[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZhoNWVfEWhFnVT1l@casper.infradead.org>
Date: Sat, 13 Apr 2024 05:43:05 +0100
From: Matthew Wilcox <willy@...radead.org>
To: Vlastimil Babka <vbabka@...e.cz>
Cc: Jianfeng Wang <jianfeng.w.wang@...cle.com>,
"Christoph Lameter (Ampere)" <cl@...ux.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, penberg@...nel.org,
rientjes@...gle.com, iamjoonsoo.kim@....com,
akpm@...ux-foundation.org, junxiao.bi@...cle.com
Subject: Re: [External] : Re: [PATCH] slub: limit number of slabs to scan in
count_partial()
On Fri, Apr 12, 2024 at 10:20:48PM +0200, Vlastimil Babka wrote:
> On 4/12/24 7:29 PM, Jianfeng Wang wrote:
> > Yes.
> > On a server with one NUMA node, I create a case that uses many dentry objects.
>
> Could you describe in more detail how do you make dentry cache to grow such
> a large partial slabs list? Thanks.
I don't know precisely which (customer) problem Jianfeng is looking
at, but here's one we got to publish a couple of years ago:
https://lore.kernel.org/linux-fsdevel/3a7abaca-e20f-ad59-f6f0-caedd8450f9f@oracle.com/
(is LSFMM coming up? Must be time to have that discussion again!)
https://lwn.net/Articles/894098/
Powered by blists - more mailing lists