* [PATCH] tools/virtio/ringtest: add usage example to README
@ 2016-05-04 6:12 Mike Rapoport
2016-05-04 6:12 ` [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu Mike Rapoport
` (2 more replies)
0 siblings, 3 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-04 6:12 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization, Mike Rapoport
Having typical usage example in the README file is more convinient than in
the git history...
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
tools/virtio/ringtest/README | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README
index 34e94c4..d83707a 100644
--- a/tools/virtio/ringtest/README
+++ b/tools/virtio/ringtest/README
@@ -1,2 +1,6 @@
Partial implementation of various ring layouts, useful to tune virtio design.
Uses shared memory heavily.
+
+Typical use:
+
+# sh run-on-all.sh perf stat -r 10 --log-fd 1 -- ./ring
--
1.9.1
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 6:12 [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
@ 2016-05-04 6:12 ` Mike Rapoport
2016-05-04 6:40 ` Cornelia Huck
2016-05-04 6:40 ` Cornelia Huck
2016-05-04 6:12 ` [PATCH] " Mike Rapoport
2016-05-24 12:41 ` [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
2 siblings, 2 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-04 6:12 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization, Mike Rapoport
/dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
Using /proc/cpuinfo to get processors count is more portable.
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
tools/virtio/ringtest/run-on-all.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 52b0f71..38ccfa3 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -3,10 +3,10 @@
#use last CPU for host. Why not the first?
#many devices tend to use cpu0 by default so
#it tends to be busier
-HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+HOST_AFFINITY=$(($(grep -c processor /proc/cpuinfo) - 1))
#run command on all cpus
-for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+for cpu in $(seq 0 $HOST_AFFINITY)
do
#Don't run guest and host on same CPU
#It actually works ok if using signalling
--
1.9.1
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 6:12 [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
2016-05-04 6:12 ` [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu Mike Rapoport
@ 2016-05-04 6:12 ` Mike Rapoport
2016-05-24 12:41 ` [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
2 siblings, 0 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-04 6:12 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: Mike Rapoport, kvm, virtualization
/dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
Using /proc/cpuinfo to get processors count is more portable.
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
tools/virtio/ringtest/run-on-all.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 52b0f71..38ccfa3 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -3,10 +3,10 @@
#use last CPU for host. Why not the first?
#many devices tend to use cpu0 by default so
#it tends to be busier
-HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+HOST_AFFINITY=$(($(grep -c processor /proc/cpuinfo) - 1))
#run command on all cpus
-for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+for cpu in $(seq 0 $HOST_AFFINITY)
do
#Don't run guest and host on same CPU
#It actually works ok if using signalling
--
1.9.1
^ permalink raw reply related [flat|nested] 19+ messages in thread
* Re: [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 6:12 ` [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu Mike Rapoport
2016-05-04 6:40 ` Cornelia Huck
@ 2016-05-04 6:40 ` Cornelia Huck
2016-05-04 7:59 ` [PATCH v2] " Mike Rapoport
2016-05-04 7:59 ` Mike Rapoport
1 sibling, 2 replies; 19+ messages in thread
From: Cornelia Huck @ 2016-05-04 6:40 UTC (permalink / raw)
To: Mike Rapoport; +Cc: Michael S. Tsirkin, kvm, virtualization
On Wed, 4 May 2016 09:12:56 +0300
Mike Rapoport <rppt@linux.vnet.ibm.com> wrote:
> /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> Using /proc/cpuinfo to get processors count is more portable.
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> tools/virtio/ringtest/run-on-all.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> index 52b0f71..38ccfa3 100755
> --- a/tools/virtio/ringtest/run-on-all.sh
> +++ b/tools/virtio/ringtest/run-on-all.sh
> @@ -3,10 +3,10 @@
> #use last CPU for host. Why not the first?
> #many devices tend to use cpu0 by default so
> #it tends to be busier
> -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> +HOST_AFFINITY=$(($(grep -c processor /proc/cpuinfo) - 1))
>
> #run command on all cpus
> -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> +for cpu in $(seq 0 $HOST_AFFINITY)
> do
> #Don't run guest and host on same CPU
> #It actually works ok if using signalling
As you're touching this anyway: Is there any way to avoid the
architecture-specific /proc/cpuinfo and do whatever lscpu does?
