- a large rework of cephx auth code to cope with CONFIG_VMAP_STACK
(myself). Also fixed a deadlock caused by a bogus allocation on the
writeback path and authorize reply verification.
- a fix for long stalls during fsync (Jeff Layton). The client now
has a way to force the MDS log flush, leading to ~100x speedups in
some synthetic tests.
- a new [no]require_active_mds mount option (Zheng Yan). On mount, we
will now check whether any of the MDSes are available and bail rather
than block if none are. This check can be avoided by specifying the
"no" option.
- a couple of MDS cap handling fixes and a few assorted patches
throughout.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2
iQEcBAABCAAGBQJYVByGAAoJEEp/3jgCEfOLBqkH/A7nVf7ObSDYmLuYgg1gJ8zq
4zDDE42S4yZwayAVpn3UjbfPuez5J44lsdXitExdfiHOdIQZDa/WqAbSqQ48HCSg
7sG6ecRWg3G5zG0psPZnB+S5wGMvsLXmj2hvzV1lt2t0lI5bDLSlNRSnElbhilD/
8Z7+Ni2go8DMC9o49SJU32lBW7IByKl4p4flveItgwUvGkIFNd8OT3CyPBUqonQs
lRCeImRYU8Jghb+ifnRxWSbuDf7pZAPc9kL0vibpUUT/1bH6iHsedKp37WQKqc/w
KDSNnKiZcz0gY/hJeLqE3ymCIKO6SU+JkMQSaYNTouLO5fQsRr8/uWQXSe6S5oc=
=ypWx
-----END PGP SIGNATURE-----
Merge tag 'ceph-for-4.10-rc1' of git://github.com/ceph/ceph-client
Pull ceph updates from Ilya Dryomov:
"A varied set of changes:
- a large rework of cephx auth code to cope with CONFIG_VMAP_STACK
(myself). Also fixed a deadlock caused by a bogus allocation on the
writeback path and authorize reply verification.
- a fix for long stalls during fsync (Jeff Layton). The client now
has a way to force the MDS log flush, leading to ~100x speedups in
some synthetic tests.
- a new [no]require_active_mds mount option (Zheng Yan).
On mount, we will now check whether any of the MDSes are available
and bail rather than block if none are. This check can be avoided
by specifying the "no" option.
- a couple of MDS cap handling fixes and a few assorted patches
throughout"
* tag 'ceph-for-4.10-rc1' of git://github.com/ceph/ceph-client: (32 commits)
libceph: remove now unused finish_request() wrapper
libceph: always signal completion when done
ceph: avoid creating orphan object when checking pool permission
ceph: properly set issue_seq for cap release
ceph: add flags parameter to send_cap_msg
ceph: update cap message struct version to 10
ceph: define new argument structure for send_cap_msg
ceph: move xattr initialzation before the encoding past the ceph_mds_caps
ceph: fix minor typo in unsafe_request_wait
ceph: record truncate size/seq for snap data writeback
ceph: check availability of mds cluster on mount
ceph: fix splice read for no Fc capability case
ceph: try getting buffer capability for readahead/fadvise
ceph: fix scheduler warning due to nested blocking
ceph: fix printing wrong return variable in ceph_direct_read_write()
crush: include mapper.h in mapper.c
rbd: silence bogus -Wmaybe-uninitialized warning
libceph: no need to drop con->mutex for ->get_authorizer()
libceph: drop len argument of *verify_authorizer_reply()
libceph: verify authorize reply on connect
...
