[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3173770.1742484356@warthog.procyon.org.uk>
Date: Thu, 20 Mar 2025 15:25:56 +0000
From: David Howells <dhowells@...hat.com>
To: Viacheslav Dubeyko <Slava.Dubeyko@....com>
Cc: dhowells@...hat.com, Alex Markuze <amarkuze@...hat.com>,
"slava@...eyko.com" <slava@...eyko.com>,
"linux-block@...r.kernel.org" <linux-block@...r.kernel.org>,
"idryomov@...il.com" <idryomov@...il.com>,
"jlayton@...nel.org" <jlayton@...nel.org>,
"linux-fsdevel@...r.kernel.org" <linux-fsdevel@...r.kernel.org>,
"ceph-devel@...r.kernel.org" <ceph-devel@...r.kernel.org>,
"dongsheng.yang@...ystack.cn" <dongsheng.yang@...ystack.cn>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [RFC PATCH 32/35] netfs: Add some more RMW support for ceph
Viacheslav Dubeyko <Slava.Dubeyko@....com> wrote:
> > + rreq->buffer.iter = *iter;
>
> The struct iov_iter structure is complex enough and we assign it by value to
> rreq->buffer.iter. So, the initial pointer will not receive any changes
> then. Is it desired behavior here?
Yes. The buffer described by the iterator is going to get partitioned across
a number of subrequests, each of which will get a copy of the iterator
suitably advanced and truncated. As they may run in parallel, there's no way
for them to share the original iterator.
David
Powered by blists - more mailing lists