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 6:12 ` [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu Mike Rapoport
@ 2016-05-04 6:40 ` Cornelia Huck
2016-05-04 6:40 ` Cornelia Huck
1 sibling, 0 replies; 19+ messages in thread
From: Cornelia Huck @ 2016-05-04 6:40 UTC (permalink / raw)
To: Mike Rapoport; +Cc: virtualization, kvm, Michael S. Tsirkin
On Wed, 4 May 2016 09:12:56 +0300
Mike Rapoport <rppt@linux.vnet.ibm.com> wrote:
> /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> Using /proc/cpuinfo to get processors count is more portable.
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> tools/virtio/ringtest/run-on-all.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> index 52b0f71..38ccfa3 100755
> --- a/tools/virtio/ringtest/run-on-all.sh
> +++ b/tools/virtio/ringtest/run-on-all.sh
> @@ -3,10 +3,10 @@
> #use last CPU for host. Why not the first?
> #many devices tend to use cpu0 by default so
> #it tends to be busier
> -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> +HOST_AFFINITY=$(($(grep -c processor /proc/cpuinfo) - 1))
>
> #run command on all cpus
> -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> +for cpu in $(seq 0 $HOST_AFFINITY)
> do
> #Don't run guest and host on same CPU
> #It actually works ok if using signalling
As you're touching this anyway: Is there any way to avoid the
architecture-specific /proc/cpuinfo and do whatever lscpu does?
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v2] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 6:40 ` Cornelia Huck
2016-05-04 7:59 ` [PATCH v2] " Mike Rapoport
@ 2016-05-04 7:59 ` Mike Rapoport
2016-05-04 8:14 ` Cornelia Huck
2016-05-04 8:14 ` Cornelia Huck
1 sibling, 2 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-04 7:59 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: Cornelia Huck, kvm, virtualization, Mike Rapoport
/dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
Using lscpu to get processors count is more portable.
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
tools/virtio/ringtest/run-on-all.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 52b0f71..0177d50 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -3,10 +3,10 @@
#use last CPU for host. Why not the first?
#many devices tend to use cpu0 by default so
#it tends to be busier
-HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+HOST_AFFINITY=$(lscpu -p | tail -n 1 | cut -d',' -f1)
#run command on all cpus
-for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+for cpu in $(seq 0 $HOST_AFFINITY)
do
#Don't run guest and host on same CPU
#It actually works ok if using signalling
--
1.9.1
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v2] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 6:40 ` Cornelia Huck
@ 2016-05-04 7:59 ` Mike Rapoport
2016-05-04 7:59 ` Mike Rapoport
1 sibling, 0 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-04 7:59 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: Mike Rapoport, kvm, virtualization
/dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
Using lscpu to get processors count is more portable.
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
tools/virtio/ringtest/run-on-all.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 52b0f71..0177d50 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -3,10 +3,10 @@
#use last CPU for host. Why not the first?
#many devices tend to use cpu0 by default so
#it tends to be busier
-HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+HOST_AFFINITY=$(lscpu -p | tail -n 1 | cut -d',' -f1)
#run command on all cpus
-for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+for cpu in $(seq 0 $HOST_AFFINITY)
do
#Don't run guest and host on same CPU
#It actually works ok if using signalling
--
1.9.1
^ permalink raw reply related [flat|nested] 19+ messages in thread
* Re: [PATCH v2] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 7:59 ` Mike Rapoport
2016-05-04 8:14 ` Cornelia Huck
@ 2016-05-04 8:14 ` Cornelia Huck
2016-05-04 10:15 ` [PATCH v3] " Mike Rapoport
1 sibling, 1 reply; 19+ messages in thread
From: Cornelia Huck @ 2016-05-04 8:14 UTC (permalink / raw)
To: Mike Rapoport; +Cc: Michael S. Tsirkin, kvm, virtualization
On Wed, 4 May 2016 10:59:53 +0300
Mike Rapoport <rppt@linux.vnet.ibm.com> wrote:
> /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> Using lscpu to get processors count is more portable.
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
>
> tools/virtio/ringtest/run-on-all.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> index 52b0f71..0177d50 100755
> --- a/tools/virtio/ringtest/run-on-all.sh
> +++ b/tools/virtio/ringtest/run-on-all.sh
> @@ -3,10 +3,10 @@
> #use last CPU for host. Why not the first?
