Date: Sat, 5 Dec 2015 19:16:51 -0800 From: Eitan Adler <lists@eitanadler.com> To: Maxim Sobolev <sobomax@freebsd.org>, FreeBSD Hackers <freebsd-hackers@freebsd.org>, Pawel Jakub Dawidek <pjd@freebsd.org> Subject: Re: DELETE support in the VOP_STRATEGY(9)? Message-ID: <CAF6rxg=H-r=B=YHxOf_gb5KgUas1k30G4pzKzWsvygpTrJNmeA@mail.gmail.com> In-Reply-To: <CAH7qZftiiqM5WpT%2BDvRpjyduw2OrPseCUQpt4uCbAWfRNfDUbA@mail.gmail.com> References: <CAH7qZftiiqM5WpT%2BDvRpjyduw2OrPseCUQpt4uCbAWfRNfDUbA@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
+ correct mailing list - non-technical list On 4 December 2015 at 21:38, Maxim Sobolev <sobomax@freebsd.org> wrote: > Hi folks, do we support delete operation in the vnode layer? This comes from > observation that md(4) converts from DELETE into sector-size zero buffer > write before it feeds it to the vnode. It's shame that a trim operation is > getting lost when you run md(4)+ufs atop a vnode. With the magnetic spinning > storage joining home particle accelerators, aka CRTs in the hall of fame > soon, we better make sure it's turtles all the way down in either direction. > By which I mean make sure that trim can not only propagate from VFS to BIO > but also the other way around . I believe having this would also allow > "punch-hole" API in the userland to be implemented trivially, syscall that > VM's out there would love to have. > > -Max -- Eitan Adler
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAF6rxg=H-r=B=YHxOf_gb5KgUas1k30G4pzKzWsvygpTrJNmeA>