-
Notifications
You must be signed in to change notification settings - Fork 4
HiTopo
The HiTopo framework provides an unified way of getting the geographical location of a process or group of processes.
Source code is available here : http://bitbucket.org/jeaugeys/hitopo/.
HiTopo defines 8 topology levels. Each MPI process will have an address for each of these levels.
This level is currently unused (always equal to 0) but could be used in grids to number different clusters of the same computing center.
Islands are currently used to group nodes connected by a fat-tree. Islands are connected to each other by a lighter (non fat-tree) network. We currently determine the island number by looking at L2 switches.
But this is just one possible usage. Islands can be used as any level 2 network grouping level.
The switch level is the smallest network grouping level, currently used to reflect the lower level switch (leaf switch).
The node level reflects the node name/number.
This level is used for multi board machines. The L2 NUMA address is the number of the NUMA board.
The socket level indicates on which socket the MPI process is running. On recent AMD/Intel processors, it can also be seen as the L1 NUMA level.
The core level indicates the core number.
The HT level is not currently detected, but is used to distinguish two MPI processes running on the same core.
Depends on : SLURM resource manager
The SLURM components retrieves the environment variables provided by SLURM (SLURMTOPOLOGYADDR and SLURMTOPOLOGYADDR_PATTERN) to fill level 3 (node) and potentially level 2 and 1 (switch and island).
''' Depends on :''' x86 processors
Fills levels 5 and 6 (sockets and cores) if the process is bound to a socket/core.
''' Depends on :''' linux
Fills level 3 (node name).
''' Depends on :''' Open Fabrics Networks
Fills level 4 (L1 IB switch) and may also fill level 5 (island).
After each process has determined its own physical address (through the above components), an Allgather operation will be performed. Addresses will be recomputed to number each value from 0 to n.
Example :
For a job running on cluster0, island2, switch2 to switch 5, one process may have the following raw address : cluster0.island2.switch3.node4.0.3.2 (l2numa 0, socket 3, core 2) which may be renumbered this way : 0.0.1.4.0.3.2.0 (only one cluster ; one island ; switch2 is 0, so switch3 is 1 ; node4 has index 4 ; and the rest of the address is unchanged, given that all nodes are fully used)
hitopointt* ompihitopogetaddr(ompicommunicatort* comm, int process_rank)
will return the hitopo address for a given process in a given comm. Note that hitopo addresses may be different depending on the communicator (renumbering will renumber address fields starting at 0).
hitopointt** ompihitopogetaddrs(ompicommunicatort* comm)
will return the full table of the given communicator.