refactor(profiling): store memalloc samples as native objects #15372

danielsn · 2025-11-21T04:14:29Z

Description

Previously, we kept tracebacks in python objects, which meant that dealing with them required careful work with the GIL.
Replacing with native storage makes the code much cleaner.

Testing

Existing tests

Risks

This is a substantial change to how the profiler works, and should be looked at carefully.

Additional Notes

github-actions · 2025-11-21T04:15:09Z

CODEOWNERS have been resolved as:

ddtrace/internal/datadog/profiling/dd_wrapper/include/sample.hpp        @DataDog/profiling-python
ddtrace/internal/datadog/profiling/dd_wrapper/src/ddup_interface.cpp    @DataDog/profiling-python
ddtrace/internal/datadog/profiling/dd_wrapper/src/sample.cpp            @DataDog/profiling-python
ddtrace/profiling/collector/_memalloc.cpp                               @DataDog/profiling-python
ddtrace/profiling/collector/_memalloc_heap.cpp                          @DataDog/profiling-python
ddtrace/profiling/collector/_memalloc_heap.h                            @DataDog/profiling-python
ddtrace/profiling/collector/_memalloc_heap_map.cpp                      @DataDog/profiling-python
ddtrace/profiling/collector/_memalloc_heap_map.hpp                      @DataDog/profiling-python
ddtrace/profiling/collector/_memalloc_tb.cpp                            @DataDog/profiling-python
ddtrace/profiling/collector/_memalloc_tb.h                              @DataDog/profiling-python
ddtrace/profiling/collector/memalloc.py                                 @DataDog/profiling-python
ddtrace/profiling/collector/test/README.md                              @DataDog/profiling-python
ddtrace/profiling/collector/test/test_memalloc_heap_map.cpp             @DataDog/profiling-python
riotfile.py                                                             @DataDog/apm-python
setup.py                                                                @DataDog/python-guild
src/native/Cargo.lock                                                   @DataDog/apm-core-python
tests/profiling_v2/collector/test_memalloc.py                           @DataDog/profiling-python

danielsn · 2025-11-21T04:29:45Z

tests/profiling_v2/collector/test_memalloc.py

-        assert "No samples found" in str(e)
-
-
+@pytest.mark.skip(reason="Temporarily suppressed - crashes with large number of samples")


@nsrip-dd What does this test do, and why is it around

Are you asking about test_heap_profiler_large_heap_overhead or is this comment referencing test_memory_collector_ignore_profiler we discussed yesterday?

If it's about test_heap_profiler_large_heap_overhead, see #12394 which added the test (the blame view helps here) and #12286. In short, that test demonstrated significant overhead prior to switching to a hash map in the heap profiler, and it is a regression test for a crash when we incorrectly used 16-bit indices in some places. The second thing should have been linked in the PR that added the test, but oh well.

BTW the comment at the beggining of the tests is stale; we haven't skipped this test in a while.

danielsn · 2025-11-21T04:30:17Z

riotfile.py

-                                    "pymalloc",
-                                    "malloc_debug",
-                                    "pymalloc_debug",


TODO roll this back when ready, its just to make tests run faster for now

danielsn · 2025-11-21T04:30:47Z

ddtrace/profiling/collector/memalloc.py

+        # Note: events are now exported directly to pprof, so we return empty samples
        return tuple()

    def test_snapshot(self) -> Tuple[MemorySample, ...]:


this is really only necessary for the legacy v1 tests, can remove once those are gone

ddtrace/profiling/collector/_memalloc_heap.cpp

danielsn · 2025-11-21T04:40:30Z

ddtrace/profiling/collector/_memalloc_tb.h

    /* True if this sample has been reported previously */
    bool reported;
    /* Count of allocations this sample represents (for scaling) */
    size_t count;


this may not be needed anymore

danielsn · 2025-11-21T04:41:59Z

ddtrace/profiling/collector/_memalloc_tb.cpp

+ * tracking. We're already inside a reentrancy guard and GC is disabled, so it's safe
+ * to call Python functions here (similar to how we call PyUnicode_AsUTF8String for frames).
+ */
+static void


Can someone who understands python refcounting make sure this is doing the right things?

github-actions · 2025-11-21T04:42:17Z

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 264 ± 4 ms.

The average import time from base is: 273 ± 6 ms.

The import time difference between this PR and base is: -9.1 ± 0.2 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 7.289 ms (2.76%)

ddtrace.bootstrap.sitecustomize 4.219 ms (1.60%)

ddtrace.bootstrap.preload 4.219 ms (1.60%)

ddtrace.internal.settings.dynamic_instrumentation 0.718 ms (0.27%)

ddtrace.internal.remoteconfig.worker 0.692 ms (0.26%)

ddtrace.internal.remoteconfig.client 0.669 ms (0.25%)

ddtrace 3.070 ms (1.16%)

ddtrace.trace 0.980 ms (0.37%)

ddtrace._logger 0.691 ms (0.26%)

ddtrace.internal.telemetry 0.691 ms (0.26%)

ddtrace.internal.telemetry.writer 0.691 ms (0.26%)

ddtrace.internal.utils.version 0.691 ms (0.26%)

ddtrace.internal._unpatched 0.036 ms (0.01%)

json 0.036 ms (0.01%)

json.decoder 0.036 ms (0.01%)

re 0.036 ms (0.01%)

enum 0.036 ms (0.01%)

types 0.036 ms (0.01%)

danielsn · 2025-11-21T04:42:24Z

ddtrace/profiling/collector/_memalloc_tb.cpp

+                    if (name_ptr != NULL) {
+                        Py_ssize_t name_len = PyBytes_Size(name_bytes);
+                        // Store the thread name in a std::string
+                        thread_name = std::string(name_ptr, name_len);


this can probably be a string_view

danielsn · 2025-11-21T04:42:55Z

ddtrace/profiling/collector/_memalloc_tb.cpp

-            frames.emplace_back(pyframe);
-        }
+    // Validate Sample object is in a valid state before use
+    if (max_nframe == 0) {


not sure what value this adds

danielsn · 2025-11-21T04:44:02Z

ddtrace/profiling/collector/_memalloc_tb.cpp

+
+        // Now safe to release the bytes objects since push_frame has copied the strings
+        Py_XDECREF(name_bytes);
+        Py_XDECREF(filename_bytes);


if someone who understands python refcounting could confirm that that would be great

PyUnicode_AsUTF8String returns a new reference so when no longer needed the refcount needs to be decremented

danielsn · 2025-11-21T04:48:29Z

ddtrace/profiling/collector/_memalloc_heap.cpp

+        tb->reported = true;
    }
-    return nullptr;
+    delete tb; // Safe to delete nullptr


instead of new/delete, consider keeping a pool of these around

danielsn · 2025-11-21T04:49:12Z

ddtrace/profiling/collector/_memalloc_heap_map.cpp

        /* This should not happen. It means we did not properly remove a previously-tracked
-         * allocation from the map. This should probably be an assertion. Return the previous
-         * entry as it is for an allocation that has been freed. */
+         * allocation from the map. This should probably be an assertion. Delete the previous


consider adding that assertion

pr-commenter · 2025-11-21T05:42:03Z

Performance SLOs

Comparing candidate dsn/traceback-sample (536df5f) with baseline main (9739b2f)

📈 Performance Regressions (1 suite)

