rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2026-05-30 19:40:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into yuchen/scrubber-scan-cleanup-before-prod

Browse Source
This commit is contained in:
Yuchen Liang
2024-08-02 09:53:20 -04:00
committed by GitHub
parent f8a727ac47 8c828c586e
commit b2ea4bb366
54 changed files with 3749 additions and 903 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
test_runner/regress/test_branching.py
View File

@@ -18,7 +18,6 @@ from fixtures.pageserver.utils import wait_until_tenant_active
from fixtures.utils import query_scalar
from performance.test_perf_pgbench import get_scales_matrix
from requests import RequestException
from requests.exceptions import RetryError
# Test branch creation
@@ -151,7 +150,7 @@ def test_cannot_create_endpoint_on_non_uploaded_timeline(neon_env_builder: NeonE
env.pageserver.allowed_errors.extend(
[
".*request{method=POST path=/v1/tenant/.*/timeline request_id=.*}: request was dropped before completing.*",
".*page_service_conn_main.*: query handler for 'basebackup .* is not active, state: Loading",
".*page_service_conn_main.*: query handler for 'basebackup .* ERROR: Not found: Timeline",
]
)
ps_http = env.pageserver.http_client()
@@ -176,10 +175,12 @@ def test_cannot_create_endpoint_on_non_uploaded_timeline(neon_env_builder: NeonE
env.neon_cli.map_branch(initial_branch, env.initial_tenant, env.initial_timeline)
with pytest.raises(RuntimeError, match="is not active, state: Loading"):
env.endpoints.create_start(initial_branch, tenant_id=env.initial_tenant)
with pytest.raises(RuntimeError, match="ERROR: Not found: Timeline"):
env.endpoints.create_start(
initial_branch, tenant_id=env.initial_tenant, basebackup_request_tries=2
)
ps_http.configure_failpoints(("before-upload-index-pausable", "off"))
finally:
# FIXME: paused uploads bother shutdown
env.pageserver.stop(immediate=True)
t.join()
@@ -193,8 +194,11 @@ def test_cannot_branch_from_non_uploaded_branch(neon_env_builder: NeonEnvBuilder
env = neon_env_builder.init_configs()
env.start()
env.pageserver.allowed_errors.append(
".*request{method=POST path=/v1/tenant/.*/timeline request_id=.*}: request was dropped before completing.*"
env.pageserver.allowed_errors.extend(
[
".*request{method=POST path=/v1/tenant/.*/timeline request_id=.*}: request was dropped before completing.*",
".*request{method=POST path=/v1/tenant/.*/timeline request_id=.*}: .*Cannot branch off the timeline that's not present in pageserver.*",
]
)
ps_http = env.pageserver.http_client()
@@ -216,7 +220,10 @@ def test_cannot_branch_from_non_uploaded_branch(neon_env_builder: NeonEnvBuilder
branch_id = TimelineId.generate()
with pytest.raises(RetryError, match="too many 503 error responses"):
with pytest.raises(
PageserverApiException,
match="Cannot branch off the timeline that's not present in pageserver",
):
ps_http.timeline_create(
env.pg_version,
env.initial_tenant,

