Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 9 Oct 2018 16:13:36 -0700
From:   Andrew Morton <akpm@linux-foundation.org>
To:     Jack Wang <xjtuwjp@gmail.com>
Cc:     gregkh@linuxfoundation.org, florian-ewald.mueller@profitbricks.com,
        linux-kernel@vger.kernel.org,
        Jack Wang <jinpu.wang@profitbricks.com>
Subject: Re: [PATCH] lib: memcmp optimization
Message-Id: <20181009161336.1abf11d48a9adf40486c30eb@linux-foundation.org>
In-Reply-To: <1539095291-9926-1-git-send-email-jinpuwang@gmail.com>
References: <1539095291-9926-1-git-send-email-jinpuwang@gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue,  9 Oct 2018 16:28:11 +0200 Jack Wang <xjtuwjp@gmail.com> wrote:

> From: Florian-Ewald Mueller <florian-ewald.mueller@profitbricks.com>
> 
> During testing, I have configured 128 md/raid1's and, while under
> heavy IO, I started a check on each of them
> (echo check > /sys/block/mdx/md/sync_action).
> 
> The CPU utilization went through the ceiling and when looking for
> the cause (with 'perf top'). I've discovered that ~50% of the time
> was spend in memcmp() called from process_checks().
> 
> With this patch applied, it drops to 4% - 10%.

Which CPU architecture?  Most important architectures appear to define
__HAVE_ARCH_MEMCMP.

> --- a/lib/string.c
> +++ b/lib/string.c
> @@ -852,7 +852,7 @@ EXPORT_SYMBOL(memmove);
>   * @count: The size of the area.
>   */
>  #undef memcmp
> -__visible int memcmp(const void *cs, const void *ct, size_t count)
> +static inline int __memcmp(const void *cs, const void *ct, size_t count)

What the heck does __visible do?

>  {
>  	const unsigned char *su1, *su2;
>  	int res = 0;
> @@ -862,6 +862,20 @@ __visible int memcmp(const void *cs, const void *ct, size_t count)
>  			break;
>  	return res;
>  }
> +__visible int memcmp(const void *cs, const void *ct, size_t count)
> +{
> +	const uint64_t *l1p = cs;
> +	const uint64_t *l2p = ct;
> +
> +	while (count >= sizeof(*l1p)) {
> +		if (*l1p != *l2p)
> +			return __memcmp(l1p, l2p, sizeof(*l1p));
> +		count -= sizeof(*l1p);
> +		++l1p;
> +		++l2p;
> +	}
> +	return __memcmp(l1p, l2p, count);
> +}

This is going to do bad things if the incoming addresses aren't
suitably aligned.

Certainly, byte-at-a-time is a pretty lame implementation when the
addresses are suitably aligned.  A fallback to the lame version when
there is misalignment will be simple to do.  And presumably there will
be decent benefits to whoever is actually using this code.  But I'm
wondering who is actually using this code!