Alex Elder [Thu, 19 Jul 2012 14:09:27 +0000 (09:09 -0500)]
rbd: drop rbd_header_from_disk() gfp_flags parameter
The function rbd_header_from_disk() is only called in one spot, and
it passes GFP_KERNEL as its value for the gfp_flags parameter.
Just drop that parameter and substitute GFP_KERNEL everywhere within
that function it had been used. (If we find we need the parameter
again in the future it's easy enough to add back again.)
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Tue, 3 Jul 2012 21:01:19 +0000 (16:01 -0500)]
rbd: rename rbd_device->id
The "id" field of an rbd device structure represents the unique
client-local device id mapped to the underlying rbd image. Each rbd
image will have another id--the image id--and each snapshot has its
own id as well. The simple name "id" no longer conveys the
information one might like to have.
Rename the device "id" field in struct rbd_dev to be "dev_id" to
make it a little more obvious what we're dealing with without having
to think more about context.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Wed, 25 Jul 2012 14:32:40 +0000 (09:32 -0500)]
rbd: encapsulate header validity test
If an rbd image header is read and it doesn't begin with the
expected magic information, a warning is displayed. This is
a fairly simple test, but it could be extended at some point.
Fix the comparison so it actually looks at the "text" field
rather than the front of the structure.
In any case, encapsulate the validity test in its own function.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Sat, 14 Jul 2012 01:35:11 +0000 (20:35 -0500)]
ceph: define snap counts as u32 everywhere
There are two structures in which a count of snapshots are
maintained:
struct ceph_snap_context {
...
u32 num_snaps;
...
}
and
struct ceph_snap_realm {
...
u32 num_prior_parent_snaps; /* had prior to parent_since */
...
u32 num_snaps;
...
}
These fields never take on negative values (e.g., to hold special
meaning), and so are really inherently unsigned. Furthermore they
take their value from over-the-wire or on-disk formatted 32-bit
values.
So change their definition to have type u32, and change some spots
elsewhere in the code to account for this change.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Sat, 14 Jul 2012 01:35:11 +0000 (20:35 -0500)]
rbd: clean up a few dout() calls
There was a dout() call in rbd_do_request() that was reporting
the reporting the offset as the length and vice versa. While
fixing that I did a quick scan of other dout() calls and fixed
a couple of other minor things.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Thu, 19 Jul 2012 13:49:18 +0000 (08:49 -0500)]
rbd: kill rbd_image_header->snap_seq
The snap_seq field in an rbd_image_header structure held the value
from the rbd image header when it was last refreshed. We now
maintain this value in the snapc->seq field. So get rid of the
other one.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Thu, 19 Jul 2012 13:49:18 +0000 (08:49 -0500)]
rbd: set snapc->seq only when refreshing header
In rbd_header_add_snap() there is code to set snapc->seq to the
just-added snapshot id. This is the only remnant left of the
use of that field for recording which snapshot an rbd_dev was
associated with. That functionality is no longer supported,
so get rid of that final bit of code.
Doing so means we never actually set snapc->seq any more. On the
server, the snapshot context's sequence value represents the highest
snapshot id ever issued for a particular rbd image. So we'll make
it have that meaning here as well. To do so, set this value
whenever the rbd header is (re-)read. That way it will always be
consistent with the rest of the snapshot context we maintain.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Thu, 19 Jul 2012 13:49:18 +0000 (08:49 -0500)]
rbd: preserve snapc->seq in rbd_header_set_snap()
In rbd_header_set_snap(), there is logic to make the snap context's
seq field get set to a particular snapshot id, or 0 if there is no
snapshot for the rbd image.
This seems to be an artifact of how the current snapshot id for an
rbd_dev was recorded before the rbd_dev->snap_id field began to be
used for that purpose.
There's no need to update the value of snapc->seq here any more, so
stop doing it. Tidy up a few local variables in that function
while we're at it.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Thu, 19 Jul 2012 13:49:18 +0000 (08:49 -0500)]
rbd: don't use snapc->seq that way
In what appears to be an artifact of a different way of encoding
whether an rbd image maps a snapshot, __rbd_refresh_header() has
code that arranges to update the seq value in an rbd image's
snapshot context to point to the first entry in its snapshot
array if that's where it was pointing initially.
We now use rbd_dev->snap_id to record the snapshot id--using the
special value CEPH_NOSNAP to indicate the rbd_dev is not mapping a
snapshot at all.
