From: Herbert Xu Subject: Re: [PATCH v2 04/10] crypto/compress: add asynchronous compression support Date: Fri, 29 Jan 2016 18:09:01 +0800 Message-ID: <20160129100901.GA17272@gondor.apana.org.au> References: <1453796112-14273-1-git-send-email-iamjoonsoo.kim@lge.com> <1453796112-14273-5-git-send-email-iamjoonsoo.kim@lge.com> <20160127074140.GA30335@gondor.apana.org.au> <56A878C9.8050202@intel.com> <20160127080355.GA31330@gondor.apana.org.au> <20160127080926.GA31516@gondor.apana.org.au> <20160128031941.GA14467@js1304-P5Q-DELUXE> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "Li, Weigang" , "David S. Miller" , Sergey Senozhatsky , Minchan Kim , Dan Streetman , linux-crypto@vger.kernel.org, linux-kernel@vger.kernel.org To: Joonsoo Kim Return-path: Received: from helcar.hengli.com.au ([209.40.204.226]:58254 "EHLO helcar.hengli.com.au" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752564AbcA2KJb (ORCPT ); Fri, 29 Jan 2016 05:09:31 -0500 Content-Disposition: inline In-Reply-To: <20160128031941.GA14467@js1304-P5Q-DELUXE> Sender: linux-crypto-owner@vger.kernel.org List-ID: On Thu, Jan 28, 2016 at 12:19:42PM +0900, Joonsoo Kim wrote: > > I have tested asynchronous compression APIs in zram and I saw > regression. Atomic allocation and setting up SG lists are culprit > for this regression. Moreover, zram optimizes linearisation So which is it, atomic allocations or setting up SG lists? There is nothing in acomp that requires you to do an atomic allocation. Cheers, -- Email: Herbert Xu Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt