Commit Graph

2486 Commits

Author SHA1 Message Date
Lars Ellenberg
5cdb0bf322 drbd: remove now unused seq_num member from struct drbd_request
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:19 +01:00
Lars Ellenberg
4b8514ee28 drbd: fix potential data corruption and protocol error
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:19 +01:00
Lars Ellenberg
e8744f5aca drbd: Fixed detach
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:18 +01:00
Lars Ellenberg
d93f63028f drbd: Fix a potential write ordering issue on SyncTarget nodes
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:18 +01:00
Lars Ellenberg
81f448629a drbd: Fix a potential race that could case data inconsistency
When we have a write request and a state change C_WF_BITMAP_S -> C_SYNC_SOURCE
at the same time, and it happens that the line

    remote = remote && drbd_should_do_remote(s);

stills sees C_WF_BITMAP_S, and

     send_oos = rw == WRITE && drbd_should_send_oos(s);

already sees C_SYNC_SOURCE both are 0.

This causes the write to not be mirrored, but marked as out-of-sync on the
Sync_Source node.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:17 +01:00
Philipp Reisner
38a05c16b8 drbd: Consider that bio->bi_bdev might be modified below DRBD
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:17 +01:00
Philipp Reisner
72585d2428 drbd: add missing part_round_stats to _drbd_start_io_acct
Without this, iostat frequently sees bogus svctime and >= 100% "utilization".

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:17 +01:00
Philipp Reisner
dd9b360475 drbd: Fix module refcount leak in drbd_accept()
drbd_accept was modelled after kernel_accept
with drbd commit 53eb779 in July 2008.

Only, kernel_accept was then broken, and only fixed later
with kernel commit 1b08534e in Dec 2008:
net: Fix module refcount leak in kernel_accept()

Impact: protocol families provided as modules, e.g. ipv6 or ib_sdp,
would soon have their reference count become negative, preventing
them from being unloaded (likely), or worse, hit zero without actually
being unused, allowing them to be unloaded while still in use (unlikely,
but if triggered, causing a kernel crash).

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:16 +01:00
Philipp Reisner
93f5afe956 drbd: If disk timeout expires fail only the affected volume
...and not all volumes of the resource

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:16 +01:00
Philipp Reisner
32db80f6f6 drbd: Consider the disk-timeout also for meta-data IO operations
If the backing device is already frozen during attach, we failed
to recognize that. The current disk-timeout code works on top
of the drbd_request objects. During attach we do not allow IO
and therefore never generate a drbd_request object but block
before that in drbd_make_request().

This patch adds the timeout to all drbd_md_sync_page_io().

Before this patch we used to go from D_ATTACHING directly
to D_DISKLESS if IO failed during attach. We can no longer
do this since we have to stay in D_FAILED until all IO
ops issued to the backing device returned.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:15 +01:00
Philipp Reisner
25b0d6c8c1 drbd: Reinstate disabling AL updates with invalidate-remote
Commit d0ef827e (drbd: switch configuration interface from connector to
genetlink) introduced a regression by removing the ability to set all
bits in the out of sync bitmap and to suspend updates to the activity log
of a disconnected device via the invalidate-remote management call.

Credits for reporting the issue are going to Arne Redlich.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:15 +01:00
Lars Ellenberg
b17f33cb0a drbd: explicitly clear unused dp_flags in drbd_send_block
We send left-over garbage from the previous packet in P_DATA_REPLY and
P_RS_DATA_REPLY packets. That's bad behaviour.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:15 +01:00
Philipp Reisner
4d0fc3fdc3 drbd: Fixed compat issue with disconnecting 8.4 from a primary 8.3
For compatibility reasons 8.4 has to send P_STATE_CHG_REQ (instead
of P_CONN_ST_CHG_REQ) when disconnecting.

In the receiving code path we missed to convert the old
answer (P_STATE_CHG_REPLY) back to 8.4 logic. Therefore
the CL_ST_CHG_SUCCESS or CL_ST_CHG_FAIL bit in the flags word
of mdev got set, while the state code was waiting for
the CONN_WD_ST_CHG_OKAY or CONN_WD_ST_CHG_FAIL bits in tconn.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:14 +01:00
Andreas Gruenbacher
1a3cde4406 drbd: drbd_bm_ALe_set_all(): Remove unused function
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:14 +01:00
Philipp Reisner
69b6a3b159 drbd: restart loop in drbd_make_request() [prepare for Linux-3.2]
With Linux-3.2 generic_make_request() will no longer loop over
the request function until it finally returns 0. Move this
loop into our drbd_make_request() function.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:13 +01:00
Philipp Reisner
7da358625c drbd: Restore late assigning of tconn->data.sock and meta.sock
With commit from Mon Mar 28 16:33:12 2011 +0200
"drbd: drbd_connect(): Initialize struct drbd_socket before sending anything"

tconn->data.sock and tconn->meta.sock get assigned early, in
conn_connect.

