Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20211020192430.GA1861@pc638.lan> <163481121586.17149.4002493290882319236@noble.neil.brown.name>
 <YXFAkFx8PCCJC0Iy@dhcp22.suse.cz> <20211021104038.GA1932@pc638.lan>
 <163485654850.17149.3604437537345538737@noble.neil.brown.name>
 <20211025094841.GA1945@pc638.lan> <163520582122.16092.9250045450947778926@noble.neil.brown.name>
 <YXeraV5idipgWDB+@dhcp22.suse.cz> <163524388152.8576.15706993879941541847@noble.neil.brown.name>
 <CA+KHdyWev2RwoO1o9OrAkaE2VdC7iSXnJdBR+qzarqYOse3cXA@mail.gmail.com> <YXgUI33cfWYYrjXw@dhcp22.suse.cz>
In-Reply-To: <YXgUI33cfWYYrjXw@dhcp22.suse.cz>
From:   Uladzislau Rezki <urezki@gmail.com>
Date:   Tue, 26 Oct 2021 17:40:33 +0200
Message-ID: <CA+KHdyV2_s6Jro2JhQ2kNhexN+ktR+fCcMZHW8uq+3X+hak5ow@mail.gmail.com>
Subject: Re: [RFC 2/3] mm/vmalloc: add support for __GFP_NOFAIL
To:     Michal Hocko <mhocko@suse.com>
Cc:     NeilBrown <neilb@suse.de>,
        Linux Memory Management List <linux-mm@kvack.org>,
        Dave Chinner <david@fromorbit.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Christoph Hellwig <hch@infradead.org>,
        linux-fsdevel@vger.kernel.org, LKML <linux-kernel@vger.kernel.org>,
        Ilya Dryomov <idryomov@gmail.com>,
        Jeff Layton <jlayton@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

> > > > Is this really required to be part of the initial support?
> > >
> > > No.... I was just thinking out-loud.
> > >
> > alloc_vmap_area() has an retry path, basically if it fails the code
> > will try to "purge"
> > areas and repeat it one more time. So we do not need to purge outside some where
> > else.
>
> I think that Neil was not concerned about the need for purging something
> but rather a waiting event the retry loop could hook into. So that the
> sleep wouldn't have to be a random timeout but something that is
> actually actionable - like somebody freeing an area.
>
I see this point. But sometimes it is not as straightforward as it could be. If
we have lack of vmap space within a specific range, it might be not about
reclaiming(nobody frees to that area and no outstanding areas) thus we
can do nothing.

-- 
Uladzislau Rezki