mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-08 14:02:55 +00:00
53f438a8a8
We use the term "endpoint" in for compute Postgres nodes in the web UI
and user-facing documentation now. Adjust the nomenclature in the code.
This changes the name of the "neon_local pg" command to "neon_local
endpoint". Also adjust names of classes, variables etc. in the python
tests accordingly.
This also changes the directory structure so that endpoints are now
stored in:
.neon/endpoints/<endpoint id>
instead of:
.neon/pgdatadirs/tenants/<tenant_id>/<endpoint (node) name>
The tenant ID is no longer part of the path. That means that you
cannot have two endpoints with the same name/ID in two different
tenants anymore. That's consistent with how we treat endpoints in the
real control plane and proxy: the endpoint ID must be globally unique.
75 lines
2.8 KiB
Python
75 lines
2.8 KiB
Python
from fixtures.log_helper import log
|
|
from fixtures.neon_fixtures import NeonEnvBuilder
|
|
from fixtures.pageserver.utils import assert_tenant_state, wait_until_tenant_active
|
|
from fixtures.types import TenantId, TimelineId
|
|
from fixtures.utils import wait_until
|
|
|
|
|
|
def get_only_element(l): # noqa: E741
|
|
assert len(l) == 1
|
|
return l[0]
|
|
|
|
|
|
# Test that gc and compaction tenant tasks start and stop correctly
|
|
def test_tenant_tasks(neon_env_builder: NeonEnvBuilder):
|
|
name = "test_tenant_tasks"
|
|
env = neon_env_builder.init_start()
|
|
client = env.pageserver.http_client()
|
|
|
|
def get_state(tenant):
|
|
all_states = client.tenant_list()
|
|
matching = [t for t in all_states if TenantId(t["id"]) == tenant]
|
|
return get_only_element(matching)["state"]
|
|
|
|
def delete_all_timelines(tenant: TenantId):
|
|
timelines = [TimelineId(t["timeline_id"]) for t in client.timeline_list(tenant)]
|
|
for t in timelines:
|
|
client.timeline_delete(tenant, t)
|
|
|
|
# Create tenant, start compute
|
|
tenant, _ = env.neon_cli.create_tenant()
|
|
env.neon_cli.create_timeline(name, tenant_id=tenant)
|
|
endpoint = env.endpoints.create_start(name, tenant_id=tenant)
|
|
assert_tenant_state(
|
|
client,
|
|
tenant,
|
|
expected_state="Active",
|
|
message="Pageserver should activate a tenant and start background jobs if timelines are loaded",
|
|
)
|
|
|
|
# Stop compute
|
|
endpoint.stop()
|
|
|
|
# Delete all timelines on all tenants.
|
|
#
|
|
# FIXME: we used to check that the background jobs are stopped when all timelines
|
|
# are removed, but we don't stop them anymore. Not sure if this test still makes sense
|
|
# or we should just remove it.
|
|
for tenant_info in client.tenant_list():
|
|
tenant_id = TenantId(tenant_info["id"])
|
|
delete_all_timelines(tenant_id)
|
|
wait_until_tenant_active(client, tenant_id, iterations=10, period=0.2)
|
|
|
|
# Assert that all tasks finish quickly after tenant is detached
|
|
task_starts = client.get_metric_value("pageserver_tenant_task_events_total", {"event": "start"})
|
|
assert task_starts is not None
|
|
assert int(task_starts) > 0
|
|
client.tenant_detach(tenant)
|
|
client.tenant_detach(env.initial_tenant)
|
|
|
|
def assert_tasks_finish():
|
|
tasks_started = client.get_metric_value(
|
|
"pageserver_tenant_task_events_total", {"event": "start"}
|
|
)
|
|
tasks_ended = client.get_metric_value(
|
|
"pageserver_tenant_task_events_total", {"event": "stop"}
|
|
)
|
|
tasks_panicked = client.get_metric_value(
|
|
"pageserver_tenant_task_events_total", {"event": "panic"}
|
|
)
|
|
log.info(f"started {tasks_started}, ended {tasks_ended}, panicked {tasks_panicked}")
|
|
assert tasks_started == tasks_ended
|
|
assert tasks_panicked is None or int(tasks_panicked) == 0
|
|
|
|
wait_until(10, 0.2, assert_tasks_finish)
|