All the DIS runner scripts as used for the (rejected) RTSS'20 submission

DANGER! There's an inconsistency in the input files used for the
all-pairs tests and those used for the baseline tests.

Baselines: run_all_dis.sh calls run_dis.sh to do all baselines.
All-pairs: Uses old TACLe script (not included here).
Cache allocation 2nd-order effects on SMT friendliness: run_pair_convexity.sh

1 files changed, 14 insertions, 5 deletions

diff --git a/dis/setup_mem_and_global.sh b/dis/setup_mem_and_global.sh
index 56d6219..6bddb2f 100755
--- a/dis/setup_mem_and_global.sh
+++ b/dis/setup_mem_and_global.sh
@@ -1,13 +1,22 @@
 # Setup group
+mount -t resctrl resctrl /sys/fs/resctrl
 mkdir -p /sys/fs/resctrl/benchmarks
 echo 15 > /sys/fs/resctrl/benchmarks/cpus_list
-# Remove mem from global domain
+echo 31 > /sys/fs/resctrl/benchmarks/cpus_list
+# Remove mem from global domain and assign to local
 echo "L3:0=ffff;1=ffff;2=ffff;3=0000" > /sys/fs/resctrl/schemata
-# Remove bandwidth from global domain
-echo "MB:0=2;1=2;2=2;3=2" > /sys/fs/resctrl/schemata
-echo "MB:0=2048;1=2048;2=2048;3=2048" > /sys/fs/resctrl/benchmarks/schemata
+echo "L3:0=ffff;1=ffff;2=ffff;3=ffff" > /sys/fs/resctrl/benchmarks/schemata
+if [[ $1 == "--bandwith" ]]; then
+    # Remove bandwidth from global domain
+    echo "MB:0=2;1=2;2=2;3=2" > /sys/fs/resctrl/schemata
+    echo "MB:0=2048;1=2048;2=2048;3=2048" > /sys/fs/resctrl/benchmarks/schemata
+else
+    # Disable bandwidth control
+    echo "MB:0=2048;1=2048;2=2048;3=2048" > /sys/fs/resctrl/schemata
+    echo "MB:0=2048;1=2048;2=2048;3=2048" > /sys/fs/resctrl/benchmarks/schemata
+fi
 echo "=== Global Config ==="
 cat /sys/fs/resctrl/schemata
-echo "=== Core 15 Config ==="
+echo "=== Core 15 & 31 Config ==="
 cat /sys/fs/resctrl/benchmarks/schemata