There is therefore no need to check for this case, nor to update the
seq value, in __rbd_refresh_header(). Just preserve the seq value
that rbd_read_header() provides (which, at the moment, is nothing).
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin [Mon, 5 Dec 2011 22:03:05 +0000 (14:03 -0800)]
rbd: use reference counting for the snap context
This prevents a race between requests with a given snap context and
header updates that free it. The osd client was already expecting the
snap context to be reference counted, since it get()s it in
ceph_osdc_build_request and put()s it when the request completes.
Also remove the second down_read()/up_read() on header_rwsem in
rbd_do_request, which wasn't actually preventing this race or
protecting any other data.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> Reviewed-by: Alex Elder <elder@inktank.com>
Josh Durgin [Tue, 22 Nov 2011 02:14:25 +0000 (18:14 -0800)]
rbd: return errors for mapped but deleted snapshot
When a snapshot is deleted, the OSD will return ENOENT when reading
from it. This is normally interpreted as a hole by rbd, which will
return zeroes. To minimize the time in which this can happen, stop
requests early when we are notified that our snapshot no longer
exists.
Sage Weil [Mon, 30 Jul 2012 23:22:05 +0000 (16:22 -0700)]
libceph: reset connection retry on successfully negotiation
We exponentially back off when we encounter connection errors. If several
errors accumulate, we will eventually wait ages before even trying to
reconnect.
Fix this by resetting the backoff counter after a successful negotiation/
connection with the remote node. Fixes ceph issue #2802.
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com>
Sage Weil [Mon, 30 Jul 2012 23:21:40 +0000 (16:21 -0700)]
libceph: protect ceph_con_open() with mutex
Take the con mutex while we are initiating a ceph open. This is necessary
because the may have previously been in use and then closed, which could
result in a racing workqueue running con_work().
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com>
Sage Weil [Mon, 30 Jul 2012 23:21:17 +0000 (16:21 -0700)]
ceph: close old con before reopening on mds reconnect
When we detect a mds session reset, close the old ceph_connection before
reopening it. This ensures we clean up the old socket properly and keep
the ceph_connection state correct.
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Sage Weil [Mon, 30 Jul 2012 23:20:25 +0000 (16:20 -0700)]
libceph: (re)initialize bio_iter on start of message receive
Previously, we were opportunistically initializing the bio_iter if it
appeared to be uninitialized in the middle of the read path. The problem
is that a sequence like:
- start reading message
- initialize bio_iter
- read half a message
- messenger fault, reconnect
- restart reading message
- ** bio_iter now non-NULL, not reinitialized **
- read past end of bio, crash
Instead, initialize the bio_iter unconditionally when we allocate/claim
the message for read.
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Sage Weil [Mon, 30 Jul 2012 23:19:28 +0000 (16:19 -0700)]
libceph: resubmit linger ops when pg mapping changes
The linger op registration (i.e., watch) modifies the object state. As
such, the OSD will reply with success if it has already applied without
doing the associated side-effects (setting up the watch session state).
If we lose the ACK and resubmit, we will see success but the watch will not
be correctly registered and we won't get notifies.
To fix this, always resubmit the linger op with a new tid. We accomplish
this by re-registering as a linger (i.e., 'registered') if we are not yet
registered. Then the second loop will treat this just like a normal
case of re-registering.
This mirrors a similar fix on the userland ceph.git, commit 5dd68b95, and
ceph bug #2796.
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Sage Weil [Tue, 31 Jul 2012 01:15:23 +0000 (18:15 -0700)]
libceph: support crush tunables
The server side recently added support for tuning some magic
crush variables. Decode these variables if they are present, or use the
default values if they are not present.
Alex Elder [Tue, 26 Jun 2012 19:57:03 +0000 (12:57 -0700)]
rbd: kill num_reply parameters
Several functions include a num_reply parameter, but it is never
used. Just get rid of it everywhere--it seems to be something
that never got fully implemented.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Tue, 3 Jul 2012 21:01:18 +0000 (16:01 -0500)]
rbd: more symbol renames
Rename variables named "obj" which represent object names so they're
consistently named "object_name".
Rename the "cls" and "method" parameters in rbd_req_sync_exec()
to be "class_name" and "method_name", and make similar changes
to the names of local variables in that function representing
the lengths of those names.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Tue, 3 Jul 2012 21:01:18 +0000 (16:01 -0500)]
rbd: use rbd_dev consistently
Most variables that represent a struct rbd_device are named
"rbd_dev", but in some cases "dev" is used instead. Change all the
"dev" references so they use "rbd_dev" consistently, to make it
clear from the name that we're working with an RBD device (as
opposed to, for example, a struct device). Similarly, change the
name of the "dev" field in struct rbd_notify_info to be "rbd_dev".
