From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752273AbbD3VYI (ORCPT ); Thu, 30 Apr 2015 17:24:08 -0400 Received: from shelob.surriel.com ([74.92.59.67]:40948 "EHLO shelob.surriel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751298AbbD3VYE (ORCPT ); Thu, 30 Apr 2015 17:24:04 -0400 From: riel@redhat.com To: linux-kernel@vger.kernel.org Cc: x86@kernel.org, williams@redhat.com, luto@kernel.org, mingo@kernel.org, bonzini@redhat.com, fweisbec@redhat.com, peterz@infradead.org, heiko.carstens@de.ibm.com, tglx@linutronix.de Subject: [PATCH 0/3] reduce nohz_full syscall overhead by 10% Date: Thu, 30 Apr 2015 17:23:52 -0400 Message-Id: <1430429035-25563-1-git-send-email-riel@redhat.com> X-Mailer: git-send-email 2.1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Profiling reveals that a lot of the overhead from the nohz_full accounting seems to come not from the accounting itself, but from disabling and re-enabling interrupts. This patch series removes the interrupt disabling & re-enabling from __acct_update_integrals, which is called on both syscall entry and exit, as well as from the user_exit called on syscall entry. Together they speed up a benchmark that calls getpriority in a row 10 million times by about 10%: run time system time vanilla 5.49s 2.08s __acct patch 5.21s 1.92s both patches 4.88s 1.71s