From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756799AbcJTHeS (ORCPT ); Thu, 20 Oct 2016 03:34:18 -0400 Received: from mail-pf0-f172.google.com ([209.85.192.172]:33330 "EHLO mail-pf0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751039AbcJTHeR (ORCPT ); Thu, 20 Oct 2016 03:34:17 -0400 From: Joel Fernandes To: linux-kernel@vger.kernel.org Cc: Kees Cook , Joel Fernandes Subject: [PATCH v2 0/7] pstore: Improve performance of ftrace backend with ramoops Date: Thu, 20 Oct 2016 00:33:59 -0700 Message-Id: <1476948846-15006-1-git-send-email-joelaf@google.com> X-Mailer: git-send-email 2.7.4 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Currently ramoops uses a single zone to store function traces. To make this work, it has to uses locking to synchronize accesses to the buffers. Recently the synchronization was completely moved from a cmpxchg mechanism to raw spinlocks due to difficulties in using cmpxchg on uncached memory and also on RAMs behind PCIe. [1] This change further dropped the peformance of ramoops pstore backend by more than half in my tests. This patch series improves the situation dramatically by around 280% from what it is now by creating a ramoops persistent zone for each CPU and avoiding use of locking altogether for ftrace. At init time, the persistent zones are then merged together. Here are some tests to show the improvements. Tested using a qemu quad core x86_64 instance with -mem-path to persist the guest RAM to a file. I measured avergage throughput of dd over 30 seconds: dd if=/dev/zero | pv | dd of=/dev/null Without this patch series: 24MB/s with per-cpu buffers and trace_clock: 51.9 MB/s With per-cpu buffers and counter increment: 91.5 MB/s (improvement by ~ 281%) Changes since v1: - Use PSTORE_ prefix for RAM_LOCK and RAM_NOLOCK macros Changes since RFC [2]: - improve commit message clarity for optional locking of zone buffers. - use macro for better code clarity of locking requirements - use kcalloc instead of kmalloc for allocating prz array - print warning if pmsg calls write_buf instead of write_buf_user - free zones properly for ftrace per CPU usecase. [1] https://lkml.org/lkml/2016/9/8/375 [2] https://lkml.org/lkml/2016/10/8/12 Joel Fernandes (7): pstore: Make spinlock per zone instead of global pstore: locking: dont lock unless caller asks to pstore: Warn for the case of PSTORE_TYPE_PMSG write using deprecated function pstore: Make ramoops_init_przs generic for other prz arrays ramoops: Split ftrace buffer space into per-CPU zones pstore: Add support to store timestamp counter in ftrace records pstore: Merge per-CPU ftrace zones into one zone for output fs/pstore/ftrace.c | 3 + fs/pstore/inode.c | 7 +- fs/pstore/internal.h | 34 ------- fs/pstore/ram.c | 236 +++++++++++++++++++++++++++++++++++---------- fs/pstore/ram_core.c | 30 +++--- include/linux/pstore.h | 69 +++++++++++++ include/linux/pstore_ram.h | 14 ++- 7 files changed, 291 insertions(+), 102 deletions(-) -- 2.7.4