📈 iastaspects - 118/118

✅ add_aspect

Time: ✅ 0.407µs (SLO: <10.000µs 📉 -95.9%) vs baseline: +0.9%

Memory: ✅ 39.911MB (SLO: <41.500MB -3.8%) vs baseline: +6.1%

✅ add_inplace_aspect

Time: ✅ 0.403µs (SLO: <10.000µs 📉 -96.0%) vs baseline: -1.2%

Memory: ✅ 39.793MB (SLO: <41.500MB -4.1%) vs baseline: +5.7%

✅ add_inplace_noaspect

Time: ✅ 0.316µs (SLO: <10.000µs 📉 -96.8%) vs baseline: -2.2%

Memory: ✅ 39.558MB (SLO: <41.500MB -4.7%) vs baseline: +5.0%

✅ add_noaspect

Time: ✅ 0.284µs (SLO: <10.000µs 📉 -97.2%) vs baseline: +2.7%

Memory: ✅ 39.675MB (SLO: <41.500MB -4.4%) vs baseline: +5.2%

✅ bytearray_aspect

Time: ✅ 1.316µs (SLO: <10.000µs 📉 -86.8%) vs baseline: -1.9%

Memory: ✅ 39.558MB (SLO: <41.500MB -4.7%) vs baseline: +5.0%

✅ bytearray_extend_aspect

Time: ✅ 1.540µs (SLO: <10.000µs 📉 -84.6%) vs baseline: +0.7%

Memory: ✅ 39.499MB (SLO: <41.500MB -4.8%) vs baseline: +5.0%

✅ bytearray_extend_noaspect

Time: ✅ 0.617µs (SLO: <10.000µs 📉 -93.8%) vs baseline: +1.3%

Memory: ✅ 39.459MB (SLO: <41.500MB -4.9%) vs baseline: +4.8%

✅ bytearray_noaspect

Time: ✅ 0.484µs (SLO: <10.000µs 📉 -95.2%) vs baseline: +0.7%

Memory: ✅ 39.558MB (SLO: <41.500MB -4.7%) vs baseline: +5.0%

✅ bytes_aspect

Time: ✅ 1.293µs (SLO: <10.000µs 📉 -87.1%) vs baseline: +0.4%

Memory: ✅ 39.872MB (SLO: <41.500MB -3.9%) vs baseline: +6.0%

✅ bytes_noaspect

Time: ✅ 0.493µs (SLO: <10.000µs 📉 -95.1%) vs baseline: -0.2%

Memory: ✅ 39.793MB (SLO: <41.500MB -4.1%) vs baseline: +5.9%

✅ bytesio_aspect

Time: ✅ 1.295µs (SLO: <10.000µs 📉 -87.1%) vs baseline: -0.7%

Memory: ✅ 39.577MB (SLO: <41.500MB -4.6%) vs baseline: +5.2%

✅ bytesio_noaspect

Time: ✅ 0.493µs (SLO: <10.000µs 📉 -95.1%) vs baseline: -0.7%

Memory: ✅ 39.911MB (SLO: <41.500MB -3.8%) vs baseline: +6.1%

✅ capitalize_aspect

Time: ✅ 0.733µs (SLO: <10.000µs 📉 -92.7%) vs baseline: -1.0%

Memory: ✅ 39.341MB (SLO: <41.500MB -5.2%) vs baseline: +4.7%

✅ capitalize_noaspect

Time: ✅ 0.436µs (SLO: <10.000µs 📉 -95.6%) vs baseline: +0.5%

Memory: ✅ 39.440MB (SLO: <41.500MB -5.0%) vs baseline: +4.9%

✅ casefold_aspect

Time: ✅ 0.732µs (SLO: <10.000µs 📉 -92.7%) vs baseline: -0.2%

Memory: ✅ 39.518MB (SLO: <41.500MB -4.8%) vs baseline: +4.8%

✅ casefold_noaspect

Time: ✅ 0.371µs (SLO: <10.000µs 📉 -96.3%) vs baseline: -1.0%

Memory: ✅ 39.852MB (SLO: <41.500MB -4.0%) vs baseline: +5.8%

✅ decode_aspect

Time: ✅ 0.731µs (SLO: <10.000µs 📉 -92.7%) vs baseline: +1.5%

Memory: ✅ 39.361MB (SLO: <41.500MB -5.2%) vs baseline: +4.5%

✅ decode_noaspect

Time: ✅ 0.423µs (SLO: <10.000µs 📉 -95.8%) vs baseline: +1.5%

Memory: ✅ 39.892MB (SLO: <41.500MB -3.9%) vs baseline: +5.8%

✅ encode_aspect

Time: ✅ 0.710µs (SLO: <10.000µs 📉 -92.9%) vs baseline: -0.3%

Memory: ✅ 39.499MB (SLO: <41.500MB -4.8%) vs baseline: +5.0%

✅ encode_noaspect

Time: ✅ 0.406µs (SLO: <10.000µs 📉 -95.9%) vs baseline: +0.9%

Memory: ✅ 39.793MB (SLO: <41.500MB -4.1%) vs baseline: +5.8%

✅ format_aspect

Time: ✅ 3.499µs (SLO: <10.000µs 📉 -65.0%) vs baseline: +4.9%

Memory: ✅ 39.872MB (SLO: <41.500MB -3.9%) vs baseline: +6.1%

✅ format_map_aspect

Time: ✅ 3.557µs (SLO: <10.000µs 📉 -64.4%) vs baseline: +2.1%

Memory: ✅ 39.518MB (SLO: <41.500MB -4.8%) vs baseline: +4.8%

✅ format_map_noaspect

Time: ✅ 0.784µs (SLO: <10.000µs 📉 -92.2%) vs baseline: +1.5%

Memory: ✅ 39.479MB (SLO: <41.500MB -4.9%) vs baseline: +5.0%

✅ format_noaspect

Time: ✅ 0.595µs (SLO: <10.000µs 📉 -94.1%) vs baseline: ~same

Memory: ✅ 39.951MB (SLO: <41.500MB -3.7%) vs baseline: +6.2%

✅ index_aspect

Time: ✅ 0.359µs (SLO: <10.000µs 📉 -96.4%) vs baseline: +0.6%

Memory: ✅ 39.813MB (SLO: <41.500MB -4.1%) vs baseline: +6.0%

✅ index_noaspect

Time: ✅ 0.277µs (SLO: <10.000µs 📉 -97.2%) vs baseline: -0.6%

Memory: ✅ 39.931MB (SLO: <41.500MB -3.8%) vs baseline: +6.1%

✅ join_aspect

Time: ✅ 1.388µs (SLO: <10.000µs 📉 -86.1%) vs baseline: +0.4%

Memory: ✅ 39.833MB (SLO: <41.500MB -4.0%) vs baseline: +5.8%

✅ join_noaspect

Time: ✅ 0.489µs (SLO: <10.000µs 📉 -95.1%) vs baseline: -1.0%

Memory: ✅ 39.675MB (SLO: <41.500MB -4.4%) vs baseline: +5.5%

✅ ljust_aspect

Time: ✅ 2.529µs (SLO: <20.000µs 📉 -87.4%) vs baseline: +0.6%

Memory: ✅ 39.892MB (SLO: <41.500MB -3.9%) vs baseline: +6.1%

✅ ljust_noaspect

Time: ✅ 0.404µs (SLO: <10.000µs 📉 -96.0%) vs baseline: +1.3%

Memory: ✅ 39.754MB (SLO: <41.500MB -4.2%) vs baseline: +5.7%

✅ lower_aspect

Time: ✅ 2.195µs (SLO: <10.000µs 📉 -78.0%) vs baseline: -0.3%

Memory: ✅ 39.852MB (SLO: <41.500MB -4.0%) vs baseline: +6.0%

✅ lower_noaspect

Time: ✅ 0.368µs (SLO: <10.000µs 📉 -96.3%) vs baseline: +1.4%

Memory: ✅ 39.951MB (SLO: <41.500MB -3.7%) vs baseline: +6.1%

✅ lstrip_aspect

Time: ✅ 2.487µs (SLO: <20.000µs 📉 -87.6%) vs baseline: 📈 +12.3%

Memory: ✅ 39.951MB (SLO: <41.500MB -3.7%) vs baseline: +6.1%

✅ lstrip_noaspect

Time: ✅ 0.382µs (SLO: <10.000µs 📉 -96.2%) vs baseline: -1.3%

Memory: ✅ 39.911MB (SLO: <41.500MB -3.8%) vs baseline: +6.1%

✅ modulo_aspect

Time: ✅ 1.052µs (SLO: <10.000µs 📉 -89.5%) vs baseline: +1.5%

Memory: ✅ 39.440MB (SLO: <41.500MB -5.0%) vs baseline: +4.9%

✅ modulo_aspect_for_bytearray_bytearray

Time: ✅ 1.555µs (SLO: <10.000µs 📉 -84.5%) vs baseline: -0.2%

Memory: ✅ 39.852MB (SLO: <41.500MB -4.0%) vs baseline: +5.9%

✅ modulo_aspect_for_bytes

Time: ✅ 0.980µs (SLO: <10.000µs 📉 -90.2%) vs baseline: +0.7%

Memory: ✅ 39.911MB (SLO: <41.500MB -3.8%) vs baseline: +5.8%

✅ modulo_aspect_for_bytes_bytearray

Time: ✅ 1.297µs (SLO: <10.000µs 📉 -87.0%) vs baseline: +2.9%

Memory: ✅ 39.440MB (SLO: <41.500MB -5.0%) vs baseline: +4.9%

✅ modulo_noaspect

Time: ✅ 0.626µs (SLO: <10.000µs 📉 -93.7%) vs baseline: -0.5%

Memory: ✅ 39.833MB (SLO: <41.500MB -4.0%) vs baseline: +5.7%

✅ replace_aspect

Time: ✅ 5.389µs (SLO: <10.000µs 📉 -46.1%) vs baseline: 📈 +10.2%

Memory: ✅ 39.931MB (SLO: <41.500MB -3.8%) vs baseline: +6.3%

✅ replace_noaspect

