diff options
| author | Raghavendra K T | 2013-10-21 18:05:08 +0200 |
|---|---|---|
| committer | Ingo Molnar | 2013-10-26 12:23:22 +0200 |
| commit | 4c4e4f61368164f326fe59e2156c70d7faa72c17 (patch) | |
| tree | 3507a3abdf0622bb04503f07941b52d2088a3bd6 /arch/x86/Kconfig | |
| parent | lockstat: Report avg wait and hold times (diff) | |
| download | kernel-qcow2-linux-4c4e4f61368164f326fe59e2156c70d7faa72c17.tar.gz kernel-qcow2-linux-4c4e4f61368164f326fe59e2156c70d7faa72c17.tar.xz kernel-qcow2-linux-4c4e4f61368164f326fe59e2156c70d7faa72c17.zip | |
x86/locking/kconfig: Update paravirt spinlock Kconfig description
Since the paravirt spinlock optimizations went into the v3.12 kernel
we have a very good performance benefit for paravirtualized KVM / Xen
kernels. Also we no longer suffer from 5% side effect on native
kernel that is mentioned in the Kconfig entry.
So update the Kconfig entry accordingly.
pvspinlock benefit on KVM link:
https://lkml.org/lkml/2013/8/6/178
Attilio's tests on native kernel impact:
http://blog.xen.org/index.php/2012/05/11/benchmarking-the-new-pv-ticketlock-implementation/
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: <konrad.wilk@oracle.com>
Cc: <linux@eikelenboom.it>
Cc: <gleb@redhat.com>
Cc: <pbonzini@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1382371508-3843-1-git-send-email-raghavendra.kt@linux.vnet.ibm.com
[ Updated the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/Kconfig')
| -rw-r--r-- | arch/x86/Kconfig | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ee2fb9d37745..a92572de2ac1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -638,10 +638,10 @@ config PARAVIRT_SPINLOCKS spinlock implementation with something virtualization-friendly (for example, block the virtual CPU rather than spinning). - Unfortunately the downside is an up to 5% performance hit on - native kernels, with various workloads. + It has a minimal impact on native kernels and gives a nice performance + benefit on paravirtualized KVM / Xen kernels. - If you are unsure how to answer this question, answer N. + If you are unsure how to answer this question, answer Y. source "arch/x86/xen/Kconfig" |