Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755601Ab0D1QRO (ORCPT ); Wed, 28 Apr 2010 12:17:14 -0400 Received: from fxip-0047f.externet.hu ([88.209.222.127]:40628 "EHLO pomaz-ex.szeredi.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755568Ab0D1QRM (ORCPT ); Wed, 28 Apr 2010 12:17:12 -0400 Message-Id: <20100428161636.272097923@szeredi.hu> User-Agent: quilt/0.46-1 Date: Wed, 28 Apr 2010 18:16:36 +0200 From: Miklos Szeredi To: linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: jens.axboe@oracle.com, akpm@linux-foundation.org, torvalds@linux-foundation.org Subject: [RFC PATCH 0/6] fuse: implement zero copy read Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 998 Lines: 27 This series implements splice(2) to the fuse device. With this it's possible to move pages directly into the page cache of the fuse filesystem without ever having to copy the contents. The next series will implement splicing from the fuse device for zero copy write operations. Testing shows improved bandwidth and reduced system time (as expected). However there's still some overhead in shuffling pages between caches. Further improvements could be achieved by - implementing replace_page_cache_page() which atomically removes an old page and replaces it with a new one - implementing splice a-la O_DIRECT which, instead of populating the page cache, would just send/receive data directly in pipe buffers. Comments? Thanks, Miklos -- -- 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/