Time: ✅ 0.463µs (SLO: <10.000µs 📉 -95.4%) vs baseline: +0.8%

Memory: ✅ 39.813MB (SLO: <41.500MB -4.1%) vs baseline: +5.6%

✅ repr_aspect

Time: ✅ 0.907µs (SLO: <10.000µs 📉 -90.9%) vs baseline: -0.1%

Memory: ✅ 39.951MB (SLO: <41.500MB -3.7%) vs baseline: +6.3%

✅ repr_noaspect

Time: ✅ 0.418µs (SLO: <10.000µs 📉 -95.8%) vs baseline: +1.0%

Memory: ✅ 39.754MB (SLO: <41.500MB -4.2%) vs baseline: +5.4%

✅ rstrip_aspect

Time: ✅ 1.881µs (SLO: <20.000µs 📉 -90.6%) vs baseline: +1.2%

Memory: ✅ 39.872MB (SLO: <41.500MB -3.9%) vs baseline: +6.0%

✅ rstrip_noaspect

Time: ✅ 0.380µs (SLO: <10.000µs 📉 -96.2%) vs baseline: -0.7%

Memory: ✅ 39.833MB (SLO: <41.500MB -4.0%) vs baseline: +5.7%

✅ slice_aspect

Time: ✅ 0.491µs (SLO: <10.000µs 📉 -95.1%) vs baseline: -0.5%

Memory: ✅ 39.793MB (SLO: <41.500MB -4.1%) vs baseline: +5.8%

✅ slice_noaspect

Time: ✅ 0.450µs (SLO: <10.000µs 📉 -95.5%) vs baseline: ~same

Memory: ✅ 39.872MB (SLO: <41.500MB -3.9%) vs baseline: +6.1%

✅ stringio_aspect

Time: ✅ 1.537µs (SLO: <10.000µs 📉 -84.6%) vs baseline: ~same

Memory: ✅ 39.479MB (SLO: <41.500MB -4.9%) vs baseline: +4.9%

✅ stringio_noaspect

Time: ✅ 0.730µs (SLO: <10.000µs 📉 -92.7%) vs baseline: +1.3%

Memory: ✅ 40.029MB (SLO: <41.500MB -3.5%) vs baseline: +6.4%

✅ strip_aspect

Time: ✅ 2.225µs (SLO: <20.000µs 📉 -88.9%) vs baseline: +1.1%

Memory: ✅ 39.852MB (SLO: <41.500MB -4.0%) vs baseline: +6.0%

✅ strip_noaspect

Time: ✅ 0.392µs (SLO: <10.000µs 📉 -96.1%) vs baseline: +1.4%

Memory: ✅ 39.931MB (SLO: <41.500MB -3.8%) vs baseline: +6.3%

✅ swapcase_aspect

Time: ✅ 2.512µs (SLO: <10.000µs 📉 -74.9%) vs baseline: +4.5%

Memory: ✅ 39.892MB (SLO: <41.500MB -3.9%) vs baseline: +6.2%

✅ swapcase_noaspect

Time: ✅ 0.541µs (SLO: <10.000µs 📉 -94.6%) vs baseline: +1.3%

Memory: ✅ 39.872MB (SLO: <41.500MB -3.9%) vs baseline: +5.7%

✅ title_aspect

Time: ✅ 2.369µs (SLO: <10.000µs 📉 -76.3%) vs baseline: +1.1%

Memory: ✅ 39.813MB (SLO: <41.500MB -4.1%) vs baseline: +5.7%

✅ title_noaspect

Time: ✅ 0.503µs (SLO: <10.000µs 📉 -95.0%) vs baseline: ~same

Memory: ✅ 39.892MB (SLO: <41.500MB -3.9%) vs baseline: +5.9%

✅ translate_aspect

Time: ✅ 3.388µs (SLO: <10.000µs 📉 -66.1%) vs baseline: +5.5%

Memory: ✅ 39.911MB (SLO: <41.500MB -3.8%) vs baseline: +6.2%

✅ translate_noaspect

Time: ✅ 1.043µs (SLO: <10.000µs 📉 -89.6%) vs baseline: +0.5%

Memory: ✅ 39.538MB (SLO: <41.500MB -4.7%) vs baseline: +5.1%

✅ upper_aspect

Time: ✅ 2.303µs (SLO: <10.000µs 📉 -77.0%) vs baseline: +4.4%

Memory: ✅ 39.793MB (SLO: <41.500MB -4.1%) vs baseline: +5.5%

✅ upper_noaspect

Time: ✅ 0.372µs (SLO: <10.000µs 📉 -96.3%) vs baseline: +0.5%

Memory: ✅ 39.872MB (SLO: <41.500MB -3.9%) vs baseline: +5.8%

🟡 Near SLO Breach (1 suite)

🟡 telemetryaddmetric - 30/30

✅ 1-count-metric-1-times

Time: ✅ 2.990µs (SLO: <20.000µs 📉 -85.1%) vs baseline: +3.1%

Memory: ✅ 34.682MB (SLO: <35.500MB -2.3%) vs baseline: +5.2%

✅ 1-count-metrics-100-times

Time: ✅ 201.374µs (SLO: <220.000µs -8.5%) vs baseline: +1.0%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.9%

✅ 1-distribution-metric-1-times

Time: ✅ 3.563µs (SLO: <20.000µs 📉 -82.2%) vs baseline: +9.6%

Memory: ✅ 34.564MB (SLO: <35.500MB -2.6%) vs baseline: +5.1%

✅ 1-distribution-metrics-100-times

Time: ✅ 213.687µs (SLO: <230.000µs -7.1%) vs baseline: -0.9%

Memory: ✅ 34.662MB (SLO: <35.500MB -2.4%) vs baseline: +5.1%

✅ 1-gauge-metric-1-times

Time: ✅ 2.174µs (SLO: <20.000µs 📉 -89.1%) vs baseline: +0.5%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.6%

✅ 1-gauge-metrics-100-times

Time: ✅ 137.619µs (SLO: <150.000µs -8.3%) vs baseline: +0.6%

Memory: ✅ 34.662MB (SLO: <35.500MB -2.4%) vs baseline: +5.0%

✅ 1-rate-metric-1-times

Time: ✅ 3.045µs (SLO: <20.000µs 📉 -84.8%) vs baseline: ~same

Memory: ✅ 34.485MB (SLO: <35.500MB -2.9%) vs baseline: +4.3%

✅ 1-rate-metrics-100-times

Time: ✅ 215.342µs (SLO: <250.000µs 📉 -13.9%) vs baseline: +0.7%

Memory: ✅ 34.603MB (SLO: <35.500MB -2.5%) vs baseline: +4.9%

✅ 100-count-metrics-100-times

Time: ✅ 20.544ms (SLO: <22.000ms -6.6%) vs baseline: +1.3%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +5.0%

✅ 100-distribution-metrics-100-times

Time: ✅ 2.265ms (SLO: <2.300ms 🟡 -1.5%) vs baseline: +1.3%

Memory: ✅ 34.524MB (SLO: <35.500MB -2.7%) vs baseline: +4.8%

✅ 100-gauge-metrics-100-times

Time: ✅ 1.412ms (SLO: <1.550ms -8.9%) vs baseline: +0.2%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.7%

✅ 100-rate-metrics-100-times

Time: ✅ 2.249ms (SLO: <2.550ms 📉 -11.8%) vs baseline: +2.5%

Memory: ✅ 34.485MB (SLO: <35.500MB -2.9%) vs baseline: +4.3%

✅ flush-1-metric

Time: ✅ 4.823µs (SLO: <20.000µs 📉 -75.9%) vs baseline: +8.6%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +5.0%

✅ flush-100-metrics

Time: ✅ 172.902µs (SLO: <250.000µs 📉 -30.8%) vs baseline: -0.6%

Memory: ✅ 34.485MB (SLO: <35.500MB -2.9%) vs baseline: +4.3%

✅ flush-1000-metrics

Time: ✅ 2.123ms (SLO: <2.500ms 📉 -15.1%) vs baseline: -0.2%

Memory: ✅ 35.350MB (SLO: <36.500MB -3.2%) vs baseline: +4.7%

⚠️ Unstable Tests (1 suite)

⚠️

coreapiscenario - 10/10 (1 unstable)

⚠️ context_with_data_listeners

Time: ⚠️ 13.242µs (SLO: <20.000µs 📉 -33.8%) vs baseline: ~same

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.9%

✅ context_with_data_no_listeners

Time: ✅ 3.292µs (SLO: <10.000µs 📉 -67.1%) vs baseline: +0.8%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.5%

✅ get_item_exists

Time: ✅ 0.574µs (SLO: <10.000µs 📉 -94.3%) vs baseline: -0.6%

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +5.0%

✅ get_item_missing

Time: ✅ 0.629µs (SLO: <10.000µs 📉 -93.7%) vs baseline: -1.0%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.6%

✅ set_item

Time: ✅ 24.183µs (SLO: <30.000µs 📉 -19.4%) vs baseline: +0.4%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ All Tests Passing (20 suites)