> #many devices tend to use cpu0 by default so
> #it tends to be busier
> -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> +HOST_AFFINITY=$(lscpu -p | tail -n 1 | cut -d',' -f1)
Shorter:
lscpu -p=cpu | tail -1
Should be good enough for a test tool :)
>
> #run command on all cpus
> -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> +for cpu in $(seq 0 $HOST_AFFINITY)
> do
> #Don't run guest and host on same CPU
> #It actually works ok if using signalling
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH v2] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 7:59 ` Mike Rapoport
@ 2016-05-04 8:14 ` Cornelia Huck
2016-05-04 8:14 ` Cornelia Huck
1 sibling, 0 replies; 19+ messages in thread
From: Cornelia Huck @ 2016-05-04 8:14 UTC (permalink / raw)
To: Mike Rapoport; +Cc: virtualization, kvm, Michael S. Tsirkin
On Wed, 4 May 2016 10:59:53 +0300
Mike Rapoport <rppt@linux.vnet.ibm.com> wrote:
> /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> Using lscpu to get processors count is more portable.
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
>
> tools/virtio/ringtest/run-on-all.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> index 52b0f71..0177d50 100755
> --- a/tools/virtio/ringtest/run-on-all.sh
> +++ b/tools/virtio/ringtest/run-on-all.sh
> @@ -3,10 +3,10 @@
> #use last CPU for host. Why not the first?
> #many devices tend to use cpu0 by default so
> #it tends to be busier
> -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> +HOST_AFFINITY=$(lscpu -p | tail -n 1 | cut -d',' -f1)
Shorter:
lscpu -p=cpu | tail -1
Should be good enough for a test tool :)
>
> #run command on all cpus
> -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> +for cpu in $(seq 0 $HOST_AFFINITY)
> do
> #Don't run guest and host on same CPU
> #It actually works ok if using signalling
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 8:14 ` Cornelia Huck
@ 2016-05-04 10:15 ` Mike Rapoport
2016-05-04 10:24 ` Cornelia Huck
2016-05-24 12:41 ` Mike Rapoport
0 siblings, 2 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-04 10:15 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: Mike Rapoport, kvm, virtualization
/dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
Using lscpu to get processors count is more portable.
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
v3: simplify by using lscpu -p=cpu
v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
tools/virtio/ringtest/run-on-all.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 52b0f71..2e69ca8 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -3,10 +3,10 @@
#use last CPU for host. Why not the first?
#many devices tend to use cpu0 by default so
#it tends to be busier
-HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
#run command on all cpus
-for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+for cpu in $(seq 0 $HOST_AFFINITY)
do
#Don't run guest and host on same CPU
#It actually works ok if using signalling
--
1.9.1
^ permalink raw reply related [flat|nested] 19+ messages in thread
* Re: [PATCH v3] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 10:15 ` [PATCH v3] " Mike Rapoport
@ 2016-05-04 10:24 ` Cornelia Huck
2016-05-24 12:41 ` Mike Rapoport
1 sibling, 0 replies; 19+ messages in thread
From: Cornelia Huck @ 2016-05-04 10:24 UTC (permalink / raw)
To: Mike Rapoport; +Cc: virtualization, kvm, Michael S. Tsirkin
On Wed, 4 May 2016 13:15:50 +0300
Mike Rapoport <rppt@linux.vnet.ibm.com> wrote:
> /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> Using lscpu to get processors count is more portable.
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> v3: simplify by using lscpu -p=cpu
> v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
>
> tools/virtio/ringtest/run-on-all.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> index 52b0f71..2e69ca8 100755
> --- a/tools/virtio/ringtest/run-on-all.sh
> +++ b/tools/virtio/ringtest/run-on-all.sh
> @@ -3,10 +3,10 @@
> #use last CPU for host. Why not the first?
> #many devices tend to use cpu0 by default so
> #it tends to be busier
> -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> +HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
>
> #run command on all cpus
> -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> +for cpu in $(seq 0 $HOST_AFFINITY)
> do
> #Don't run guest and host on same CPU
> #It actually works ok if using signalling
I think it's fine to depend on lscpu for such a test tool.
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH] tools/virtio/ringtest: add usage example to README
2016-05-04 6:12 [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
2016-05-04 6:12 ` [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu Mike Rapoport
2016-05-04 6:12 ` [PATCH] " Mike Rapoport
@ 2016-05-24 12:41 ` Mike Rapoport
2016-06-06 6:56 ` Mike Rapoport
2016-06-06 6:56 ` Mike Rapoport
2 siblings, 2 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-24 12:41 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization
Michael,
Any updates on this?
