On Fri, Apr 26, 2013 at 7:44 PM, Maxim V. Patlasov
<[email protected]> wrote:
> I'm for accounting NR_WRITEBACK_TEMP because balance_dirty_pages is already
> overcomplicated (imho) and adding new clauses for FUSE makes me sick.

Agreed.

But instead of further complexifying balance_dirty_pages() fuse
specific throttling can be done in fuse_page_mkwrite(), I think.

And at that point NR_WRITEBACK_TEMP really becomes irrelevant to the
dirty balancing logic.

Thanks,
Miklos
_______________________________________________
Devel mailing list
[email protected]
https://lists.openvz.org/mailman/listinfo/devel

Reply via email to