From 7ded6000f356ae5fe4e1fd73c6a2e278affd1777 Mon Sep 17 00:00:00 2001
From: Katie Byers <lobsterkatie@gmail.com>
Date: Mon, 24 Nov 2025 14:58:51 -0800
Subject: [PATCH] add options to control caching

---
 src/sentry/options/defaults.py | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/src/sentry/options/defaults.py b/src/sentry/options/defaults.py
index 00b3e00d8fe80e..950e31fc7fbcbf 100644
--- a/src/sentry/options/defaults.py
+++ b/src/sentry/options/defaults.py
@@ -2863,6 +2863,39 @@
     flags=FLAG_AUTOMATOR_MODIFIABLE,
 )
 
+# When handling grouphashes during ingest, use the cache to reduce postgres load. With secondary
+# grouphashes we want to use ones which are already there but not create new ones, so we track the
+# boolean result of their `.exists()` check. For all existing grouphashes, secondary or not, we know
+# that if they already have a group assigned they won't be modified, so in that case we also cache
+# the full `GroupHash` object. The killswitch below controls both caches, but they have separate
+# expiry times because the secondary grouphash existence cache is used less frequently and has a
+# lighter memory footprint, so we can afford to cache things there for longer.
+#
+# TODO: Check hit/miss rates for both caches and adjust the two expiry options accordingly.
+register(
+    "grouping.use_ingest_grouphash_caching",
+    type=Bool,
+    default=True,
+    flags=FLAG_AUTOMATOR_MODIFIABLE,
+)
+
+# How long to cache a boolean indicating whether or not a grouphash exists for a given secondary
+# hash value
+register(
+    "grouping.ingest_grouphash_existence_cache_expiry",
+    type=Int,
+    default=60,  # seconds
+    flags=FLAG_AUTOMATOR_MODIFIABLE,
+)
+
+# How long to cache actual `GroupHash` objects
+register(
+    "grouping.ingest_grouphash_object_cache_expiry",
+    type=Int,
+    default=60,  # seconds
+    flags=FLAG_AUTOMATOR_MODIFIABLE,
+)
+
 
 # Sample rate for double writing to experimental dsn
 register(