87
test_runner/regress/test_remote_storage.py
View File

@@ -12,7 +12,6 @@ from fixtures.neon_fixtures import (
NeonEnvBuilder,
wait_for_last_flush_lsn,
)
from fixtures.pageserver.common_types import parse_layer_file_name
from fixtures.pageserver.http import PageserverApiException, PageserverHttpClient
from fixtures.pageserver.utils import (
timeline_delete_wait_completed,
@@ -313,6 +312,7 @@ def test_remote_storage_upload_queue_retries(
def churn_while_failpoints_active(result):
overwrite_data_and_wait_for_it_to_arrive_at_pageserver("c")
# this call will wait for the failpoints to be turned off
client.timeline_checkpoint(tenant_id, timeline_id)
client.timeline_compact(tenant_id, timeline_id)
overwrite_data_and_wait_for_it_to_arrive_at_pageserver("d")
@@ -332,8 +332,8 @@ def test_remote_storage_upload_queue_retries(
# Exponential back-off in upload queue, so, gracious timeouts.
wait_until(30, 1, lambda: assert_gt(get_queued_count(file_kind="layer", op_kind="upload"), 0))
wait_until(30, 1, lambda: assert_ge(get_queued_count(file_kind="index", op_kind="upload"), 2))
wait_until(30, 1, lambda: assert_gt(get_queued_count(file_kind="layer", op_kind="delete"), 0))
wait_until(30, 1, lambda: assert_ge(get_queued_count(file_kind="index", op_kind="upload"), 1))
wait_until(30, 1, lambda: assert_eq(get_queued_count(file_kind="layer", op_kind="delete"), 0))
# unblock churn operations
configure_storage_sync_failpoints("off")
@@ -769,11 +769,11 @@ def test_empty_branch_remote_storage_upload_on_restart(neon_env_builder: NeonEnv
create_thread.join()
def test_compaction_waits_for_upload(
def test_paused_upload_stalls_checkpoint(
neon_env_builder: NeonEnvBuilder,
):
"""
This test forces a race between upload and compaction.
This test checks that checkpoints block on uploads to remote storage.
"""
neon_env_builder.enable_pageserver_remote_storage(RemoteStorageKind.LOCAL_FS)
@@ -788,6 +788,10 @@ def test_compaction_waits_for_upload(
}
)
env.pageserver.allowed_errors.append(
f".*PUT.* path=/v1/tenant/{env.initial_tenant}/timeline.* request was dropped before completing"
)
tenant_id = env.initial_tenant
timeline_id = env.initial_timeline
@@ -808,76 +812,9 @@ def test_compaction_waits_for_upload(
endpoint.safe_psql("CREATE TABLE foo AS SELECT x FROM generate_series(1, 10000) g(x)")
wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
client.timeline_checkpoint(tenant_id, timeline_id)
deltas_at_first = len(client.layer_map_info(tenant_id, timeline_id).delta_layers())
assert (
deltas_at_first == 2
), "are you fixing #5863? just add one more checkpoint after 'CREATE TABLE bar ...' statement."
endpoint.safe_psql("CREATE TABLE bar AS SELECT x FROM generate_series(1, 10000) g(x)")
endpoint.safe_psql("UPDATE foo SET x = 0 WHERE x = 1")
wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
layers_before_last_checkpoint = client.layer_map_info(tenant_id, timeline_id).historic_by_name()
upload_stuck_layers = layers_before_last_checkpoint - layers_at_creation.historic_by_name()
assert len(upload_stuck_layers) > 0
for name in upload_stuck_layers:
assert env.pageserver.layer_exists(
tenant_id, timeline_id, parse_layer_file_name(name)
), "while uploads are stuck the layers should be present on disk"
# now this will do the L0 => L1 compaction and want to remove
# upload_stuck_layers and the original initdb L0
client.timeline_checkpoint(tenant_id, timeline_id)
# as uploads are paused, the upload_stuck_layers should still be with us
for name in upload_stuck_layers:
assert env.pageserver.layer_exists(
tenant_id, timeline_id, parse_layer_file_name(name)
), "uploads are stuck still over compaction"
compacted_layers = client.layer_map_info(tenant_id, timeline_id).historic_by_name()
overlap = compacted_layers.intersection(upload_stuck_layers)
assert len(overlap) == 0, "none of the L0's should remain after L0 => L1 compaction"
assert (
len(compacted_layers) == 1
), "there should be one L1 after L0 => L1 compaction (without #5863 being fixed)"
def layer_deletes_completed():
m = client.get_metric_value("pageserver_layer_completed_deletes_total")
if m is None:
return 0
return int(m)
# if initdb created an initial delta layer, it might already be gc'd
# because it was uploaded before the failpoint was enabled. however, the
# deletion is not guaranteed to be complete.
assert layer_deletes_completed() <= 1
client.configure_failpoints(("before-upload-layer-pausable", "off"))
# Ensure that this actually terminates
wait_upload_queue_empty(client, tenant_id, timeline_id)
def until_layer_deletes_completed():
deletes = layer_deletes_completed()
log.info(f"layer_deletes: {deletes}")
# ensure that initdb delta layer AND the previously stuck are now deleted
assert deletes >= len(upload_stuck_layers) + 1
wait_until(10, 1, until_layer_deletes_completed)
for name in upload_stuck_layers:
assert not env.pageserver.layer_exists(
tenant_id, timeline_id, parse_layer_file_name(name)
), "l0 should now be removed because of L0 => L1 compaction and completed uploads"
# We should not have hit the error handling path in uploads where a uploaded file is gone
assert not env.pageserver.log_contains(
"File to upload doesn't exist. Likely the file has been deleted and an upload is not required any more."
)
with pytest.raises(ReadTimeout):
client.timeline_checkpoint(tenant_id, timeline_id, timeout=5)
client.configure_failpoints(("before-upload-layer-pausable", "off"))
def wait_upload_queue_empty(