On Wed, May 04, 2016 at 09:12:55AM +0300, Mike Rapoport wrote:
> Having typical usage example in the README file is more convinient than in
> the git history...
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> tools/virtio/ringtest/README | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README
> index 34e94c4..d83707a 100644
> --- a/tools/virtio/ringtest/README
> +++ b/tools/virtio/ringtest/README
> @@ -1,2 +1,6 @@
> Partial implementation of various ring layouts, useful to tune virtio design.
> Uses shared memory heavily.
> +
> +Typical use:
> +
> +# sh run-on-all.sh perf stat -r 10 --log-fd 1 -- ./ring
> --
> 1.9.1
>
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH v3] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-04 10:15 ` [PATCH v3] " Mike Rapoport
2016-05-04 10:24 ` Cornelia Huck
@ 2016-05-24 12:41 ` Mike Rapoport
2016-06-06 6:55 ` Mike Rapoport
` (2 more replies)
1 sibling, 3 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-05-24 12:41 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization
Michael,
Any updates on this?
On Wed, May 04, 2016 at 01:15:50PM +0300, Mike Rapoport wrote:
> /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> Using lscpu to get processors count is more portable.
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> v3: simplify by using lscpu -p=cpu
> v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
>
> tools/virtio/ringtest/run-on-all.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> index 52b0f71..2e69ca8 100755
> --- a/tools/virtio/ringtest/run-on-all.sh
> +++ b/tools/virtio/ringtest/run-on-all.sh
> @@ -3,10 +3,10 @@
> #use last CPU for host. Why not the first?
> #many devices tend to use cpu0 by default so
> #it tends to be busier
> -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> +HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
>
> #run command on all cpus
> -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> +for cpu in $(seq 0 $HOST_AFFINITY)
> do
> #Don't run guest and host on same CPU
> #It actually works ok if using signalling
> --
> 1.9.1
>
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH v3] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-24 12:41 ` Mike Rapoport
2016-06-06 6:55 ` Mike Rapoport
@ 2016-06-06 6:55 ` Mike Rapoport
[not found] ` <201606060656.u566rhsn006487@mx0a-001b2d01.pphosted.com>
2 siblings, 0 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-06-06 6:55 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: Cornelia Huck, kvm, virtualization
Ping?
On Tue, May 24, 2016 at 03:41:33PM +0300, Mike Rapoport wrote:
> Michael,
>
> Any updates on this?
>
> On Wed, May 04, 2016 at 01:15:50PM +0300, Mike Rapoport wrote:
> > /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> > Using lscpu to get processors count is more portable.
> >
> > Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> > ---
> > v3: simplify by using lscpu -p=cpu
> > v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
> >
> > tools/virtio/ringtest/run-on-all.sh | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> > index 52b0f71..2e69ca8 100755
> > --- a/tools/virtio/ringtest/run-on-all.sh
> > +++ b/tools/virtio/ringtest/run-on-all.sh
> > @@ -3,10 +3,10 @@
> > #use last CPU for host. Why not the first?
> > #many devices tend to use cpu0 by default so
> > #it tends to be busier
> > -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> > +HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
> >
> > #run command on all cpus
> > -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> > +for cpu in $(seq 0 $HOST_AFFINITY)
> > do
> > #Don't run guest and host on same CPU
> > #It actually works ok if using signalling
> > --
> > 1.9.1
> >
>
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH v3] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
2016-05-24 12:41 ` Mike Rapoport
@ 2016-06-06 6:55 ` Mike Rapoport
2016-06-06 6:55 ` Mike Rapoport
[not found] ` <201606060656.u566rhsn006487@mx0a-001b2d01.pphosted.com>
2 siblings, 0 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-06-06 6:55 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization
Ping?
On Tue, May 24, 2016 at 03:41:33PM +0300, Mike Rapoport wrote:
> Michael,
>
> Any updates on this?
>
> On Wed, May 04, 2016 at 01:15:50PM +0300, Mike Rapoport wrote:
> > /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> > Using lscpu to get processors count is more portable.
