* [PATCH] config: arm: imx: remove PROVE_LOCKING from defconfig
[not found] <CGME20181009153526eucas1p2cdbb125bc7a66e0685f2277740a25630@eucas1p2.samsung.com>
@ 2018-10-09 15:35 ` Lukasz Luba
0 siblings, 0 replies; 4+ messages in thread
From: Lukasz Luba @ 2018-10-09 15:35 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel
Cc: l.luba, b.zolnierkie, s.hauer, kernel, fabio.estevam, linux-imx
PROVE_LOCKING enables LOCKDEP, which causes big overhead on cache and
bus transactions.
On some ARM big.LITTLE architecutres (Exynos 5433) the overhead is really big.
The overhead can be measures using hackbench which will speed up
by x3 times (11sec -> 3.4sec).
When you check transaction on cache or buses, the results are way higher
than normal for the same hackbench test:
L1d cache invalidations: 26mln vs 4mln
L2u cache invalidations: 42mln vs 12mln
bus cyc/access: 30cyc/access vs. 20cyc/access
context switch is x3 times cheaper
Enable this option only when you have some locking issue to investigate.
Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
---
arch/arm/configs/imx_v6_v7_defconfig | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 7eca43f..f55cd2d 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -425,7 +425,6 @@ CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
# CONFIG_SCHED_DEBUG is not set
-CONFIG_PROVE_LOCKING=y
# CONFIG_DEBUG_BUGVERBOSE is not set
# CONFIG_FTRACE is not set
# CONFIG_ARM_UNWIND is not set
--
2.7.4
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH] config: arm: imx: remove PROVE_LOCKING from defconfig
@ 2018-10-09 15:35 ` Lukasz Luba
0 siblings, 0 replies; 4+ messages in thread
From: Lukasz Luba @ 2018-10-09 15:35 UTC (permalink / raw)
To: linux-arm-kernel
PROVE_LOCKING enables LOCKDEP, which causes big overhead on cache and
bus transactions.
On some ARM big.LITTLE architecutres (Exynos 5433) the overhead is really big.
The overhead can be measures using hackbench which will speed up
by x3 times (11sec -> 3.4sec).
When you check transaction on cache or buses, the results are way higher
than normal for the same hackbench test:
L1d cache invalidations: 26mln vs 4mln
L2u cache invalidations: 42mln vs 12mln
bus cyc/access: 30cyc/access vs. 20cyc/access
context switch is x3 times cheaper
Enable this option only when you have some locking issue to investigate.
Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
---
arch/arm/configs/imx_v6_v7_defconfig | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 7eca43f..f55cd2d 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -425,7 +425,6 @@ CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
# CONFIG_SCHED_DEBUG is not set
-CONFIG_PROVE_LOCKING=y
# CONFIG_DEBUG_BUGVERBOSE is not set
# CONFIG_FTRACE is not set
# CONFIG_ARM_UNWIND is not set
--
2.7.4
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH] config: arm: imx: remove PROVE_LOCKING from defconfig
2018-10-09 15:35 ` Lukasz Luba
@ 2018-10-10 12:55 ` Fabio Estevam
-1 siblings, 0 replies; 4+ messages in thread
From: Fabio Estevam @ 2018-10-10 12:55 UTC (permalink / raw)
To: l.luba
Cc: moderated list:ARM/FREESCALE IMX / MXC ARM ARCHITECTURE,
linux-kernel, Bartlomiej Zolnierkiewicz, Sascha Hauer,
NXP Linux Team, Sascha Hauer, Fabio Estevam,
Russell King - ARM Linux
Hi Lukasz,
On Tue, Oct 9, 2018 at 12:36 PM Lukasz Luba <l.luba@partner.samsung.com> wrote:
>
> PROVE_LOCKING enables LOCKDEP, which causes big overhead on cache and
> bus transactions.
>
> On some ARM big.LITTLE architecutres (Exynos 5433) the overhead is really big.
> The overhead can be measures using hackbench which will speed up
> by x3 times (11sec -> 3.4sec).
> When you check transaction on cache or buses, the results are way higher
> than normal for the same hackbench test:
> L1d cache invalidations: 26mln vs 4mln
> L2u cache invalidations: 42mln vs 12mln
> bus cyc/access: 30cyc/access vs. 20cyc/access
> context switch is x3 times cheaper
>
> Enable this option only when you have some locking issue to investigate.
>
> Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
> ---
> arch/arm/configs/imx_v6_v7_defconfig | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
> index 7eca43f..f55cd2d 100644
> --- a/arch/arm/configs/imx_v6_v7_defconfig
> +++ b/arch/arm/configs/imx_v6_v7_defconfig
> @@ -425,7 +425,6 @@ CONFIG_PRINTK_TIME=y
> CONFIG_DEBUG_FS=y
> CONFIG_MAGIC_SYSRQ=y
> # CONFIG_SCHED_DEBUG is not set
> -CONFIG_PROVE_LOCKING=y
Russell explains here why it is desirable to have
CONFIG_PROVE_LOCKING=y for development:
https://www.spinics.net/lists/kernel/msg2929513.html
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH] config: arm: imx: remove PROVE_LOCKING from defconfig
@ 2018-10-10 12:55 ` Fabio Estevam
0 siblings, 0 replies; 4+ messages in thread
From: Fabio Estevam @ 2018-10-10 12:55 UTC (permalink / raw)
To: linux-arm-kernel
Hi Lukasz,
On Tue, Oct 9, 2018 at 12:36 PM Lukasz Luba <l.luba@partner.samsung.com> wrote:
>
> PROVE_LOCKING enables LOCKDEP, which causes big overhead on cache and
> bus transactions.
>
> On some ARM big.LITTLE architecutres (Exynos 5433) the overhead is really big.
> The overhead can be measures using hackbench which will speed up
> by x3 times (11sec -> 3.4sec).
> When you check transaction on cache or buses, the results are way higher
> than normal for the same hackbench test:
> L1d cache invalidations: 26mln vs 4mln
> L2u cache invalidations: 42mln vs 12mln
> bus cyc/access: 30cyc/access vs. 20cyc/access
> context switch is x3 times cheaper
>
> Enable this option only when you have some locking issue to investigate.
>
> Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
> ---
> arch/arm/configs/imx_v6_v7_defconfig | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
> index 7eca43f..f55cd2d 100644
> --- a/arch/arm/configs/imx_v6_v7_defconfig
> +++ b/arch/arm/configs/imx_v6_v7_defconfig
> @@ -425,7 +425,6 @@ CONFIG_PRINTK_TIME=y
> CONFIG_DEBUG_FS=y
> CONFIG_MAGIC_SYSRQ=y
> # CONFIG_SCHED_DEBUG is not set
> -CONFIG_PROVE_LOCKING=y
Russell explains here why it is desirable to have
CONFIG_PROVE_LOCKING=y for development:
https://www.spinics.net/lists/kernel/msg2929513.html
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2018-10-10 12:55 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <CGME20181009153526eucas1p2cdbb125bc7a66e0685f2277740a25630@eucas1p2.samsung.com>
2018-10-09 15:35 ` [PATCH] config: arm: imx: remove PROVE_LOCKING from defconfig Lukasz Luba
2018-10-09 15:35 ` Lukasz Luba
2018-10-10 12:55 ` Fabio Estevam
2018-10-10 12:55 ` Fabio Estevam
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.