✅ djangosimple - 30/30

✅ appsec

Time: ✅ 19.237ms (SLO: <22.300ms 📉 -13.7%) vs baseline: -0.2%

Memory: ✅ 67.869MB (SLO: <70.500MB -3.7%) vs baseline: +4.3%

✅ exception-replay-enabled

Time: ✅ 1.339ms (SLO: <1.450ms -7.7%) vs baseline: -0.2%

Memory: ✅ 66.109MB (SLO: <67.500MB -2.1%) vs baseline: +5.0%

✅ iast

Time: ✅ 19.258ms (SLO: <22.250ms 📉 -13.4%) vs baseline: -0.2%

Memory: ✅ 67.849MB (SLO: <70.000MB -3.1%) vs baseline: +4.3%

✅ profiler

Time: ✅ 15.532ms (SLO: <16.550ms -6.1%) vs baseline: ~same

Memory: ✅ 55.989MB (SLO: <57.500MB -2.6%) vs baseline: +4.9%

✅ resource-renaming

Time: ✅ 19.330ms (SLO: <21.750ms 📉 -11.1%) vs baseline: -0.1%

Memory: ✅ 68.066MB (SLO: <70.500MB -3.5%) vs baseline: +4.7%

✅ span-code-origin

Time: ✅ 22.772ms (SLO: <28.200ms 📉 -19.2%) vs baseline: ~same

Memory: ✅ 69.309MB (SLO: <71.000MB -2.4%) vs baseline: +5.0%

✅ tracer

Time: ✅ 19.304ms (SLO: <21.750ms 📉 -11.2%) vs baseline: +0.2%

Memory: ✅ 67.892MB (SLO: <70.000MB -3.0%) vs baseline: +4.7%

✅ tracer-and-profiler

Time: ✅ 21.346ms (SLO: <23.500ms -9.2%) vs baseline: ~same

Memory: ✅ 69.226MB (SLO: <71.000MB -2.5%) vs baseline: +5.2%

✅ tracer-dont-create-db-spans

Time: ✅ 19.303ms (SLO: <21.500ms 📉 -10.2%) vs baseline: ~same

Memory: ✅ 67.810MB (SLO: <70.000MB -3.1%) vs baseline: +4.4%

✅ tracer-minimal

Time: ✅ 16.697ms (SLO: <17.500ms -4.6%) vs baseline: +0.3%

Memory: ✅ 67.771MB (SLO: <70.000MB -3.2%) vs baseline: +4.8%

✅ tracer-native

Time: ✅ 19.166ms (SLO: <21.750ms 📉 -11.9%) vs baseline: -0.4%

Memory: ✅ 67.967MB (SLO: <72.500MB -6.3%) vs baseline: +4.8%

✅ tracer-no-caches

Time: ✅ 17.277ms (SLO: <19.650ms 📉 -12.1%) vs baseline: ~same

Memory: ✅ 67.830MB (SLO: <70.000MB -3.1%) vs baseline: +4.8%

✅ tracer-no-databases

Time: ✅ 18.766ms (SLO: <20.100ms -6.6%) vs baseline: +0.2%

Memory: ✅ 67.731MB (SLO: <70.000MB -3.2%) vs baseline: +4.8%

✅ tracer-no-middleware

Time: ✅ 18.956ms (SLO: <21.500ms 📉 -11.8%) vs baseline: +0.2%

Memory: ✅ 67.830MB (SLO: <70.000MB -3.1%) vs baseline: +4.9%

✅ tracer-no-templates

Time: ✅ 19.079ms (SLO: <22.000ms 📉 -13.3%) vs baseline: -0.1%

Memory: ✅ 67.692MB (SLO: <70.500MB -4.0%) vs baseline: +4.6%

✅ errortrackingdjangosimple - 6/6

✅ errortracking-enabled-all

Time: ✅ 16.338ms (SLO: <19.850ms 📉 -17.7%) vs baseline: +0.2%

Memory: ✅ 67.711MB (SLO: <70.000MB -3.3%) vs baseline: +4.8%

✅ errortracking-enabled-user

Time: ✅ 16.430ms (SLO: <19.400ms 📉 -15.3%) vs baseline: +0.8%

Memory: ✅ 67.745MB (SLO: <70.000MB -3.2%) vs baseline: +5.0%

✅ tracer-enabled

Time: ✅ 16.336ms (SLO: <19.450ms 📉 -16.0%) vs baseline: +0.1%

Memory: ✅ 67.709MB (SLO: <70.000MB -3.3%) vs baseline: +4.9%

✅ errortrackingflasksqli - 6/6

✅ errortracking-enabled-all

Time: ✅ 2.074ms (SLO: <2.300ms -9.8%) vs baseline: +0.4%

Memory: ✅ 54.696MB (SLO: <56.500MB -3.2%) vs baseline: +5.0%

✅ errortracking-enabled-user

Time: ✅ 2.083ms (SLO: <2.250ms -7.4%) vs baseline: +0.8%

Memory: ✅ 54.460MB (SLO: <56.500MB -3.6%) vs baseline: +4.6%

✅ tracer-enabled

Time: ✅ 2.070ms (SLO: <2.300ms -10.0%) vs baseline: -0.1%

Memory: ✅ 54.578MB (SLO: <56.500MB -3.4%) vs baseline: +4.9%

✅ flasksimple - 18/18

✅ appsec-get

Time: ✅ 4.577ms (SLO: <4.750ms -3.6%) vs baseline: -0.3%

Memory: ✅ 64.051MB (SLO: <66.500MB -3.7%) vs baseline: +4.8%

✅ appsec-post

Time: ✅ 6.601ms (SLO: <6.750ms -2.2%) vs baseline: ~same

Memory: ✅ 64.386MB (SLO: <66.500MB -3.2%) vs baseline: +4.8%

✅ appsec-telemetry

Time: ✅ 4.577ms (SLO: <4.750ms -3.6%) vs baseline: -0.4%

Memory: ✅ 64.082MB (SLO: <66.500MB -3.6%) vs baseline: +4.9%

✅ debugger

Time: ✅ 1.856ms (SLO: <2.000ms -7.2%) vs baseline: +0.2%

Memory: ✅ 47.927MB (SLO: <49.500MB -3.2%) vs baseline: +4.9%

✅ iast-get

Time: ✅ 1.854ms (SLO: <2.000ms -7.3%) vs baseline: -0.2%

Memory: ✅ 44.799MB (SLO: <49.000MB -8.6%) vs baseline: +4.8%

✅ profiler

Time: ✅ 1.924ms (SLO: <2.100ms -8.4%) vs baseline: ~same

Memory: ✅ 48.399MB (SLO: <50.000MB -3.2%) vs baseline: +4.8%

✅ resource-renaming

Time: ✅ 3.368ms (SLO: <3.650ms -7.7%) vs baseline: ~same

Memory: ✅ 54.686MB (SLO: <56.000MB -2.3%) vs baseline: +4.7%

✅ tracer

Time: ✅ 3.357ms (SLO: <3.650ms -8.0%) vs baseline: -0.1%

Memory: ✅ 54.729MB (SLO: <56.500MB -3.1%) vs baseline: +4.8%

✅ tracer-native

Time: ✅ 3.356ms (SLO: <3.650ms -8.1%) vs baseline: +0.1%

Memory: ✅ 54.671MB (SLO: <60.000MB -8.9%) vs baseline: +4.8%

✅ flasksqli - 6/6

✅ appsec-enabled

Time: ✅ 3.947ms (SLO: <4.200ms -6.0%) vs baseline: -0.3%

Memory: ✅ 64.468MB (SLO: <66.000MB -2.3%) vs baseline: +4.8%

✅ iast-enabled

Time: ✅ 2.429ms (SLO: <2.800ms 📉 -13.3%) vs baseline: -0.6%

Memory: ✅ 60.496MB (SLO: <62.500MB -3.2%) vs baseline: +4.8%

✅ tracer-enabled

Time: ✅ 2.056ms (SLO: <2.250ms -8.6%) vs baseline: -0.1%

Memory: ✅ 54.618MB (SLO: <56.500MB -3.3%) vs baseline: +4.7%

✅ httppropagationextract - 60/60

✅ all_styles_all_headers

Time: ✅ 82.452µs (SLO: <100.000µs 📉 -17.5%) vs baseline: +1.8%

Memory: ✅ 34.524MB (SLO: <35.500MB -2.7%) vs baseline: +4.4%

✅ b3_headers

Time: ✅ 14.197µs (SLO: <20.000µs 📉 -29.0%) vs baseline: -0.4%

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +4.7%

✅ b3_single_headers

Time: ✅ 13.301µs (SLO: <20.000µs 📉 -33.5%) vs baseline: -1.0%

Memory: ✅ 34.564MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ datadog_tracecontext_tracestate_not_propagated_on_trace_id_no_match

Time: ✅ 63.696µs (SLO: <80.000µs 📉 -20.4%) vs baseline: ~same

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.4%

✅ datadog_tracecontext_tracestate_propagated_on_trace_id_match

Time: ✅ 65.897µs (SLO: <80.000µs 📉 -17.6%) vs baseline: ~same

Memory: ✅ 34.465MB (SLO: <35.500MB -2.9%) vs baseline: +4.4%

✅ empty_headers

Time: ✅ 1.607µs (SLO: <10.000µs 📉 -83.9%) vs baseline: -0.3%

Memory: ✅ 34.524MB (SLO: <35.500MB -2.7%) vs baseline: +4.5%

✅ full_t_id_datadog_headers

Time: ✅ 22.808µs (SLO: <30.000µs 📉 -24.0%) vs baseline: +1.7%

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +4.9%

✅ invalid_priority_header

Time: ✅ 6.580µs (SLO: <10.000µs 📉 -34.2%) vs baseline: +0.6%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +5.1%

✅ invalid_span_id_header

Time: ✅ 6.706µs (SLO: <10.000µs 📉 -32.9%) vs baseline: +1.4%

Memory: ✅ 34.564MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ invalid_tags_header

Time: ✅ 6.580µs (SLO: <10.000µs 📉 -34.2%) vs baseline: +0.3%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +5.1%

✅ invalid_trace_id_header

Time: ✅ 6.586µs (SLO: <10.000µs 📉 -34.1%) vs baseline: +0.3%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.6%

✅ large_header_no_matches

Time: ✅ 27.616µs (SLO: <30.000µs -7.9%) vs baseline: ~same

Memory: ✅ 34.603MB (SLO: <35.500MB -2.5%) vs baseline: +4.6%

✅ large_valid_headers_all

Time: ✅ 28.751µs (SLO: <40.000µs 📉 -28.1%) vs baseline: ~same

Memory: ✅ 34.662MB (SLO: <35.500MB -2.4%) vs baseline: +5.0%

✅ medium_header_no_matches

Time: ✅ 9.894µs (SLO: <20.000µs 📉 -50.5%) vs baseline: -0.4%

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +4.7%

✅ medium_valid_headers_all

Time: ✅ 11.364µs (SLO: <20.000µs 📉 -43.2%) vs baseline: -0.2%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.6%

✅ none_propagation_style

Time: ✅ 1.720µs (SLO: <10.000µs 📉 -82.8%) vs baseline: ~same

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.6%

✅ tracecontext_headers

Time: ✅ 34.672µs (SLO: <40.000µs 📉 -13.3%) vs baseline: ~same

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +4.9%

✅ valid_headers_all

Time: ✅ 6.584µs (SLO: <10.000µs 📉 -34.2%) vs baseline: +0.2%

Memory: ✅ 34.603MB (SLO: <35.500MB -2.5%) vs baseline: +4.8%

✅ valid_headers_basic

Time: ✅ 6.121µs (SLO: <10.000µs 📉 -38.8%) vs baseline: -1.1%

Memory: ✅ 34.603MB (SLO: <35.500MB -2.5%) vs baseline: +4.9%

✅ wsgi_empty_headers

Time: ✅ 1.616µs (SLO: <10.000µs 📉 -83.8%) vs baseline: +0.4%

Memory: ✅ 34.505MB (SLO: <35.500MB -2.8%) vs baseline: +4.5%

✅ wsgi_invalid_priority_header

Time: ✅ 6.641µs (SLO: <10.000µs 📉 -33.6%) vs baseline: +0.5%

Memory: ✅ 34.682MB (SLO: <35.500MB -2.3%) vs baseline: +5.1%

✅ wsgi_invalid_span_id_header

Time: ✅ 1.630µs (SLO: <10.000µs 📉 -83.7%) vs baseline: +2.0%

Memory: ✅ 34.485MB (SLO: <35.500MB -2.9%) vs baseline: +4.3%

✅ wsgi_invalid_tags_header

Time: ✅ 6.640µs (SLO: <10.000µs 📉 -33.6%) vs baseline: +0.2%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.7%

