00fb8ac048
concurrent crawl limits: (addresses #866) - support limits on concurrent crawls that can be run within a single org - change 'waiting' state to 'waiting_org_limit' for concurrent crawl limit and 'waiting_capacity' for capacity-based limits orgs: - add 'maxConcurrentCrawl' to new 'quotas' object on orgs - add /quotas endpoint for updating quotas object operator: - add all crawljobs as related, appear to be returned in creation order - operator: if concurrent crawl limit set, ensures current job is in the first N set of crawljobs (as provided via 'related' list of crawljob objects) before it can proceed to 'starting', otherwise set to 'waiting_org_limit' - api: add org /quotas endpoint for configuring quotas - remove 'new' state, always start with 'starting' - crawljob: add 'oid' to crawljob spec and label for easier querying - more stringent state transitions: add allowed_from to set_state() - ensure state transitions only happened from allowed states, while failed/canceled can happen from any state - ensure finished and state synched from db if transition not allowed - add crawl indices by oid and cid frontend: - show different waiting states on frontend: 'Waiting (Crawl Limit) and 'Waiting (At Capacity)' - add gear icon on orgs admin page - and initial popup for setting org quotas, showing all properties from org 'quotas' object tests: - add concurrent crawl limit nightly tests - fix state waiting -> waiting_capacity - ci: add logging of operator output on test failure
108 lines
2.7 KiB
Python
108 lines
2.7 KiB
Python
import requests
|
|
import time
|
|
|
|
from .conftest import API_PREFIX
|
|
|
|
crawl_id_a = None
|
|
crawl_id_b = None
|
|
|
|
|
|
def test_set_concurrent_crawl_limit(org_with_quotas, admin_auth_headers):
|
|
r = requests.post(
|
|
f"{API_PREFIX}/orgs/{org_with_quotas}/quotas",
|
|
headers=admin_auth_headers,
|
|
json={"maxConcurrentCrawls": 1},
|
|
)
|
|
data = r.json()
|
|
assert data.get("updated") == True
|
|
|
|
|
|
def test_run_two_only_one_concurrent(org_with_quotas, admin_auth_headers):
|
|
global crawl_id_a
|
|
crawl_id_a = run_crawl(org_with_quotas, admin_auth_headers)
|
|
time.sleep(1)
|
|
|
|
global crawl_id_b
|
|
crawl_id_b = run_crawl(org_with_quotas, admin_auth_headers)
|
|
|
|
while (
|
|
get_crawl_status(org_with_quotas, crawl_id_a, admin_auth_headers) == "starting"
|
|
):
|
|
time.sleep(2)
|
|
|
|
assert (
|
|
get_crawl_status(org_with_quotas, crawl_id_a, admin_auth_headers) == "running"
|
|
)
|
|
|
|
while (
|
|
get_crawl_status(org_with_quotas, crawl_id_b, admin_auth_headers) == "starting"
|
|
):
|
|
time.sleep(2)
|
|
|
|
assert (
|
|
get_crawl_status(org_with_quotas, crawl_id_b, admin_auth_headers)
|
|
== "waiting_org_limit"
|
|
)
|
|
|
|
|
|
def test_cancel_and_run_other(org_with_quotas, admin_auth_headers):
|
|
r = requests.post(
|
|
f"{API_PREFIX}/orgs/{org_with_quotas}/crawls/{crawl_id_a}/cancel",
|
|
headers=admin_auth_headers,
|
|
)
|
|
data = r.json()
|
|
assert data["success"] == True
|
|
|
|
while (
|
|
get_crawl_status(org_with_quotas, crawl_id_a, admin_auth_headers) != "canceled"
|
|
):
|
|
time.sleep(2)
|
|
|
|
while (
|
|
get_crawl_status(org_with_quotas, crawl_id_b, admin_auth_headers)
|
|
== "waiting_org_limit"
|
|
):
|
|
time.sleep(5)
|
|
|
|
assert get_crawl_status(org_with_quotas, crawl_id_b, admin_auth_headers) in (
|
|
"starting",
|
|
"running",
|
|
)
|
|
|
|
# cancel second crawl as well
|
|
r = requests.post(
|
|
f"{API_PREFIX}/orgs/{org_with_quotas}/crawls/{crawl_id_b}/cancel",
|
|
headers=admin_auth_headers,
|
|
)
|
|
data = r.json()
|
|
assert data["success"] == True
|
|
|
|
|
|
def run_crawl(org_id, headers):
|
|
crawl_data = {
|
|
"runNow": True,
|
|
"name": "Concurrent Crawl",
|
|
"config": {
|
|
"seeds": [{"url": "https://specs.webrecorder.net/"}],
|
|
"limit": 1,
|
|
},
|
|
}
|
|
r = requests.post(
|
|
f"{API_PREFIX}/orgs/{org_id}/crawlconfigs/",
|
|
headers=headers,
|
|
json=crawl_data,
|
|
)
|
|
data = r.json()
|
|
|
|
return data["run_now_job"]
|
|
|
|
|
|
def get_crawl_status(org_id, crawl_id, headers):
|
|
while True:
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{org_id}/crawls/{crawl_id}/replay.json",
|
|
headers=headers,
|
|
)
|
|
data = r.json()
|
|
return data["state"]
|