Accelerator's count and read_thread's count were used as criteria for sweep evaluation, but the results are confusing.

I ran evaluations while varying the number of accelerators and the number of read threads. I expected the I/O throughput to scale proportionally with accelerator × read_thread, but as shown below the performance drops dramatically when I use five accelerators. Even if I keep increasing the number of accelerators and read threads, I thought the system would eventually hit a bottleneck, yet instead of a gradual bottleneck the performance collapses.

For the tests I only added the read_thread option to the default run command you provided, and before each run I re‑formatted the NVMe device and remounted the XFS filesystem (the initialization step).

Could you help me figure out why I’m getting these results? Is there something wrong with my setup?

No files, tests, or entry points are named. Start by reproducing the default run with read_thread, five accelerators, and the stated NVMe reformat/XFS remount initialization, then compare the sweep results across accelerator and read_thread counts. Done means identifying whether the collapse comes from the setup or benchmark behavior and documenting the cause.