mirror of
https://github.com/neondatabase/neon.git
synced 2025-12-25 15:19:58 +00:00
e3778381a8
## Problem Test deletes tenant and recreates with the same ID. The recreation bumps generation number. This could lead to stale generation warnings in the logs. ## Summary of changes Handle this more gracefully by re-creating in the same generation that the tenant was previously attached in. We could also update the tenant delete path to have the attachment service to drop tenant state on delete, but I like having it there: it makes debug easier, and the only time it's a problem is when a test is re-using a tenant ID after deletion. ## Checklist before requesting a review - [ ] I have performed a self-review of my code. - [ ] If it is a core feature, I have added thorough tests. - [ ] Do we need to implement analytics? if so did you add the relevant metrics to the dashboard? - [ ] If this PR requires public announcement, mark it with /release-notes label and add several sentences in this section. ## Checklist before merging - [ ] Do not forget to reformat commit message to not include the above checklist
79 lines
3.1 KiB
Python
79 lines
3.1 KiB
Python
from contextlib import closing
|
|
|
|
from fixtures.benchmark_fixture import MetricReport
|
|
from fixtures.compare_fixtures import NeonCompare, PgCompare
|
|
from fixtures.pageserver.utils import wait_tenant_status_404
|
|
from fixtures.pg_version import PgVersion
|
|
from fixtures.types import Lsn
|
|
|
|
|
|
#
|
|
# Run bulk INSERT test.
|
|
#
|
|
# Collects metrics:
|
|
#
|
|
# 1. Time to INSERT 5 million rows
|
|
# 2. Disk writes
|
|
# 3. Disk space used
|
|
# 4. Peak memory usage
|
|
#
|
|
def test_bulk_insert(neon_with_baseline: PgCompare):
|
|
env = neon_with_baseline
|
|
|
|
start_lsn = Lsn(env.pg.safe_psql("SELECT pg_current_wal_lsn()")[0][0])
|
|
|
|
with closing(env.pg.connect()) as conn:
|
|
with conn.cursor() as cur:
|
|
cur.execute("create table huge (i int, j int);")
|
|
|
|
# Run INSERT, recording the time and I/O it takes
|
|
with env.record_pageserver_writes("pageserver_writes"):
|
|
with env.record_duration("insert"):
|
|
cur.execute("insert into huge values (generate_series(1, 5000000), 0);")
|
|
env.flush()
|
|
|
|
env.report_peak_memory_use()
|
|
env.report_size()
|
|
|
|
# Report amount of wal written. Useful for comparing vanilla wal format vs
|
|
# neon wal format, measuring neon write amplification, etc.
|
|
end_lsn = Lsn(env.pg.safe_psql("SELECT pg_current_wal_lsn()")[0][0])
|
|
wal_written_bytes = end_lsn - start_lsn
|
|
wal_written_mb = round(wal_written_bytes / (1024 * 1024))
|
|
env.zenbenchmark.record("wal_written", wal_written_mb, "MB", MetricReport.TEST_PARAM)
|
|
|
|
# When testing neon, also check how long it takes the pageserver to reingest the
|
|
# wal from safekeepers. If this number is close to total runtime, then the pageserver
|
|
# is the bottleneck.
|
|
if isinstance(env, NeonCompare):
|
|
measure_recovery_time(env)
|
|
|
|
|
|
def measure_recovery_time(env: NeonCompare):
|
|
client = env.env.pageserver.http_client()
|
|
pg_version = PgVersion(client.timeline_detail(env.tenant, env.timeline)["pg_version"])
|
|
|
|
# Delete the Tenant in the pageserver: this will drop local and remote layers, such that
|
|
# when we "create" the Tenant again, we will replay the WAL from the beginning.
|
|
#
|
|
# This is a "weird" thing to do, and can confuse the attachment service as we're re-using
|
|
# the same tenant ID for a tenant that is logically different from the pageserver's point
|
|
# of view, but the same as far as the safekeeper/WAL is concerned. To work around that,
|
|
# we will explicitly create the tenant in the same generation that it was previously
|
|
# attached in.
|
|
assert env.env.attachment_service is not None
|
|
attach_status = env.env.attachment_service.inspect(tenant_id=env.tenant)
|
|
assert attach_status is not None
|
|
(attach_gen, _) = attach_status
|
|
|
|
client.tenant_delete(env.tenant)
|
|
wait_tenant_status_404(client, env.tenant, iterations=60, interval=0.5)
|
|
env.env.pageserver.tenant_create(tenant_id=env.tenant, generation=attach_gen)
|
|
|
|
# Measure recovery time
|
|
with env.record_duration("wal_recovery"):
|
|
client.timeline_create(pg_version, env.tenant, env.timeline)
|
|
|
|
# Flush, which will also wait for lsn to catch up
|
|
env.flush()
|