linux-stable.git/net/tipc/core.h, branch linux-4.8.y

tipc: add neighbor monitoring framework

2016-06-15T21:06:28+00:00

TIPC based clusters are by default set up with full-mesh link
connectivity between all nodes. Those links are expected to provide
a short failure detection time, by default set to 1500 ms. Because
of this, the background load for neighbor monitoring in an N-node
cluster increases with a factor N on each node, while the overall
monitoring traffic through the network infrastructure increases at
a ~(N * (N - 1)) rate. Experience has shown that such clusters don't
scale well beyond ~100 nodes unless we significantly increase failure
discovery tolerance.

This commit introduces a framework and an algorithm that drastically
reduces this background load, while basically maintaining the original
failure detection times across the whole cluster. Using this algorithm,
background load will now grow at a rate of ~(2 * sqrt(N)) per node, and
at ~(2 * N * sqrt(N)) in traffic overhead. As an example, each node will
now have to actively monitor 38 neighbors in a 400-node cluster, instead
of as before 399.

This "Overlapping Ring Supervision Algorithm" is completely distributed
and employs no centralized or coordinated state. It goes as follows:

- Each node makes up a linearly ascending, circular list of all its N
  known neighbors, based on their TIPC node identity. This algorithm
  must be the same on all nodes.

- The node then selects the next M = sqrt(N) - 1 nodes downstream from
  itself in the list, and chooses to actively monitor those. This is
  called its "local monitoring domain".

- It creates a domain record describing the monitoring domain, and
  piggy-backs this in the data area of all neighbor monitoring messages
  (LINK_PROTOCOL/STATE) leaving that node. This means that all nodes in
  the cluster eventually (default within 400 ms) will learn about
  its monitoring domain.

- Whenever a node discovers a change in its local domain, e.g., a node
  has been added or has gone down, it creates and sends out a new
  version of its node record to inform all neighbors about the change.

- A node receiving a domain record from anybody outside its local domain
  matches this against its own list (which may not look the same), and
  chooses to not actively monitor those members of the received domain
  record that are also present in its own list. Instead, it relies on
  indications from the direct monitoring nodes if an indirectly
  monitored node has gone up or down. If a node is indicated lost, the
  receiving node temporarily activates its own direct monitoring towards
  that node in order to confirm, or not, that it is actually gone.

- Since each node is actively monitoring sqrt(N) downstream neighbors,
  each node is also actively monitored by the same number of upstream
  neighbors. This means that all non-direct monitoring nodes normally
  will receive sqrt(N) indications that a node is gone.

- A major drawback with ring monitoring is how it handles failures that
  cause massive network partitionings. If both a lost node and all its
  direct monitoring neighbors are inside the lost partition, the nodes in
  the remaining partition will never receive indications about the loss.
  To overcome this, each node also chooses to actively monitor some
  nodes outside its local domain. Those nodes are called remote domain
  "heads", and are selected in such a way that no node in the cluster
  will be more than two direct monitoring hops away. Because of this,
  each node, apart from monitoring the member of its local domain, will
  also typically monitor sqrt(N) remote head nodes.

- As an optimization, local list status, domain status and domain
  records are marked with a generation number. This saves senders from
  unnecessarily conveying  unaltered domain records, and receivers from
  performing unneeded re-adaptations of their node monitoring list, such
  as re-assigning domain heads.

- As a measure of caution we have added the possibility to disable the
  new algorithm through configuration. We do this by keeping a threshold
  value for the cluster size; a cluster that grows beyond this value
  will switch from full-mesh to ring monitoring, and vice versa when
  it shrinks below the value. This means that if the threshold is set to
  a value larger than any anticipated cluster size (default size is 32)
  the new algorithm is effectively disabled. A patch set for altering the
  threshold value and for listing the table contents will follow shortly.

- This change is fully backwards compatible.

Acked-by: Ying Xue 
Signed-off-by: Jon Maloy 
Signed-off-by: David S. Miller

tipc: make dist queue pernet

2016-04-11T19:22:20+00:00

Nametable updates received from the network that cannot be applied
immediately are placed on a defer queue. This queue is global to the
TIPC module, which might cause problems when using TIPC in containers.
To prevent nametable updates from escaping into the wrong namespace,
we make the queue pernet instead.

Signed-off-by: Erik Hugne 
Signed-off-by: Jon Maloy 
Signed-off-by: David S. Miller

tipc: reduce code dependency between binding table and node layer

2015-11-20T19:06:10+00:00

The file name_distr.c currently contains three functions,
named_cluster_distribute(), tipc_publ_subcscribe() and
tipc_publ_unsubscribe() that all directly access fields in
struct tipc_node. We want to eliminate such dependencies, so
we move those functions to the file node.c and rename them to
tipc_node_broadcast(), tipc_node_subscribe() and tipc_node_unsubscribe()
respectively.

