[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20b896db-9dd6-fcc3-a72a-ce0044d4ab75@suse.cz>
Date: Tue, 21 Mar 2023 10:41:12 +0100
From: Vlastimil Babka <vbabka@...e.cz>
To: Mike Rapoport <rppt@...nel.org>
Cc: "chenjun (AM)" <chenjun102@...wei.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>,
"cl@...ux.com" <cl@...ux.com>,
"penberg@...nel.org" <penberg@...nel.org>,
"rientjes@...gle.com" <rientjes@...gle.com>,
"iamjoonsoo.kim@....com" <iamjoonsoo.kim@....com>,
"akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
Hyeonggon Yoo <42.hyeyoo@...il.com>,
"xuqiang (M)" <xuqiang36@...wei.com>,
"Wangkefeng (OS Kernel Lab)" <wangkefeng.wang@...wei.com>,
Michal Hocko <mhocko@...nel.org>,
Mel Gorman <mgorman@...hsingularity.net>,
Matthew Wilcox <willy@...radead.org>
Subject: Re: [PATCH] mm/slub: Reduce memory consumption in extreme scenarios
On 3/20/23 10:12, Mike Rapoport wrote:
> On Mon, Mar 20, 2023 at 09:05:57AM +0100, Vlastimil Babka wrote:
>> On 3/19/23 08:22, chenjun (AM) wrote:
>> > 在 2023/3/17 20:06, Vlastimil Babka 写道:
>> >
>> > If we ignore __GFP_ZERO passed by kzalloc, kzalloc will not work.
>> > Could we just unmask __GFP_RECLAIMABLE | __GFP_RECLAIM?
>> >
>> > pc.flags &= ~(__GFP_RECLAIMABLE | __GFP_RECLAIM)
>> > pc.flags |= __GFP_THISNODE
>>
>> __GFP_RECLAIMABLE would be wrong, but also ignored as new_slab() does:
>> flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK)
>>
>> which would filter out __GFP_ZERO as well. That's not a problem as kzalloc()
>> will zero out the individual allocated objects, so it doesn't matter if we
>> don't zero out the whole slab page.
>>
>> But I wonder, if we're not past due time for a helper e.g.
>> gfp_opportunistic(flags) that would turn any allocation flags to a
>> GFP_NOWAIT while keeping the rest of relevant flags intact, and thus there
>> would be one canonical way to do it - I'm sure there's a number of places
>> with their own variants now?
>> With such helper we'd just add __GFP_THISNODE to the result here as that's
>> specific to this particular opportunistic allocation.
>
> I like the idea, but maybe gfp_no_reclaim() would be clearer?
Well, that name would say how it's implemented, but not exactly as we also
want to add __GFP_NOWARN. "gfp_opportunistic()" or a better name with
similar meaning was meant to convey the intention of what this allocation is
trying to do, and I think that's better from the API users POV?
Powered by blists - more mailing lists