From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-8.6 required=3.0 tests=DKIM_SIGNED,DKIM_VALID, DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_PASS, T_DKIMWL_WL_MED,URIBL_BLOCKED,USER_IN_DEF_DKIM_WL autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id D3240C46460 for ; Wed, 15 Aug 2018 01:19:22 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 6E1342098B for ; Wed, 15 Aug 2018 01:19:22 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="cXmG/yC4" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 6E1342098B Authentication-Results: mail.kernel.org; dmarc=fail (p=reject dis=none) header.from=google.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1725962AbeHOEID (ORCPT ); Wed, 15 Aug 2018 00:08:03 -0400 Received: from mail-ua1-f67.google.com ([209.85.222.67]:43250 "EHLO mail-ua1-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725831AbeHOEID (ORCPT ); Wed, 15 Aug 2018 00:08:03 -0400 Received: by mail-ua1-f67.google.com with SMTP id f4-v6so15320461uao.10 for ; Tue, 14 Aug 2018 18:18:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=m3e1kVnJ8jDYpUaQegebiyDo9+ltxR6W39l+IdShOJo=; b=cXmG/yC43BDNPZsEQsofCpLAb/KgYdziHk4zmBjVqo2M6UmRTtjfTk0YUPk6g7odrv AZ1n4PNnNZz8FLVJth9gvKe00C6qeJHL8WOFnv0P3aIFi2EReHC2Y9X1bCseyOmGYQKV Jc4sC+sHLMdoz71YmXBCL6maco2y7fh2gcb6H9GKRSMHRBr+Cl4D8V8tz2v7iuiKkt3k W2GVCiza5nQZYHoat17dlMCWuYIl8KyAPOwVkNZ2+s5dlboLsXj3MArLPs7Rtqavszdb WE8KpoKlvKivcS8H6LYYpIVYSQotsi+X1rSOb+S4xzgAGfTNkZv6PHE3ZqxIDyZZQSwa vomw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=m3e1kVnJ8jDYpUaQegebiyDo9+ltxR6W39l+IdShOJo=; b=V8CpNgq0WTsaVkwdWDcgLIucDGeGCON7Xx5NAMPdeINgpk8R/dmMvcPoHm7GcjxeOc Gcc+Ywob1E1rYtHwOtO/9ugEsPanm9yZayAK9/+H4jLUGM37BEpUK0trLSM9A4d3ZE6L z+Z6tfaybsjFW0x+WdO71SQboO56lYvwg21BRUs9X9j6cy013q3e8qjsn0ax3iTvkqxQ CG0nMZa1CVsL3/8W6aqJIRvgIHpqNRH0VmsfB6mOq+hVQkQ9zjrjKvG0N5CFMcVFPpKg /tmn1JlkBTPAD6dHSwTDmTt3+Q8jJAb+ABinJ2AXppFFzf673Qp8mBoAulL+LgS9SAWb dMaQ== X-Gm-Message-State: AOUpUlEraW35oL3lQ0d4RMTGgiq5To/5h9X4oXNKU6fora4e7n0JbmWL ZcrYqK0qz3TMWDfLdPQ5tcceDciybq9nPQjgGFZHEw== X-Google-Smtp-Source: AA+uWPwvhmy09ACHq+S+8oSNU8riSv2zAHR5QCcDV+z1sz9vK5xSZ8yLE/GMDX3eADz7blsQRpawxxZIOOkvW5Qfx5o= X-Received: by 2002:a9f:2c87:: with SMTP id w7-v6mr15378043uaj.21.1534295892682; Tue, 14 Aug 2018 18:18:12 -0700 (PDT) MIME-Version: 1.0 References: <20180815003620.15678-1-guro@fb.com> In-Reply-To: <20180815003620.15678-1-guro@fb.com> From: Shakeel Butt Date: Tue, 14 Aug 2018 18:18:01 -0700 Message-ID: Subject: Re: [RFC PATCH 1/2] mm: rework memcg kernel stack accounting To: Roman Gushchin Cc: Linux MM , LKML , kernel-team@fb.com, Johannes Weiner , Michal Hocko , luto@kernel.org, koct9i@gmail.com, Tejun Heo Content-Type: text/plain; charset="UTF-8" Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Aug 14, 2018 at 5:37 PM Roman Gushchin wrote: > > If CONFIG_VMAP_STACK is set, kernel stacks are allocated > using __vmalloc_node_range() with __GFP_ACCOUNT. So kernel > stack pages are charged against corresponding memory cgroups > on allocation and uncharged on releasing them. > > The problem is that we do cache kernel stacks in small > per-cpu caches and do reuse them for new tasks, which can > belong to different memory cgroups. > > Each stack page still holds a reference to the original cgroup, > so the cgroup can't be released until the vmap area is released. > > To make this happen we need more than two subsequent exits > without forks in between