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Tue, 10 Jul 2012 02:04:24 +0000 (21:04 -0500)]
rbd: dynamically allocate snapshot name
There is no need to impose a small limit the length of the snapshot
name recorded for an rbd image in a struct rbd_dev. Remove the
limitation by allocating space for the snapshot name dynamically.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Tue, 10 Jul 2012 02:04:23 +0000 (21:04 -0500)]
rbd: dynamically allocate image name
There is no need to impose a small limit the length of the rbd image
name recorded in a struct rbd_dev. Remove the limitation by
allocating space for the image name dynamically.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Tue, 10 Jul 2012 02:04:23 +0000 (21:04 -0500)]
rbd: dynamically allocate image header name
There is no need to impose a small limit the length of the header
name recorded for an rbd image in a struct rbd_dev. Remove the
limitation by allocating space for the header name dynamically.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Tue, 10 Jul 2012 02:04:24 +0000 (21:04 -0500)]
rbd: dynamically allocate object prefix
There is no need to impose a small limit the length of the object
prefix recorded for an rbd image in a struct rbd_image_header.
Remove the limitation by allocating space for the object prefix
dynamically.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Thu, 12 Jul 2012 15:46:35 +0000 (10:46 -0500)]
rbd: dynamically allocate pool name
There is no need to impose a small limit the length of the pool name
recorded for an rbd image in a struct rbd_device. Remove the
limitation by allocating space for the pool name ynamically.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Thu, 12 Jul 2012 15:46:35 +0000 (10:46 -0500)]
rbd: create pool_id device attribute
Add an entry under /sys/bus/rbd/devices/<N>/ named "pool_id" that
provides the id for the pool the rbd image is assocatied with. This
is in addition to the pool name already provided.
Rename the "poolid" field in struct rbd_device to be "pool_id".
Update the documentation to reflect the addition of this new entry.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Alex Elder [Wed, 11 Jul 2012 01:30:09 +0000 (20:30 -0500)]
rbd: rename rbd_dev->block_name
Each rbd image has a name that forms the basis of all data objects
backing the device. Old (format 1) images refer to this name as the
"block name," while new (format 2) images use the term "object
prefix" for this.
Change the field name in the in-core rbd image header structure to
reflect the more modern usage. We intentionally keep the the name
"block_name" in the on-disk definition for format 1 image headers.
Alex Elder [Wed, 11 Jul 2012 13:24:45 +0000 (08:24 -0500)]
libceph: define ceph_extract_encoded_string()
This adds a new utility routine which will return a dynamically-
allocated buffer containing a string that has been decoded from ceph
over-the-wire format. It also returns the length of the string
if the address of a size variable is supplied to receive it.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Tue, 3 Jul 2012 21:01:18 +0000 (16:01 -0500)]
libceph: fix off-by-one bug in ceph_encode_filepath()
There is a BUG_ON() call that doesn't account for the single byte
structure version at the start of an encoded filepath in
ceph_encode_filepath(). Fix that.
Guanjun He [Mon, 9 Jul 2012 02:50:33 +0000 (19:50 -0700)]
libceph: prevent the race of incoming work during teardown
Add an atomic variable 'stopping' as flag in struct ceph_messenger,
set this flag to 1 in function ceph_destroy_client(), and add the condition code
in function ceph_data_ready() to test the flag value, if true(1), just return.
Signed-off-by: Guanjun He <gjhe@suse.com> Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 10 Jul 2012 18:53:34 +0000 (11:53 -0700)]
libceph: fix messenger retry
In ancient times, the messenger could both initiate and accept connections.
An artifact if that was data structures to store/process an incoming
ceph_msg_connect request and send an outgoing ceph_msg_connect_reply.
Sadly, the negotiation code was referencing those structures and ignoring
important information (like the peer's connect_seq) from the correct ones.
Among other things, this fixes tight reconnect loops where the server sends
RETRY_SESSION and we (the client) retries with the same connect_seq as last
time. This bug pretty easily triggered by injecting socket failures on the
MDS and running some fs workload like workunits/direct_io/test_sync_io.
