Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753629Ab0HIScN (ORCPT ); Mon, 9 Aug 2010 14:32:13 -0400 Received: from mail-yw0-f46.google.com ([209.85.213.46]:33049 "EHLO mail-yw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752547Ab0HIScM (ORCPT ); Mon, 9 Aug 2010 14:32:12 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; b=UUkKKYUVYnC0obN3M7Qkhfk2cXEQ2yw0V5jDrrhHdEyzrJpNNSMfqe8FNUlmMEjV8s Eyb6j+Yz+gBwQm+XduT0Igp8S1UNs/yR6knP4h+yLwql0XHR8RLZeJ1NfR8eGSmO1w22 Uu73BxjEao1jzVSpIWd7d1d6bWsr0Mo6ETqMk= MIME-Version: 1.0 In-Reply-To: <1281374816-904-8-git-send-email-ngupta@vflare.org> References: <1281374816-904-1-git-send-email-ngupta@vflare.org> <1281374816-904-8-git-send-email-ngupta@vflare.org> Date: Mon, 9 Aug 2010 21:32:11 +0300 X-Google-Sender-Auth: Kr7sn1hLNaeprvjyouI0-d1WYCc Message-ID: Subject: Re: [PATCH 07/10] Increase compressed page size threshold From: Pekka Enberg To: Nitin Gupta Cc: Pekka Enberg , Minchan Kim , Andrew Morton , Greg KH , Linux Driver Project , linux-mm , linux-kernel Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1160 Lines: 25 Hi Nitin, On Mon, Aug 9, 2010 at 8:26 PM, Nitin Gupta wrote: > Compression takes much more time than decompression. So, its quite > wasteful in terms of both CPU cycles and memory usage to have a very > low compressed page size threshold and thereby storing such not-so-well > compressible pages as-is (uncompressed). So, increasing it from > PAGE_SIZE/2 to PAGE_SIZE/8*7. A low threshold was useful when we had > "backing swap" support where we could forward such pages to the backing > device (applicable only when zram was used as swap disk). > > It is not yet configurable through sysfs but may be exported in future, > along with threshold for average compression ratio. > > Signed-off-by: Nitin Gupta The description makes sense but lacks any real data. What kind of workloads did you test this with? Where does it help most? How much? Pekka -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/