✅ wsgi_invalid_trace_id_header

Time: ✅ 6.597µs (SLO: <10.000µs 📉 -34.0%) vs baseline: +0.1%

Memory: ✅ 34.603MB (SLO: <35.500MB -2.5%) vs baseline: +5.0%

✅ wsgi_large_header_no_matches

Time: ✅ 28.685µs (SLO: <40.000µs 📉 -28.3%) vs baseline: ~same

Memory: ✅ 34.564MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ wsgi_large_valid_headers_all

Time: ✅ 30.199µs (SLO: <40.000µs 📉 -24.5%) vs baseline: +0.9%

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +4.9%

✅ wsgi_medium_header_no_matches

Time: ✅ 10.169µs (SLO: <20.000µs 📉 -49.2%) vs baseline: +0.4%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.9%

✅ wsgi_medium_valid_headers_all

Time: ✅ 11.608µs (SLO: <20.000µs 📉 -42.0%) vs baseline: ~same

Memory: ✅ 34.662MB (SLO: <35.500MB -2.4%) vs baseline: +4.9%

✅ wsgi_valid_headers_all

Time: ✅ 6.714µs (SLO: <10.000µs 📉 -32.9%) vs baseline: +1.3%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.6%

✅ wsgi_valid_headers_basic

Time: ✅ 6.176µs (SLO: <10.000µs 📉 -38.2%) vs baseline: -0.3%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.9%

✅ httppropagationinject - 16/16

✅ ids_only

Time: ✅ 20.968µs (SLO: <30.000µs 📉 -30.1%) vs baseline: +0.3%

Memory: ✅ 34.505MB (SLO: <35.500MB -2.8%) vs baseline: +4.6%

✅ with_all

Time: ✅ 27.862µs (SLO: <40.000µs 📉 -30.3%) vs baseline: +0.7%

Memory: ✅ 34.564MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ with_dd_origin

Time: ✅ 24.739µs (SLO: <30.000µs 📉 -17.5%) vs baseline: +0.2%

Memory: ✅ 34.524MB (SLO: <35.500MB -2.7%) vs baseline: +4.8%

✅ with_priority_and_origin

Time: ✅ 25.141µs (SLO: <40.000µs 📉 -37.1%) vs baseline: +4.6%

Memory: ✅ 34.662MB (SLO: <35.500MB -2.4%) vs baseline: +5.0%

✅ with_sampling_priority

Time: ✅ 21.047µs (SLO: <30.000µs 📉 -29.8%) vs baseline: +0.6%

Memory: ✅ 34.544MB (SLO: <35.500MB -2.7%) vs baseline: +4.6%

✅ with_tags

Time: ✅ 27.288µs (SLO: <40.000µs 📉 -31.8%) vs baseline: +5.6%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ with_tags_invalid