> >
> > Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> > ---
> > v3: simplify by using lscpu -p=cpu
> > v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
> >
> > tools/virtio/ringtest/run-on-all.sh | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> > index 52b0f71..2e69ca8 100755
> > --- a/tools/virtio/ringtest/run-on-all.sh
> > +++ b/tools/virtio/ringtest/run-on-all.sh
> > @@ -3,10 +3,10 @@
> > #use last CPU for host. Why not the first?
> > #many devices tend to use cpu0 by default so
> > #it tends to be busier
> > -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> > +HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
> >
> > #run command on all cpus
> > -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> > +for cpu in $(seq 0 $HOST_AFFINITY)
> > do
> > #Don't run guest and host on same CPU
> > #It actually works ok if using signalling
> > --
> > 1.9.1
> >
>
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH] tools/virtio/ringtest: add usage example to README
2016-05-24 12:41 ` [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
2016-06-06 6:56 ` Mike Rapoport
@ 2016-06-06 6:56 ` Mike Rapoport
1 sibling, 0 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-06-06 6:56 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization
Ping?
On Tue, May 24, 2016 at 03:41:04PM +0300, Mike Rapoport wrote:
> Michael,
>
> Any updates on this?
>
> On Wed, May 04, 2016 at 09:12:55AM +0300, Mike Rapoport wrote:
> > Having typical usage example in the README file is more convinient than in
> > the git history...
> >
> > Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> > ---
> > tools/virtio/ringtest/README | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README
> > index 34e94c4..d83707a 100644
> > --- a/tools/virtio/ringtest/README
> > +++ b/tools/virtio/ringtest/README
> > @@ -1,2 +1,6 @@
> > Partial implementation of various ring layouts, useful to tune virtio design.
> > Uses shared memory heavily.
> > +
> > +Typical use:
> > +
> > +# sh run-on-all.sh perf stat -r 10 --log-fd 1 -- ./ring
> > --
> > 1.9.1
> >
>
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH] tools/virtio/ringtest: add usage example to README
2016-05-24 12:41 ` [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
@ 2016-06-06 6:56 ` Mike Rapoport
2016-06-06 6:56 ` Mike Rapoport
1 sibling, 0 replies; 19+ messages in thread
From: Mike Rapoport @ 2016-06-06 6:56 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization
Ping?
On Tue, May 24, 2016 at 03:41:04PM +0300, Mike Rapoport wrote:
> Michael,
>
> Any updates on this?
>
> On Wed, May 04, 2016 at 09:12:55AM +0300, Mike Rapoport wrote:
> > Having typical usage example in the README file is more convinient than in
> > the git history...
> >
> > Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> > ---
> > tools/virtio/ringtest/README | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README
> > index 34e94c4..d83707a 100644
> > --- a/tools/virtio/ringtest/README
> > +++ b/tools/virtio/ringtest/README
> > @@ -1,2 +1,6 @@
> > Partial implementation of various ring layouts, useful to tune virtio design.
> > Uses shared memory heavily.
> > +
> > +Typical use:
> > +
> > +# sh run-on-all.sh perf stat -r 10 --log-fd 1 -- ./ring
> > --
> > 1.9.1
> >
>
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH v3] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
[not found] ` <201606060656.u566rhsn006487@mx0a-001b2d01.pphosted.com>
@ 2016-06-06 13:57 ` Michael S. Tsirkin
2016-06-06 13:57 ` Michael S. Tsirkin
1 sibling, 0 replies; 19+ messages in thread
From: Michael S. Tsirkin @ 2016-06-06 13:57 UTC (permalink / raw)
To: Mike Rapoport; +Cc: Cornelia Huck, kvm, virtualization
It's queued in my tree and will be merged shortly.
Thanks!
On Mon, Jun 06, 2016 at 09:55:59AM +0300, Mike Rapoport wrote:
> Ping?
>
> On Tue, May 24, 2016 at 03:41:33PM +0300, Mike Rapoport wrote:
> > Michael,
> >
> > Any updates on this?
> >
> > On Wed, May 04, 2016 at 01:15:50PM +0300, Mike Rapoport wrote:
> > > /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> > > Using lscpu to get processors count is more portable.
