...
At the very bottom of this page are graphs from a test run by Ben Pennell, which shows a similar pattern in the timing of ingests of over 100k objects. He experienced the repository becoming non-responsive near the 200k object mark.
Updated (at the bottom of the page) with results from a hierarchical test (same architecture, but using a 64/64/64 structure).
Results from the First Round of Testing
...
| Configuration | Results Graph | Throughput |
|---|---|---|
| 200 KB objects (get more info from Ben - transactions with 500 objects?) |  |  |
| Configuration | Results Graph |
|---|---|
| leveldb-default (262,144 1 MB objects / 1 thread) - tested with curl - using a 64/64/64 hierarchical structure. |  |