Kqr Row Cache Contention Check Gets -

def get(key): if key in cache: return cache[key] else: value = db.query("SELECT * FROM items WHERE id = ?", key) // slow cache[key] = value return value Because the cache was empty, all 10,000 threads saw a at the exact same moment. They all rushed to the database.

— KQR’s row cache for item:42 expired. 9:00:02 — 10,000 concurrent GET requests arrived simultaneously. kqr row cache contention check gets

From that day on, KQR’s monitoring dashboard had a new rule: If row cache contention check gets > 1000 per second — flip on single-flight mode. And the team learned a valuable lesson: sometimes, the most dangerous lock isn’t in your database — it’s in your cache’s eagerness to help . def get(key): if key in cache: return cache[key]

But they didn’t just rush to the database — they collided at the . You see, KQR’s cache was protected by a single, global synchronized block for writes. But they didn’t just rush to the database

She hot-patched KQR’s logic to use :

KQR’s cache logic looked like this (pseudocode):

def get(key): if key in cache: return cache[key] else: // Only one thread goes to DB; others wait for its result return cache.load_or_wait(key) Within 30 seconds, the contention ratio dropped from 1.00 to 0.001.