78
test_runner/regress/test_storage_scrubber.py
View File

@@ -13,6 +13,7 @@ from fixtures.neon_fixtures import (
NeonEnv,
NeonEnvBuilder,
)
from fixtures.pg_version import PgVersion
from fixtures.remote_storage import S3Storage, s3_storage
from fixtures.utils import wait_until
from fixtures.workload import Workload
@@ -265,10 +266,85 @@ def test_scrubber_physical_gc_ancestors(
# attach it, to drop any local state, then check it's still readable.
workload.stop()
drop_local_state(env, tenant_id)
workload.validate()
def test_scrubber_physical_gc_timeline_deletion(neon_env_builder: NeonEnvBuilder):
"""
When we delete a timeline after a shard split, the child shards do not directly delete the
layers in the ancestor shards. They rely on the scrubber to clean up.
"""
neon_env_builder.enable_pageserver_remote_storage(s3_storage())
neon_env_builder.num_pageservers = 2
env = neon_env_builder.init_configs()
env.start()
tenant_id = TenantId.generate()
timeline_id = TimelineId.generate()
env.neon_cli.create_tenant(
tenant_id,
timeline_id,
shard_count=None,
conf={
# Small layers and low compaction thresholds, so that when we split we can expect some to
# be dropped by child shards
"checkpoint_distance": f"{1024 * 1024}",
"compaction_threshold": "1",
"compaction_target_size": f"{1024 * 1024}",
"image_creation_threshold": "2",
"image_layer_creation_check_threshold": "0",
# Disable background compaction, we will do it explicitly
"compaction_period": "0s",
# No PITR, so that as soon as child shards generate an image layer, it covers ancestor deltas
# and makes them GC'able
"pitr_interval": "0s",
},
)
# Make sure the original shard has some layers
workload = Workload(env, tenant_id, timeline_id)
workload.init()
workload.write_rows(100)
new_shard_count = 4
shards = env.storage_controller.tenant_shard_split(tenant_id, shard_count=new_shard_count)
# Create a second timeline so that when we delete the first one, child shards still have some content in S3.
#
# This is a limitation of the scrubber: if a shard isn't in S3 (because it has no timelines), then the scrubber
# doesn't know about it, and won't perceive its ancestors as ancestors.
other_timeline_id = TimelineId.generate()
env.storage_controller.pageserver_api().timeline_create(
PgVersion.NOT_SET, tenant_id, other_timeline_id
)
# Write after split so that child shards have some indices in S3
workload.write_rows(100, upload=False)
for shard in shards:
ps = env.get_tenant_pageserver(shard)
log.info(f"Waiting for shard {shard} on pageserver {ps.id}")
ps.http_client().timeline_checkpoint(
shard, timeline_id, compact=False, wait_until_uploaded=True
)
# The timeline still exists in child shards and they reference its layers, so scrubbing
# now shouldn't delete anything.
gc_summary = env.storage_scrubber.pageserver_physical_gc(min_age_secs=0, mode="full")
assert gc_summary["remote_storage_errors"] == 0
assert gc_summary["indices_deleted"] == 0
assert gc_summary["ancestor_layers_deleted"] == 0
# Delete the timeline
env.storage_controller.pageserver_api().timeline_delete(tenant_id, timeline_id)
# Subsequently doing physical GC should clean up the ancestor layers
gc_summary = env.storage_scrubber.pageserver_physical_gc(min_age_secs=0, mode="full")
assert gc_summary["remote_storage_errors"] == 0
assert gc_summary["indices_deleted"] == 0
assert gc_summary["ancestor_layers_deleted"] > 0
def test_scrubber_physical_gc_ancestors_split(neon_env_builder: NeonEnvBuilder):
"""
Exercise ancestor GC while a tenant is partly split: this test ensures that if we have some child shards