Dirty snapshot data needs to be flushed unconditionally. If they
were created before truncation, writeback should use old truncate
size/seq.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
For readahead/fadvise cases, caller of ceph_readpages does not
hold buffer capability. Pages can be added to page cache while
there is no buffer capability. This can cause data integrity
issue.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Add a 'wake' flag to ceph_cap_flush struct, which indicates if there
is someone waiting for it to finish. When getting flush ack message,
we check the 'wake' flag in corresponding ceph_cap_flush struct to
decide if we should wake up waiters. One corner case is that the
acked cap flush has 'wake' flags is set, but it is not the first one
on the flushing list. We do not wake up waiters in this case, set
'wake' flags of preceding ceph_cap_flush struct instead
Signed-off-by: Yan, Zheng <zyan@redhat.com>
This patch devide __ceph_flush_snaps() into two stags. In the first
stage, __ceph_flush_snaps() assign snapcaps flush TIDs and add them
to cap flush lists. __ceph_flush_snaps() keeps holding the
i_ceph_lock in this stagge. So inode's auth cap can not change. In
the second stage, __ceph_flush_snaps() send flushsnap cap messages.
i_ceph_lock is unlocked before sending each cap message. If auth cap
changes in the middle, __ceph_flush_snaps() just stops. This is OK
because kick_flushing_inode_caps() will re-send flushsnap cap messages
to inode's new auth MDS.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
make ceph_kick_flushing_caps() ignore inodes whose cap flushes
have already been re-sent by ceph_early_kick_flushing_caps()
Signed-off-by: Yan, Zheng <zyan@redhat.com>
This patch includes following changes
- Assign flush tid to snapcap flush
- Remove session's s_cap_snaps_flushing list. Add inode to session's
s_cap_flushing list instead. Inode is removed from the list when
there is no pending snapcap flush or cap flush.
- make __kick_flushing_caps() re-send both snapcap flushes and cap
flushes.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
We don't have requirement of searching cap flush by TID. In most cases,
we just need to know TID of the oldest cap flush. List is ideal for this
usage.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
To mount non-default filesytem, user currently needs to provide mds
namespace ID. This is inconvenience.
This patch makes user be able to mount filesystem by name. If user
wants to mount non-default filesystem. Client first subscribes to
fsmap.user. Subscribe to mdsmap.<ID> after getting ID of filesystem.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
This patch adds codes that decode pool namespace information in
cap message and request reply. Pool namespace is saved in i_layout,
it will be passed to libceph when doing read/write.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
There are several issues in fscache revalidation code.
- In ceph_revalidate_work(), fscache_invalidate() is called when
fscache_check_consistency() return 0. This is complete wrong
because 0 means cache is valid.
- Handle_cap_grant() calls ceph_queue_revalidate() if client
already has CAP_FILE_CACHE. This code is confusing. Client
should revalidate the cache each time it got CAP_FILE_CACHE
anew.
- In Handle_cap_grant(), fscache_invalidate() is called if MDS
revokes CAP_FILE_CACHE. This is inconsistency with the case
that inode get evicted. In the later case, the cache is not
discarded. Client may use the cache when inode is reloaded.
This patch moves the fscache revalidation into ceph_get_caps().
Client revalidates the cache after it gets CAP_FILE_CACHE.
i_rdcache_gen should keep constance while CAP_FILE_CACHE is
used. If i_fscache_gen is not equal to i_rdcache_gen, client
needs to check cache's consistency.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Pull Ceph updates from Sage Weil:
"This changeset has a few main parts:
- Ilya has finished a huge refactoring effort to sync up the
client-side logic in libceph with the user-space client code, which
has evolved significantly over the last couple years, with lots of
additional behaviors (e.g., how requests are handled when cluster
is full and transitions from full to non-full).
This structure of the code is more closely aligned with userspace
now such that it will be much easier to maintain going forward when
behavior changes take place. There are some locking improvements
bundled in as well.
- Zheng adds multi-filesystem support (multiple namespaces within the
same Ceph cluster)
- Zheng has changed the readdir offsets and directory enumeration so
that dentry offsets are hash-based and therefore stable across
directory fragmentation events on the MDS.