Time: ✅ 28.734µs (SLO: <40.000µs 📉 -28.2%) vs baseline: +5.9%

Memory: ✅ 34.505MB (SLO: <35.500MB -2.8%) vs baseline: +4.7%

✅ with_tags_max_size

Time: ✅ 27.312µs (SLO: <40.000µs 📉 -31.7%) vs baseline: +4.4%

Memory: ✅ 34.524MB (SLO: <35.500MB -2.7%) vs baseline: +4.6%

✅ iast_aspects - 40/40

✅ re_expand_aspect

Time: ✅ 31.862µs (SLO: <40.000µs 📉 -20.3%) vs baseline: +0.5%

Memory: ✅ 39.931MB (SLO: <41.000MB -2.6%) vs baseline: +5.1%

✅ re_expand_noaspect

Time: ✅ 29.640µs (SLO: <40.000µs 📉 -25.9%) vs baseline: +3.2%

Memory: ✅ 39.852MB (SLO: <41.000MB -2.8%) vs baseline: +5.1%

✅ re_findall_aspect

Time: ✅ 2.932µs (SLO: <10.000µs 📉 -70.7%) vs baseline: +0.7%

Memory: ✅ 39.793MB (SLO: <41.000MB -2.9%) vs baseline: +4.6%

✅ re_findall_noaspect

Time: ✅ 1.416µs (SLO: <10.000µs 📉 -85.8%) vs baseline: -0.3%

Memory: ✅ 39.813MB (SLO: <41.000MB -2.9%) vs baseline: +4.7%

✅ re_finditer_aspect

Time: ✅ 4.488µs (SLO: <10.000µs 📉 -55.1%) vs baseline: +1.5%

Memory: ✅ 39.911MB (SLO: <41.000MB -2.7%) vs baseline: +5.1%

✅ re_finditer_noaspect

Time: ✅ 1.407µs (SLO: <10.000µs 📉 -85.9%) vs baseline: +0.6%

Memory: ✅ 39.892MB (SLO: <41.000MB -2.7%) vs baseline: +4.8%

✅ re_fullmatch_aspect

Time: ✅ 2.913µs (SLO: <10.000µs 📉 -70.9%) vs baseline: +8.7%

Memory: ✅ 39.892MB (SLO: <41.000MB -2.7%) vs baseline: +5.0%

✅ re_fullmatch_noaspect

Time: ✅ 1.292µs (SLO: <10.000µs 📉 -87.1%) vs baseline: ~same

Memory: ✅ 39.872MB (SLO: <41.000MB -2.8%) vs baseline: +5.0%

✅ re_group_aspect

Time: ✅ 2.926µs (SLO: <10.000µs 📉 -70.7%) vs baseline: -0.2%

Memory: ✅ 39.715MB (SLO: <41.000MB -3.1%) vs baseline: +4.8%

✅ re_group_noaspect

Time: ✅ 1.640µs (SLO: <10.000µs 📉 -83.6%) vs baseline: +0.9%

Memory: ✅ 39.931MB (SLO: <41.000MB -2.6%) vs baseline: +4.9%

✅ re_groups_aspect

Time: ✅ 3.038µs (SLO: <10.000µs 📉 -69.6%) vs baseline: -1.4%

Memory: ✅ 39.852MB (SLO: <41.000MB -2.8%) vs baseline: +5.1%

✅ re_groups_noaspect

Time: ✅ 1.721µs (SLO: <10.000µs 📉 -82.8%) vs baseline: +0.3%

Memory: ✅ 39.813MB (SLO: <41.000MB -2.9%) vs baseline: +4.5%

✅ re_match_aspect

Time: ✅ 2.673µs (SLO: <10.000µs 📉 -73.3%) vs baseline: -2.1%

Memory: ✅ 39.813MB (SLO: <41.000MB -2.9%) vs baseline: +4.8%

✅ re_match_noaspect

Time: ✅ 1.297µs (SLO: <10.000µs 📉 -87.0%) vs baseline: -2.7%

Memory: ✅ 39.793MB (SLO: <41.000MB -2.9%) vs baseline: +4.9%

✅ re_search_aspect

Time: ✅ 2.568µs (SLO: <10.000µs 📉 -74.3%) vs baseline: +0.9%

Memory: ✅ 39.911MB (SLO: <41.000MB -2.7%) vs baseline: +5.0%

✅ re_search_noaspect

Time: ✅ 1.198µs (SLO: <10.000µs 📉 -88.0%) vs baseline: -0.7%

Memory: ✅ 39.793MB (SLO: <41.000MB -2.9%) vs baseline: +4.7%

✅ re_sub_aspect

Time: ✅ 3.373µs (SLO: <10.000µs 📉 -66.3%) vs baseline: -0.6%

Memory: ✅ 39.892MB (SLO: <41.000MB -2.7%) vs baseline: +4.9%

✅ re_sub_noaspect

Time: ✅ 1.535µs (SLO: <10.000µs 📉 -84.7%) vs baseline: +0.4%

Memory: ✅ 39.813MB (SLO: <41.000MB -2.9%) vs baseline: +4.9%

✅ re_subn_aspect

Time: ✅ 3.592µs (SLO: <10.000µs 📉 -64.1%) vs baseline: -0.3%

Memory: ✅ 39.892MB (SLO: <41.000MB -2.7%) vs baseline: +5.1%

✅ re_subn_noaspect

Time: ✅ 1.605µs (SLO: <10.000µs 📉 -84.0%) vs baseline: +0.1%

Memory: ✅ 40.010MB (SLO: <41.000MB -2.4%) vs baseline: +5.3%

✅ iastaspectsospath - 24/24

✅ ospathbasename_aspect

Time: ✅ 4.327µs (SLO: <10.000µs 📉 -56.7%) vs baseline: +1.8%

Memory: ✅ 39.852MB (SLO: <41.000MB -2.8%) vs baseline: +4.8%

✅ ospathbasename_noaspect

Time: ✅ 1.079µs (SLO: <10.000µs 📉 -89.2%) vs baseline: ~same

Memory: ✅ 39.833MB (SLO: <41.000MB -2.8%) vs baseline: +4.8%

✅ ospathjoin_aspect

Time: ✅ 6.187µs (SLO: <10.000µs 📉 -38.1%) vs baseline: -0.9%

Memory: ✅ 39.872MB (SLO: <41.000MB -2.8%) vs baseline: +5.3%

✅ ospathjoin_noaspect

Time: ✅ 2.299µs (SLO: <10.000µs 📉 -77.0%) vs baseline: +0.6%

Memory: ✅ 39.774MB (SLO: <41.000MB -3.0%) vs baseline: +4.5%

✅ ospathnormcase_aspect

Time: ✅ 3.542µs (SLO: <10.000µs 📉 -64.6%) vs baseline: -1.0%

Memory: ✅ 39.793MB (SLO: <41.000MB -2.9%) vs baseline: +4.7%

✅ ospathnormcase_noaspect

Time: ✅ 0.575µs (SLO: <10.000µs 📉 -94.3%) vs baseline: +1.9%

Memory: ✅ 39.813MB (SLO: <41.000MB -2.9%) vs baseline: +4.6%

✅ ospathsplit_aspect

Time: ✅ 4.904µs (SLO: <10.000µs 📉 -51.0%) vs baseline: +0.7%

Memory: ✅ 39.774MB (SLO: <41.000MB -3.0%) vs baseline: +4.7%

✅ ospathsplit_noaspect

Time: ✅ 1.582µs (SLO: <10.000µs 📉 -84.2%) vs baseline: +0.3%

Memory: ✅ 39.951MB (SLO: <41.000MB -2.6%) vs baseline: +5.0%

✅ ospathsplitdrive_aspect

Time: ✅ 3.719µs (SLO: <10.000µs 📉 -62.8%) vs baseline: -0.1%

Memory: ✅ 39.793MB (SLO: <41.000MB -2.9%) vs baseline: +4.7%

✅ ospathsplitdrive_noaspect

Time: ✅ 0.700µs (SLO: <10.000µs 📉 -93.0%) vs baseline: +0.5%

Memory: ✅ 39.793MB (SLO: <41.000MB -2.9%) vs baseline: +4.7%

✅ ospathsplitext_aspect

Time: ✅ 4.611µs (SLO: <10.000µs 📉 -53.9%) vs baseline: -0.4%

Memory: ✅ 39.754MB (SLO: <41.000MB -3.0%) vs baseline: +4.7%

✅ ospathsplitext_noaspect

Time: ✅ 1.371µs (SLO: <10.000µs 📉 -86.3%) vs baseline: +0.2%

Memory: ✅ 39.774MB (SLO: <41.000MB -3.0%) vs baseline: +4.7%

✅ iastaspectssplit - 12/12

✅ rsplit_aspect

Time: ✅ 1.389µs (SLO: <10.000µs 📉 -86.1%) vs baseline: +0.2%

Memory: ✅ 39.852MB (SLO: <41.000MB -2.8%) vs baseline: +4.8%

✅ rsplit_noaspect

Time: ✅ 0.580µs (SLO: <10.000µs 📉 -94.2%) vs baseline: +0.4%

Memory: ✅ 39.911MB (SLO: <41.000MB -2.7%) vs baseline: +5.2%

✅ split_aspect

Time: ✅ 1.358µs (SLO: <10.000µs 📉 -86.4%) vs baseline: -0.6%

Memory: ✅ 39.951MB (SLO: <41.000MB -2.6%) vs baseline: +4.9%

✅ split_noaspect

Time: ✅ 0.572µs (SLO: <10.000µs 📉 -94.3%) vs baseline: -0.9%

Memory: ✅ 39.813MB (SLO: <41.000MB -2.9%) vs baseline: +4.5%

✅ splitlines_aspect

Time: ✅ 1.378µs (SLO: <10.000µs 📉 -86.2%) vs baseline: -1.5%

Memory: ✅ 39.970MB (SLO: <41.000MB -2.5%) vs baseline: +5.0%

✅ splitlines_noaspect

Time: ✅ 0.587µs (SLO: <10.000µs 📉 -94.1%) vs baseline: +0.5%

Memory: ✅ 39.852MB (SLO: <41.000MB -2.8%) vs baseline: +4.8%

✅ otelsdkspan - 24/24

✅ add-event

Time: ✅ 40.348ms (SLO: <42.000ms -3.9%) vs baseline: +0.3%