The early assigning can trigger an OOPS, because it may released the socket
without acquiring the mutex protecting the socket. An other thread (worker)
might use setsockopt() on the socket while it gets free()ed.

Restored the (proven) 8.3 behavior of assigning these sockets after the two
connections are established.

Credits for reporting the issue are going to Arne Redlich.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:13 +01:00
Philipp Reisner
a01842ebee drbd: Log failures of connection state changes
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:13 +01:00
Philipp Reisner
e8cdc34335 drbd: Consider that read requests could be NEG_ACKEDed
ap_in_flight only counts writes. NEG_ACKED is an action
on a request that might be called for reads and writes.

This bug was there forever, but it becomes much more
relevant with the read balincing code.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:12 +01:00
Philipp Reisner
6ab9b1b60b drbd: Do not send state packets while lower than C_CONNECTED cstate
I.e. in C_WF_REPORT_PARAMS or in C_WF_CONNECTION.
Sending may already work in these cstates, but the peer still expects
the HandShake / ConnectionFeatures packet.

Actually triggered by the Testuite on kugel.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:12 +01:00
Philipp Reisner
b8853dbd8c drbd: fix race between disconnect and receive_state
If the asender thread, or request_timer_fn(), or some other part of
the code, decided to drop the connection (because of timeout or other),
but the receiver just now was processing a P_STATE packet, there was a
chance that receive_state() would do a hard state change
"re-establishing" an already failed connection without additional handshake.

Log excerpt:
  Remote failed to finish a request within ko-count * timeout
  peer( Secondary -> Unknown ) conn( Connected -> Timeout ) pdsk( UpToDate -> DUnknown )
  asender terminated
  ...
  peer( Unknown -> Secondary ) conn( Timeout -> Connected ) pdsk( DUnknown -> UpToDate ) peer_isp( 0 -> 1 )
  ...
  Connection closed
  peer( Secondary -> Unknown ) conn( Connected -> Unconnected ) pdsk( UpToDate -> DUnknown ) peer_isp( 1 -> 0 )
  receiver terminated

Impact:
while the connection state is erroneously "Connected",
requests may be queued and even sent,
which would never be acknowledged,
and may have been missed by the cleanup.
These requests would never be completed.

The next drbd_suspend_io() will then lock up,
waiting forever for these requests to complete.

Fixed in several code paths:
  Make sure the connection state is NetworkFailure or worse
  before starting the cleanup in drbd_disconnect().
  This should make sure the cleanup won't miss any requests.

  Disallow receive_state() to "upgrade" the connection state
  from an error state. This will make sure the "illegal" state
  transition won't happen.

  For all connection failure states,
  relax the safe-guard in sanitize_state() again
  to silently mask out those state changes
  (e.g. Timeout -> Connected becomes Timeout -> Timeout).

 Note by Philipp Reisner:
  The 3rd chunk described as "relax the safe-guard..."
  is not there in 8.4 as it is relaxed to the maximum in
  8.4 already

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:12 +01:00
Philipp Reisner
57bcb6cf1d drbd: Do not call generic_make_request() while holding req_lock
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:11 +01:00
Philipp Reisner
d60de03a66 drbd: Load balancing method: striping
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:11 +01:00
Philipp Reisner
380207d08e drbd: Load balancing of read requests
New config option for the disk secition "read-balancing", with
the values: prefer-local, prefer-remote, round-robin, when-congested-remote.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:10 +01:00
Philipp Reisner
d10b4ea32b drbd: Get rid of "ASSERTION FAILED: tconn->current_epoch->list not empty"
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:10 +01:00
Lars Ellenberg
615e087fbd drbd: add missing rcu locks around recently introduced idr_for_each
Recent commit
 drbd: Move write_ordering from mdev to tconn
introduced a new idr_for_each loop over all volumes,
but did not take necessary rcu locks or krefs.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:10 +01:00
Andreas Gruenbacher
03d63e1d1e drbd: Remove leftover prototype
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:09 +01:00
Philipp Reisner
975b297947 drbd: fix potential spinlock deadlock
drbd_try_clear_on_disk_bm() has a sanity check for the number of blocks
left to be resynced (rs_left) in the current resync extent.
If it detects a mismatch, it complains, and forces a disconnect using
drbd_force_state(mdev, NS(conn, C_DISCONNECTING));

Unfortunately, this may be called while holding the req_lock,
and drbd_force_state() want's to aquire that lock itself. Deadlock.

Don't force a disconnect, but fix up rs_left by recounting and
reassigning the number of dirty blocks in that extent.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:09 +01:00
Philipp Reisner
77fede5137 drbd: Fix the WO=drain implementation for multiple volumes
Wait until IO is drained in all volumes.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:08 +01:00
Philipp Reisner
1e9dd2912e drbd: Switch drbd_may_finish_epoch() from mdev to tconn
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:08 +01:00
Philipp Reisner
12038a3a71 drbd: Move list of epochs from mdev to tconn
This is necessary since the transfer_log on the sending is also
per tconn.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:08 +01:00
Philipp Reisner
1d2783d532 drbd: Prepare epochs per connection
An epoch object needs a pointer to the mdev it was received for.
This is necessary to be able to send the barrier ack packet for
the same volume as the original barrier packet was assigned to.

