Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755407AbZKLXpO (ORCPT ); Thu, 12 Nov 2009 18:45:14 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755257AbZKLXpN (ORCPT ); Thu, 12 Nov 2009 18:45:13 -0500 Received: from mx1.redhat.com ([209.132.183.28]:11999 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755242AbZKLXpM (ORCPT ); Thu, 12 Nov 2009 18:45:12 -0500 From: Vivek Goyal To: linux-kernel@vger.kernel.org, jens.axboe@oracle.com Cc: 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, vgoyal@redhat.com, akpm@linux-foundation.org, riel@redhat.com, kamezawa.hiroyu@jp.fujitsu.com Subject: [PATCH 07/16] blkio: Introduce per cfq group weights and vdisktime calculations Date: Thu, 12 Nov 2009 18:32:27 -0500 Message-Id: <1258068756-10766-8-git-send-email-vgoyal@redhat.com> In-Reply-To: <1258068756-10766-1-git-send-email-vgoyal@redhat.com> References: <1258068756-10766-1-git-send-email-vgoyal@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4826 Lines: 172 o Bring in the per cfq group weight and how vdisktime is calculated for the group. Also bring in the functionality of updating the min_vdisktime of the group service tree. Signed-off-by: Vivek Goyal --- block/Kconfig.iosched | 9 ++++++- block/cfq-iosched.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 69 insertions(+), 2 deletions(-) diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index be0280d..fa95fa7 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -23,7 +23,6 @@ config IOSCHED_DEADLINE config IOSCHED_CFQ tristate "CFQ I/O scheduler" - select BLK_CGROUP default y ---help--- The CFQ I/O scheduler tries to distribute bandwidth equally @@ -33,6 +32,14 @@ config IOSCHED_CFQ This is the default I/O scheduler. +config CFQ_GROUP_IOSCHED + bool "CFQ Group Scheduling support" + depends on IOSCHED_CFQ && CGROUPS + select BLK_CGROUP + default n + ---help--- + Enable group IO scheduling in CFQ. + choice prompt "Default I/O scheduler" default DEFAULT_CFQ diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index f8688b4..1354c6b 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -13,6 +13,7 @@ #include #include #include +#include "blk-cgroup.h" /* * tunables @@ -49,6 +50,7 @@ static const int cfq_hist_divisor = 4; #define CFQ_SLICE_SCALE (5) #define CFQ_HW_QUEUE_MIN (5) +#define CFQ_SERVICE_SHIFT 12 #define RQ_CIC(rq) \ ((struct cfq_io_context *) (rq)->elevator_private) @@ -78,6 +80,7 @@ struct cfq_rb_root { struct rb_node *left; unsigned count; u64 min_vdisktime; + struct rb_node *active; }; #define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, } @@ -162,6 +165,7 @@ struct cfq_group { /* group service_tree key */ u64 vdisktime; + unsigned int weight; bool on_st; /* number of cfqq currently on this group */ @@ -417,6 +421,51 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio); } +static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg) +{ + u64 d = delta << CFQ_SERVICE_SHIFT; + + d = d * BLKIO_WEIGHT_DEFAULT; + do_div(d, cfqg->weight); + return d; +} + +static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime) +{ + s64 delta = (s64)(vdisktime - min_vdisktime); + if (delta > 0) + min_vdisktime = vdisktime; + + return min_vdisktime; +} + +static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime) +{ + s64 delta = (s64)(vdisktime - min_vdisktime); + if (delta < 0) + min_vdisktime = vdisktime; + + return min_vdisktime; +} + +static void update_min_vdisktime(struct cfq_rb_root *st) +{ + u64 vdisktime = st->min_vdisktime; + struct cfq_group *cfqg; + + if (st->active) { + cfqg = rb_entry(st->active, struct cfq_group, rb_node); + vdisktime = cfqg->vdisktime; + } + + if (st->left) { + cfqg = rb_entry(st->left, struct cfq_group, rb_node); + vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime); + } + + st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime); +} + /* * get averaged number of queues of RT/BE priority. * average is updated, with a formula that gives more weight to higher numbers, @@ -718,8 +767,12 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg) { struct cfq_rb_root *st = &cfqd->grp_service_tree; + if (st->active == &cfqg->rb_node) + st->active = NULL; + BUG_ON(cfqg->nr_cfqq < 1); cfqg->nr_cfqq--; + /* If there are other cfq queues under this group, don't delete it */ if (cfqg->nr_cfqq) return; @@ -1667,10 +1720,14 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg) static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd) { struct cfq_rb_root *st = &cfqd->grp_service_tree; + struct cfq_group *cfqg; if (RB_EMPTY_ROOT(&st->rb)) return NULL; - return cfq_rb_first_group(st); + cfqg = cfq_rb_first_group(st); + st->active = &cfqg->rb_node; + update_min_vdisktime(st); + return cfqg; } static void cfq_choose_cfqg(struct cfq_data *cfqd) @@ -3146,6 +3203,9 @@ static void *cfq_init_queue(struct request_queue *q) cfqg->service_tree_idle = CFQ_RB_ROOT; RB_CLEAR_NODE(&cfqg->rb_node); + /* Give preference to root group over other groups */ + cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT; + /* * Not strictly needed (since RB_ROOT just clears the node and we * zeroed cfqd on alloc), but better be safe in case someone decides -- 1.6.2.5 -- 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/