Re: [PATCH 6.1 036/197] readahead: avoid multiple marked readahead pages

On Tue, Feb 20, 2024 at 09:05:53PM +0000, Matthew Wilcox wrote:

On Tue, Feb 20, 2024 at 09:49:55PM +0100, Greg Kroah-Hartman wrote:

...

6.1-stable review patch. If anyone has any objections, please let me know.

Maybe hold off on this one?

kernel test robot noticed a -21.4% regression of vm-scalability.throughput on: commit: ab4443fe3ca6298663a55c4a70efc6c3ce913ca6 ("readahead: avoid multiple marked readahead pages")

https://lore.kernel.org/linux-fsdevel/202402201642.c8d6bbc3-oliver.sang@inte...

Not a definite no just yet; nobody's dug into it, but some caution seems warranted.

Thanks for the warning, I've dropped it from all stable queues now. If you all figure it out, let us know and we can add it back in.

thanks,

greg k-h