Memory: ✅ 36.923MB (SLO: <39.000MB -5.3%) vs baseline: +4.7%

✅ add-link

Time: ✅ 36.168ms (SLO: <38.550ms -6.2%) vs baseline: +0.3%

Memory: ✅ 37.021MB (SLO: <39.000MB -5.1%) vs baseline: +4.9%

✅ add-metrics

Time: ✅ 218.937ms (SLO: <232.000ms -5.6%) vs baseline: -0.5%

Memory: ✅ 36.864MB (SLO: <39.000MB -5.5%) vs baseline: +4.5%

✅ add-tags

Time: ✅ 212.436ms (SLO: <221.600ms -4.1%) vs baseline: +1.4%

Memory: ✅ 36.844MB (SLO: <39.000MB -5.5%) vs baseline: +4.4%

✅ get-context

Time: ✅ 29.593ms (SLO: <31.300ms -5.5%) vs baseline: +2.2%

Memory: ✅ 36.962MB (SLO: <39.000MB -5.2%) vs baseline: +4.7%

✅ is-recording

Time: ✅ 29.000ms (SLO: <31.000ms -6.5%) vs baseline: ~same

Memory: ✅ 37.061MB (SLO: <39.000MB -5.0%) vs baseline: +5.1%

✅ record-exception

Time: ✅ 63.321ms (SLO: <65.850ms -3.8%) vs baseline: +0.2%

Memory: ✅ 36.884MB (SLO: <39.000MB -5.4%) vs baseline: +4.4%

✅ set-status

Time: ✅ 32.264ms (SLO: <34.150ms -5.5%) vs baseline: +1.1%

Memory: ✅ 36.962MB (SLO: <39.000MB -5.2%) vs baseline: +4.6%

✅ start

Time: ✅ 28.781ms (SLO: <30.150ms -4.5%) vs baseline: ~same

Memory: ✅ 36.923MB (SLO: <39.000MB -5.3%) vs baseline: +4.9%

✅ start-finish

Time: ✅ 34.296ms (SLO: <35.350ms -3.0%) vs baseline: +1.1%

Memory: ✅ 36.825MB (SLO: <39.000MB -5.6%) vs baseline: +4.3%

✅ start-finish-telemetry

Time: ✅ 33.839ms (SLO: <35.450ms -4.5%) vs baseline: -0.2%

Memory: ✅ 36.923MB (SLO: <39.000MB -5.3%) vs baseline: +4.6%

✅ update-name

Time: ✅ 31.139ms (SLO: <33.400ms -6.8%) vs baseline: +1.1%

Memory: ✅ 36.903MB (SLO: <39.000MB -5.4%) vs baseline: +4.5%

✅ otelspan - 22/22

✅ add-event

Time: ✅ 38.521ms (SLO: <47.150ms 📉 -18.3%) vs baseline: +0.4%

Memory: ✅ 38.955MB (SLO: <47.000MB 📉 -17.1%) vs baseline: +4.4%

✅ add-metrics

Time: ✅ 258.689ms (SLO: <344.800ms 📉 -25.0%) vs baseline: +0.7%

Memory: ✅ 43.313MB (SLO: <47.500MB -8.8%) vs baseline: +4.8%

✅ add-tags

Time: ✅ 314.489ms (SLO: <321.000ms -2.0%) vs baseline: -0.1%

Memory: ✅ 43.258MB (SLO: <47.500MB -8.9%) vs baseline: +4.8%

✅ get-context

Time: ✅ 78.797ms (SLO: <92.350ms 📉 -14.7%) vs baseline: +0.7%

Memory: ✅ 39.366MB (SLO: <46.500MB 📉 -15.3%) vs baseline: +4.8%

✅ is-recording

Time: ✅ 36.034ms (SLO: <44.500ms 📉 -19.0%) vs baseline: -0.1%

Memory: ✅ 38.878MB (SLO: <47.500MB 📉 -18.2%) vs baseline: +4.7%

✅ record-exception

Time: ✅ 57.249ms (SLO: <67.650ms 📉 -15.4%) vs baseline: +0.3%

Memory: ✅ 39.418MB (SLO: <47.000MB 📉 -16.1%) vs baseline: +4.8%

✅ set-status

Time: ✅ 42.399ms (SLO: <50.400ms 📉 -15.9%) vs baseline: ~same

Memory: ✅ 38.953MB (SLO: <47.000MB 📉 -17.1%) vs baseline: +4.7%

✅ start

Time: ✅ 35.310ms (SLO: <43.450ms 📉 -18.7%) vs baseline: -0.3%

Memory: ✅ 38.853MB (SLO: <47.000MB 📉 -17.3%) vs baseline: +4.5%

✅ start-finish

Time: ✅ 81.707ms (SLO: <88.000ms -7.2%) vs baseline: -0.2%

Memory: ✅ 36.628MB (SLO: <46.500MB 📉 -21.2%) vs baseline: +4.6%

✅ start-finish-telemetry

Time: ✅ 83.474ms (SLO: <89.000ms -6.2%) vs baseline: +0.2%

Memory: ✅ 36.569MB (SLO: <46.500MB 📉 -21.4%) vs baseline: +4.6%

✅ update-name

Time: ✅ 36.819ms (SLO: <45.150ms 📉 -18.5%) vs baseline: -0.4%

Memory: ✅ 38.991MB (SLO: <47.000MB 📉 -17.0%) vs baseline: +4.7%

✅ packagespackageforrootmodulemapping - 4/4

✅ cache_off

Time: ✅ 340.785ms (SLO: <354.300ms -3.8%) vs baseline: -0.6%

Memory: ✅ 40.306MB (SLO: <41.500MB -2.9%) vs baseline: +4.9%

✅ cache_on

Time: ✅ 0.387µs (SLO: <10.000µs 📉 -96.1%) vs baseline: +1.5%

Memory: ✅ 39.432MB (SLO: <41.000MB -3.8%) vs baseline: +4.9%

✅ packagesupdateimporteddependencies - 24/24

✅ import_many

Time: ✅ 154.867µs (SLO: <170.000µs -8.9%) vs baseline: ~same

Memory: ✅ 39.177MB (SLO: <41.000MB -4.4%) vs baseline: +5.0%

✅ import_many_cached

Time: ✅ 121.277µs (SLO: <130.000µs -6.7%) vs baseline: +0.2%

Memory: ✅ 38.843MB (SLO: <41.000MB -5.3%) vs baseline: +4.0%

✅ import_many_stdlib

Time: ✅ 1.663ms (SLO: <1.750ms -5.0%) vs baseline: -0.4%

Memory: ✅ 39.341MB (SLO: <41.000MB -4.0%) vs baseline: +4.5%

✅ import_many_stdlib_cached

Time: ✅ 0.992ms (SLO: <1.100ms -9.8%) vs baseline: -0.5%

Memory: ✅ 39.094MB (SLO: <41.000MB -4.6%) vs baseline: +4.0%

✅ import_many_unknown

Time: ✅ 828.313µs (SLO: <890.000µs -6.9%) vs baseline: ~same

Memory: ✅ 39.281MB (SLO: <41.000MB -4.2%) vs baseline: +4.7%

✅ import_many_unknown_cached

Time: ✅ 788.446µs (SLO: <870.000µs -9.4%) vs baseline: -1.0%

Memory: ✅ 39.182MB (SLO: <41.000MB -4.4%) vs baseline: +4.2%

✅ import_one

Time: ✅ 19.683µs (SLO: <30.000µs 📉 -34.4%) vs baseline: -0.6%

Memory: ✅ 39.036MB (SLO: <41.000MB -4.8%) vs baseline: +4.7%

✅ import_one_cache

Time: ✅ 6.263µs (SLO: <10.000µs 📉 -37.4%) vs baseline: -0.2%

Memory: ✅ 38.934MB (SLO: <41.000MB -5.0%) vs baseline: +3.6%

✅ import_one_stdlib

Time: ✅ 18.626µs (SLO: <20.000µs -6.9%) vs baseline: -0.2%

Memory: ✅ 38.937MB (SLO: <41.000MB -5.0%) vs baseline: +3.8%

✅ import_one_stdlib_cache

Time: ✅ 6.247µs (SLO: <10.000µs 📉 -37.5%) vs baseline: -0.8%

Memory: ✅ 38.975MB (SLO: <41.000MB -4.9%) vs baseline: +4.4%

✅ import_one_unknown

Time: ✅ 45.424µs (SLO: <50.000µs -9.2%) vs baseline: ~same

Memory: ✅ 38.982MB (SLO: <41.000MB -4.9%) vs baseline: +3.9%

✅ import_one_unknown_cache

Time: ✅ 6.262µs (SLO: <10.000µs 📉 -37.4%) vs baseline: -0.5%

Memory: ✅ 38.759MB (SLO: <41.000MB -5.5%) vs baseline: +4.0%

✅ ratelimiter - 12/12

✅ defaults

Time: ✅ 2.348µs (SLO: <10.000µs 📉 -76.5%) vs baseline: +0.1%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ high_rate_limit

Time: ✅ 2.430µs (SLO: <10.000µs 📉 -75.7%) vs baseline: +1.0%

Memory: ✅ 34.524MB (SLO: <35.500MB -2.7%) vs baseline: +4.7%

✅ long_window

Time: ✅ 2.372µs (SLO: <10.000µs 📉 -76.3%) vs baseline: +0.2%

Memory: ✅ 34.603MB (SLO: <35.500MB -2.5%) vs baseline: +4.9%

✅ low_rate_limit

Time: ✅ 2.369µs (SLO: <10.000µs 📉 -76.3%) vs baseline: +1.1%

Memory: ✅ 34.662MB (SLO: <35.500MB -2.4%) vs baseline: +5.3%

✅ no_rate_limit

Time: ✅ 0.829µs (SLO: <10.000µs 📉 -91.7%) vs baseline: +0.3%

Memory: ✅ 34.564MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ short_window