- Zheng has a smorgasbord of bug fixes across fs/ceph"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (71 commits)
ceph: fix wake_up_session_cb()
ceph: don't use truncate_pagecache() to invalidate read cache
ceph: SetPageError() for writeback pages if writepages fails
ceph: handle interrupted ceph_writepage()
ceph: make ceph_update_writeable_page() uninterruptible
libceph: make ceph_osdc_wait_request() uninterruptible
ceph: handle -EAGAIN returned by ceph_update_writeable_page()
ceph: make fault/page_mkwrite return VM_FAULT_OOM for -ENOMEM
ceph: block non-fatal signals for fault/page_mkwrite
ceph: make logical calculation functions return bool
ceph: tolerate bad i_size for symlink inode
ceph: improve fragtree change detection
ceph: keep leaf frag when updating fragtree
ceph: fix dir_auth check in ceph_fill_dirfrag()
ceph: don't assume frag tree splits in mds reply are sorted
ceph: fix inode reference leak
ceph: using hash value to compose dentry offset
ceph: don't forbid marking directory complete after forward seek
ceph: record 'offset' for each entry of readdir result
ceph: define 'end/complete' in readdir reply as bit flags
...
If MDS sorts dentries in dirfrag in hash order, we use hash value to
compose dentry offset. dentry offset is:
(0xff << 52) | ((24 bits hash) << 28) |
(the nth entry hash hash collision)
This offset is stable across directory fragmentation. This alos means
there is no need to reset readdir offset if directory get fragmented
in the middle of readdir.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
When mds session gets killed, read/write operation may hang.
Client waits for Frw caps, but mds does not know what caps client
wants. To recover this, client sends an open request to mds. The
request will tell mds what caps client wants.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
To access non-default filesystem, we just need to subscribe to
mdsmap.<MDS_NAMESPACE_ID> and add a new mount option for mds
namespace id.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
[idryomov@gmail.com: switch to a new libceph API]
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Add a catch-all xattr handler at the end of ceph_xattr_handlers. Check
for valid attribute names there, and remove those checks from
__ceph_{get,set,remove}xattr instead. No "system.*" xattrs need to be
handled by the catch-all handler anymore.
The set xattr handler is called with a NULL value to indicate that the
attribute should be removed; __ceph_setxattr already handles that case
correctly (ceph_set_acl could already calling __ceph_setxattr with a NULL
value).
Move the check for snapshots from ceph_{set,remove}xattr into
__ceph_{set,remove}xattr. With that, ceph_{get,set,remove}xattr can be
replaced with the generic iops.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Create a variant of ceph_setattr that takes an inode instead of a
dentry. Change __ceph_setxattr (and also __ceph_removexattr) to take an
inode instead of a dentry. Use those in ceph_set_acl so that we no
longer need a dentry there.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
When security is enabled, security module can call filesystem's
getxattr/setxattr callbacks during d_instantiate(). For cephfs,
d_instantiate() is usually called by MDS' dispatch thread, while
handling MDS reply. If the MDS reply does not include xattrs and
corresponding caps, getxattr/setxattr need to send a new request
to MDS and waits for the reply. This makes MDS' dispatch sleep,
nobody handles later MDS replies.
The fix is make sure lookup/atomic_open reply include xattrs and
corresponding caps. So getxattr can be handled by cached xattrs.
This requires some modification to both MDS and request message.
(Client tells MDS what caps it wants; MDS encodes proper caps in
the reply)
Smack security module may call setxattr during d_instantiate().
Unlike getxattr, we can't force MDS to issue CEPH_CAP_XATTR_EXCL
to us. So just make setxattr return error when called by MDS'
dispatch thread.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
ceph_empty_snapc->num_snaps == 0 at all times. Passing such a snapc to
ceph_osdc_alloc_request() (possibly through ceph_osdc_new_request()) is
equivalent to passing NULL, as ceph_osdc_alloc_request() uses it only
for sizing the request message.
Further, in all four cases the subsequent ceph_osdc_build_request() is
passed NULL for snapc, meaning that 0 is encoded for seq and num_snaps
and making ceph_empty_snapc entirely useless. The two cases where it
actually mattered were removed in commits 8605609049 ("ceph: avoid
sending unnessesary FLUSHSNAP message") and 23078637e0 ("ceph: fix
queuing inode to mdsdir's snaprealm").
