aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorHalil Pasic <pasic@linux.vnet.ibm.com>2016-08-29 12:25:22 -0400
committerMichael S. Tsirkin <mst@redhat.com>2017-01-19 16:46:31 -0500
commit21f5eda9b8671744539c8295b9df62991fffb2ce (patch)
tree53af8d3a01968664733472f34ea6d7a999c39fe7
parent8379cadf71c3ee8173a1c6fc1ea7762a9638c047 (diff)
tools/virtio/ringtest: fix run-on-all.sh for offline cpus
Since ef1b144d ("tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu") run-on-all.sh uses seq 0 $HOST_AFFINITY as the list of ids of the CPUs to run the command on (assuming ids of online CPUs are consecutive and start from 0), where $HOST_AFFINITY is the highest CPU id in the system previously determined using lscpu. This can fail on systems with offline CPUs. Instead let's use lscpu to determine the list of online CPUs. Signed-off-by: Halil Pasic <pasic@linux.vnet.ibm.com> Fixes: ef1b144d ("tools/virtio/ringtest: fix run-on-all.sh to work without /dev/cpu") Reviewed-by: Sascha Silbe <silbe@linux.vnet.ibm.com> Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
-rwxr-xr-xtools/virtio/ringtest/run-on-all.sh5
1 files changed, 3 insertions, 2 deletions
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 2e69ca812b4c..29b0d3920bfc 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -1,12 +1,13 @@
1#!/bin/sh 1#!/bin/sh
2 2
3CPUS_ONLINE=$(lscpu --online -p=cpu|grep -v -e '#')
3#use last CPU for host. Why not the first? 4#use last CPU for host. Why not the first?
4#many devices tend to use cpu0 by default so 5#many devices tend to use cpu0 by default so
5#it tends to be busier 6#it tends to be busier
6HOST_AFFINITY=$(lscpu -p=cpu | tail -1) 7HOST_AFFINITY=$(echo "${CPUS_ONLINE}"|tail -n 1)
7 8
8#run command on all cpus 9#run command on all cpus
9for cpu in $(seq 0 $HOST_AFFINITY) 10for cpu in $CPUS_ONLINE
10do 11do
11 #Don't run guest and host on same CPU 12 #Don't run guest and host on same CPU
12 #It actually works ok if using signalling 13 #It actually works ok if using signalling