Sage Weil [Wed, 27 Jun 2012 19:31:02 +0000 (12:31 -0700)]
libceph: allow sock transition from CONNECTING to CLOSED
It is possible to close a socket that is in the OPENING state. For
example, it can happen if ceph_con_close() is called on the con before
the TCP connection is established. con_work() will come around and shut
down the socket.
Sage Weil [Wed, 27 Jun 2012 19:24:34 +0000 (12:24 -0700)]
libceph: initialize mon_client con only once
Do not re-initialize the con on every connection attempt. When we
ceph_con_close, there may still be work queued on the socket (e.g., to
close it), and re-initializing will clobber the work_struct state.
Alex Elder [Thu, 21 Jun 2012 19:49:23 +0000 (12:49 -0700)]
libceph: drop declaration of ceph_con_get()
For some reason the declaration of ceph_con_get() and
ceph_con_put() did not get deleted in this commit: d59315ca libceph: drop ceph_con_get/put helpers and nref member
Alex Elder [Mon, 11 Jun 2012 19:57:13 +0000 (14:57 -0500)]
libceph: small changes to messenger.c
This patch gathers a few small changes in "net/ceph/messenger.c":
out_msg_pos_next()
- small logic change that mostly affects indentation
write_partial_msg_pages().
- use a local variable trail_off to represent the offset into
a message of the trail portion of the data (if present)
- once we are in the trail portion we will always be there, so we
don't always need to check against our data position
- avoid computing len twice after we've reached the trail
- get rid of the variable tmpcrc, which is not needed
- trail_off and trail_len never change so mark them const
- update some comments
read_partial_message_bio()
- bio_iovec_idx() will never return an error, so don't bother
checking for it
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Thu, 24 May 2012 16:55:03 +0000 (11:55 -0500)]
libceph: distinguish two phases of connect sequence
Currently a ceph connection enters a "CONNECTING" state when it
begins the process of (re-)connecting with its peer. Once the two
ends have successfully exchanged their banner and addresses, an
additional NEGOTIATING bit is set in the ceph connection's state to
indicate the connection information exhange has begun. The
CONNECTING bit/state continues to be set during this phase.
Rather than have the CONNECTING state continue while the NEGOTIATING
bit is set, interpret these two phases as distinct states. In other
words, when NEGOTIATING is set, clear CONNECTING. That way only
one of them will be active at a time.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Thu, 31 May 2012 16:37:29 +0000 (11:37 -0500)]
libceph: separate banner and connect writes
There are two phases in the process of linking together the two ends
of a ceph connection. The first involves exchanging a banner and
IP addresses, and if that is successful a second phase exchanges
some detail about each side's connection capabilities.
When initiating a connection, the client side now queues to send
its information for both phases of this process at the same time.
This is probably a bit more efficient, but it is slightly messier
from a layering perspective in the code.
So rearrange things so that the client doesn't send the connection
information until it has received and processed the response in the
initial banner phase (in process_banner()).
Move the code (in the (con->sock == NULL) case in try_write()) that
prepares for writing the connection information, delaying doing that
until the banner exchange has completed. Move the code that begins
the transition to this second "NEGOTIATING" phase out of
process_banner() and into its caller, so preparing to write the
connection information and preparing to read the response are
adjacent to each other.
Finally, preparing to write the connection information now requires
the output kvec to be reset in all cases, so move that into the
prepare_write_connect() and delete it from all callers.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Wed, 23 May 2012 19:35:23 +0000 (14:35 -0500)]
libceph: clear NEGOTIATING when done
A connection state's NEGOTIATING bit gets set while in CONNECTING
state after we have successfully exchanged a ceph banner and IP
addresses with the connection's peer (the server). But that bit
is not cleared again--at least not until another connection attempt
is initiated.
Instead, clear it as soon as the connection is fully established.
Also, clear it when a socket connection gets prematurely closed
in the midst of establishing a ceph connection (in case we had
reached the point where it was set).
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Thu, 21 Jun 2012 02:53:53 +0000 (21:53 -0500)]
libceph: clear CONNECTING in ceph_con_close()
A connection that is closed will no longer be connecting. So
clear the CONNECTING state bit in ceph_con_close(). Similarly,
if the socket has been closed we no longer are in connecting
state (a new connect sequence will need to be initiated).
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Thu, 21 Jun 2012 02:53:53 +0000 (21:53 -0500)]
libceph: don't touch con state in con_close_socket()
In con_close_socket(), a connection's SOCK_CLOSED flag gets set and
then cleared while its shutdown method is called and its reference
gets dropped.