Time: ✅ 2.501µs (SLO: <10.000µs 📉 -75.0%) vs baseline: ~same

Memory: ✅ 34.505MB (SLO: <35.500MB -2.8%) vs baseline: +4.6%

✅ recursivecomputation - 8/8

✅ deep

Time: ✅ 309.056ms (SLO: <320.950ms -3.7%) vs baseline: -0.3%

Memory: ✅ 35.409MB (SLO: <36.500MB -3.0%) vs baseline: +5.0%

✅ deep-profiled

Time: ✅ 330.812ms (SLO: <359.150ms -7.9%) vs baseline: +0.1%

Memory: ✅ 39.204MB (SLO: <40.500MB -3.2%) vs baseline: +4.6%

✅ medium

Time: ✅ 6.979ms (SLO: <7.400ms -5.7%) vs baseline: -0.3%

Memory: ✅ 34.564MB (SLO: <35.500MB -2.6%) vs baseline: +4.6%

✅ shallow

Time: ✅ 0.939ms (SLO: <1.050ms 📉 -10.5%) vs baseline: -0.2%

Memory: ✅ 34.603MB (SLO: <35.500MB -2.5%) vs baseline: +4.9%

✅ samplingrules - 8/8

✅ average_match

Time: ✅ 137.521µs (SLO: <290.000µs 📉 -52.6%) vs baseline: -0.5%

Memory: ✅ 34.426MB (SLO: <35.500MB -3.0%) vs baseline: +4.4%

✅ high_match

Time: ✅ 173.984µs (SLO: <480.000µs 📉 -63.8%) vs baseline: ~same

Memory: ✅ 34.406MB (SLO: <35.500MB -3.1%) vs baseline: +4.4%

✅ low_match

Time: ✅ 99.015µs (SLO: <120.000µs 📉 -17.5%) vs baseline: +0.7%

Memory: ✅ 603.190MB (SLO: <700.000MB 📉 -13.8%) vs baseline: +4.8%

✅ very_low_match

Time: ✅ 2.666ms (SLO: <8.500ms 📉 -68.6%) vs baseline: +0.6%

Memory: ✅ 70.563MB (SLO: <75.000MB -5.9%) vs baseline: +4.7%

✅ sethttpmeta - 32/32

✅ all-disabled

Time: ✅ 10.541µs (SLO: <20.000µs 📉 -47.3%) vs baseline: +0.2%

Memory: ✅ 35.016MB (SLO: <36.000MB -2.7%) vs baseline: +4.7%

✅ all-enabled

Time: ✅ 39.979µs (SLO: <50.000µs 📉 -20.0%) vs baseline: -0.2%

Memory: ✅ 35.016MB (SLO: <36.000MB -2.7%) vs baseline: +4.8%

✅ collectipvariant_exists

Time: ✅ 40.839µs (SLO: <50.000µs 📉 -18.3%) vs baseline: +0.2%

Memory: ✅ 34.996MB (SLO: <36.000MB -2.8%) vs baseline: +4.8%

✅ no-collectipvariant

Time: ✅ 40.085µs (SLO: <50.000µs 📉 -19.8%) vs baseline: +0.4%

Memory: ✅ 34.977MB (SLO: <36.000MB -2.8%) vs baseline: +4.9%

✅ no-useragentvariant

Time: ✅ 38.659µs (SLO: <50.000µs 📉 -22.7%) vs baseline: -0.4%

Memory: ✅ 34.957MB (SLO: <36.000MB -2.9%) vs baseline: +4.6%

✅ obfuscation-no-query

Time: ✅ 40.690µs (SLO: <50.000µs 📉 -18.6%) vs baseline: ~same

Memory: ✅ 35.095MB (SLO: <36.000MB -2.5%) vs baseline: +5.0%

✅ obfuscation-regular-case-explicit-query

Time: ✅ 76.110µs (SLO: <90.000µs 📉 -15.4%) vs baseline: +0.7%

Memory: ✅ 35.311MB (SLO: <36.500MB -3.3%) vs baseline: +4.6%

✅ obfuscation-regular-case-implicit-query

Time: ✅ 76.649µs (SLO: <90.000µs 📉 -14.8%) vs baseline: +0.5%

Memory: ✅ 35.291MB (SLO: <36.500MB -3.3%) vs baseline: +4.3%

✅ obfuscation-send-querystring-disabled

Time: ✅ 154.460µs (SLO: <170.000µs -9.1%) vs baseline: +0.3%

Memory: ✅ 35.409MB (SLO: <36.500MB -3.0%) vs baseline: +4.7%

✅ obfuscation-worst-case-explicit-query

Time: ✅ 148.789µs (SLO: <160.000µs -7.0%) vs baseline: ~same

Memory: ✅ 35.271MB (SLO: <36.500MB -3.4%) vs baseline: +4.5%

✅ obfuscation-worst-case-implicit-query

Time: ✅ 154.971µs (SLO: <170.000µs -8.8%) vs baseline: +0.3%

Memory: ✅ 35.448MB (SLO: <36.500MB -2.9%) vs baseline: +4.8%

✅ useragentvariant_exists_1

Time: ✅ 39.525µs (SLO: <50.000µs 📉 -21.0%) vs baseline: ~same

Memory: ✅ 34.957MB (SLO: <36.000MB -2.9%) vs baseline: +4.6%

✅ useragentvariant_exists_2

Time: ✅ 40.723µs (SLO: <50.000µs 📉 -18.6%) vs baseline: +0.2%

Memory: ✅ 34.996MB (SLO: <36.000MB -2.8%) vs baseline: +4.5%

✅ useragentvariant_exists_3

Time: ✅ 39.998µs (SLO: <50.000µs 📉 -20.0%) vs baseline: +0.2%

Memory: ✅ 34.918MB (SLO: <36.000MB -3.0%) vs baseline: +4.5%

✅ useragentvariant_not_exists_1

Time: ✅ 39.424µs (SLO: <50.000µs 📉 -21.2%) vs baseline: -0.9%

Memory: ✅ 34.977MB (SLO: <36.000MB -2.8%) vs baseline: +4.6%

✅ useragentvariant_not_exists_2

Time: ✅ 39.455µs (SLO: <50.000µs 📉 -21.1%) vs baseline: -0.5%

Memory: ✅ 34.996MB (SLO: <36.000MB -2.8%) vs baseline: +4.7%

✅ span - 26/26

✅ add-event

Time: ✅ 17.333ms (SLO: <22.500ms 📉 -23.0%) vs baseline: +0.1%

Memory: ✅ 36.494MB (SLO: <53.000MB 📉 -31.1%) vs baseline: +4.9%

✅ add-metrics

Time: ✅ 86.350ms (SLO: <93.500ms -7.6%) vs baseline: -0.3%

Memory: ✅ 40.918MB (SLO: <53.000MB 📉 -22.8%) vs baseline: +5.2%

✅ add-tags

Time: ✅ 139.080ms (SLO: <155.000ms 📉 -10.3%) vs baseline: +0.2%

Memory: ✅ 40.560MB (SLO: <53.000MB 📉 -23.5%) vs baseline: +5.0%

✅ get-context

Time: ✅ 16.176ms (SLO: <20.500ms 📉 -21.1%) vs baseline: +1.2%

Memory: ✅ 36.298MB (SLO: <53.000MB 📉 -31.5%) vs baseline: +4.7%

✅ is-recording

Time: ✅ 16.304ms (SLO: <20.500ms 📉 -20.5%) vs baseline: -0.1%

Memory: ✅ 36.271MB (SLO: <53.000MB 📉 -31.6%) vs baseline: +4.8%

✅ record-exception

Time: ✅ 35.428ms (SLO: <40.000ms 📉 -11.4%) vs baseline: ~same

Memory: ✅ 36.880MB (SLO: <53.000MB 📉 -30.4%) vs baseline: +4.7%

✅ set-status

Time: ✅ 17.926ms (SLO: <22.000ms 📉 -18.5%) vs baseline: +1.2%

Memory: ✅ 36.199MB (SLO: <53.000MB 📉 -31.7%) vs baseline: +4.4%

✅ start

Time: ✅ 16.077ms (SLO: <20.500ms 📉 -21.6%) vs baseline: +1.8%

Memory: ✅ 36.273MB (SLO: <53.000MB 📉 -31.6%) vs baseline: +4.6%

✅ start-finish

Time: ✅ 51.411ms (SLO: <52.500ms -2.1%) vs baseline: +0.8%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.8%

✅ start-finish-telemetry

Time: ✅ 52.318ms (SLO: <54.500ms -4.0%) vs baseline: ~same

Memory: ✅ 34.485MB (SLO: <35.500MB -2.9%) vs baseline: +4.6%

✅ start-finish-traceid128

Time: ✅ 55.178ms (SLO: <57.000ms -3.2%) vs baseline: +2.1%

Memory: ✅ 34.583MB (SLO: <35.500MB -2.6%) vs baseline: +4.7%

✅ start-traceid128

Time: ✅ 16.365ms (SLO: <22.500ms 📉 -27.3%) vs baseline: ~same

Memory: ✅ 36.346MB (SLO: <53.000MB 📉 -31.4%) vs baseline: +4.6%

✅ update-name

Time: ✅ 16.515ms (SLO: <22.000ms 📉 -24.9%) vs baseline: +0.6%

Memory: ✅ 36.310MB (SLO: <53.000MB 📉 -31.5%) vs baseline: +4.4%

✅ tracer - 6/6

✅ large

Time: ✅ 29.162ms (SLO: <32.950ms 📉 -11.5%) vs baseline: +0.9%

Memory: ✅ 35.606MB (SLO: <36.500MB -2.5%) vs baseline: +4.4%

✅ medium

Time: ✅ 2.874ms (SLO: <3.200ms 📉 -10.2%) vs baseline: +0.3%

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +5.0%

✅ small

Time: ✅ 325.763µs (SLO: <370.000µs 📉 -12.0%) vs baseline: -0.2%

Memory: ✅ 34.485MB (SLO: <35.500MB -2.9%) vs baseline: +4.3%

ℹ️ Scenarios Missing SLO Configuration (9 scenarios)

The following scenarios exist in candidate data but have no SLO thresholds configured:

coreapiscenario-core_dispatch_listeners
coreapiscenario-core_dispatch_no_listeners
coreapiscenario-core_dispatch_with_results_listeners
coreapiscenario-core_dispatch_with_results_no_listeners
djangosimple-baseline
errortrackingdjangosimple-baseline
errortrackingflasksqli-baseline
flasksimple-baseline
flasksqli-baseline

P403n1x87 · 2025-11-21T16:16:26Z

ddtrace/profiling/collector/_memalloc_tb.cpp


-    Py_INCREF(name);
-    Py_INCREF(filename);
+    // Get thread native ID from Python


We can extract the thread tracking logic from echion and make generally available to the profiler, so that we have a convenient way of retrieving thread information within the native layer

dd-trace-py/ddtrace/internal/datadog/profiling/stack_v2/src/sampler.cpp

Line 253 in 53726a1

auto it = thread_info_map.find(id);

Awesome. lmk when that's available?

P403n1x87 · 2025-11-21T16:22:19Z

ddtrace/profiling/collector/_memalloc_tb.cpp

+    // Note: Sample.push_frame() comment says it "Assumes frames are pushed in leaf-order",
+    // but we push root-to-leaf. Set reverse_locations so the sample will be reversed when exported.
+    sample.set_reverse_locations(true);
+    for (PyFrameObject* frame = pyframe; frame != NULL;) {


We should avoid unwinding the stack using PyFrameObjects in versions of CPython where PyInterpreterFrame is available to avoid allocations (see e.g. https://github.com/P403n1x87/echion/blob/b6d048df7d22fba77b7996964817d2bded7ec08e/echion/stacks.h#L211-L223)

Also, because we probably hold the GIL here, it wouldn't make sense to ask Echion to give us the call stack because we don't need to make safe copies

danielsn added 10 commits November 20, 2025 15:37

Profiling: use sample instead of python traceback for memory profiler

d49e9b6

don't need to defend against uninitilized sample

805a7e8

able to handle multiple sample types

14c347e

reformat

2f0a225

cleaned up tests

32aa187

use native functions to get threadname and id

d68543b

use python thread names for now

8fe22f2

only export the sample

c93d834

tests pass without the python traceback at all

05f8aef

and now we just delete things, no freezer

05cf27b

danielsn added the Profiling Continous Profling label Nov 21, 2025

export_heap can be marked no_cypthon

aac261c

danielsn commented Nov 21, 2025

View reviewed changes

more stuff can be marked no_cypthon

2940414

danielsn commented Nov 21, 2025

View reviewed changes

ddtrace/profiling/collector/_memalloc_heap.cpp Outdated Show resolved Hide resolved

danielsn commented Nov 21, 2025

View reviewed changes

just directly delete old tracebacks in the map

7563130

danielsn commented Nov 21, 2025

View reviewed changes

try exporting old frames, see if it helps

0a240db

P403n1x87 reviewed Nov 21, 2025

View reviewed changes

danielsn changed the title ~~refactor(profiling): use native tracebacks in memalloc profiler~~ refactor(profiling): store memalloc samples as native objects Nov 21, 2025

more defensive threadinfo

536df5f

		assert "No samples found" in str(e)


		@pytest.mark.skip(reason="Temporarily suppressed - crashes with large number of samples")

refactor(profiling): store memalloc samples as native objects #15372

Are you sure you want to change the base?

refactor(profiling): store memalloc samples as native objects #15372

Conversation

danielsn commented Nov 21, 2025

Description

Testing

Risks

Additional Notes

Uh oh!

github-actions bot commented Nov 21, 2025

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

github-actions bot commented Nov 21, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Bootstrap import analysis

Summary

Import time breakdown

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

pr-commenter bot commented Nov 21, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Performance SLOs

✅ add_aspect

✅ add_inplace_aspect

✅ add_inplace_noaspect

✅ add_noaspect

✅ bytearray_aspect

✅ bytearray_extend_aspect

✅ bytearray_extend_noaspect

✅ bytearray_noaspect

✅ bytes_aspect

✅ bytes_noaspect

✅ bytesio_aspect

✅ bytesio_noaspect

✅ capitalize_aspect

✅ capitalize_noaspect

✅ casefold_aspect

✅ casefold_noaspect

✅ decode_aspect

✅ decode_noaspect

✅ encode_aspect

✅ encode_noaspect

✅ format_aspect

✅ format_map_aspect

✅ format_map_noaspect

✅ format_noaspect

✅ index_aspect

✅ index_noaspect

✅ join_aspect

✅ join_noaspect

✅ ljust_aspect

✅ ljust_noaspect

✅ lower_aspect

✅ lower_noaspect

✅ lstrip_aspect

✅ lstrip_noaspect

github-actions bot commented Nov 21, 2025 •

edited

Loading

pr-commenter bot commented Nov 21, 2025 •

edited

Loading