Benchmarking The BORE Scheduler Performance With CachyOS Linux

Written by Michael Larabel in Operating Systems on 4 June 2026 at 08:46 PM EDT. Page 3 of 4. 39 Comments.

👁 Flexible IO Tester benchmark with settings of Type: Random Read, Engine: IO_uring, Direct: No, Block Size: 4KB, Job Count: 16, Disk Target: Default Test Directory. linux-cachyos-lts was the fastest.

👁 Flexible IO Tester benchmark with settings of Type: Random Read, Engine: IO_uring, Direct: No, Block Size: 4KB, Job Count: 64, Disk Target: Default Test Directory. linux-cachyos-lts was the fastest.

👁 Flexible IO Tester benchmark with settings of Type: Random Read, Engine: IO_uring, Direct: Yes, Block Size: 4KB, Job Count: 16, Disk Target: Default Test Directory. linux-cachyos-rc was the fastest.

👁 Flexible IO Tester benchmark with settings of Type: Random Write, Engine: IO_uring, Direct: No, Block Size: 4KB, Job Count: 16, Disk Target: Default Test Directory. linux-cachyos-lts was the fastest.

👁 Flexible IO Tester benchmark with settings of Type: Random Write, Engine: IO_uring, Direct: No, Block Size: 4KB, Job Count: 64, Disk Target: Default Test Directory. linux-cachyos-lts was the fastest.

👁 Flexible IO Tester benchmark with settings of Type: Sequential Read, Engine: IO_uring, Direct: No, Block Size: 2MB, Job Count: 16, Disk Target: Default Test Directory. linux-cachyos-lts was the fastest.

👁 Flexible IO Tester benchmark with settings of Type: Sequential Read, Engine: IO_uring, Direct: No, Block Size: 2MB, Job Count: 64, Disk Target: Default Test Directory. linux-cachyos-lts was the fastest.

👁 Flexible IO Tester benchmark with settings of Type: Sequential Write, Engine: IO_uring, Direct: No, Block Size: 2MB, Job Count: 64, Disk Target: Default Test Directory. linux-cachyos-server was the fastest.

With linux-cachyos-lts having patched in the BORE scheduler and using it by default, some speculated in the prior article that some of the LTS kernel wins were due to the BORE scheduler. But as we see now with the linux-cachyos-bore kernel, it's not due to BORE leading to the nice I/O performance in FIO with linux-cachyos-lts.

👁 Ethr benchmark with settings of Server Address: localhost, Protocol: TCP, Test: Bandwidth, Threads: 32. linux-cachyos-server was the fastest.

👁 Ethr benchmark with settings of Server Address: localhost, Protocol: TCP, Test: Bandwidth, Threads: 64. linux-cachyos-server was the fastest.

👁 Ethr benchmark with settings of Server Address: localhost, Protocol: TCP, Test: Latency, Threads: 32. linux-cachyos-lts was the fastest.

👁 Ethr benchmark with settings of Server Address: localhost, Protocol: UDP, Test: Bandwidth, Threads: 32. linux-cachyos-server was the fastest.

👁 Ethr benchmark with settings of Server Address: localhost, Protocol: UDP, Test: Bandwidth, Threads: 64. linux-cachyos-bore was the fastest.

The linux-cachyos-bore kernel also behaved different from the LTS kernel in the Ethr network benchmarks.

👁 Sockperf benchmark with settings of Test: Throughput. linux-cachyos-lts was the fastest.

The linux-cachyos-bore kernel trailed the LTS kernel and matched other non-hardened kernels in Sockperf.

39 Comments - Next Page

Page: 1 2 3 4 Next Page

URL: https://www.phoronix.com/review/cachyos-bore/3

⇱ Benchmarking The BORE Scheduler Performance With CachyOS Linux - Phoronix

Benchmarking The BORE Scheduler Performance With CachyOS Linux