Previously, that flag got set only if it had not already been set,
so setting it in con_close_socket() might have prevented additional
processing being done on a socket being shut down. We no longer set
SOCK_CLOSED in the socket event routine conditionally, so setting
that bit here no longer provides whatever benefit it might have
provided before.
A race condition could still leave the SOCK_CLOSED bit set even
after we've issued the call to con_close_socket(), so we still clear
that bit after shutting the socket down. Add a comment explaining
the reason for this.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Thu, 21 Jun 2012 02:53:53 +0000 (21:53 -0500)]
libceph: just set SOCK_CLOSED when state changes
When a TCP_CLOSE or TCP_CLOSE_WAIT event occurs, the SOCK_CLOSED
connection flag bit is set, and if it had not been previously set
queue_con() is called to ensure con_work() will get a chance to
handle the changed state.
con_work() atomically checks--and if set, clears--the SOCK_CLOSED
bit if it was set. This means that even if the bit were set
repeatedly, the related processing in con_work() only gets called
once per transition of the bit from 0 to 1.
What's important then is that we ensure con_work() gets called *at
least* once when a socket close event occurs, not that it gets
called *exactly* once.
The work queue mechanism already takes care of queueing work
only if it is not already queued, so there's no need for us
to call queue_con() conditionally.
So this patch just makes it so the SOCK_CLOSED flag gets set
unconditionally in ceph_sock_state_change().
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Thu, 21 Jun 2012 02:53:53 +0000 (21:53 -0500)]
libceph: don't change socket state on sock event
Currently the socket state change event handler records an error
message on a connection to distinguish a close while connecting from
a close while a connection was already established.
Changing connection information during handling of a socket event is
not very clean, so instead move this assignment inside con_work(),
where it can be done during normal connection-level processing (and
under protection of the connection mutex as well).
Move the handling of a socket closed event up to the top of the
processing loop in con_work(); there's no point in handling backoff
etc. if we have a newly-closed socket to take care of.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Mon, 11 Jun 2012 19:57:13 +0000 (14:57 -0500)]
libceph: don't use bio_iter as a flag
Recently a bug was fixed in which the bio_iter field in a ceph
message was not being properly re-initialized when a message got
re-transmitted:
commit 43643528cce60ca184fe8197efa8e8da7c89a037
Author: Yan, Zheng <zheng.z.yan@intel.com>
rbd: Clear ceph_msg->bio_iter for retransmitted message
We are now only initializing the bio_iter field when we are about to
start to write message data (in prepare_write_message_data()),
rather than every time we are attempting to write any portion of the
message data (in write_partial_msg_pages()). This means we no
longer need to use the msg->bio_iter field as a flag.
So just don't do that any more. Trust prepare_write_message_data()
to ensure msg->bio_iter is properly initialized, every time we are
about to begin writing (or re-writing) a message's bio data.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Mon, 11 Jun 2012 19:57:13 +0000 (14:57 -0500)]
libceph: move init of bio_iter
If a message has a non-null bio pointer, its bio_iter field is
initialized in write_partial_msg_pages() if this has not been done
already. This is really a one-time setup operation for sending a
message's (bio) data, so move that initialization code into
prepare_write_message_data() which serves that purpose.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Mon, 11 Jun 2012 19:57:13 +0000 (14:57 -0500)]
libceph: don't mark footer complete before it is
This is a nit, but prepare_write_message() sets the FOOTER_COMPLETE
flag before the CRC for the data portion (recorded in the footer)
has been completely computed. Hold off setting the complete flag
until we've decided it's ready to send.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Mon, 11 Jun 2012 19:57:13 +0000 (14:57 -0500)]
libceph: encapsulate advancing msg page
In write_partial_msg_pages(), once all the data from a page has been
sent we advance to the next one. Put the code that takes care of
this into its own function.
While modifying write_partial_msg_pages(), make its local variable
"in_trail" be Boolean, and use the local variable "msg" (which is
just the connection's current out_msg pointer) consistently.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil [Mon, 11 Jun 2012 03:43:56 +0000 (20:43 -0700)]
libceph: flush msgr queue during mon_client shutdown
We need to flush the msgr workqueue during mon_client shutdown to
ensure that any work affecting our embedded ceph_connection is
finished so that we can be safely destroyed.
Previously, we were flushing the work queue after osd_client
shutdown and before mon_client shutdown to ensure that any osd
connection refs to authorizers are flushed. Remove the redundant
flush, and document in the comment that the mon_client flush is
needed to cover that case as well.
