mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-14 00:42:54 +00:00
82484e8241
## Problem This PR includes doc changes to the current metrics as well as adding new metrics. With the new set of metrics, we can quantitatively analyze the read amp., write amp. and space amp. in the system, when used together with https://github.com/neondatabase/neonbench close https://github.com/neondatabase/neon/issues/4312 ref https://github.com/neondatabase/neon/issues/4347 compaction metrics TBD, a novel idea is to print L0 file number and number of layers in the system, and we can do this in the future when we start working on compaction. ## Summary of changes * Add `READ_NUM_FS_LAYERS` for computing read amp. * Add `MATERIALIZED_PAGE_CACHE_HIT_UPON_REQUEST`. * Add `GET_RECONSTRUCT_DATA_TIME`. GET_RECONSTRUCT_DATA_TIME + RECONSTRUCT_TIME + WAIT_LSN_TIME should be approximately total time of reads. * Add `5.0` and `10.0` to `STORAGE_IO_TIME_BUCKETS` given some fsync runs slow (i.e., > 1s) in some cases. * Some `WAL_REDO` metrics are only used when Postgres is involved in the redo process. --------- Signed-off-by: Alex Chi <iskyzh@gmail.com>
96 lines
3.6 KiB
Python
96 lines
3.6 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: Optional[Dict[str, str]] = None) -> List[Sample]:
|
|
filter = filter or {}
|
|
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_remote_timeline_client_bytes_started_total",
|
|
"pageserver_remote_timeline_client_bytes_finished_total",
|
|
)
|
|
|
|
PAGESERVER_GLOBAL_METRICS: Tuple[str, ...] = (
|
|
"pageserver_storage_operations_seconds_global_count",
|
|
"pageserver_storage_operations_seconds_global_sum",
|
|
"pageserver_storage_operations_seconds_global_bucket",
|
|
"pageserver_unexpected_ondemand_downloads_count_total",
|
|
"libmetrics_launch_timestamp",
|
|
"libmetrics_build_info",
|
|
"libmetrics_tracing_event_count_total",
|
|
)
|
|
|
|
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_getpage_get_reconstruct_data_seconds_bucket",
|
|
"pageserver_getpage_get_reconstruct_data_seconds_count",
|
|
"pageserver_getpage_get_reconstruct_data_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_materialized_cache_hits_direct_total",
|
|
"pageserver_read_num_fs_layers_bucket",
|
|
"pageserver_read_num_fs_layers_count",
|
|
"pageserver_read_num_fs_layers_sum",
|
|
"pageserver_smgr_query_seconds_bucket",
|
|
"pageserver_smgr_query_seconds_count",
|
|
"pageserver_smgr_query_seconds_sum",
|
|
"pageserver_storage_operations_seconds_count_total",
|
|
"pageserver_storage_operations_seconds_sum_total",
|
|
"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_tenant_states_count",
|
|
"pageserver_evictions_total",
|
|
"pageserver_evictions_with_low_residence_duration_total",
|
|
*PAGESERVER_PER_TENANT_REMOTE_TIMELINE_CLIENT_METRICS,
|
|
)
|