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;
Sender: Minchan Kim <minchan.kim@gmail.com>
Date:   Thu, 20 Jan 2022 13:22:47 -0800
From:   Minchan Kim <minchan@kernel.org>
To:     David Hildenbrand <david@redhat.com>
Cc:     Michal Hocko <mhocko@suse.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        linux-mm <linux-mm@kvack.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Suren Baghdasaryan <surenb@google.com>,
        John Dias <joaodias@google.com>
Subject: Re: [RESEND][PATCH v2] mm: don't call lru draining in the nested
 lru_cache_disable
Message-ID: <YenSp5l80kBLijcd@google.com>
References: <20211230193627.495145-1-minchan@kernel.org>
 <YeVzWlrojI1+buQx@dhcp22.suse.cz>
 <YedXhpwURNTkW1Z3@google.com>
 <644356e5-2a85-fcea-2280-ff779ae8d38d@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <644356e5-2a85-fcea-2280-ff779ae8d38d@redhat.com>
Precedence: bulk

On Thu, Jan 20, 2022 at 09:42:23AM +0100, David Hildenbrand wrote:
> On 19.01.22 01:12, Minchan Kim wrote:
> > On Mon, Jan 17, 2022 at 02:47:06PM +0100, Michal Hocko wrote:
> >> On Thu 30-12-21 11:36:27, Minchan Kim wrote:
> >>> lru_cache_disable involves IPIs to drain pagevec of each core,
> >>> which sometimes takes quite long time to complete depending
> >>> on cpu's business, which makes allocation too slow up to
> >>> sveral hundredth milliseconds. Furthermore, the repeated draining
> >>> in the alloc_contig_range makes thing worse considering caller
> >>> of alloc_contig_range usually tries multiple times in the loop.
> >>>
> >>> This patch makes the lru_cache_disable aware of the fact the
> >>> pagevec was already disabled. With that, user of alloc_contig_range
> >>> can disable the lru cache in advance in their context during the
> >>> repeated trial so they can avoid the multiple costly draining
> >>> in cma allocation.
> >>
> >> Do you have any numbers on any improvements?
> > 
> > The LRU draining consumed above 50% overhead for the 20M CMA alloc.
> > 
> >>
> >> Now to the change. I do not like this much to be honest. LRU cache
> >> disabling is a complex synchronization scheme implemented in
> >> __lru_add_drain_all now you are stacking another level on top of that.
> >>
> >> More fundamentally though. I am not sure I understand the problem TBH.
> > 
> > The problem is that kinds of IPI using normal prority workqueue to drain
> > takes much time depending on the system CPU business.
> > 
> >> What prevents you from calling lru_cache_disable at the cma level in the
> >> first place?
> > 
> > You meant moving the call from alloc_contig_range to caller layer?
> > So, virtio_mem_fake_online, too? It could and make sense from
> > performance perspective since upper layer usually calls the
> > alloc_contig_range multiple times on retrial loop.
> > 
> 
> ^ I actually do have something like that on my TODO list.

I'm glad to hear you are also looking the direction.
If we move some information out of alloc_contig_range,
upper layer has higher chance to make it fast. A example,
"failure pfn and why it fails"

> 
> The issue is that we have demanding requirements for
> alloc_contig_range(), discussed in the past for CMA bulk allocations:
> 
> (1) Fast, unreliable allocations
> 
> Fail fast and let caller continue with next allocation instead of
> retrying. Try to not degrade system performance.
> 
> (2) Slow, reliable allocations
> 
> Retry as good as possible. Degrading system performance (e.g., disabling
> lru) is acceptable.

"Fast and unreliable" provides lots of flexibilty for us to design
since it's okay to fail. For "Slow, reliable", "the slow" should be not
too much and we need to keep effort to make it faster.