit_end && (page->index > strip_unit_end)) {

				dout("end of strip unit %p\n", page);

				unlock_page(page);

				break;

			}
@@ -921,15 +935,6 @@ static int ceph_writepages_start(struct address_space *mapping, 
				wait_on_page_writeback(page);

			}



			/* only if matching snap context */

			pgsnapc = page_snap_context(page);

			if (pgsnapc != snapc) {

				dout("page snapc %p %lld != oldest %p %lld\n",

				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);

				unlock_page(page);

				continue;

			}



			if (!clear_page_dirty_for_io(page)) {

				dout("%p !clear_page_dirty_for_io\n", page);

				unlock_page(page);
@@ -945,19 +950,15 @@ static int ceph_writepages_start(struct address_space *mapping, 
			if (locked_pages == 0) {

				u64 objnum;

				u64 objoff;

				u32 xlen;



				/* prepare async write request */

				offset = (u64)page_offset(page);

				len = wsize;



				rc = ceph_calc_file_object_mapping(&ci->i_layout,

								offset, len,

				ceph_calc_file_object_mapping(&ci->i_layout,

							      offset, wsize,

							      &objnum, &objoff,

								&len);

				if (rc < 0) {

					unlock_page(page);

					break;

				}

							      &xlen);

				len = xlen;



				num_ops = 1;

				strip_unit_end = page->index +
@@ -1146,7 +1147,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
		 * we tagged for writeback prior to entering this loop.

		 */

		if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE)

			done = stop = true;

			done = true;



release_pvec_pages:

		dout("pagevec_release on %d pages (%p)\n", (int)pvec.nr,

fs/ceph/cache.c

+2 −2
Original line number Diff line number Diff line
@@ -51,7 +51,7 @@ static const struct fscache_cookie_def ceph_fscache_fsid_object_def = { 
	.type		= FSCACHE_COOKIE_TYPE_INDEX,

};



int ceph_fscache_register(void)

int __init ceph_fscache_register(void)

{

	return fscache_register_netfs(&ceph_cache_netfs);

}
@@ -135,7 +135,7 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux( 
	if (memcmp(data, &aux, sizeof(aux)) != 0)

		return FSCACHE_CHECKAUX_OBSOLETE;



	dout("ceph inode 0x%p cached okay", ci);

	dout("ceph inode 0x%p cached okay\n", ci);

	return FSCACHE_CHECKAUX_OKAY;

}