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Yan, Zheng <zyan@redhat.com>
When rbytes mount option is enabled, directory size is recursive
size. Recursive size is not updated instantly. This can cause
directory size to change between successive stat(1)
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Add support for the format change of MClientReply/MclientCaps.
Also add code that denies access to inodes with pool_ns layouts.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
If we get a unsafe reply for request that created/modified inode,
add the unsafe request to a list in the newly created/modified
inode. So we can make fsync() wait these unsafe requests.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
commit e548e9b93d makes the kclient
only re-send cap flush once during MDS failover. If the kclient sends
a cap flush after MDS enters reconnect stage but before MDS recovers.
The kclient will skip re-sending the same cap flush when MDS recovers.
This causes problem for newly created inode. The MDS handles cap
flushes before replaying unsafe requests, so it's possible that MDS
find corresponding inode is missing when handling cap flush. The fix
is reverting to old behaviour: always re-send when MDS recovers
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Previously our dcache readdir code relies on that child dentries in
directory dentry's d_subdir list are sorted by dentry's offset in
descending order. When adding dentries to the dcache, if a dentry
already exists, our readdir code moves it to head of directory
dentry's d_subdir list. This design relies on dcache internals.
Al Viro suggests using ncpfs's approach: keeping array of pointers
to dentries in page cache of directory inode. the validity of those
pointers are presented by directory inode's complete and ordered
flags. When a dentry gets pruned, we clear directory inode's complete
flag in the d_prune() callback. Before moving a dentry to other
directory, we clear the ordered flag for both old and new directory.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
if flushing caps were revoked, we should re-send the cap flush in
client reconnect stage. This guarantees that MDS processes the cap
flush message before issuing the flushing caps to other client.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
So we know TID of the oldest pending caps flushing. Later patch will
send this information to MDS, so that MDS can trim its completed caps
flush list.
Tracking pending caps flushing globally also simplifies syncfs code.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Previously we do not trace accurate TID for flushing caps. when
MDS failovers, we have no choice but to re-send all flushing caps
with a new TID. This can cause problem because MDS can has already
flushed some caps and has issued the same caps to other client.
The re-sent cap flush has a new TID, which makes MDS unable to
detect if it has already processed the cap flush.
This patch adds code to track pending caps flushing accurately.
When re-sending cap flush is needed, we use its original flush
TID.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Previously we pre-allocate cap release messages for each caps. This
wastes lots of memory when there are large amount of caps. This patch
make the code not pre-allocate the cap release messages. Instead,
we add the corresponding ceph_cap struct to a list when releasing a
cap. Later when flush cap releases is needed, we allocate the cap
release messages dynamically.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
when a snap notification contains no new snapshot, we can avoid
sending FLUSHSNAP message to MDS. But we still need to create
cap_snap in some case because it's required by write path and
page writeback path
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Cached_context in ceph_snap_realm is directly accessed by
uninline_data() and get_pool_perm(). This is racy in theory.
both uninline_data() and get_pool_perm() do not modify existing
object, they only create new object. So we can pass the empty
snap context to them. Unlike cached_context in ceph_snap_realm,
we do not need to protect the empty snap context.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
When snaprealm is created, its initial reference count is zero.
But in some rare cases, the newly created snaprealm is not referenced
by anyone. This causes snaprealm with zero reference count not freed.
The fix is set reference count of newly snaprealm to 1. The reference
is return the function who requests to create the snaprealm. When the
function finishes its job, it releases the reference.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
After converting inline data to normal data, client need to flush
the new i_inline_version (CEPH_INLINE_NONE) to MDS. This commit makes
cap messages (sent to MDS) contain inline_version and inline_data.
Client always converts inline data to normal data before data write,
so the inline data length part is always zero.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Before any data write, convert inline data to normal data and set
i_inline_version to CEPH_INLINE_NONE. The OSD request that saves
inline data to object contains 3 operations (CMPXATTR, WRITE and
SETXATTR). It compares a xattr named 'inline_version' to prevent
old data overwrites newer data.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Linus Torvalds