BFQ Gets Another Notable Responsiveness Fix
In addition to the BFQ improvements already staged for Linux 4.14, it looks like another fix will be on the way.
BFQ I/O scheduler maintainer Paolo Valente has managed to fix another bug that was causing poor performance in at least one of our recent BFQ tests. From our Some Fresh I/O Scheduler Benchmarks: Linux 4.13 With BFQ, CFQ, Kyber, Deadline article, with the Phoronix Test Suite he investigated and fixed BFQ's bad showing in particularly the Background I/O Type: Random - Background I/O mix: Reads and writes - Application to start: LibreOffice Writer run.
He thinks BFQ's responsiveness should be better now. Once the latest work has received some testing, it should be working its way to mainline. The patch for those interested can be found here for testing.
I'll be working on some Linux 4.14-based I/O scheduler (and general disk / IO benchmarks) shortly with different hardware.
BFQ I/O scheduler maintainer Paolo Valente has managed to fix another bug that was causing poor performance in at least one of our recent BFQ tests. From our Some Fresh I/O Scheduler Benchmarks: Linux 4.13 With BFQ, CFQ, Kyber, Deadline article, with the Phoronix Test Suite he investigated and fixed BFQ's bad showing in particularly the Background I/O Type: Random - Background I/O mix: Reads and writes - Application to start: LibreOffice Writer run.
He thinks BFQ's responsiveness should be better now. Once the latest work has received some testing, it should be working its way to mainline. The patch for those interested can be found here for testing.
I'll be working on some Linux 4.14-based I/O scheduler (and general disk / IO benchmarks) shortly with different hardware.
10 Comments