In Ceph version 17.2.5, a notable performance drop is observed when executing list
operations on non-existent objects, especially for large buckets undergoing high
concurrency with frequent updates.
For the context, initiating concurrent PUT/DELETE/LIST operations on 4 buckets, each
containing ~10 million objects, initially yields satisfactory latencies. However, as
updates continue to accumulate, the efficiency of the `negative list` operation diminishes
notably. I suspect that over time, with many object insertions and deletions, the bucket
index gets fragmented. While this affects all operations, negative lookups appear to be
particularly hampered, possibly because they necessitate a comprehensive scan of the
fragmented index.
With the LIST arguments defined as $prefix=xxx $max-keys=2, are there any recommendations
to optimize the Ceph configuration to enhance the performance of negative list operations?
Show replies by date