This patch changes that we don't ack each message. Lowcomms will take
care about to send an ack back after a bulk of messages was processed.
Currently it's only when the whole receive buffer was processed, there
might better positions to send an ack back but only the lowcomms
implementation know when there are more data to receive. This patch has
also disadvantages that we might retransmit more on errors, however this
is a very rare case.
Tested with make_panic on gfs2 with three nodes by running:
trace-cmd record -p function -l 'dlm_send_ack' sleep 100
and
trace-cmd report | wc -l
Before patch:
- 20548
- 21376
- 21398
After patch:
- 18338
- 20679
- 19949
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch renames DEFAULT_BUFFER_SIZE to DLM_MAX_SOCKET_BUFSIZE and
LOWCOMMS_MAX_TX_BUFFER_LEN to DLM_MAX_APP_BUFSIZE as they are proper
names to define what's behind those values. The DLM_MAX_SOCKET_BUFSIZE
defines the maximum size of buffer which can be handled on socket layer,
the DLM_MAX_APP_BUFSIZE defines the maximum size of buffer which can be
handled by the DLM application layer.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch introduce to make a tcp lowcomms connection reliable even if
reconnects occurs. This is done by an application layer re-transmission
handling and sequence numbers in dlm protocols. There are three new dlm
commands:
DLM_OPTS:
This will encapsulate an existing dlm message (and rcom message if they
don't have an own application side re-transmission handling). As optional
handling additional tlv's (type length fields) can be appended. This can
be for example a sequence number field. However because in DLM_OPTS the
lockspace field is unused and a sequence number is a mandatory field it
isn't made as a tlv and we put the sequence number inside the lockspace
id. The possibility to add optional options are still there for future
purposes.
DLM_ACK:
Just a dlm header to acknowledge the receive of a DLM_OPTS message to
it's sender.
DLM_FIN:
This provides a 4 way handshake for connection termination inclusive
support for half-closed connections. It's provided on application layer
because SCTP doesn't support half-closed sockets, the shutdown() call
can interrupted by e.g. TCP resets itself and a hard logic to implement
it because the othercon paradigm in lowcomms. The 4-way termination
handshake also solve problems to synchronize peer EOF arrival and that
the cluster manager removes the peer in the node membership handling of
DLM. In some cases messages can be still transmitted in this time and we
need to wait for the node membership event.
To provide a reliable connection the node will retransmit all
unacknowledges message to it's peer on reconnect. The receiver will then
filtering out the next received message and drop all messages which are
duplicates.
As RCOM_STATUS and RCOM_NAMES messages are the first messages which are
exchanged and they have they own re-transmission handling, there exists
logic that these messages must be first. If these messages arrives we
store the dlm version field. This handling is on DLM 3.1 and after this
patch 3.2 the same. A backwards compatibility handling has been added
which seems to work on tests without tcpkill, however it's not recommended
to use DLM 3.1 and 3.2 at the same time, because DLM 3.2 tries to fix long
term bugs in the DLM protocol.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch moves out some lowcomms hash functionality into lowcomms
header to provide them to other layers like midcomms as well.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch introduces a retransmit functionality for a lowcomms message
handle. It's just allocates a new buffer and transmit it again, no
special handling about prioritize it because keeping bytestream in order.
To avoid another connection look some refactor was done to make a new
buffer allocation with a preexisting connection pointer.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch makes the void pointer handle for lowcomms functionality per
message and not per page allocation entry. A refcount handling for the
handle was added to keep the message alive until the user doesn't need
it anymore.
There exists now a per message callback which will be called when
allocating a new buffer. This callback will be guaranteed to be called
according the order of the sending buffer, which can be used that the
caller increments a sequence number for the dlm message handle.
For transition process we cast the dlm_mhandle to dlm_msg and vice versa
until the midcomms layer will implement a specific dlm_mhandle structure.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch adds checks for dlm config attributes regarding to protocol
parameters as it makes only sense to change them when dlm is not running.
It also adds a check for valid protocol specifiers and return invalid
argument if they are not supported.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch fixes an deadlock issue when dlm_lowcomms_close() is called.
