From mboxrd@z Thu Jan  1 00:00:00 1970
From: Jaegeuk Kim <jaegeuk@kernel.org>
Subject: Re: [f2fs-dev] [PATCH 2/3] f2fs crypto: use bounce pages from
 mempool first
Date: Wed, 27 May 2015 12:09:34 -0700
Message-ID: <20150527190815.GA91133@jaegeuk-mac02.mot-mobility.com>
References: <1432255225-76792-1-git-send-email-jaegeuk@kernel.org>
 <1432255225-76792-2-git-send-email-jaegeuk@kernel.org>
 <00d101d096d1$c7300a50$55901ef0$@samsung.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net
To: Chao Yu <chao2.yu@samsung.com>
Return-path: <linux-kernel-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <00d101d096d1$c7300a50$55901ef0$@samsung.com>
Sender: linux-kernel-owner@vger.kernel.org
List-Id: linux-fsdevel.vger.kernel.org

Hi Chao,

On Mon, May 25, 2015 at 06:00:47PM +0800, Chao Yu wrote:
> Hi Jaegeuk,
> 
> > -----Original Message-----
> > From: Jaegeuk Kim [mailto:jaegeuk@kernel.org]
> > Sent: Friday, May 22, 2015 8:40 AM
> > To: linux-kernel@vger.kernel.org; linux-fsdevel@vger.kernel.org;
> > linux-f2fs-devel@lists.sourceforge.net
> > Cc: Jaegeuk Kim
> > Subject: [f2fs-dev] [PATCH 2/3] f2fs crypto: use bounce pages from mempool first
> > 
> > If a lot of write streams are triggered, alloc_page and __free_page are
> > costly called, resulting in high memory pressure.
> > 
> > In order to avoid that, let's reuse mempool pages for writeback pages.
> > 
> > Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> > ---
> >  fs/f2fs/crypto.c | 16 ++++------------
> >  1 file changed, 4 insertions(+), 12 deletions(-)
> > 
> > diff --git a/fs/f2fs/crypto.c b/fs/f2fs/crypto.c
> > index 2c7819a..2ceee68 100644
> > --- a/fs/f2fs/crypto.c
> > +++ b/fs/f2fs/crypto.c
> > @@ -408,20 +408,12 @@ struct page *f2fs_encrypt(struct inode *inode,
> >  		return (struct page *)ctx;
> > 
> >  	/* The encryption operation will require a bounce page. */
> > -	ciphertext_page = alloc_page(GFP_NOFS);
> > +	ciphertext_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOFS);
> >  	if (!ciphertext_page) {
> > -		/*
> > -		 * This is a potential bottleneck, but at least we'll have
> > -		 * forward progress.
> > -		 */
> > -		ciphertext_page = mempool_alloc(f2fs_bounce_page_pool,
> > -							GFP_NOFS);
> > -		if (WARN_ON_ONCE(!ciphertext_page))
> > -			ciphertext_page = mempool_alloc(f2fs_bounce_page_pool,
> > -						GFP_NOFS | __GFP_WAIT);
> > -		ctx->flags &= ~F2FS_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL;
> > -	} else {
> > +		ciphertext_page = alloc_page(GFP_NOFS);
> 
> Using alloc_page(GFP_NOFS | __GFP_WAIT) to avoid failure?

#define GFP_NOFS	(__GFP_WAIT | __GFP_IO)

Thanks,

> 
> Thanks,
> 
> >  		ctx->flags |= F2FS_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL;
> > +	} else {
> > +		ctx->flags &= ~F2FS_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL;
> >  	}
> >  	ctx->flags |= F2FS_WRITE_PATH_FL;
> >  	ctx->w.bounce_page = ciphertext_page;
> > --
> > 2.1.1
> > 
> > 
> > ------------------------------------------------------------------------------
> > One dashboard for servers and applications across Physical-Virtual-Cloud
> > Widest out-of-the-box monitoring support with 50+ applications
> > Performance metrics, stats and reports that give you Actionable Insights
> > Deep dive visibility with transaction tracing using APM Insight.
> > http://ad.doubleclick.net/ddm/clk/290420510;117567292;y
> > _______________________________________________
> > Linux-f2fs-devel mailing list
> > Linux-f2fs-devel@lists.sourceforge.net
> > https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel