From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1953775AbdDZE2u (ORCPT <rfc822;w@1wt.eu>);
        Wed, 26 Apr 2017 00:28:50 -0400
Received: from mail-pg0-f68.google.com ([74.125.83.68]:35847 "EHLO
        mail-pg0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1034543AbdDZE2k (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Wed, 26 Apr 2017 00:28:40 -0400
Date: Wed, 26 Apr 2017 13:28:26 +0900
From: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
To: js1304@gmail.com
Cc: Andrew Morton <akpm@linux-foundation.org>,
        Minchan Kim <minchan@kernel.org>,
        Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
        linux-kernel@vger.kernel.org, kernel-team@lge.com,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>
Subject: Re: [PATCH v4 2/4] zram: implement deduplication in zram
Message-ID: <20170426042826.GD673@jagdpanzerIV.localdomain>
References: <1493167946-10936-1-git-send-email-iamjoonsoo.kim@lge.com>
 <1493167946-10936-3-git-send-email-iamjoonsoo.kim@lge.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1493167946-10936-3-git-send-email-iamjoonsoo.kim@lge.com>
User-Agent: Mutt/1.8.2 (2017-04-18)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On (04/26/17 09:52), js1304@gmail.com wrote:
[..]
> +struct zram_hash {
> +	spinlock_t lock;
> +	struct rb_root rb_root;
>  };

just a note.

we can easily have N CPUs spinning on ->lock for __zram_dedup_get() lookup,
which can invole a potentially slow zcomp_decompress() [zlib, for example,
with 64k pages] and memcmp(). the larger PAGE_SHIFT is, the more serialized
IOs become. in theory, at least.

CPU0				CPU1		...	CPUN

__zram_bvec_write()	__zram_bvec_write()		__zram_bvec_write()
 zram_dedup_find()	 zram_dedup_find()		 zram_dedup_find()
  spin_lock(&hash->lock);
			  spin_lock(&hash->lock);	  spin_lock(&hash->lock);
   __zram_dedup_get()
    zcomp_decompress()
     ...


so may be there is a way to use read-write lock instead on spinlock for hash
and reduce write/read IO serialization.

	-ss