This prepares the next step, in which the (receiver side)
epoch list is moved from the device (mdev) to the connection (tconn)
object.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:07 +01:00
Philipp Reisner
4b0007c0e8 drbd: Move write_ordering from mdev to tconn
This is necessary in order to prepare the move of the (receiver side)
epoch list from the device (mdev) to the connection (tconn) objects.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:07 +01:00
Philipp Reisner
6936fcb49a drbd: Move the CREATE_BARRIER flag from connection to device
That is necessary since the whole transfer log is per connection(tconn)
and not per device(mdev).

This bug caused list corruption on the worker list. When a barrier is queued
for sending in the context of one device, another device did not see the
CREATE_BARRIER bit, and queued the same object again -> list corruption.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:06 +01:00
Philipp Reisner
36baf6117b drbd: Fixed an obvious copy-n-paste mistake
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:06 +01:00
Philipp Reisner
43de7c852b drbd: Fixes from the drbd-8.3 branch
* drbd-8.3:
  drbd: O_SYNC gives EIO on ramdisks for some kernels (eg. RHEL6).
  drbd: send intermediate state change results to the peer

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:06 +01:00
Philipp Reisner
0cfac5dd90 drbd: Fixes from the drbd-8.3 branch
* drbd-8.3:
  drbd: fix spurious meta data IO "error"
  drbd: Fixed a race condition between detach and start of resync
  drbd: fix harmless race to not trigger an ASSERT
  drbd: Derive sync-UUIDs only from the bitmap-uuid if it is non-zero
  drbd: Fixed current UUID generation (regression introduced recently, after 8.3.11)

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:05 +01:00
Philipp Reisner
376694a054 drbd: Silenced compiler warnings
Since version 4.6.1 gcc warns about variables that get
a value assigned, but which are never read later on.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:05 +01:00
Philipp Reisner
9bcd252182 drbd: fix "stalled" empty resync
With sync-after dependencies, given "lucky" timing of pause/unpause
events, and the end of an empty (0 bits set) resync was sometimes not
detected on the SyncTarget, leading to a "stalled" SyncSource state.

Fixed this by expecting not only "Inconsistent -> UpToDate" but also
"Consistent -> UpToDate" transitions for the peer disk state
to end a resync.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:04 +01:00
Lars Ellenberg
22d81140ae drbd: fix bitmap writeout after aborted resync
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:04 +01:00
Philipp Reisner
08b165ba11 drbd: Consider the discard-my-data flag for all volumes [bugz 359]
...not only for the first volume

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:04 +01:00
Andreas Gruenbacher
935be260c1 drbd: Improve error reporting in drbd_md_sync_page_io()
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:03 +01:00
Lars Ellenberg
25e409321a drbd: fix connect failure with all default net-options
If no net-options are configured (all on their default),
no DRBD_NLA_NET_CONF will be passed to the kernel.
The kernel must not require its presence,
there is no required option in there.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:03 +01:00
Andreas Gruenbacher
a209b4aec3 drbd: Update some outdated comments to match the code
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:02 +01:00
Philipp Reisner
c4e7afdc01 drbd: Remove unused code
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:02 +01:00
Philipp Reisner
4276dea70c drbd: Remove dead code
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:02 +01:00
Philipp Reisner
85d735138a drbd: Cleanup all epoch objects upon connection loss
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:01 +01:00
Philipp Reisner
f132f554ce drbd: Do not display bogus log lines for pdsk in case pdsk < D_UNKNOWN
This was a regression recently introduced with commit
7848ddb752c09b6dfd1ddfabb06b69b08aa8f6b9
"drbd: Correctly handle resources without volumes"

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:00 +01:00
Lars Ellenberg
97ddb68790 drbd: detach must not try to abort non-local requests
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:00 +01:00
Andreas Gruenbacher
f497609e4c drbd: Get rid of MR_{READ,WRITE}_SHIFT
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:58:00 +01:00
Philipp Reisner
823bd832a6 drbd: Bugfix for the connection behavior
If we get into the C_BROKEN_PIPE cstate once, the state engine set the
thi->t_state of the receiver thread to restarting.  But with the while loop
in drbdd_init() a new connection gets established. After the call into
drbdd() returns immediately since the thi->t_state is not RUNNING.  The
restart of drbd_init() then resets thi->t_state to RUNNING.

I.e. after entering C_BROKEN_PIPE once, the next successful established
connection gets wasted.

The two parts of the fix:
  * Do not cause the thread to restart if we detect the issue
    with the sockets while we are in C_WF_CONNECTION.

  * Make sure that all actions that would have set us to C_BROKEN_PIPE
    happen before the state change to C_WF_REPORT_PARAMS.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
2012-11-08 16:57:59 +01:00