JVM Instances |
jvm_Ctr_1(1), jvm_Backend_1(6), jvm_TxInjector_1(6)
|
OS Image Description |
os_1
|
Tuning |
- cpufreq-set -g performance
- echo 200000 > /proc/sys/vm/nr_hugepages
- ppc64_cpu --dscr=3
- ulimit -n 1048576
- echo 1000 > /proc/sys/kernel/sched_migration_cost_ns
- echo 65000000 > /proc/sys/kernel/sched_min_granularity_ns
- echo 24000000 > /proc/sys/kernel/sched_wakeup_granularity_ns
|
Notes |
None
|
Parts of Benchmark |
Controller
|
JVM Instance Description |
jvm_1
|
Command Line |
-XX:-RuntimeInstrumentation -Xms1g -Xmx1g -Xmn800m -Xcompressedrefs -XX:-EnableHCR
|
Tuning |
None
|
Notes |
None
|
Parts of Benchmark |
Backend
|
JVM Instance Description |
jvm_1
|
Command Line |
-XX:-RuntimeInstrumentation -Xlp -Xms63g -Xmx63g -Xmn60g -Xcompressedrefs -Xtrace:none -Xconcurrentlevel0 -Xaggressive -XX:-EnableHCR
|
Tuning |
numactl used to affinitize each Backend JVM - numactl --physcpubind=0-27 --membind=0
- numactl --physcpubind=28-55 --membind=0
- numactl --physcpubind=56-83 --membind=0
- numactl --physcpubind=88-115 --membind=8
- numactl --physcpubind=116-143 --membind=8
- numactl --physcpubind=144-171 --membind=8
|
Notes |
None
|
Parts of Benchmark |
TxInjector
|
JVM Instance Description |
jvm_1
|
Command Line |
-XX:-RuntimeInstrumentation -Xlp -Xms2000m -Xmx2000m -Xmn1700m -Xcompressedrefs -Xtrace:none -Xconcurrentlevel0 -Xaggressive -XX:-EnableHCR
|
Tuning |
numactl used to affinitize each TxInjector JVM to a single processor - numactl --physcpubind=0-3 --membind=0
- numactl --physcpubind=28-31 --membind=0
- numactl --physcpubind=56-59 --membind=0
- numactl --physcpubind=88-91 --membind=8
- numactl --physcpubind=116-119 --membind=8
- numactl --physcpubind=144-147 --membind=8
|
Notes |
None
|