From: Tejun Heo Subject: [PATCH cgroup/for-5.0] cgroup, rstat: Don't flush subtree root unless necessary Date: Fri, 15 Feb 2019 11:05:35 -0800 Message-ID: <20190215190535.GR50184@devbig004.ftw2.facebook.com> Mime-Version: 1.0 Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:date:from:to:cc:subject:message-id:mime-version :content-disposition:user-agent; bh=542kMV/M+F4ke2Nez4pG0EO/cK2G2uhP23eV8bg4uGc=; b=fqohBaoCh6j07OJSvNB8YJkGy7d7sCxJdAaXOMg30nSbXziT7y+/S7HPkzBp6tv5w+ 4jtBehbmIspbhohxS9FyV/e2dwR2scC7ZpC3s2Bl6Ybj4qu8PEFgAspIEyvzVIjcOfaP +vOGLsHhI0UIvoH3WvYEXBJ5q2LAY5AloHoXnKtT0ao/23j1Y2Z6CgwyyHQqahMRP5R1 LoaaDrFQvxX3f3xGdS7bw4CIJj25lYnf+HUBqesdGzEYESkRDd86qs2zqwJOJ/p2pguE pAp0v9FP7bVkWKMFGa9uHOJiTXm1sFOStnuow7/yDaN3Q97YYAPA4VudCAXI2ldAK0Op ur0g== Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Li Zefan , Johannes Weiner Cc: cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com From b4ff1b44bcd384d22fcbac6ebaf9cc0d33debe50 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 15 Feb 2019 11:01:31 -0800 cgroup_rstat_cpu_pop_updated() is used to traverse the updated cgroups on flush. While it was only visiting updated ones in the subtree, it was visiting @root unconditionally. We can easily check whether @root is updated or not by looking at its ->updated_next just as with the cgroups in the subtree. * Remove the unnecessary cgroup_parent() test. The system root cgroup is never updated and thus its ->updated_next is always NULL. No need to test whether cgroup_parent() exists in addition to ->updated_next. * Terminate traverse if ->updated_next is NULL. This can only happen for subtree @root and there's no reason to visit it if it's not marked updated. This reduces cpu consumption when reading a lot of rstat backed files. In a micro benchmark reading stat from ~1600 cgroups, the sys time was lowered by >40%. Signed-off-by: Tejun Heo --- Hello, I'm applying this on for-5.0. It's a fairly straight forward optimization. Thanks. kernel/cgroup/rstat.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index d503d1a9007c..bb95a35e8c2d 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -87,7 +87,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, struct cgroup *root, int cpu) { struct cgroup_rstat_cpu *rstatc; - struct cgroup *parent; if (pos == root) return NULL; @@ -115,8 +114,8 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, * However, due to the way we traverse, @pos will be the first * child in most cases. The only exception is @root. */ - parent = cgroup_parent(pos); - if (parent && rstatc->updated_next) { + if (rstatc->updated_next) { + struct cgroup *parent = cgroup_parent(pos); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); struct cgroup_rstat_cpu *nrstatc; struct cgroup **nextp; @@ -140,9 +139,12 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, * updated stat. */ smp_mb(); + + return pos; } - return pos; + /* only happens for @root */ + return NULL; } /* see cgroup_rstat_flush() */ -- 2.17.1