Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |  

This web mail archive is frozen.

This page is part of a frozen web archive of this mailing list.

You can still navigate around this archive, but know that no new mails have been added to it since July of 2016.

Click here to be taken to the new web archives of this list; it includes all the mails that are in this frozen archive plus all new mails that have been sent to the list since it was migrated to the new archives.

Subject: [OMPI devel] Inconsistent description of btl_openib_eager_rdma_num parameter in FAQ
From: Lars Schäfers (slars_at_[hidden])
Date: 2013-09-10 05:42:16


Hi,

for quite a long time already, there is a confusing inconsistency of the
description of the OpenIB parameters related to eager messages on this
FAQ site (see details below):
http://www.open-mpi.org/faq/?category=openfabrics

Does somebody here has the necessary permissions to fix this?

The answer to question 20 says (last row in the table):

"Each MPI process will use RDMA buffers for eager fragments up to
btl_openib_eager_rdma_num MPI peers. Upon receiving the
btl_openib_eager_rdma_threshhold'th message from an MPI peer process, if
both sides have not yet setup btl_openib_eager_rdma_num sets of eager
RDMA buffers, a new set will be created. The set will contain
btl_openib_max_eager_rdma buffers; each buffer will be
btl_openib_eager_limit bytes (i.e., the maximum size of an eager
fragment)."

while part of the answer of question 24 says the following:

  * btl_openib_max_eager_rdma (default value: 16): This parameter
    controls the maximum number of peers that can receive and RDMA
    connection for short messages. It is not advisable to change this
    value to a very large number because the polling time increase with
    the number of the connections; as a direct result, short message
    latency will increase.

  * btl_openib_eager_rdma_num (default value: 16): This parameter
    controls the maximum number of pre-allocated buffers allocated to
    each peer for small messages.

- Lars

-- 
Lars Schaefers
Computer Engineering Group of Prof. Dr. Marco Platzner
Paderborn Center for Parallel Computing, University of Paderborn
Pohlweg 47-49, 33098 Paderborn, Germany
Tel: +49 (0)5251 60 4341, Fax: +49 (0)5251 60 5377
Office: Building O 3.119