Reviewed-by: Ying Xue 
Signed-off-by: Jon Maloy 
Signed-off-by: David S. Miller

tipc: clean up unused code and structures

2015-10-24T13:56:47+00:00

After the previous changes in this series, we can now remove some
unused code and structures, both in the broadcast, link aggregation
and link code.

There are no functional changes in this commit.

Signed-off-by: Jon Maloy 
Reviewed-by: Ying Xue 
Signed-off-by: David S. Miller

tipc: let broadcast packet reception use new link receive function

2015-10-24T13:56:37+00:00

The code path for receiving broadcast packets is currently distinct
from the unicast path. This leads to unnecessary code and data
duplication, something that can be avoided with some effort.

We now introduce separate per-peer tipc_link instances for handling
broadcast packet reception. Each receive link keeps a pointer to the
common, single, broadcast link instance, and can hence handle release
and retransmission of send buffers as if they belonged to the own
instance.

Furthermore, we let each unicast link instance keep a reference to both
the pertaining broadcast receive link, and to the common send link.
This makes it possible for the unicast links to easily access data for
broadcast link synchronization, as well as for carrying acknowledges for
received broadcast packets.

Signed-off-by: Jon Maloy 
Reviewed-by: Ying Xue 
Signed-off-by: David S. Miller

tipc: move broadcast link lock to struct tipc_net

2015-10-24T13:56:25+00:00

The broadcast lock will need to be acquired outside bcast.c in a later
commit. For this reason, we move the lock to struct tipc_net. Consistent
with the changes in the previous commit, we also introducee two new
functions tipc_bcast_lock() and tipc_bcast_unlock(). The code that is
currently using tipc_bclink_lock()/unlock() will be phased out during
the coming commits in this series.

Signed-off-by: Jon Maloy 
Reviewed-by: Ying Xue 
Signed-off-by: David S. Miller

tipc: move bcast definitions to bcast.c

2015-10-24T13:56:24+00:00

Currently, a number of structure and function definitions related
to the broadcast functionality are unnecessarily exposed in the file
bcast.h. This obscures the fact that the external interface towards
the broadcast link in fact is very narrow, and causes unnecessary
recompilations of other files when anything changes in those
definitions.

In this commit, we move as many of those definitions as is currently
possible to the file bcast.c.

We also rename the structure 'tipc_bclink' to 'tipc_bc_base', both
since the name does not correctly describe the contents of this
struct, and will do so even less in the future, and because we want
to use the term 'link' more appropriately in the functionality
introduced later in this series.

Finally, we rename a couple of functions, such as tipc_bclink_xmit()
and others that will be kept in the future, to include the term 'bcast'
instead.

There are no functional changes in this commit.

Signed-off-by: Jon Maloy 
Reviewed-by: Ying Xue 
Signed-off-by: David S. Miller

tipc: clean up link creation

2015-07-31T00:25:15+00:00

We simplify the link creation function tipc_link_create() and the way
the link struct it is connected to the node struct. In particular, we
remove the duplicate initialization of some fields which are anyway set
in tipc_link_reset().

Tested-by: Ying Xue 
Signed-off-by: Jon Maloy 
Signed-off-by: David S. Miller

tipc: reduce locking scope during packet reception

2015-07-21T03:41:16+00:00

We convert packet/message reception according to the same principle
we have been using for message sending and timeout handling:

We move the function tipc_rcv() to node.c, hence handling the initial
packet reception at the link aggregation level. The function grabs
the node lock, selects the receiving link, and accesses it via a new
call tipc_link_rcv(). This function appends buffers to the input
queue for delivery upwards, but it may also append outgoing packets
to the xmit queue, just as we do during regular message sending. The
latter will happen when buffers are forwarded from the link backlog,
or when retransmission is requested.

Upon return of this function, and after having released the node lock,
tipc_rcv() delivers/tranmsits the contents of those queues, but it may
also perform actions such as link activation or reset, as indicated by
the return flags from the link.

This reduces the number of cpu cycles spent inside the node spinlock,
and reduces contention on that lock.

Reviewed-by: Ying Xue 
Signed-off-by: Jon Maloy 
Signed-off-by: David S. Miller

tipc: simplify packet sequence number handling

2015-05-14T16:24:46+00:00

Although the sequence number in the TIPC protocol is 16 bits, we have
until now stored it internally as an unsigned 32 bits integer.
We got around this by always doing explicit modulo-65535 operations
whenever we need to access a sequence number.

We now make the incoming and outgoing sequence numbers to unsigned
16-bit integers, and remove the modulo operations where applicable.

We also move the arithmetic inline functions for 16 bit integers
to core.h, and the function buf_seqno() to msg.h, so they can easily
be accessed from anywhere in the code.

Reviewed-by: Erik Hugne 
Reviewed-by: Ying Xue 
Signed-off-by: Jon Maloy 
Signed-off-by: David S. Miller