mirror of
https://github.com/vale981/ray
synced 2025-03-06 02:21:39 -05:00
[Test] Migrate the first test to the new infra (#22770)
This migrate the simplest nightly test to the new infra. I will also explore k8s migration with this test
This commit is contained in:
parent
2490b3e383
commit
9d0148dbbe
4 changed files with 33 additions and 18 deletions
|
@ -3,15 +3,15 @@
|
||||||
#
|
#
|
||||||
# Test basic single node 10GB shuffle with a small number of partitions.
|
# Test basic single node 10GB shuffle with a small number of partitions.
|
||||||
# This doesn't require object spilling.
|
# This doesn't require object spilling.
|
||||||
- name: shuffle_10gb
|
# - name: shuffle_10gb
|
||||||
team: core
|
# team: core
|
||||||
cluster:
|
# cluster:
|
||||||
app_config: shuffle/shuffle_app_config.yaml
|
# app_config: shuffle/shuffle_app_config.yaml
|
||||||
compute_template: shuffle/shuffle_compute_single.yaml
|
# compute_template: shuffle/shuffle_compute_single.yaml
|
||||||
|
|
||||||
run:
|
# run:
|
||||||
timeout: 3000
|
# timeout: 3000
|
||||||
script: python shuffle/shuffle_test.py --num-partitions=50 --partition-size=200e6
|
# script: python shuffle/shuffle_test.py --num-partitions=50 --partition-size=200e6
|
||||||
|
|
||||||
# Test single node 50GB shuffle with a large number of partitions.
|
# Test single node 50GB shuffle with a large number of partitions.
|
||||||
- name: shuffle_50gb
|
- name: shuffle_50gb
|
||||||
|
|
|
@ -26,15 +26,6 @@ start = time.time()
|
||||||
next_feedback = start
|
next_feedback = start
|
||||||
max_time = start + args.max_time_s
|
max_time = start + args.max_time_s
|
||||||
|
|
||||||
|
|
||||||
def num_alive_nodes():
|
|
||||||
n = 0
|
|
||||||
for node in ray.nodes():
|
|
||||||
if node.get("Alive", False):
|
|
||||||
n += 1
|
|
||||||
return n
|
|
||||||
|
|
||||||
|
|
||||||
while not curr_nodes >= args.num_nodes:
|
while not curr_nodes >= args.num_nodes:
|
||||||
now = time.time()
|
now = time.time()
|
||||||
|
|
||||||
|
@ -54,7 +45,7 @@ while not curr_nodes >= args.num_nodes:
|
||||||
next_feedback = now + args.feedback_interval_s
|
next_feedback = now + args.feedback_interval_s
|
||||||
|
|
||||||
time.sleep(5)
|
time.sleep(5)
|
||||||
curr_nodes = num_alive_nodes()
|
curr_nodes = len(ray.nodes())
|
||||||
|
|
||||||
passed = time.time() - start
|
passed = time.time() - start
|
||||||
print(
|
print(
|
||||||
|
|
|
@ -25,6 +25,7 @@ curr_nodes = 0
|
||||||
start = time.time()
|
start = time.time()
|
||||||
next_feedback = start
|
next_feedback = start
|
||||||
max_time = start + args.max_time_s
|
max_time = start + args.max_time_s
|
||||||
|
|
||||||
while not curr_nodes >= args.num_nodes:
|
while not curr_nodes >= args.num_nodes:
|
||||||
now = time.time()
|
now = time.time()
|
||||||
|
|
||||||
|
|
|
@ -761,3 +761,26 @@
|
||||||
|
|
||||||
alert: tune_tests
|
alert: tune_tests
|
||||||
|
|
||||||
|
########################
|
||||||
|
# Core Nightly Tests
|
||||||
|
########################
|
||||||
|
|
||||||
|
- name: shuffle_10gb
|
||||||
|
group: Core nightly tests
|
||||||
|
team: core
|
||||||
|
working_dir: nightly_tests
|
||||||
|
|
||||||
|
legacy:
|
||||||
|
test_name: shuffle_10gb
|
||||||
|
test_suite: nightly_tests
|
||||||
|
|
||||||
|
cluster:
|
||||||
|
cluster_env: shuffle/shuffle_app_config.yaml
|
||||||
|
cluster_compute: shuffle/shuffle_compute_single.yaml
|
||||||
|
|
||||||
|
run:
|
||||||
|
timeout: 3000
|
||||||
|
script: python shuffle/shuffle_test.py --num-partitions=50 --partition-size=200e6
|
||||||
|
|
||||||
|
type: sdk_command
|
||||||
|
file_manager: sdk
|
||||||
|
|
Loading…
Add table
Reference in a new issue