Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756041AbZKMKkB (ORCPT ); Fri, 13 Nov 2009 05:40:01 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755765AbZKMKj6 (ORCPT ); Fri, 13 Nov 2009 05:39:58 -0500 Received: from mail-yw0-f202.google.com ([209.85.211.202]:65195 "EHLO mail-yw0-f202.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755683AbZKMKj5 convert rfc822-to-8bit (ORCPT ); Fri, 13 Nov 2009 05:39:57 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=sDZzAHDWZlaGL5n15/DGZ1vOxG7H0FNx/6Dq6tm0KwtJrsLPjWmn3aGLPnb0WpHfQ4 b72jo811C+ME4c/duZRpSP8jjAAePmlBJKS8BD0jPiWslWmFtM47lsK8GlCWKghhEHzw 4vbykcnRWr9yP9cLmC6hdoIx6qKIEFo6TCE8U= MIME-Version: 1.0 In-Reply-To: <1258068756-10766-4-git-send-email-vgoyal@redhat.com> References: <1258068756-10766-1-git-send-email-vgoyal@redhat.com> <1258068756-10766-4-git-send-email-vgoyal@redhat.com> Date: Fri, 13 Nov 2009 11:39:51 +0100 Message-ID: <4e5e476b0911130239j3bfdef6q789fa78da36c6023@mail.gmail.com> Subject: Re: [PATCH 03/16] blkio: Keep queue on service tree until we expire it From: Corrado Zoccolo To: Vivek Goyal Cc: linux-kernel@vger.kernel.org, jens.axboe@oracle.com, nauman@google.com, dpshah@google.com, lizf@cn.fujitsu.com, ryov@valinux.co.jp, fernando@oss.ntt.co.jp, s-uchida@ap.jp.nec.com, taka@valinux.co.jp, guijianfeng@cn.fujitsu.com, jmoyer@redhat.com, balbir@linux.vnet.ibm.com, righi.andrea@gmail.com, m-ikeda@ds.jp.nec.com, akpm@linux-foundation.org, riel@redhat.com, kamezawa.hiroyu@jp.fujitsu.com Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2902 Lines: 82 Hi Vivek, the following is probably not on a critical path, but maybe it can be written more efficiently. Now, it will cicle through all service trees multiple times, to retrieve the queues for the last one. What about having a cfq_for_each_queue that takes a function pointer and will apply it to all of them? On Fri, Nov 13, 2009 at 12:32 AM, Vivek Goyal wrote: > +static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) > +{ > +       struct cfq_group *cfqg = &cfqd->root_group; > +       struct cfq_queue *cfqq; > +       int i, j; > + > +       if (!cfqd->rq_queued) > +               return NULL; > + > +       for (i = 0; i < 2; ++i) { > +               for (j = 0; j < 3; ++j) { > +                       cfqq = cfq_rb_first(&cfqg->service_trees[i][j]); > +                       if (cfqq) > +                               return cfqq; > +               } > +       } > + > +       cfqq = cfq_rb_first(&cfqg->service_tree_idle); > +       if (cfqq) > +               return cfqq; > +       return NULL; > +} > + >  /* >  * Get and set a new active queue for service. >  */ > @@ -1590,16 +1633,8 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd) >  { >        struct cfq_queue *cfqq; >        int dispatched = 0; > -       int i, j; > -       struct cfq_group *cfqg = &cfqd->root_group; > - > -       for (i = 0; i < 2; ++i) > -               for (j = 0; j < 3; ++j) > -                       while ((cfqq = cfq_rb_first(&cfqg->service_trees[i][j])) > -                               != NULL) > -                               dispatched += __cfq_forced_dispatch_cfqq(cfqq); > > -       while ((cfqq = cfq_rb_first(&cfqg->service_tree_idle)) != NULL) > +       while ((cfqq = cfq_get_next_queue(cfqd)) != NULL) >                dispatched += __cfq_forced_dispatch_cfqq(cfqq); > >        cfq_slice_expired(cfqd, 0); > @@ -1770,13 +1805,14 @@ static void cfq_put_queue(struct cfq_queue *cfqq) >        cfq_log_cfqq(cfqd, cfqq, "put_queue"); >        BUG_ON(rb_first(&cfqq->sort_list)); >        BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]); > -       BUG_ON(cfq_cfqq_on_rr(cfqq)); > >        if (unlikely(cfqd->active_queue == cfqq)) { >                __cfq_slice_expired(cfqd, cfqq, 0); >                cfq_schedule_dispatch(cfqd); >        } > > +       BUG_ON(cfq_cfqq_on_rr(cfqq)); > + >        kmem_cache_free(cfq_pool, cfqq); >  } > > -- > 1.6.2.5 > Thanks Corrado -- 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/