Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(scan_operations): add retry policy to cql query #9600

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix(scan_operations): add retry policy to cql query #9600

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
737d3bb
fix(scan_operations): add retry policy to cql query
aleksbykov Dec 20, 2024
b27d808
revert(yaml): add parameters
aleksbykov Dec 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions sdcm/scan_operation_thread.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
from cassandra import ConsistencyLevel, OperationTimedOut, ReadTimeout
from cassandra.cluster import ResponseFuture, ResultSet # pylint: disable=no-name-in-module
from cassandra.query import SimpleStatement # pylint: disable=no-name-in-module
from cassandra.policies import ExponentialBackoffRetryPolicy

from sdcm.remote import LocalCmdRunner
from sdcm.sct_events import Severity
Expand Down Expand Up @@ -106,6 +107,10 @@ def __init__(self, generator: random.Random, thread_params: ThreadParams, thread
self.db_node = self._get_random_node()
self.current_operation_stat = None
self.log.info("FullscanOperationBase init finished")
self._exp_backoff_retry_policy_params = {
"max_num_retries": 15.0, "min_interval": 1.0, "max_interval": 1800.0
}
self._request_default_timeout = 1800

def _get_random_node(self) -> BaseNode:
return self.generator.choice(self.fullscan_params.db_cluster.data_nodes)
Expand All @@ -120,6 +125,8 @@ def execute_query(
| FullPartitionScanReversedOrderEvent]) -> ResultSet:
# pylint: disable=unused-argument
self.log.debug('Will run command %s', cmd)
session.cluster.default_retry_policy = ExponentialBackoffRetryPolicy(**self._exp_backoff_retry_policy_params)
Copy link
Contributor

@fruch fruch Dec 23, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is a bit weird it comes next to the code executing the query, and no the code creating the session.

I would recommend consolidating the session creating code into something like:

@property
def cql_connection(self, **kwargs):
    with self.fullscan_params.db_cluster.cql_connection_patient(
                    node=self.db_node,
                    user=self.fullscan_params.user,
                    password=self.fullscan_params.user_password, **kwargs) as session:
        session.cluster.default_retry_policy = ExponentialBackoffRetryPolicy(**self._exp_backoff_retry_policy_params)
        session.default_timeout = self._request_default_timeout
        yield session

there way too many repetitions of applying this retry, and it should be across the board for all of the sessions.

session.default_timeout = self._request_default_timeout
return session.execute(SimpleStatement(
cmd,
fetch_size=self.fullscan_params.page_size,
Expand Down Expand Up @@ -242,6 +249,8 @@ def get_table_clustering_order(self) -> str:
with self.fullscan_params.db_cluster.cql_connection_patient(node=node, connect_timeout=300) as session:
# Using CL ONE. No need for a quorum since querying a constant fixed attribute of a table.
session.default_consistency_level = ConsistencyLevel.ONE
session.cluster.default_retry_policy = ExponentialBackoffRetryPolicy(
**self._exp_backoff_retry_policy_params)
return get_table_clustering_order(ks_cf=self.fullscan_params.ks_cf,
ck_name=self.fullscan_params.ck_name, session=session)
except Exception as error: # pylint: disable=broad-except # noqa: BLE001
Expand All @@ -266,6 +275,8 @@ def randomly_form_cql_statement(self) -> Optional[tuple[str, str]]: # pylint: d

with self.fullscan_params.db_cluster.cql_connection_patient(
node=db_node, connect_timeout=300) as session:
session.cluster.default_retry_policy = ExponentialBackoffRetryPolicy(
**self._exp_backoff_retry_policy_params)
ck_random_min_value = self.generator.randint(a=1, b=self.fullscan_params.rows_count)
ck_random_max_value = self.generator.randint(a=ck_random_min_value, b=self.fullscan_params.rows_count)
self.ck_filter = ck_filter = self.generator.choice(list(self.reversed_query_filter_ck_by.keys()))
Expand Down Expand Up @@ -351,6 +362,9 @@ def execute_query(
self.log.debug('Will run command "%s"', cmd)
session.default_fetch_size = self.fullscan_params.page_size
session.default_consistency_level = ConsistencyLevel.ONE
session.cluster.default_retry_policy = ExponentialBackoffRetryPolicy(**self._exp_backoff_retry_policy_params)
session.default_timeout = self._request_default_timeout

return session.execute_async(cmd)

def reset_output_files(self):
Expand Down Expand Up @@ -460,6 +474,9 @@ def execute_query(self, session, cmd: str,
| FullPartitionScanReversedOrderEvent]) -> None:
self.log.debug('Will run command %s', cmd)
validate_mapreduce_service_requests_start_time = time.time()
session.cluster.default_retry_policy = ExponentialBackoffRetryPolicy(**self._exp_backoff_retry_policy_params)
session.default_timeout = self._session_execution_timeout
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is there a difference between self._request_default_timeout and self._request_default_timeout? maybe it could be reused?


try:
cmd_result = session.execute(
query=cmd, trace=False, timeout=self._session_execution_timeout)
Expand Down
6 changes: 4 additions & 2 deletions test-cases/longevity/longevity-100gb-4h.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,9 @@ seeds_num: 3

instance_type_db: 'i4i.4xlarge'

nemesis_class_name: 'SisyphusMonkey'
nemesis_class_name: 'ClusterRollingRestart'
nemesis_seed: '032'
nemesis_interval: 5
nemesis_interval: 1
nemesis_filter_seeds: false

user_prefix: 'longevity-100gb-4h'
Expand All @@ -29,3 +29,5 @@ sstable_size: 100

hinted_handoff: 'enabled'
parallel_node_operations: true

run_fullscan: ['{"mode": "table_and_aggregate", "ks_cf": "keyspace1.standard1", "interval": 60}']
Loading