Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Active messenger fails when sending over 2 GiB of data due to MPI limitations #1111

Closed
lifflander opened this issue Oct 13, 2020 · 1 comment · Fixed by #1113
Closed

Active messenger fails when sending over 2 GiB of data due to MPI limitations #1111

lifflander opened this issue Oct 13, 2020 · 1 comment · Fixed by #1113
Assignees
@lifflander
Labels
1.0.0-beta.10.3 type: bug

Comments

@lifflander
Copy link
Collaborator

Describe the bug
Due to limitations in MPI, the code fails when sending a single payload over 2 GiB due to overflow.
@lifflander lifflander self-assigned this Oct 13, 2020
lifflander added a commit that referenced this issue Oct 13, 2020
@lifflander
#1111: tests: write test for large message sends
224c2c1
@lifflander lifflander mentioned this issue Oct 14, 2020
Merged
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: tests: split into two sets of types for clarity without string
299c431
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: cmake: import new GoogleTest*cmake w/3.18 and **fix bugs**
3c43914 
There is a major bug in the cmake googletest filter generation for
type-parameterized tests! This is causing some of our tests to never
run...including the ones that I just wrote which should always fail
without the associated fix.

Fix the regular expressions to generate a proper ctest filter that
will actually run *every* test
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: cmake: remove debugging print
ad77334
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: tests: limit to 2 nodes and less max memory
8a53a88
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: config: expand MsgSizeType to 64 bits
22d60ab
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: active: create function for allocating MPI tags
45f7b41
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: active: allow in-progress irecv to not pass request
bcddb8a
lifflander added a commit that referenced this issue Oct 14, 2020
@lifflander
#1111: active: implement multiple sends/recvs when larger some size
74e3eb7
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: tests: reduce size for serialized test also to fit in memory
a8c664f
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: active: implement cohesive solution for multi-chunk data sends
ce04d36
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: rdma/serial: adjust APIs to work with new AM sendData/recvData
16f1b6e
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: tests: assert that data matches on other end
04d7e93
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: tests: fix a test failure exposed by gtest fixes
6e40b2c
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: active: fix bug in trace build
0973c7b
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: active: return event and fix managed msg bug
ea5ca54
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: tests: fix location bug revealed from actually running test
87d5d2e
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: rdma: fix missing allow MPI calls causing test failure
a6bef90
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: tests: fix bug introduced by refactoring
40e207e
lifflander added a commit that referenced this issue Oct 16, 2020
@lifflander
#1111: active: fix another compile-time tracing bug
0bed983
lifflander added a commit that referenced this issue Oct 20, 2020
@lifflander
#1111: tests: write test for large message sends
995093e
lifflander added a commit that referenced this issue Oct 20, 2020
@lifflander
#1111: tests: split into two sets of types for clarity without string
905919d
lifflander added a commit that referenced this issue Oct 20, 2020
@lifflander
#1111: cmake: import new GoogleTest*cmake w/3.18 and **fix bugs**
ecee18a 
There is a major bug in the cmake googletest filter generation for
type-parameterized tests! This is causing some of our tests to never
run...including the ones that I just wrote which should always fail
without the associated fix.

Fix the regular expressions to generate a proper ctest filter that
will actually run *every* test
lifflander added a commit that referenced this issue Oct 20, 2020
@lifflander
#1111: cmake: remove debugging print
a250bc1
lifflander added a commit that referenced this issue Oct 20, 2020
@lifflander
#1111: tests: limit to 2 nodes and less max memory
cac8f9d
lifflander added a commit that referenced this issue Nov 13, 2020
@lifflander
#1111: tests: work around test compile failure w/nvidia
4003573
lifflander added a commit that referenced this issue Nov 13, 2020
@lifflander
#1111: active: improve spacing and comments for clarity
cd98980
lifflander added a commit that referenced this issue Nov 13, 2020
@lifflander
#1111: active: make allow-mpi calls tigher in blocks
90c9305
lifflander added a commit that referenced this issue Dec 16, 2020
@lifflander
#1111: active: implment fixes for large message sends
8c4677c
@lifflander
Copy link
Collaborator Author

for release, branch 1111-try-port-to-release is squashed and rebased on 1.0.0

cz4rs pushed a commit that referenced this issue Dec 21, 2020
@lifflander @cz4rs
#1111: active: implment fixes for large message sends
a9a551c
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: active: fix argument handling
afff29e
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: active: backport memory units
390e7ed
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: fix argument handling
06e2707
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: memory units
719edba
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: fix sendMsg call
f4d1f51
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: remove redundant braces
34c337d
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: skip diagnostic
ee68ab5
cz4rs pushed a commit that referenced this issue Dec 21, 2020
@lifflander @cz4rs
#1111: active: implment fixes for large message sends
6c04ed2
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: fix argument handling
3d70940
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: memory units
86a80d1
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: fix sendMsg calls
e7870c5
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: remove redundant braces
518d53d
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: skip diagnostic
936dcf5
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: test: implement addAdditionalArgs
065bf8a
@cz4rs cz4rs mentioned this issue Dec 21, 2020
Merged
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: fix configuration handling
22ab8e5
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: memory units
81241fc
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: fix sendMsg calls
daea467
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: remove redundant braces
881e3aa
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: skip diagnostic
3036beb
cz4rs added a commit that referenced this issue Dec 21, 2020
@cz4rs
#1111: backport: test: implement addAdditionalArgs
dde46c1
cz4rs added a commit that referenced this issue Jan 5, 2021
@cz4rs
#1111: backport: remove merge leftover
fc0e51b
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@lifflander lifflander

Labels
1.0.0-beta.10.3 type: bug
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

1111 Fix for large message sends DARMA-tasking/vt
1 participant
@lifflander