Improve configs - ObservabilityConfig (#17453)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/config.py

@@ -14,6 +14,7 @@ from collections import Counter
 from contextlib import contextmanager
 from dataclasses import (MISSING, dataclass, field, fields, is_dataclass,
                          replace)
+from functools import cached_property
 from importlib.util import find_spec
 from pathlib import Path
 from typing import (TYPE_CHECKING, Any, Callable, ClassVar, Literal, Optional,
@@ -26,6 +27,7 @@ from transformers import PretrainedConfig
 from typing_extensions import deprecated
 
 import vllm.envs as envs
+from vllm import version
 from vllm.compilation.inductor_pass import CallableInductorPass, InductorPass
 from vllm.logger import init_logger
 from vllm.model_executor.layers.quantization import (QUANTIZATION_METHODS,
@@ -3285,20 +3287,55 @@ class DecodingConfig:
             self.disable_additional_properties = True
 
 
+DetailedTraceModules = Literal["model", "worker", "all"]
+
+
+@config
 @dataclass
 class ObservabilityConfig:
     """Configuration for observability - metrics and tracing."""
-    show_hidden_metrics: bool = False
+
+    show_hidden_metrics_for_version: Optional[str] = None
+    """Enable deprecated Prometheus metrics that have been hidden since the
+    specified version. For example, if a previously deprecated metric has been
+    hidden since the v0.7.0 release, you use
+    `--show-hidden-metrics-for-version=0.7` as a temporary escape hatch while
+    you migrate to new metrics. The metric is likely to be removed completely
+    in an upcoming release."""
+
+    @cached_property
+    def show_hidden_metrics(self) -> bool:
+        """Check if the hidden metrics should be shown."""
+        if self.show_hidden_metrics_for_version is None:
+            return False
+        return version._prev_minor_version_was(
+            self.show_hidden_metrics_for_version)
 
     otlp_traces_endpoint: Optional[str] = None
+    """Target URL to which OpenTelemetry traces will be sent."""
 
-    # Collecting detailed timing information for each request can be expensive.
+    collect_detailed_traces: Optional[list[DetailedTraceModules]] = None
+    """It makes sense to set this only if `--otlp-traces-endpoint` is set. If
+    set, it will collect detailed traces for the specified modules. This
+    involves use of possibly costly and or blocking operations and hence might
+    have a performance impact.
 
-    # If set, collects the model forward time for the request.
-    collect_model_forward_time: bool = False
+    Note that collecting detailed timing information for each request can be
+    expensive."""
 
-    # If set, collects the model execute time for the request.
-    collect_model_execute_time: bool = False
+    @cached_property
+    def collect_model_forward_time(self) -> bool:
+        """Whether to collect model forward time for the request."""
+        return (self.collect_detailed_traces is not None
+                and ("model" in self.collect_detailed_traces
+                     or "all" in self.collect_detailed_traces))
+
+    @cached_property
+    def collect_model_execute_time(self) -> bool:
+        """Whether to collect model execute time for the request."""
+        return (self.collect_detailed_traces is not None
+                and ("worker" in self.collect_detailed_traces
+                     or "all" in self.collect_detailed_traces))
 
     def compute_hash(self) -> str:
         """
@@ -3320,12 +3357,23 @@ class ObservabilityConfig:
         return hash_str
 
     def __post_init__(self):
+        if (self.collect_detailed_traces is not None
+                and len(self.collect_detailed_traces) == 1
+                and "," in self.collect_detailed_traces[0]):
+            self._parse_collect_detailed_traces()
+
         if not is_otel_available() and self.otlp_traces_endpoint is not None:
             raise ValueError(
                 "OpenTelemetry is not available. Unable to configure "
                 "'otlp_traces_endpoint'. Ensure OpenTelemetry packages are "
                 f"installed. Original error:\n{otel_import_error_traceback}")
 
+    def _parse_collect_detailed_traces(self):
+        assert isinstance(self.collect_detailed_traces, list)
+        self.collect_detailed_traces = cast(
+            list[DetailedTraceModules],
+            self.collect_detailed_traces[0].split(","))
+
 
 class KVTransferConfig(BaseModel):
     """Configuration for distributed KV cache transfer."""