Add a web dashboard for monitoring node resource usage (#4066)

This commit is contained in:
Daniel Edgecumbe
2019-02-21 00:10:04 -08:00
committed by Robert Nishihara
parent 3ac8fd7ee8
commit 2e30f7ba38
13 changed files with 1239 additions and 44 deletions
+14 -12
View File
@@ -1,3 +1,7 @@
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import shutil
import time
@@ -67,15 +71,14 @@ def test_raylet_tempfiles():
ray.init(num_cpus=0)
node = ray.worker._global_node
top_levels = set(os.listdir(node.get_temp_dir_path()))
assert top_levels == {"ray_ui.ipynb", "sockets", "logs"}
assert top_levels.issuperset({"sockets", "logs"})
log_files = set(os.listdir(node.get_logs_dir_path()))
assert log_files == {
assert log_files.issuperset({
"log_monitor.out", "log_monitor.err", "plasma_store.out",
"plasma_store.err", "webui.out", "webui.err", "monitor.out",
"monitor.err", "raylet_monitor.out", "raylet_monitor.err",
"redis-shard_0.out", "redis-shard_0.err", "redis.out", "redis.err",
"raylet.out", "raylet.err"
} # with raylet logs
"plasma_store.err", "monitor.out", "monitor.err", "raylet_monitor.out",
"raylet_monitor.err", "redis-shard_0.out", "redis-shard_0.err",
"redis.out", "redis.err", "raylet.out", "raylet.err"
}) # with raylet logs
socket_files = set(os.listdir(node.get_sockets_dir_path()))
assert socket_files == {"plasma_store", "raylet"}
ray.shutdown()
@@ -83,15 +86,14 @@ def test_raylet_tempfiles():
ray.init(num_cpus=2)
node = ray.worker._global_node
top_levels = set(os.listdir(node.get_temp_dir_path()))
assert top_levels == {"ray_ui.ipynb", "sockets", "logs"}
assert top_levels.issuperset({"sockets", "logs"})
time.sleep(3) # wait workers to start
log_files = set(os.listdir(node.get_logs_dir_path()))
assert log_files.issuperset({
"log_monitor.out", "log_monitor.err", "plasma_store.out",
"plasma_store.err", "webui.out", "webui.err", "monitor.out",
"monitor.err", "raylet_monitor.out", "raylet_monitor.err",
"redis-shard_0.out", "redis-shard_0.err", "redis.out", "redis.err",
"raylet.out", "raylet.err"
"plasma_store.err", "monitor.out", "monitor.err", "raylet_monitor.out",
"raylet_monitor.err", "redis-shard_0.out", "redis-shard_0.err",
"redis.out", "redis.err", "raylet.out", "raylet.err"
}) # with raylet logs
# Check numbers of worker log file.