lock's trace events can improve mutex's performance in userspace?
We found that if enable lock's trace events, the 'sysbench mutex' benchmark program can run quicker. The simple program that is attached can reproduce it, the system info, kernel config, and the script are also attached. The test step is below: # tar -zxvf test-mutex.tar.bz # cd test-mutex # make # ./tscr... 8 Apr 2010 06:09
[patch 0/12] sched: fastpath cycle recovery
Hi Peter, The following patchlets take a pinned pipe-test context switch frequency in tip from 663KHZ to 694KHZ, and an unpinned instance from 450KHz to 540KHz. With these applied to tip.today, I have zero 31-12->today regressions, and even some modest progressions. The biggest difference is made by the first... 11 Mar 2010 05:38
fs: fat: use hex_asc_lo/hex_asc_hi instead of custom one
Andy Shevchenko <andy.shevchenko(a)gmail.com> writes: On Thu, Mar 11, 2010 at 1:18 AM, OGAWA Hirofumi <hirofumi(a)mail.parknet.co.jp> wrote: + � � � � � � � � � � � � � � *op++ = hex_asc_hi(ec >> 8); + � � � � � � � � � � � � � � *op++ = hex_asc_lo(ec >> 8); + � � � � � � � � � � � � � � *op++ = hex_... 11 Mar 2010 04:33
perf: export perf_trace_regs and perf_arch_fetch_caller_regs
On Thu, Mar 11, 2010 at 03:30:35PM +0800, Xiao Guangrong wrote: Export perf_trace_regs and perf_arch_fetch_caller_regs since module will use these What modules exactly? Uusually you add the export together with the series adding the users. -- To unsubscribe from this list: send the line "unsubscribe linu... 11 Mar 2010 10:01
[PATCH] drm/i915: Convert some trace events to DEFINE_TRACE
Use DECLARE_EVENT_CLASS to remove duplicate code: text data bss dec hex filename 14655 2732 15 17402 43fa i915_trace_points.o.orig 11625 2732 10 14367 381f i915_trace_points.o 8 events are converted: i915_gem_object: i915_gem_object_{unbind, destroy} i915... 11 Mar 2010 04:33
[PATCH 4/4 v2] WATCHDOG: convert rdc321x_wdt to use southbridge accessors
With the introduction of the MFD driver which abstracts access to the PCI device configuration space the watchdog driver must be converted to use these accessors and provide safe register read/write. As a result we now use the memory resource which comes with the platform device. Signed-off-by: Florian Fainelli <... 11 Mar 2010 04:33
[PATCH 1/2] tracing: Convert some signal events to DEFINE_TRACE
Use DECLARE_EVENT_CLASS to remove duplicate code: text data bss dec hex filename 23639 6084 8 29731 7423 kernel/signal.o.orig 22727 6084 8 28819 7093 kernel/signal.o 2 events are converted: signal_queue_overflow: signal_overflow_fail, signal_lose_info No... 11 Mar 2010 04:33
[PATCH 1/4 v2] x86: remove rdc321x_defs.h
This file is going to be replaced with a cleaner version with the adding of a MFD driver for the southbridge. Signed-off-by: Florian Fainelli <florian(a)openwrt.org> --- diff --git a/arch/x86/include/asm/rdc321x_defs.h b/arch/x86/include/asm/rdc321x_defs.h deleted file mode 100644 index c8e9c8b..0000000 --- a/ar... 11 Mar 2010 04:33
[PATCH 2/4 v2] MFD: add support for the RDC321x southbridge
This patch adds a new MFD driver for the RDC321x southbridge. This southbridge is always present in the RDC321x System-on-a-Chip and provides access to some GPIOs as well as a watchdog. Access to these two functions is done using the southbridge PCI device configuration space. Signed-off-by: Florian Fainelli <flo... 11 Mar 2010 04:33
[PATCH v2 0/4] RDC321x southbridge and GPIO support
Hi Wim, Samuel, Ingo, Here are 4 patches relative to adding support for the RDC321x southbridge. This southbridge is present on all x86-based RDC321x System-on-a-Chip and provides access to GPIOs and Wathchdog. The watchdog driver is already merged. Samuel, this is rebased on top of your mfd-2.6 master branch a... 11 Mar 2010 04:33