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com>
Sage Weil [Sat, 9 Jun 2012 21:19:21 +0000 (14:19 -0700)]
libceph: transition socket state prior to actual connect
Once we call ->connect(), we are racing against the actual
connection, and a subsequent transition from CONNECTING ->
CONNECTED. Set the state to CONNECTING before that, under the
protection of the mutex, to avoid the race.
Xi Wang [Thu, 7 Jun 2012 00:35:55 +0000 (19:35 -0500)]
libceph: fix overflow in osdmap_apply_incremental()
On 32-bit systems, a large `pglen' would overflow `pglen*sizeof(u32)'
and bypass the check ceph_decode_need(p, end, pglen*sizeof(u32), bad).
It would also overflow the subsequent kmalloc() size, leading to
out-of-bounds write.
Signed-off-by: Xi Wang <xi.wang@gmail.com> Reviewed-by: Alex Elder <elder@inktank.com>
Xi Wang [Thu, 7 Jun 2012 00:35:55 +0000 (19:35 -0500)]
libceph: fix overflow in osdmap_decode()
On 32-bit systems, a large `n' would overflow `n * sizeof(u32)' and bypass
the check ceph_decode_need(p, end, n * sizeof(u32), bad). It would also
overflow the subsequent kmalloc() size, leading to out-of-bounds write.
Signed-off-by: Xi Wang <xi.wang@gmail.com> Reviewed-by: Alex Elder <elder@inktank.com>
Xi Wang [Thu, 7 Jun 2012 00:35:55 +0000 (19:35 -0500)]
libceph: fix overflow in __decode_pool_names()
`len' is read from network and thus needs validation. Otherwise a
large `len' would cause out-of-bounds access via the memcpy() call.
In addition, len = 0xffffffff would overflow the kmalloc() size,
leading to out-of-bounds write.
This patch adds a check of `len' via ceph_decode_need(). Also use
kstrndup rather than kmalloc/memcpy.
[elder@inktank.com: added -ENOMEM return for null kstrndup() result]
Signed-off-by: Xi Wang <xi.wang@gmail.com> Reviewed-by: Alex Elder <elder@inktank.com>
Alex Elder [Fri, 1 Jun 2012 19:56:43 +0000 (14:56 -0500)]
libceph: make ceph_con_revoke_message() a msg op
ceph_con_revoke_message() is passed both a message and a ceph
connection. A ceph_msg allocated for incoming messages on a
connection always has a pointer to that connection, so there's no
need to provide the connection when revoking such a message.
Note that the existing logic does not preclude the message supplied
being a null/bogus message pointer. The only user of this interface
is the OSD client, and the only value an osd client passes is a
request's r_reply field. That is always non-null (except briefly in
an error path in ceph_osdc_alloc_request(), and that drops the
only reference so the request won't ever have a reply to revoke).
So we can safely assume the passed-in message is non-null, but add a
BUG_ON() to make it very obvious we are imposing this restriction.
Rename the function ceph_msg_revoke_incoming() to reflect that it is
really an operation on an incoming message.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Fri, 1 Jun 2012 19:56:43 +0000 (14:56 -0500)]
libceph: make ceph_con_revoke() a msg operation
ceph_con_revoke() is passed both a message and a ceph connection.
Now that any message associated with a connection holds a pointer
to that connection, there's no need to provide the connection when
revoking a message.
This has the added benefit of precluding the possibility of the
providing the wrong connection pointer. If the message's connection
pointer is null, it is not being tracked by any connection, so
revoking it is a no-op. This is supported as a convenience for
upper layers, so they can revoke a message that is not actually
"in flight."
Rename the function ceph_msg_revoke() to reflect that it is really
an operation on a message, not a connection.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Mon, 4 Jun 2012 19:43:33 +0000 (14:43 -0500)]
libceph: have messages take a connection reference
There are essentially two types of ceph messages: incoming and
outgoing. Outgoing messages are always allocated via ceph_msg_new(),
and at the time of their allocation they are not associated with any
particular connection. Incoming messages are always allocated via
ceph_con_in_msg_alloc(), and they are initially associated with the
connection from which incoming data will be placed into the message.
When an outgoing message gets sent, it becomes associated with a
connection and remains that way until the message is successfully
sent. The association of an incoming message goes away at the point
it is sent to an upper layer via a con->ops->dispatch method.
