Skip to content

Commit

Permalink
Intel/CI: Enable Previously Failing tests on CI.
Browse files Browse the repository at this point in the history
- added env variable HYDRA_LAUNCHER=fork to test env
  instead of default launcher srun in order to prevent hangs
  in spawn tests.This also helped in fixing hang issues in
  other tests.
- enabled spawn, threads/spawn, errors/spawn for tcp and verbs.
- enabled threads/comm/idup_comm_gen and idup_nb for tcp
- enabled threads/pt2pt/mt_improbe_sendrecv_huge for verbs.
- increased time limit on sbatch timeout as overall PR times increased due to newly added tests.

Signed-off-by: Nikhil Nanal <[email protected]>
  • Loading branch information
nikhilnanal authored and zachdworkin committed Dec 6, 2023
1 parent 4b25d7b commit 7e47412
Show file tree
Hide file tree
Showing 2 changed files with 9 additions and 18 deletions.
2 changes: 1 addition & 1 deletion contrib/intel/jenkins/Jenkinsfile
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ properties([disableConcurrentBuilds(abortPrevious: true)])
@Field def RELEASE=false
@Field def BUILD_MODES=["reg", "dbg", "dl"]
@Field def PYTHON_VERSION="3.9"
@Field def TIMEOUT="3600"
@Field def TIMEOUT="7200"

def run_python(version, command, output=null) {
if (output != null)
Expand Down
25 changes: 8 additions & 17 deletions contrib/intel/jenkins/tests.py
Original file line number Diff line number Diff line change
Expand Up @@ -450,6 +450,7 @@ def env(self):
else:
cmd += f"export FI_PROVIDER={self.core_prov}; "
cmd += "export I_MPI_FABRICS=ofi; "
cmd += "export HYDRA_LAUNCHER=fork;"
cmd += "export MPIR_CVAR_CH4_OFI_ENABLE_ATOMICS=0; "
cmd += "export MPIR_CVAR_CH4_OFI_CAPABILITY_SETS_DEBUG=0; "
cmd += f"export LD_LIBRARY_PATH={self.mpich_dir}/lib:$LD_LIBRARY_PATH; "
Expand Down Expand Up @@ -688,23 +689,13 @@ def __init__(self, jobname, buildno, testname, core_prov, fabric,
self.pwd = os.getcwd()
self.weekly = weekly
self.mpichtests_exclude = {
'tcp' : { '.' : [('spawn','dir')],
'rma' : [('win_shared_put_flush_load 3', 'test')],
'threads' : [('spawn','dir')],
'threads/comm' : [('idup_nb 4','test'),
('idup_comm_gen 4','test')],
'errors' : [('spawn','dir')]
},
'verbs' : { '.' : [('spawn','dir')],
'threads/comm' : [('idup_nb 4','test')],
'threads' : [('spawn','dir'), ('rma','dir')],
'pt2pt' : [('sendrecv3 2','test'),
('sendrecv3 2 arg=-isendrecv','test')],
'threads/pt2pt': [(f"mt_improbe_sendrecv_huge 2 "
f"arg=-iter=64 arg=-count=4194304 "
f"env=MPIR_CVAR_CH4_OFI_EAGER_MAX_MSG_SIZE"
f"=16384", 'test')]
}
'tcp' : { 'rma' : [('win_shared_put_flush_load 3', 'test')]
},
'verbs' : { 'threads/comm' : [('idup_nb 4','test')],
'spawn' : [('concurrent_spawns 1', 'test')],
'pt2pt' : [('sendrecv3 2','test'),
('sendrecv3 2 arg=-isendrecv','test')],
}
}

def create_hostfile(self, file, hostlist):
Expand Down

0 comments on commit 7e47412

Please sign in to comment.