Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Mon, 5 Jun 2023 20:08:56 -0700 (PDT)
From:   Hugh Dickins <hughd@google.com>
To:     "Yin, Fengwei" <fengwei.yin@intel.com>
cc:     Hugh Dickins <hughd@google.com>,
        "Liam R. Howlett" <Liam.Howlett@oracle.com>,
        Peng Zhang <zhangpeng.00@bytedance.com>,
        maple-tree@lists.infradead.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, "Liu, Yujie" <yujie.liu@intel.com>,
        Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH 00/14] Reduce preallocations for maple tree
In-Reply-To: <d4d7157d-1e5b-fc7e-34de-66def46a344c@intel.com>
Message-ID: <ff754a68-4f94-e818-a31f-c8a1fd11b4b5@google.com>
References: <20230601021605.2823123-1-Liam.Howlett@oracle.com> <7a5dc9ce-b58f-e1b3-db1a-d00a8a556ae5@intel.com> <fad3c833-1ab3-2d34-aa85-dcc7c40c3587@bytedance.com> <a9d2ab1b-23a5-8c06-9f7a-6872c726db03@intel.com> <b5f2d527-8887-eb0b-d3f2-4e7cd8f3c022@intel.com>
 <4fb5f66d-c8c2-f857-7461-b974154dbc2b@bytedance.com> <20230605140344.66pwpdg5zgb6rfa7@revolver> <9f4c10bb-ee7c-cd41-f1b9-c1a7a1a562fd@google.com> <d4d7157d-1e5b-fc7e-34de-66def46a344c@intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Precedence: bulk

On Tue, 6 Jun 2023, Yin, Fengwei wrote:
> On 6/6/2023 10:41 AM, Hugh Dickins wrote:
> > On Mon, 5 Jun 2023, Liam R. Howlett wrote:
> >>
> >> You mean "mm: update validate_mm() to use vma iterator" here I guess.  I
> >> have it as a different commit id in my branch.
> >>
> >> I 'restored' some of the checking because I was able to work around not
> >> having the mt_dump() definition with the vma iterator.  I'm now
> >> wondering how wide spread CONFIG_DEBUG_VM is used and if I should not
> >> have added these extra checks.
> > 
> > Most CONFIG_DEBUG_VM checks are quite cheap, mostly VM_BUG_ONs for
> Indeed. I had CONFIG_DEBUG_VM enabled and didn't see surprise perf report.
> 
> 
> > easily checked conditions.  If validate_mm() is still the kind of thing
> > it used to be, checking through every vma on every mmap operation, please
> > don't bring that into CONFIG_DEBUG_VM - it distorts performance too much,
> > so always used to be under a separate CONFIG_DEBUG_VM_RB instead.
> So does this mean CONFIG_DEBUG_VM is allowed to be enabled for performance
> testing? Thanks.

I was going to say:
No, I did not mean that: I just meant that even developers not doing
strict performance testing still like to keep a rough eye on performance
changes; and historically CONFIG_DEBUG_VM has not distorted very much.

But then I wonder about certain distros which (wrongly or rightly) turn
CONFIG_DEBUG_VM on: I expect they do performance testing on their kernels.

Hugh