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;
Date:   Mon, 22 Mar 2021 13:02:42 +0000
From:   Matthew Wilcox <willy@infradead.org>
To:     Sergey Senozhatsky <senozhatsky@chromium.org>
Cc:     Namjae Jeon <namjae.jeon@samsung.com>,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-cifs@vger.kernel.org,
        linux-cifsd-devel@lists.sourceforge.net,
        Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
        linux-mm@vger.kernel.org, Uladzislau Rezki <urezki@gmail.com>
Subject: Re: [PATCH 3/5] cifsd: add file operations
Message-ID: <20210322130242.GL1719932@casper.infradead.org>
References: <20210322051344.1706-1-namjae.jeon@samsung.com>
 <CGME20210322052207epcas1p3f0a5bdfd2c994a849a67b465479d0721@epcas1p3.samsung.com>
 <20210322051344.1706-4-namjae.jeon@samsung.com>
 <20210322081512.GI1719932@casper.infradead.org>
 <YFhdWeedjQQgJdbi@google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <YFhdWeedjQQgJdbi@google.com>
Precedence: bulk

On Mon, Mar 22, 2021 at 06:03:21PM +0900, Sergey Senozhatsky wrote:
> On (21/03/22 08:15), Matthew Wilcox wrote:
> > 
> > What's the scenario for which your allocator performs better than slub
> > 
> 
> IIRC request and reply buffers can be up to 4M in size. So this stuff
> just allocates a number of fat buffers and keeps them around so that
> it doesn't have to vmalloc(4M) for every request and every response.

That makes a lot more sense; I was thrown off by the kvmalloc, which
is usually used for allocations that might be smaller than PAGE_SIZE.

So what this patch is really saying is that vmalloc() should include
some caching, so it can defer freeing until there's memory pressure
or it's built up a large (percpu) backlog of freed areas.

Vlad, have you thought about this?