diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-10 22:25:30 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-10 22:25:30 +0300 |
commit | b284d4d5a6785f8cd07eda2646a95782373cd01e (patch) | |
tree | 62d835dcb6a6eb30fe9b0ebad7aeba4b4234b1d6 /fs/ceph/addr.c | |
parent | a7726f6b61e8917e73101bb8071facdff7ec5d72 (diff) | |
parent | 9122eed5281e89bdb02162a8ecb3cc13ffc8985e (diff) | |
download | linux-b284d4d5a6785f8cd07eda2646a95782373cd01e.tar.xz |
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
...
Diffstat (limited to 'fs/ceph/addr.c')
-rw-r--r-- | fs/ceph/addr.c | 63 |
1 files changed, 32 insertions, 31 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b4336b42ce3b..5f7ad3d0df2e 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -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 @@ retry: * 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 @@ retry: 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 @@ get_more_pages: 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 @@ get_more_pages: 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 @@ get_more_pages: 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, - &objnum, &objoff, - &len); - if (rc < 0) { - unlock_page(page); - break; - } + ceph_calc_file_object_mapping(&ci->i_layout, + offset, wsize, + &objnum, &objoff, + &xlen); + len = xlen; num_ops = 1; strip_unit_end = page->index + @@ -1146,7 +1147,7 @@ new_request: * 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, |