> > >
> > > Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> > > ---
> > > v3: simplify by using lscpu -p=cpu
> > > v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
> > >
> > > tools/virtio/ringtest/run-on-all.sh | 4 ++--
> > > 1 file changed, 2 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> > > index 52b0f71..2e69ca8 100755
> > > --- a/tools/virtio/ringtest/run-on-all.sh
> > > +++ b/tools/virtio/ringtest/run-on-all.sh
> > > @@ -3,10 +3,10 @@
> > > #use last CPU for host. Why not the first?
> > > #many devices tend to use cpu0 by default so
> > > #it tends to be busier
> > > -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> > > +HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
> > >
> > > #run command on all cpus
> > > -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> > > +for cpu in $(seq 0 $HOST_AFFINITY)
> > > do
> > > #Don't run guest and host on same CPU
> > > #It actually works ok if using signalling
> > > --
> > > 1.9.1
> > >
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe kvm" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at http://vger.kernel.org/majordomo-info.html
> >
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH v3] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu
[not found] ` <201606060656.u566rhsn006487@mx0a-001b2d01.pphosted.com>
2016-06-06 13:57 ` Michael S. Tsirkin
@ 2016-06-06 13:57 ` Michael S. Tsirkin
1 sibling, 0 replies; 19+ messages in thread
From: Michael S. Tsirkin @ 2016-06-06 13:57 UTC (permalink / raw)
To: Mike Rapoport; +Cc: kvm, virtualization
It's queued in my tree and will be merged shortly.
Thanks!
On Mon, Jun 06, 2016 at 09:55:59AM +0300, Mike Rapoport wrote:
> Ping?
>
> On Tue, May 24, 2016 at 03:41:33PM +0300, Mike Rapoport wrote:
> > Michael,
> >
> > Any updates on this?
> >
> > On Wed, May 04, 2016 at 01:15:50PM +0300, Mike Rapoport wrote:
> > > /dev/cpu is only available on x86 with certain modules (e.g. msr) enabled.
> > > Using lscpu to get processors count is more portable.
> > >
> > > Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> > > ---
> > > v3: simplify by using lscpu -p=cpu
> > > v2: use lspcu instead of /proc/cpuinfo as per Cornelia's suggestion
> > >
> > > tools/virtio/ringtest/run-on-all.sh | 4 ++--
> > > 1 file changed, 2 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
> > > index 52b0f71..2e69ca8 100755
> > > --- a/tools/virtio/ringtest/run-on-all.sh
> > > +++ b/tools/virtio/ringtest/run-on-all.sh
> > > @@ -3,10 +3,10 @@
> > > #use last CPU for host. Why not the first?
> > > #many devices tend to use cpu0 by default so
> > > #it tends to be busier
> > > -HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
> > > +HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
> > >
> > > #run command on all cpus
> > > -for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
> > > +for cpu in $(seq 0 $HOST_AFFINITY)
> > > do
> > > #Don't run guest and host on same CPU
> > > #It actually works ok if using signalling
> > > --
> > > 1.9.1
> > >
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe kvm" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at http://vger.kernel.org/majordomo-info.html
> >
^ permalink raw reply [flat|nested] 19+ messages in thread
end of thread, other threads:[~2016-06-06 13:57 UTC | newest]
Thread overview: 19+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-05-04 6:12 [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
2016-05-04 6:12 ` [PATCH] tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu Mike Rapoport
2016-05-04 6:40 ` Cornelia Huck
2016-05-04 6:40 ` Cornelia Huck
2016-05-04 7:59 ` [PATCH v2] " Mike Rapoport
2016-05-04 7:59 ` Mike Rapoport
2016-05-04 8:14 ` Cornelia Huck
2016-05-04 8:14 ` Cornelia Huck
2016-05-04 10:15 ` [PATCH v3] " Mike Rapoport
2016-05-04 10:24 ` Cornelia Huck
2016-05-24 12:41 ` Mike Rapoport
2016-06-06 6:55 ` Mike Rapoport
2016-06-06 6:55 ` Mike Rapoport
[not found] ` <201606060656.u566rhsn006487@mx0a-001b2d01.pphosted.com>
2016-06-06 13:57 ` Michael S. Tsirkin
2016-06-06 13:57 ` Michael S. Tsirkin
2016-05-04 6:12 ` [PATCH] " Mike Rapoport
2016-05-24 12:41 ` [PATCH] tools/virtio/ringtest: add usage example to README Mike Rapoport
2016-06-06 6:56 ` Mike Rapoport
2016-06-06 6:56 ` Mike Rapoport
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.