|
| JVM Instances |
jvm_Ctr_1(1), jvm_Backend_1(4), jvm_TxInjector_1(4)
|
| OS Image Description |
os_1
|
| Tuning |
- SELINUX=disabled
- tuned-adm profile=throughput-performance
- echo 16000000 > /proc/sys/kernel/sched_latency_ns
- echo 6000000 > /proc/sys/kernel/sched_min_granularity_ns
|
| Notes |
None
|
|
| Parts of Benchmark |
Controller
|
| JVM Instance Description |
jvm_1
|
| Command Line |
None
|
| Tuning |
-Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelOldGC -XX:ParallelGCThreads=22
|
| Notes |
Used numactl to interleave memory on all CPUs
|
|
| Parts of Benchmark |
Backend
|
| JVM Instance Description |
jvm_1
|
| Command Line |
None
|
| Tuning |
-Xms29g -Xmx29g -Xmn27g -server -XX:AllocatePrefetchInstr=2 -XX:LargePageSizeInBytes=2m -XX:-UsePerfData -XX:+AggressiveOpts -XX:-UseAdaptiveSizePolicy -XX:+AlwaysPreTouch -XX:-UseBiasedLocking -XX:+UseLargePages -XX:+UseParallelOldGC -XX:SurvivorRatio=28 -XX:TargetSurvivorRatio=95 -XX:ParallelGCThreads=22 -XX:MaxTenuringThreshold=15 -XX:+PrintTenuringDistribution -XX:+PrintGCDetails -XX:+PrintGCTimeStamps
|
| Notes |
Used numactl to affinitize each Backend JVM to physical cores in a NUMA node. - numactl --physcpubind=0-10,44-54 --membind=0
- numactl --physcpubind=11-21,55-65 --membind=1
- numactl --physcpubind=22-32,66-76 --membind=2
- numactl --physcpubind=33-43,77-87 --membind=3
|
|
| Parts of Benchmark |
TxInjector
|
| JVM Instance Description |
jvm_1
|
| Command Line |
None
|
| Tuning |
-Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelOldGC -XX:ParallelGCThreads=22
|
| Notes |
Used numactl to affinitize each Transaction Injector JVM to a physical core in a NUMA node. - numactl --physcpubind=0 --membind=0
- numactl --physcpubind=11 --membind=1
- numactl --physcpubind=22 --membind=2
- numactl --physcpubind=33 --membind=3
|
