[Metrics] Some small refactoring for better maintainability (#33898)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
This commit is contained in:
@@ -126,28 +126,17 @@ class KVConnectorPromMetrics:
|
||||
self._labelnames = labelnames
|
||||
self.per_engine_labelvalues = per_engine_labelvalues
|
||||
|
||||
def make_per_engine(self, metric: PromMetric) -> dict[int, PromMetric]:
|
||||
"""
|
||||
Create a per-engine child of a prometheus_client.Metric with
|
||||
the appropriate labels set. The parent metric must be created
|
||||
using the labelnames list.
|
||||
"""
|
||||
return {
|
||||
idx: metric.labels(*labelvalues)
|
||||
for idx, labelvalues in self.per_engine_labelvalues.items()
|
||||
}
|
||||
|
||||
def observe(self, transfer_stats_data: dict[str, Any], engine_idx: int = 0):
|
||||
"""
|
||||
Record the supplied transfer statistics to Prometheus metrics. These
|
||||
statistics are engine-specific, and should be recorded to a metric
|
||||
with the appropriate 'engine' label. These metric instances can be
|
||||
created using the make_per_engine() helper method.
|
||||
created using the create_metric_per_engine() helper method.
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
class KVConnectorPrometheus:
|
||||
class KVConnectorProm:
|
||||
"""
|
||||
Support for registering per-connector Prometheus metrics, and
|
||||
recording transfer statistics to those metrics. Uses
|
||||
|
||||
@@ -65,6 +65,7 @@ from vllm.v1.kv_cache_interface import (
|
||||
SlidingWindowSpec,
|
||||
UniformTypeKVCacheSpecs,
|
||||
)
|
||||
from vllm.v1.metrics.utils import create_metric_per_engine
|
||||
from vllm.v1.worker.block_table import BlockTable
|
||||
from vllm.v1.worker.utils import select_common_block_size
|
||||
|
||||
@@ -3057,7 +3058,9 @@ class NixlPromMetrics(KVConnectorPromMetrics):
|
||||
buckets=buckets[1:],
|
||||
labelnames=labelnames,
|
||||
)
|
||||
self.nixl_histogram_xfer_time = self.make_per_engine(nixl_histogram_xfer_time)
|
||||
self.nixl_histogram_xfer_time = create_metric_per_engine(
|
||||
nixl_histogram_xfer_time, self.per_engine_labelvalues
|
||||
)
|
||||
nixl_histogram_post_time = self._histogram_cls(
|
||||
name="vllm:nixl_post_time_seconds",
|
||||
documentation="Histogram of transfer post time for NIXL KV"
|
||||
@@ -3065,7 +3068,9 @@ class NixlPromMetrics(KVConnectorPromMetrics):
|
||||
buckets=buckets,
|
||||
labelnames=labelnames,
|
||||
)
|
||||
self.nixl_histogram_post_time = self.make_per_engine(nixl_histogram_post_time)
|
||||
self.nixl_histogram_post_time = create_metric_per_engine(
|
||||
nixl_histogram_post_time, self.per_engine_labelvalues
|
||||
)
|
||||
# uniform 2kb to 16gb range
|
||||
buckets = [2 ** (10 + i) for i in range(1, 25, 2)]
|
||||
nixl_histogram_bytes_transferred = self._histogram_cls(
|
||||
@@ -3074,8 +3079,8 @@ class NixlPromMetrics(KVConnectorPromMetrics):
|
||||
buckets=buckets,
|
||||
labelnames=labelnames,
|
||||
)
|
||||
self.nixl_histogram_bytes_transferred = self.make_per_engine(
|
||||
nixl_histogram_bytes_transferred
|
||||
self.nixl_histogram_bytes_transferred = create_metric_per_engine(
|
||||
nixl_histogram_bytes_transferred, self.per_engine_labelvalues
|
||||
)
|
||||
buckets = [
|
||||
10,
|
||||
@@ -3100,24 +3105,24 @@ class NixlPromMetrics(KVConnectorPromMetrics):
|
||||
buckets=buckets,
|
||||
labelnames=labelnames,
|
||||
)
|
||||
self.nixl_histogram_num_descriptors = self.make_per_engine(
|
||||
nixl_histogram_num_descriptors
|
||||
self.nixl_histogram_num_descriptors = create_metric_per_engine(
|
||||
nixl_histogram_num_descriptors, self.per_engine_labelvalues
|
||||
)
|
||||
counter_nixl_num_failed_transfers = self._counter_cls(
|
||||
name="vllm:nixl_num_failed_transfers",
|
||||
documentation="Number of failed NIXL KV Cache transfers.",
|
||||
labelnames=labelnames,
|
||||
)
|
||||
self.counter_nixl_num_failed_transfers = self.make_per_engine(
|
||||
counter_nixl_num_failed_transfers
|
||||
self.counter_nixl_num_failed_transfers = create_metric_per_engine(
|
||||
counter_nixl_num_failed_transfers, self.per_engine_labelvalues
|
||||
)
|
||||
counter_nixl_num_failed_notifications = self._counter_cls(
|
||||
name="vllm:nixl_num_failed_notifications",
|
||||
documentation="Number of failed NIXL KV Cache notifications.",
|
||||
labelnames=labelnames,
|
||||
)
|
||||
self.counter_nixl_num_failed_notifications = self.make_per_engine(
|
||||
counter_nixl_num_failed_notifications
|
||||
self.counter_nixl_num_failed_notifications = create_metric_per_engine(
|
||||
counter_nixl_num_failed_notifications, self.per_engine_labelvalues
|
||||
)
|
||||
|
||||
counter_nixl_num_kv_expired_reqs = self._counter_cls(
|
||||
@@ -3126,8 +3131,8 @@ class NixlPromMetrics(KVConnectorPromMetrics):
|
||||
"NOTE: This metric is tracked on the P instance.",
|
||||
labelnames=labelnames,
|
||||
)
|
||||
self.counter_nixl_num_kv_expired_reqs = self.make_per_engine(
|
||||
counter_nixl_num_kv_expired_reqs
|
||||
self.counter_nixl_num_kv_expired_reqs = create_metric_per_engine(
|
||||
counter_nixl_num_kv_expired_reqs, self.per_engine_labelvalues
|
||||
)
|
||||
|
||||
def observe(self, transfer_stats_data: dict[str, Any], engine_idx: int = 0):
|
||||
|
||||
Reference in New Issue
Block a user