Merge pull request #66050 from ClickHouse/regex-cache-profile-events

rschu1ze · web-flow · commit 9b98abac42b1 · 2024-07-04T08:48:26.000Z
Add profile events for regex cache
diff --git a/src/Common/ProfileEvents.cpp b/src/Common/ProfileEvents.cpp
@@ -238,7 +238,12 @@
     \
     M(CannotRemoveEphemeralNode, "Number of times an error happened while trying to remove ephemeral node. This is not an issue, because our implementation of ZooKeeper library guarantee that the session will expire and the node will be removed.") \
     \
-    M(RegexpCreated, "Compiled regular expressions. Identical regular expressions compiled just once and cached forever.") \
+    M(RegexpWithMultipleNeedlesCreated, "Regular expressions with multiple needles (VectorScan library) compiled.") \
+    M(RegexpWithMultipleNeedlesGlobalCacheHit, "Number of times we fetched compiled regular expression with multiple needles (VectorScan library) from the global cache.") \
+    M(RegexpWithMultipleNeedlesGlobalCacheMiss, "Number of times we failed to fetch compiled regular expression with multiple needles (VectorScan library) from the global cache.") \
+    M(RegexpLocalCacheHit, "Number of times we fetched compiled regular expression from a local cache.") \
+    M(RegexpLocalCacheMiss, "Number of times we failed to fetch compiled regular expression from a local cache.") \
+    \
     M(ContextLock, "Number of times the lock of Context was acquired or tried to acquire. This is global lock.") \
     M(ContextLockWaitMicroseconds, "Context lock wait time in microseconds") \
     \
diff --git a/src/Functions/Regexps.h b/src/Functions/Regexps.h
@@ -23,7 +23,11 @@
 
 namespace ProfileEvents
 {
-extern const Event RegexpCreated;
+    extern const Event RegexpWithMultipleNeedlesCreated;
+    extern const Event RegexpWithMultipleNeedlesGlobalCacheHit;
+    extern const Event RegexpWithMultipleNeedlesGlobalCacheMiss;
+    extern const Event RegexpLocalCacheHit;
+    extern const Event RegexpLocalCacheMiss;
 }
 
 
@@ -72,18 +76,28 @@ class LocalCacheTable
         Bucket & bucket = known_regexps[hasher(pattern) % CACHE_SIZE];
 
         if (bucket.regexp == nullptr) [[unlikely]]
+        {
             /// insert new entry
+            ProfileEvents::increment(ProfileEvents::RegexpLocalCacheMiss);
             bucket = {pattern, std::make_shared<OptimizedRegularExpression>(createRegexp<like, no_capture, case_insensitive>(pattern))};
+        }
         else
+        {
             if (pattern != bucket.pattern)
+            {
                 /// replace existing entry
+                ProfileEvents::increment(ProfileEvents::RegexpLocalCacheMiss);
                 bucket = {pattern, std::make_shared<OptimizedRegularExpression>(createRegexp<like, no_capture, case_insensitive>(pattern))};
+            }
+            else
+                ProfileEvents::increment(ProfileEvents::RegexpLocalCacheHit);
+        }
 
         return bucket.regexp;
     }
 
 private:
-    constexpr static size_t CACHE_SIZE = 100; /// collision probability
+    constexpr static size_t CACHE_SIZE = 1'000; /// collision probability
 
     std::hash<String> hasher;
     struct Bucket
@@ -244,7 +258,7 @@ inline Regexps constructRegexps(const std::vector<String> & str_patterns, [[mayb
             throw Exception(ErrorCodes::BAD_ARGUMENTS, "Pattern '{}' failed with error '{}'", str_patterns[error->expression], String(error->message));
     }
 
-    ProfileEvents::increment(ProfileEvents::RegexpCreated);
+    ProfileEvents::increment(ProfileEvents::RegexpWithMultipleNeedlesCreated);
 
     /// We allocate the scratch space only once, then copy it across multiple threads with hs_clone_scratch
     /// function which is faster than allocating scratch space each time in each thread.
@@ -322,9 +336,11 @@ inline DeferredConstructedRegexpsPtr getOrSet(const std::vector<std::string_view
                 {
                     return constructRegexps<save_indices, with_edit_distance>(str_patterns, edit_distance);
                 });
+        ProfileEvents::increment(ProfileEvents::RegexpWithMultipleNeedlesGlobalCacheMiss);
         bucket = {std::move(str_patterns), edit_distance, deferred_constructed_regexps};
     }
     else
+    {
         if (bucket.patterns != str_patterns || bucket.edit_distance != edit_distance)
         {
             /// replace existing entry
@@ -333,8 +349,12 @@ inline DeferredConstructedRegexpsPtr getOrSet(const std::vector<std::string_view
                     {
                         return constructRegexps<save_indices, with_edit_distance>(str_patterns, edit_distance);
                     });
+            ProfileEvents::increment(ProfileEvents::RegexpWithMultipleNeedlesGlobalCacheMiss);
             bucket = {std::move(str_patterns), edit_distance, deferred_constructed_regexps};
         }
+        else
+            ProfileEvents::increment(ProfileEvents::RegexpWithMultipleNeedlesGlobalCacheHit);
+    }
 
     return bucket.regexps;
 }

Original file line number	Diff line number	Diff line change
`@@ -238,7 +238,12 @@`
`238`	`238`	`\`
`239`	`239`	`M(CannotRemoveEphemeralNode, "Number of times an error happened while trying to remove ephemeral node. This is not an issue, because our implementation of ZooKeeper library guarantee that the session will expire and the node will be removed.") \`
`240`	`240`	`\`
`241`		`- M(RegexpCreated, "Compiled regular expressions. Identical regular expressions compiled just once and cached forever.") \`
	`241`	`+ M(RegexpWithMultipleNeedlesCreated, "Regular expressions with multiple needles (VectorScan library) compiled.") \`
	`242`	`+ M(RegexpWithMultipleNeedlesGlobalCacheHit, "Number of times we fetched compiled regular expression with multiple needles (VectorScan library) from the global cache.") \`
	`243`	`+ M(RegexpWithMultipleNeedlesGlobalCacheMiss, "Number of times we failed to fetch compiled regular expression with multiple needles (VectorScan library) from the global cache.") \`
	`244`	`+ M(RegexpLocalCacheHit, "Number of times we fetched compiled regular expression from a local cache.") \`
	`245`	`+ M(RegexpLocalCacheMiss, "Number of times we failed to fetch compiled regular expression from a local cache.") \`
	`246`	`+ \`
`242`	`247`	`M(ContextLock, "Number of times the lock of Context was acquired or tried to acquire. This is global lock.") \`
`243`	`248`	`M(ContextLockWaitMicroseconds, "Context lock wait time in microseconds") \`
`244`	`249`	`\`