Skip to content

v3.1: rmaps: fixed the ordering of mpirun target nodes #4787

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 12, 2018

Conversation

karasevb
Copy link
Member

@karasevb karasevb commented Feb 5, 2018

Fixes #4516
Corresponds to #4781 and #4785

karasevb and others added 2 commits February 5, 2018 06:06
Fixed the desync of job-nodelists between mpirun and orted
daemons. The issue was observed when using RSH launching because user
can provide arbitrary order of nodes regarding HNP placement.
The mpirun process propagate the daemon's nodelist order to nodes.
The problem was that HNP itself is assembling the nodelist based on
user provided order. As the result ranks assignment was calculated
differently on orted and mpirun.

Consider following example:
* User launches mpirun on node cn2.
* Hostlist is cn1,cn2,cn3,cn4; ppn=1
* mpirun is passing hostlist cn[2:2,1,3-4]@0(4) to orteds
So as result mpirun will assing rank 0 on cn1 while orted will assign
rank 0 on cn2 (because orted sees cn2 as the first element in the node
list)

Signed-off-by: Boris Karasev <[email protected]>
(cherry picked from commit 52e81ee)
Signed-off-by: Ralph Castain <[email protected]>
(cherry picked from commit 73ef976)
Copy link
Member

@jjhursey jjhursey left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the PR.
I noticed that the same code structure is also in v3.0.x - do we need to update that branch as well?

@karasevb
Copy link
Member Author

karasevb commented Feb 7, 2018

@jjhursey
In fact this issue is not reproduced on v3.0.x. This branch has difference from v3.1.x and master in the follow:
v3.0.x fills the jdata->map->nodes here
https://github.com/open-mpi/ompi/blob/v3.0.x/orte/mca/rmaps/base/rmaps_base_map_job.c#L427 relatively orte_node_pool where is the correct ranks order, that avoids the problem.

@jjhursey
Copy link
Member

jjhursey commented Feb 7, 2018

@karasevb Thanks for checking!

@bwbarrett bwbarrett merged commit ede6352 into open-mpi:v3.1.x Feb 12, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants