8ace07efed
1. Galen's fine-grain control of queue pair resources in the openib
BTL.
1. Pasha's new implementation of asychronous HCA event handling.
Pasha's new implementation doesn't take much explanation, but the new
"multifrag" stuff does.
Note that "svn merge" was not used to bring this new code from the
/tmp/ib_multifrag branch -- something Bad happened in the periodic
trunk pulls on that branch making an actual merge back to the trunk
effectively impossible (i.e., lots and lots of arbitrary conflicts and
artifical changes). :-(
== Fine-grain control of queue pair resources ==
Galen's fine-grain control of queue pair resources to the OpenIB BTL
(thanks to Gleb for fixing broken code and providing additional
functionality, Pasha for finding broken code, and Jeff for doing all
the svn work and regression testing).
Prior to this commit, the OpenIB BTL created two queue pairs: one for
eager size fragments and one for max send size fragments. When the
use of the shared receive queue (SRQ) was specified (via "-mca
btl_openib_use_srq 1"), these QPs would use a shared receive queue for
receive buffers instead of the default per-peer (PP) receive queues
and buffers. One consequence of this design is that receive buffer
utilization (the size of the data received as a percentage of the
receive buffer used for the data) was quite poor for a number of
applications.
The new design allows multiple QPs to be specified at runtime. Each
QP can be setup to use PP or SRQ receive buffers as well as giving
fine-grained control over receive buffer size, number of receive
buffers to post, when to replenish the receive queue (low water mark)
and for SRQ QPs, the number of outstanding sends can also be
specified. The following is an example of the syntax to describe QPs
to the OpenIB BTL using the new MCA parameter btl_openib_receive_queues:
{{{
-mca btl_openib_receive_queues \
"P,128,16,4;S,1024,256,128,32;S,4096,256,128,32;S,65536,256,128,32"
}}}
Each QP description is delimited by ";" (semicolon) with individual
fields of the QP description delimited by "," (comma). The above
example therefore describes 4 QPs.
The first QP is:
P,128,16,4
Meaning: per-peer receive buffer QPs are indicated by a starting field
of "P"; the first QP (shown above) is therefore a per-peer based QP.
The second field indicates the size of the receive buffer in bytes
(128 bytes). The third field indicates the number of receive buffers
to allocate to the QP (16). The fourth field indicates the low
watermark for receive buffers at which time the BTL will repost
receive buffers to the QP (4).
The second QP is:
S,1024,256,128,32
Shared receive queue based QPs are indicated by a starting field of
"S"; the second QP (shown above) is therefore a shared receive queue
based QP. The second, third and fourth fields are the same as in the
per-peer based QP. The fifth field is the number of outstanding sends
that are allowed at a given time on the QP (32). This provides a
"good enough" mechanism of flow control for some regular communication
patterns.
QPs MUST be specified in ascending receive buffer size order. This
requirement may be removed prior to 1.3 release.
This commit was SVN r15474.
250 строки
7.9 KiB
Plaintext
250 строки
7.9 KiB
Plaintext
# -*- text -*-
|
|
#
|
|
# Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
# University Research and Technology
|
|
# Corporation. All rights reserved.
|
|
# Copyright (c) 2004-2005 The University of Tennessee and The University
|
|
# of Tennessee Research Foundation. All rights
|
|
# reserved.
|
|
# Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
# University of Stuttgart. All rights reserved.
|
|
# Copyright (c) 2004-2006 The Regents of the University of California.
|
|
# All rights reserved.
|
|
# Copyright (c) 2006-2007 Cisco Systems, Inc. All rights reserved.
|
|
# Copyright (c) 2007 Mellanox Technologies. All rights reserved.
|
|
# $COPYRIGHT$
|
|
#
|
|
# Additional copyrights may follow
|
|
#
|
|
# $HEADER$
|
|
#
|
|
# This is the US/English help file for Open MPI's OpenFabrics support
|
|
# (the openib BTL).
|
|
#
|
|
[ini file:file not found]
|
|
The Open MPI OpenIB BTL component was unable to find or read an INI
|
|
file that was requested via the btl_openib_hca_param_files MCA
|
|
parameter. Please check this file and/or modify the
|
|
btl_openib_hca_param_files MCA parameter:
|
|
|
|
%s
|
|
#
|
|
[ini file:not in a section]
|
|
In parsing OpenIB BTL parameter file, values were found that were not
|
|
in a valid INI section. These values will be ignored. Please
|
|
re-check this file:
|
|
|
|
%s
|
|
|
|
At line %d, near the following text:
|
|
|
|
%s
|
|
#
|
|
[ini file:unexpected token]
|
|
In parsing OpenIB BTL parameter file, unexpected tokens were found
|
|
(this may cause significant portions of the INI file to be ignored).
|
|
Please re-check this file:
|
|
|
|
%s
|
|
|
|
At line %d, near the following text:
|
|
|
|
%s
|
|
#
|
|
[ini file:expected equals]
|
|
In parsing OpenIB BTL parameter file, unexpected tokens were found
|
|
(this may cause significant portions of the INI file to be ignored).
|
|
An equals sign ("=") was expected but was not found. Please re-check
|
|
this file:
|
|
|
|
%s
|
|
|
|
At line %d, near the following text:
|
|
|
|
%s
|
|
#
|
|
[ini file:expected newline]
|
|
In parsing OpenIB BTL parameter file, unexpected tokens were found
|
|
(this may cause significant portions of the INI file to be ignored).
|
|
A newline was expected but was not found. Please re-check this file:
|
|
|
|
%s
|
|
|
|
At line %d, near the following text:
|
|
|
|
%s
|
|
#
|
|
[ini file:unknown field]
|
|
In parsing OpenIB BTL parameter file, an unrecognized field name was
|
|
found. Please re-check this file:
|
|
|
|
%s
|
|
|
|
At line %d, the field named:
|
|
|
|
%s
|
|
|
|
This field, and any other unrecognized fields, will be skipped.
|
|
#
|
|
[no hca params found]
|
|
WARNING: No HCA parameters were found for the HCA that Open MPI
|
|
detected:
|
|
|
|
Hostname: %s
|
|
HCA vendor ID: 0x%04x
|
|
HCA vendor part ID: %d
|
|
|
|
Default HCA parameters will be used, which may result in lower
|
|
performance. You can edit any of the files specified by the
|
|
btl_openib_hca_param_files MCA parameter to set values for your HCA.
|
|
|
|
NOTE: You can turn off this warning by setting the MCA parameter
|
|
btl_openib_warn_no_hca_params_found to 0.
|
|
#
|
|
[init-fail-no-mem]
|
|
The OpenIB BTL failed to initialize while trying to allocate some
|
|
locked memory. This typically can indicate that the memlock limits
|
|
are set too low. For most HPC installations, the memlock limits
|
|
should be set to "unlimited". The failure occured here:
|
|
|
|
Host: %s
|
|
OMPI source: %s:%d
|
|
Function: %s()
|
|
Device: %s
|
|
Memlock limit: %s
|
|
|
|
You may need to consult with your system administrator to get this
|
|
problem fixed. This FAQ entry on the Open MPI web site may also be
|
|
helpful:
|
|
|
|
http://www.open-mpi.org/faq/?category=openfabrics#ib-locked-pages
|
|
#
|
|
[init-fail-create-q]
|
|
The OpenIB BTL failed to initialize while trying to create an internal
|
|
queue. This typically indicates a failed OpenFabrics installation or
|
|
faulty hardware. The failure occured here:
|
|
|
|
Host: %s
|
|
OMPI source: %s:%d
|
|
Function: %s()
|
|
Error: %s (errno=%d)
|
|
Device: %s
|
|
|
|
You may need to consult with your system administrator to get this
|
|
problem fixed.
|
|
#
|
|
[btl_openib:retry-exceeded]
|
|
The InfiniBand retry count between two MPI processes has been
|
|
exceeded. "Retry count" is defined in the InfiniBand spec 1.2
|
|
(section 12.7.38):
|
|
|
|
The total number of times that the sender wishes the receiver to
|
|
retry timeout, packet sequence, etc. errors before posting a
|
|
completion error.
|
|
|
|
This error typically means that there is something awry within the
|
|
InfiniBand fabric itself. You should note the hosts on which this
|
|
error has occurred; it has been observed that rebooting or removing a
|
|
particular host from the job can sometimes resolve this issue.
|
|
|
|
Two MCA parameters can be used to control Open MPI's behavior with
|
|
respect to the retry count:
|
|
|
|
* btl_openib_ib_retry_count - The number of times the sender will
|
|
attempt to retry (defaulted to 7, the maximum value).
|
|
|
|
* btl_openib_ib_timeout - The local ACK timeout parameter (defaulted
|
|
to 10). The actual timeout value used is calculated as:
|
|
|
|
4.096 microseconds * (2^btl_openib_ib_timeout)
|
|
|
|
See the InfiniBand spec 1.2 (section 12.7.34) for more details.
|
|
#
|
|
[no active ports found]
|
|
WARNING: There is at least on IB HCA found on host '%s', but there is
|
|
no active ports detected. This is most certainly not what you wanted.
|
|
Check your cables and SM configuration.
|
|
#
|
|
[error in hca init]
|
|
WARNING: There were errors during IB HCA initialization on host '%s'.
|
|
#
|
|
[default subnet prefix]
|
|
WARNING: There are more than one active ports on host '%s', but the
|
|
default subnet GID prefix was detected on more than one of these
|
|
ports. If these ports are connected to different physical IB
|
|
networks, this configuration will fail in Open MPI. This version of
|
|
Open MPI requires that every physically separate IB subnet that is
|
|
used between connected MPI processes must have different subnet ID
|
|
values.
|
|
|
|
Please see this FAQ entry for more details:
|
|
|
|
http://www.open-mpi.org/faq/?category=openfabrics#ofa-default-subnet-gid
|
|
|
|
NOTE: You can turn off this warning by setting the MCA parameter
|
|
btl_openib_warn_default_gid_prefix to 0.
|
|
#
|
|
[ibv_fork requested but not supported]
|
|
WARNING: fork() support was requested for the openib BTL, but it is
|
|
not supported on the host %s. Deactivating the openib BTL.
|
|
#
|
|
[ibv_fork_init fail]
|
|
WARNING: fork() support was requested for the openib BTL, but the
|
|
library call ibv_fork_init() failed on the host %s.
|
|
Deactivating the openib BTL.
|
|
#
|
|
[wrong buffer alignment]
|
|
Wrong buffer alignment %d configured on host '%s'. Should be bigger
|
|
than zero and power of two. Use default %d instead.
|
|
#
|
|
[of error event]
|
|
The OpenFabrics stack has reported a network error event
|
|
Open MPI will try to continue, but your job may end up failing.
|
|
|
|
Host: %s
|
|
MPI process PID: %d
|
|
Error number: %d
|
|
Error description: %s
|
|
|
|
This error may indicate connectivity problems within the fabric;
|
|
please contact your system administrator.
|
|
#
|
|
[of unknown event]
|
|
The OpenFabrics stack has reported an unknown network error event.
|
|
Open MPI will try to continue, but the job may end up failing.
|
|
|
|
Host: %s
|
|
MPI process PID: %d
|
|
Error number: %d
|
|
|
|
This error may indicate that you are using an OpenFabrics library
|
|
version that is not currently supported by Open MPI. You might try
|
|
recompiling Open MPI against your OpenFabrics library installation to
|
|
get more information.
|
|
#
|
|
[specified include and exclude]
|
|
ERROR: You have specified both the btl_openib_if_include and
|
|
btl_openib_if_exclude MCA parameters. These two parameters are
|
|
mutually exclusive; you can only specify one or the other.
|
|
|
|
For reference, the values that you specified are:
|
|
|
|
btl_openib_if_include: %s
|
|
btl_openib_if_exclude: %s
|
|
#
|
|
[nonexistent port]
|
|
WARNING: One or more nonexistent HCAs/ports were specified:
|
|
|
|
Host: %s
|
|
MCA parameter: mca_btl_if_%sclude
|
|
Nonexistent entities: %s
|
|
|
|
These entities will be ignored. You can disable this warning by
|
|
setting the btl_openib_warn_nonexistent_if MCA parameter to 0.
|
|
#
|
|
[invalid mca param value]
|
|
WARNING: the openib BTL detected an illegal MCA parameter value:
|
|
|
|
%s
|
|
%s
|