I'll need to dig into what AIM7 actually does in this benchmark, which isn't too easy as I'm on a business trip currently, but from the list below it looks like it keeps overwriting and overwriting a file that's already been allocated. This is a pretty stupid workload, but fortunately it should also be able to be optimized by skipping the actual block lookup, which is what the old buffer.c code happens to do.
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Christoph Hellwig
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Huang, Ying
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Christoph Hellwig
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Al Viro
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Huang, Ying
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Christoph Hellwig
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Dave Chinner
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Dave Chinner
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Christoph Hellwig
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Dave Chinner
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Linus Torvalds
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Dave Chinner
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Ye Xiaolong
- Re: [LKP] [lkp] [xfs] 68a9f5e700: aim7.jobs-per-min -13.... Ye Xiaolong