Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756736Ab0BMC4R (ORCPT ); Fri, 12 Feb 2010 21:56:17 -0500 Received: from smtp-out.google.com ([216.239.44.51]:58796 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751568Ab0BMC4E (ORCPT ); Fri, 12 Feb 2010 21:56:04 -0500 DomainKey-Signature: a=rsa-sha1; s=beta; d=google.com; c=nofws; q=dns; h=subject:to:from:cc:date:message-id:in-reply-to:references: user-agent:mime-version:content-type: content-transfer-encoding:x-system-of-record; b=u/FjSyHFvAcX2rHvU2RKomCrguX9HpI6xaViGa6RhDXsRj5MMOKWjRPiLkEMWvalM NL/NR5+4jTfFhHZ46Z8Ng== Subject: [RFC PATCH v1 2/4] sched: accumulate per-cfs_rq cpu usage To: linux-kernel@vger.kernel.org From: Paul Cc: Paul Menage , Srivatsa Vaddagiri , Peter Zijlstra , Gautham R Shenoy , Dhaval Giani , Balbir Singh , Herbert Poetzl , Chris Friesen , Avi Kivity , Bharata B Rao , Nikhil Rao , Ingo Molnar , Kamalesh Babulal , Mike Waychison , Vaidyanathan Srinivasan , Pavel Emelyanov Date: Fri, 12 Feb 2010 18:55:02 -0800 Message-ID: <20100213025502.23325.47815.stgit@kitami.corp.google.com> In-Reply-To: <20100213025417.23325.90048.stgit@kitami.corp.google.com> References: <20100213025417.23325.90048.stgit@kitami.corp.google.com> User-Agent: StGit/0.15 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4932 Lines: 165 From: Paul Turner Introduce account_cfs_rq_quota() to account bandwidth usage on the cfs_rq level versus task_groups for which bandwidth has been assigned. This is tracked by whether the local cfs_rq->quota_assigned is finite or infinite (RUNTIME_INF). For cfs_rq's that belong to a bandwidth constrained task_group we introduce tg_request_cfs_quota() which attempts to allocate quota from the global pool for use locally. Updates involving the global pool are currently protected under cfs_bandwidth->lock, local pools are protected by rq->lock. This patch only attempts to assign and track quota, no action is taken in the case that cfs_rq->quota_used exceeds cfs_rq->quota_assigned. Signed-off-by: Paul Turner Signed-off-by: Nikhil Rao --- include/linux/sched.h | 4 ++++ kernel/sched.c | 13 +++++++++++++ kernel/sched_fair.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sysctl.c | 10 ++++++++++ 4 files changed, 77 insertions(+), 0 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 78efe7c..8c9d401 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1963,6 +1963,10 @@ int sched_rt_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_CFS_BANDWIDTH +extern unsigned int sysctl_sched_cfs_bandwidth_slice; +#endif + extern unsigned int sysctl_sched_compat_yield; #ifdef CONFIG_RT_MUTEXES diff --git a/kernel/sched.c b/kernel/sched.c index 6cc4bf4..fb2ffc6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1923,6 +1923,19 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) * default: 0.5s */ static u64 sched_cfs_bandwidth_period = 500000000ULL; + +/* + * default slice of quota to allocate from global tg to local cfs_rq pool on + * each refresh + * default: 10ms + */ +unsigned int sysctl_sched_cfs_bandwidth_slice = 10000UL; + +static inline u64 sched_cfs_bandwidth_slice(void) +{ + return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; +} + #endif #include "sched_stats.h" diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 7b109ff..f2741ab 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -266,6 +266,16 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) } #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_CFS_BANDWIDTH +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return &tg->cfs_bandwidth; +} + +static void account_cfs_rq_quota(struct cfs_rq *cfs_rq, + unsigned long delta_exec); +#endif + /************************************************************** * Scheduling class tree data structure manipulation methods: */ @@ -544,6 +554,9 @@ static void update_curr(struct cfs_rq *cfs_rq) cpuacct_charge(curtask, delta_exec); account_group_exec_runtime(curtask, delta_exec); } +#ifdef CONFIG_CFS_BANDWIDTH + account_cfs_rq_quota(cfs_rq, delta_exec); +#endif } static inline void @@ -1145,6 +1158,43 @@ static void yield_task_fair(struct rq *rq) } #ifdef CONFIG_CFS_BANDWIDTH +static u64 tg_request_cfs_quota(struct task_group *tg) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); + u64 delta = 0; + + if (cfs_b->runtime > 0 || cfs_b->quota == RUNTIME_INF) { + raw_spin_lock(&cfs_b->lock); + /* + * it's possible a bandwidth update has changed the global + * pool. + */ + if (cfs_b->quota == RUNTIME_INF) + delta = sched_cfs_bandwidth_slice(); + else { + delta = min(cfs_b->runtime, + sched_cfs_bandwidth_slice()); + cfs_b->runtime -= delta; + } + raw_spin_unlock(&cfs_b->lock); + } + return delta; +} + +static void account_cfs_rq_quota(struct cfs_rq *cfs_rq, + unsigned long delta_exec) +{ + if (cfs_rq->quota_assigned == RUNTIME_INF) + return; + + cfs_rq->quota_used += delta_exec; + + if (cfs_rq->quota_used < cfs_rq->quota_assigned) + return; + + cfs_rq->quota_assigned += tg_request_cfs_quota(cfs_rq->tg); +} + static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) { return 1; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8a68b24..cc5ccce 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -364,6 +364,16 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_CFS_BANDWIDTH + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, +#endif #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", -- 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/