When dlm_lowcomms_close() is called the clusters_root.subsys.su_mutex is
held to remove configfs items. At this time we flushing (e.g.
cancel_work_sync()) the workers of send and recv workqueue. Due the fact
that we accessing configfs items (mark values), these workers will lock
clusters_root.subsys.su_mutex as well which are already hold by
dlm_lowcomms_close() and ends in a deadlock situation.
[67170.703046] ======================================================
[67170.703965] WARNING: possible circular locking dependency detected
[67170.704758] 5.11.0-rc4+ #22 Tainted: G W
[67170.705433] ------------------------------------------------------
[67170.706228] dlm_controld/280 is trying to acquire lock:
[67170.706915] ffff9f2f475a6948 ((wq_completion)dlm_recv){+.+.}-{0:0}, at: __flush_work+0x203/0x4c0
[67170.708026]
but task is already holding lock:
[67170.708758] ffffffffa132f878 (&clusters_root.subsys.su_mutex){+.+.}-{3:3}, at: configfs_rmdir+0x29b/0x310
[67170.710016]
which lock already depends on the new lock.
The new behaviour adds the mark value to the node address configuration
which doesn't require to held the clusters_root.subsys.su_mutex by
accessing mark values in a separate datastructure. However the mark
values can be set now only after a node address was set which is the
case when the user is using dlm_controld.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch will set the maximum transmit buffer size for rcom messages
with "names" to 4096 bytes. It's a leftover change of
commit 4798cbbfbd ("fs: dlm: rework receive handling"). Fact is that we
cannot allocate a contiguous transmit buffer length above of 4096 bytes.
It seems at some places the upper layer protocol will calculate according
to dlm_config.ci_buffer_size the possible payload of a dlm recovery
message. As compiler setting we will use now the maximum possible
message which dlm can send out. Commit 4e192ee68e ("fs: dlm: disallow
buffer size below default") disallow a buffer setting smaller than the
4096 bytes and above 4096 bytes is definitely wrong because we will then
write out of buffer space as we cannot allocate a contiguous buffer above
4096 bytes. The ci_buffer_size is still there to define the possible
maximum receive buffer size of a recvmsg() which should be at least the
maximum possible dlm message size.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Based on 1 normalized pattern(s):
this copyrighted material is made available to anyone wishing to use
modify copy or redistribute it subject to the terms and conditions
of the gnu general public license v 2
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 45 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Richard Fontana <rfontana@redhat.com>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Steve Winslow <swinslow@gmail.com>
Reviewed-by: Alexios Zavras <alexios.zavras@intel.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190528170027.342746075@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
A deadlock sometimes occurs between dlm_controld closing
a lowcomms connection through configfs and dlm_send looking
up the address for a new connection in configfs.
dlm_controld does a configfs rmdir which calls
dlm_lowcomms_close which waits for dlm_send to
cancel work on the workqueues.
The dlm_send workqueue thread has called
tcp_connect_to_sock which calls dlm_nodeid_to_addr
which does a configfs lookup and blocks on a lock
held by dlm_controld in the rmdir path.
The solution here is to save the node addresses within
the lowcomms code so that the lowcomms workqueue does
not need to step through configfs to get a node address.
dlm_controld:
wait_for_completion+0x1d/0x20
__cancel_work_timer+0x1b3/0x1e0
cancel_work_sync+0x10/0x20
dlm_lowcomms_close+0x4c/0xb0 [dlm]
drop_comm+0x22/0x60 [dlm]
client_drop_item+0x26/0x50 [configfs]
configfs_rmdir+0x180/0x230 [configfs]
vfs_rmdir+0xbd/0xf0
do_rmdir+0x103/0x120
sys_rmdir+0x16/0x20
dlm_send:
mutex_lock+0x2b/0x50
get_comm+0x34/0x140 [dlm]
dlm_nodeid_to_addr+0x18/0xd0 [dlm]
tcp_connect_to_sock+0xf4/0x2d0 [dlm]
process_send_sockets+0x1d2/0x260 [dlm]
worker_thread+0x170/0x2a0
Signed-off-by: David Teigland <teigland@redhat.com>
Make network connections to other nodes earlier, in the context of
dlm_recoverd. This avoids connecting to nodes from dlm_send where we
try to avoid allocations which could possibly deadlock if memory reclaim
goes into the cluster fs which may try to do a dlm operation.