This patch implements reference counting for all ceph messages, such
that every message holds a reference (and a pointer) to a connection
if and only if it is associated with that connection (as described
above).
For background, here is an explanation of the ceph message
lifecycle, emphasizing when an association exists between a message
and a connection.
Outgoing Messages
An outgoing message is "owned" by its allocator, from the time it is
allocated in ceph_msg_new() up to the point it gets queued for
sending in ceph_con_send(). Prior to that point the message's
msg->con pointer is null; at the point it is queued for sending its
message pointer is assigned to refer to the connection. At that
time the message is inserted into a connection's out_queue list.
When a message on the out_queue list has been sent to the socket
layer to be put on the wire, it is transferred out of that list and
into the connection's out_sent list. At that point it is still owned
by the connection, and will remain so until an acknowledgement is
received from the recipient that indicates the message was
successfully transferred. When such an acknowledgement is received
(in process_ack()), the message is removed from its list (in
ceph_msg_remove()), at which point it is no longer associated with
the connection.
So basically, any time a message is on one of a connection's lists,
it is associated with that connection. Reference counting outgoing
messages can thus be done at the points a message is added to the
out_queue (in ceph_con_send()) and the point it is removed from
either its two lists (in ceph_msg_remove())--at which point its
connection pointer becomes null.
Incoming Messages
When an incoming message on a connection is getting read (in
read_partial_message()) and there is no message in con->in_msg,
a new one is allocated using ceph_con_in_msg_alloc(). At that
point the message is associated with the connection. Once that
message has been completely and successfully read, it is passed to
upper layer code using the connection's con->ops->dispatch method.
At that point the association between the message and the connection
no longer exists.
Reference counting of connections for incoming messages can be done
by taking a reference to the connection when the message gets
allocated, and releasing that reference when it gets handed off
using the dispatch method.
We should never fail to get a connection reference for a
message--the since the caller should already hold one.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Fri, 1 Jun 2012 19:56:43 +0000 (14:56 -0500)]
libceph: have messages point to their connection
When a ceph message is queued for sending it is placed on a list of
pending messages (ceph_connection->out_queue). When they are
actually sent over the wire, they are moved from that list to
another (ceph_connection->out_sent). When acknowledgement for the
message is received, it is removed from the sent messages list.
During that entire time the message is "in the possession" of a
single ceph connection. Keep track of that connection in the
message. This will be used in the next patch (and is a helpful
bit of information for debugging anyway).
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Mon, 4 Jun 2012 19:43:32 +0000 (14:43 -0500)]
libceph: tweak ceph_alloc_msg()
The function ceph_alloc_msg() is only used to allocate a message
that will be assigned to a connection's in_msg pointer. Rename the
function so this implied usage is more clear.
In addition, make that assignment inside the function (again, since
that's precisely what it's intended to be used for). This allows us
to return what is now provided via the passed-in address of a "skip"
variable. The return type is now Boolean to be explicit that there
are only two possible outcomes.
Make sure the result of an ->alloc_msg method call always sets the
value of *skip properly.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Alex Elder [Sun, 27 May 2012 04:26:43 +0000 (23:26 -0500)]
libceph: fully initialize connection in con_init()
Move the initialization of a ceph connection's private pointer,
operations vector pointer, and peer name information into
ceph_con_init(). Rearrange the arguments so the connection pointer
is first. Hide the byte-swapping of the peer entity number inside
ceph_con_init()
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 1 Jun 2012 03:27:50 +0000 (20:27 -0700)]
libceph: drop connection refcounting for mon_client
All references to the embedded ceph_connection come from the msgr
workqueue, which is drained prior to mon_client destruction. That
means we can ignore con refcounting entirely.
Signed-off-by: Sage Weil <sage@newdream.net> Reviewed-by: Alex Elder <elder@inktank.com>
Alex Elder [Sun, 27 May 2012 04:26:43 +0000 (23:26 -0500)]
libceph: embed ceph connection structure in mon_client
A monitor client has a pointer to a ceph connection structure in it.
This is the only one of the three ceph client types that do it this
way; the OSD and MDS clients embed the connection into their main
structures. There is always exactly one ceph connection for a
monitor client, so there is no need to allocate it separate from the
monitor client structure.
So switch the ceph_mon_client structure to embed its
ceph_connection structure.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 1 Jun 2012 03:22:18 +0000 (20:22 -0700)]
libceph: use con get/put ops from osd_client
There were a few direct calls to ceph_con_{get,put}() instead of the con
ops from osd_client.c. This is a bug since those ops aren't defined to
be ceph_con_get/put.