on the current cpu, which makes it > very unlikely to happen. As a result, I saw a significant number > of dying cgroups (in theory, up to 2 * number_of_cpu + > number_of_tasks), which can't be released even by significant > memory pressure. > > As a cgroup structure can take a significant amount of memory > (first of all, per-cpu data like memcg statistics), it leads > to a noticeable waste of memory. > > Signed-off-by: Roman Gushchin I was also looking into this issue. I was thinking of having a per-memcg per-cpu stack cache. However this solution seems much simpler. Can you also add the performance number for a similar simple benchmark done in ac496bf48d97 ("fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y"). Reviewed-by: Shakeel Butt > Cc: Johannes Weiner > Cc: Michal Hocko > Cc: Andy Lutomirski > Cc: Konstantin Khlebnikov > Cc: Tejun Heo > --- > kernel/fork.c | 44 ++++++++++++++++++++++++++++++++++++++------ > 1 file changed, 38 insertions(+), 6 deletions(-) > > diff --git a/kernel/fork.c b/kernel/fork.c > index 69b6fea5a181..91872b2b37bd 100644 > --- a/kernel/fork.c > +++ b/kernel/fork.c > @@ -224,9 +224,14 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) > return s->addr; > } > > + /* > + * Allocated stacks are cached and later reused by new threads, > + * so memcg accounting is performed manually on assigning/releasing > + * stacks to tasks. Drop __GFP_ACCOUNT. > + */ > stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, > VMALLOC_START, VMALLOC_END, > - THREADINFO_GFP, > + THREADINFO_GFP & ~__GFP_ACCOUNT, > PAGE_KERNEL, > 0, node, __builtin_return_address(0)); > > @@ -246,12 +251,41 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) > #endif > } > > +static void memcg_charge_kernel_stack(struct task_struct *tsk) > +{ > +#ifdef CONFIG_VMAP_STACK > + struct vm_struct *vm = task_stack_vm_area(tsk); > + > + if (vm) { > + int i; > + > + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) > + memcg_kmem_charge(vm->pages[i], __GFP_NOFAIL, > + compound_order(vm->pages[i])); > + > + /* All stack pages belong to the same memcg. */ > + mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB, > + THREAD_SIZE / 1024); > + } > +#endif > +} > + > static inline void free_thread_stack(struct task_struct *tsk) > { > #ifdef CONFIG_VMAP_STACK > - if (task_stack_vm_area(tsk)) { > + struct vm_struct *vm = task_stack_vm_area(tsk); > + > + if (vm) { > int i; > > + /* All stack pages belong to the same memcg. */ > + mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB, > + -(int)(THREAD_SIZE / 1024)); > + > + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) > + memcg_kmem_uncharge(vm->pages[i], > + compound_order(vm->pages[i])); > + > for (i = 0; i < NR_CACHED_STACKS; i++) { > if (this_cpu_cmpxchg(cached_stacks[i], > NULL, tsk->stack_vm_area) != NULL) > @@ -352,10 +386,6 @@ static void account_kernel_stack(struct task_struct *tsk, int account) > NR_KERNEL_STACK_KB, > PAGE_SIZE / 1024 * account); > } > - > - /* All stack pages belong to the same memcg. */ > - mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB, > - account * (THREAD_SIZE / 1024)); > } else { > /* > * All stack pages are in the same zone and belong to the > @@ -809,6 +839,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) > if (!stack) > goto free_tsk; > > + memcg_charge_kernel_stack(tsk); > + > stack_vm_area = task_stack_vm_area(tsk); > > err = arch_dup_task_struct(tsk, orig); > -- > 2.14.4 >