mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-14 17:02:56 +00:00
d7f1e30112
- Clean up redundant metric removal in TimelineMetrics::drop. RemoteTimelineClientMetrics is responsible for cleaning up REMOTE_OPERATION_TIME andREMOTE_UPLOAD_QUEUE_UNFINISHED_TASKS. - Rename `pageserver_remote_upload_queue_unfinished_tasks` to `pageserver_remote_timeline_client_calls_unfinished`. The new name reflects that the metric is with respect to the entire call to remote timeline client. This includes wait time in the upload queue and hence it's a longer span than what `pageserver_remote_OPERATION_seconds` measures. - Add the `pageserver_remote_timeline_client_calls_started` histogram. See the metric description for why we need it. - Add helper functions `call_begin` etc to `RemoteTimelineClientMetrics` to centralize the logic for updating the metrics above (they relate to each other, see comments in code). - Use these constructs to track ongoing downloads in `pageserver_remote_timeline_client_calls_unfinished` refs https://github.com/neondatabase/neon/issues/2029 fixes https://github.com/neondatabase/neon/issues/3249 closes https://github.com/neondatabase/neon/pull/3250
74 lines
2.6 KiB
Python
74 lines
2.6 KiB
Python
from collections import defaultdict
|
|
from typing import Dict, List, Optional, Tuple
|
|
|
|
from prometheus_client.parser import text_string_to_metric_families
|
|
from prometheus_client.samples import Sample
|
|
|
|
|
|
class Metrics:
|
|
metrics: Dict[str, List[Sample]]
|
|
name: str
|
|
|
|
def __init__(self, name: str = ""):
|
|
self.metrics = defaultdict(list)
|
|
self.name = name
|
|
|
|
def query_all(self, name: str, filter: Dict[str, str]) -> List[Sample]:
|
|
res = []
|
|
for sample in self.metrics[name]:
|
|
try:
|
|
if all(sample.labels[k] == v for k, v in filter.items()):
|
|
res.append(sample)
|
|
except KeyError:
|
|
pass
|
|
return res
|
|
|
|
def query_one(self, name: str, filter: Optional[Dict[str, str]] = None) -> Sample:
|
|
res = self.query_all(name, filter or {})
|
|
assert len(res) == 1, f"expected single sample for {name} {filter}, found {res}"
|
|
return res[0]
|
|
|
|
|
|
def parse_metrics(text: str, name: str = "") -> Metrics:
|
|
metrics = Metrics(name)
|
|
gen = text_string_to_metric_families(text)
|
|
for family in gen:
|
|
for sample in family.samples:
|
|
metrics.metrics[sample.name].append(sample)
|
|
|
|
return metrics
|
|
|
|
|
|
PAGESERVER_PER_TENANT_REMOTE_TIMELINE_CLIENT_METRICS: Tuple[str, ...] = (
|
|
"pageserver_remote_timeline_client_calls_unfinished",
|
|
*[f"pageserver_remote_timeline_client_calls_started_{x}" for x in ["bucket", "count", "sum"]],
|
|
*[f"pageserver_remote_operation_seconds_{x}" for x in ["bucket", "count", "sum"]],
|
|
"pageserver_remote_physical_size",
|
|
)
|
|
|
|
PAGESERVER_PER_TENANT_METRICS: Tuple[str, ...] = (
|
|
"pageserver_current_logical_size",
|
|
"pageserver_resident_physical_size",
|
|
"pageserver_getpage_reconstruct_seconds_bucket",
|
|
"pageserver_getpage_reconstruct_seconds_count",
|
|
"pageserver_getpage_reconstruct_seconds_sum",
|
|
"pageserver_io_operations_bytes_total",
|
|
"pageserver_io_operations_seconds_bucket",
|
|
"pageserver_io_operations_seconds_count",
|
|
"pageserver_io_operations_seconds_sum",
|
|
"pageserver_last_record_lsn",
|
|
"pageserver_materialized_cache_hits_total",
|
|
"pageserver_smgr_query_seconds_bucket",
|
|
"pageserver_smgr_query_seconds_count",
|
|
"pageserver_smgr_query_seconds_sum",
|
|
"pageserver_storage_operations_seconds_bucket",
|
|
"pageserver_storage_operations_seconds_count",
|
|
"pageserver_storage_operations_seconds_sum",
|
|
"pageserver_wait_lsn_seconds_bucket",
|
|
"pageserver_wait_lsn_seconds_count",
|
|
"pageserver_wait_lsn_seconds_sum",
|
|
"pageserver_created_persistent_files_total",
|
|
"pageserver_written_persistent_bytes_total",
|
|
*PAGESERVER_PER_TENANT_REMOTE_TIMELINE_CLIENT_METRICS,
|
|
)
|