This breaks refcounting on the ceph_osd structs that contain the
ceph_connections, and could lead to all manner of strangeness.
The purpose of the ->get and ->put methods in a ceph connection are
to allow the connection to indicate it has a reference to something
external to the messaging system, *not* to indicate something
external has a reference to the connection.
[elder@inktank.com: added that last sentence]
Signed-off-by: Sage Weil <sage@newdream.net> Reviewed-by: Alex Elder <elder@inktank.com>
Alex Elder [Mon, 4 Jun 2012 19:43:32 +0000 (14:43 -0500)]
libceph: osd_client: don't drop reply reference too early
In ceph_osdc_release_request(), a reference to the r_reply message
is dropped. But just after that, that same message is revoked if it
was in use to receive an incoming reply. Reorder these so we are
sure we hold a reference until we're actually done with the message.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
Dan Carpenter [Wed, 6 Jun 2012 14:15:33 +0000 (09:15 -0500)]
rbd: endian bug in rbd_req_cb()
Sparse complains about this because:
drivers/block/rbd.c:996:20: warning: cast to restricted __le32
drivers/block/rbd.c:996:20: warning: cast from restricted __le16
These are set in osd_req_encode_op() and they are le16.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Alex Elder <elder@inktank.com>
Linus Torvalds [Sun, 3 Jun 2012 00:39:40 +0000 (17:39 -0700)]
Merge tag 'dm-3.5-changes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm
Pull device-mapper updates from Alasdair G Kergon:
"Improve multipath's retrying mechanism in some defined circumstances
and provide a simple reserve/release mechanism for userspace tools to
access thin provisioning metadata while the pool is in use."
* tag 'dm-3.5-changes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm:
dm thin: provide userspace access to pool metadata
dm thin: use slab mempools
dm mpath: allow ioctls to trigger pg init
dm mpath: delay retry of bypassed pg
dm mpath: reduce size of struct multipath
Joe Thornber [Sat, 2 Jun 2012 23:30:01 +0000 (00:30 +0100)]
dm thin: provide userspace access to pool metadata
This patch implements two new messages that can be sent to the thin
pool target allowing it to take a snapshot of the _metadata_. This,
read-only snapshot can be accessed by userland, concurrently with the
live target.
Only one metadata snapshot can be held at a time. The pool's status
line will give the block location for the current msnap.
Since version 0.1.5 of the userland thin provisioning tools, the
thin_dump program displays the msnap as follows:
thin_dump -m <msnap root> <metadata dev>
Available here: https://github.com/jthornber/thin-provisioning-tools
Now that userland can access the metadata we can do various things
that have traditionally been kernel side tasks:
i) Incremental backups.
By using metadata snapshots we can work out what blocks have
changed over time. Combined with data snapshots we can ensure
the data doesn't change while we back it up.
A short proof of concept script can be found here:
Mike Snitzer [Sat, 2 Jun 2012 23:30:00 +0000 (00:30 +0100)]
dm thin: use slab mempools
Use dedicated caches prefixed with a "dm_" name rather than relying on
kmalloc mempools backed by generic slab caches so the memory usage of
thin provisioning (and any leaks) can be accounted for independently.
Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Mikulas Patocka [Sat, 2 Jun 2012 23:29:58 +0000 (00:29 +0100)]
dm mpath: allow ioctls to trigger pg init
After the failure of a group of paths, any alternative paths that
need initialising do not become available until further I/O is sent to
the device. Until this has happened, ioctls return -EAGAIN.
With this patch, new paths are made available in response to an ioctl
too. The processing of the ioctl gets delayed until this has happened.
Instead of returning an error, we submit a work item to kmultipathd
(that will potentially activate the new path) and retry in ten
milliseconds.
Note that the patch doesn't retry an ioctl if the ioctl itself fails due
to a path failure. Such retries should be handled intelligently by the
code that generated the ioctl in the first place, noting that some SCSI
commands should not be retried because they are not idempotent (XOR write
commands). For commands that could be retried, there is a danger that
if the device rejected the SCSI command, the path could be errorneously
marked as failed, and the request would be retried on another path which
might fail too. It can be determined if the failure happens on the
device or on the SCSI controller, but there is no guarantee that all
SCSI drivers set these flags correctly.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
projects / mirror_ubuntu-kernels.git / log