Signed-off-by: Christine Caulfield <ccaulfie@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This fixes up most of the things pointed out by akpm and Pavel Machek
with comments below indicating why some things have been left:
Andrew Morton wrote:
>
>> +static struct nodeinfo *nodeid2nodeinfo(int nodeid, gfp_t alloc)
>> +{
>> + struct nodeinfo *ni;
>> + int r;
>> + int n;
>> +
>> + down_read(&nodeinfo_lock);
>
> Given that this function can sleep, I wonder if `alloc' is useful.
>
> I see lots of callers passing in a literal "0" for `alloc'. That's in fact
> a secret (GFP_ATOMIC & ~__GFP_HIGH). I doubt if that's what you really
> meant. Particularly as the code could at least have used __GFP_WAIT (aka
> GFP_NOIO) which is much, much more reliable than "0". In fact "0" is the
> least reliable mode possible.
>
> IOW, this is all bollixed up.
When 0 is passed into nodeid2nodeinfo the function does not try to allocate a
new structure at all. it's an indication that the caller only wants the nodeinfo
struct for that nodeid if there actually is one in existance.
I've tidied the function itself so it's more obvious, (and tidier!)
>> +/* Data received from remote end */
>> +static int receive_from_sock(void)
>> +{
>> + int ret = 0;
>> + struct msghdr msg;
>> + struct kvec iov[2];
>> + unsigned len;
>> + int r;
>> + struct sctp_sndrcvinfo *sinfo;
>> + struct cmsghdr *cmsg;
>> + struct nodeinfo *ni;
>> +
>> + /* These two are marginally too big for stack allocation, but this
>> + * function is (currently) only called by dlm_recvd so static should be
>> + * OK.
>> + */
>> + static struct sockaddr_storage msgname;
>> + static char incmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
>
> whoa. This is globally singly-threaded code??
Yes. it is only ever run in the context of dlm_recvd.
>>
>> +static void initiate_association(int nodeid)
>> +{
>> + struct sockaddr_storage rem_addr;
>> + static char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
>
> Another static buffer to worry about. Globally singly-threaded code?
Yes. Only ever called by dlm_sendd.
>> +
>> +/* Send a message */
>> +static int send_to_sock(struct nodeinfo *ni)
>> +{
>> + int ret = 0;
>> + struct writequeue_entry *e;
>> + int len, offset;
>> + struct msghdr outmsg;
>> + static char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
>
> Singly-threaded?
Yep.
>>
>> +static void dealloc_nodeinfo(void)
>> +{
>> + int i;
>> +
>> + for (i=1; i<=max_nodeid; i++) {
>> + struct nodeinfo *ni = nodeid2nodeinfo(i, 0);
>> + if (ni) {
>> + idr_remove(&nodeinfo_idr, i);
>
> Didn't that need locking?
Not. it's only ever called at DLM shutdown after all the other threads
have been stopped.
>>
>> +static int write_list_empty(void)
>> +{
>> + int status;
>> +
>> + spin_lock_bh(&write_nodes_lock);
>> + status = list_empty(&write_nodes);
>> + spin_unlock_bh(&write_nodes_lock);
>> +
>> + return status;
>> +}
>
> This function's return value is meaningless. As soon as the lock gets
> dropped, the return value can get out of sync with reality.
>
> Looking at the caller, this _might_ happen to be OK, but it's a nasty and
> dangerous thing. Really the locking should be moved into the caller.
It's just an optimisation to allow the caller to schedule if there is no work
to do. if something arrives immediately afterwards then it will get picked up
when the process re-awakes (and it will be woken by that arrival).
The 'accepting' atomic has gone completely. as Andrew pointed out it didn't
really achieve much anyway. I suspect it was a plaster over some other
startup or shutdown bug to be honest.
Signed-off-by: Patrick Caulfield <pcaulfie@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Cc: Andrew Morton <akpm@osdl.org>
Cc: Pavel Machek <pavel@ucw.cz>
When a node is removed from a lockspace configuration, close our
connection to it, clearing any remaining messages for it.
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Patrick Caulfield <pcaulfie@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
This is the core of the distributed lock manager which is required
to use GFS2 as a cluster filesystem. It is also used by CLVM and
can be used as a standalone lock manager independantly of either
of these two projects.
It implements VAX-style locking modes.
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steve Whitehouse <swhiteho@redhat.com>
Alexander Aring