Skip to content

Commit 915eea2

Browse files
committed
uncomment training log
1 parent bcd8969 commit 915eea2

File tree

2 files changed

+11
-3
lines changed

2 files changed

+11
-3
lines changed

test/dlc_tests/container_tests/bin/efa/testEFA

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -89,7 +89,7 @@ check_efa_nccl_all_reduce(){
8989

9090
RETURN_VAL=${PIPESTATUS[0]}
9191
# In case, if you would like see logs, uncomment below line
92-
# RESULT=$(cat ${TRAINING_LOG})
92+
RESULT=$(cat ${TRAINING_LOG})
9393

9494
if [ ${RETURN_VAL} -eq 0 ]; then
9595
echo "***************************** check_efa_nccl_all_reduce passed *****************************"

test/dlc_tests/ec2/test_efa.py

Lines changed: 10 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -391,11 +391,19 @@ def _create_master_mpi_hosts_file(efa_ec2_connections, worker_instance_ids, inst
391391
)
392392

393393
# TODO: remove logging
394-
LOGGER.info(f"Verifying hosts file {HOSTS_FILE_LOCATION}:")
394+
LOGGER.info(f"Checking if hosts file exists:")
395395
run_cmd_on_container(
396396
MASTER_CONTAINER_NAME,
397397
master_connection,
398-
f"ls -l {HOSTS_FILE_LOCATION} && cat {HOSTS_FILE_LOCATION}",
398+
f"ls -l {HOSTS_FILE_LOCATION}",
399+
hide=False
400+
)
401+
402+
LOGGER.info(f"Checking hosts file contents:")
403+
run_cmd_on_container(
404+
MASTER_CONTAINER_NAME,
405+
master_connection,
406+
f"cat {HOSTS_FILE_LOCATION}",
399407
hide=False
400408
)
401409

0 commit comments

Comments
 (0)