JVM Instances |
jvm_Ctr_1(1), jvm_Backend_1(16), jvm_TxInjector_1(16)
|
OS Image Description |
os_1
|
Tuning |
- ulimit -n 65536
- sched_rt_runtime_us=990000
- sched_migration_cost_ns=1000
- sched_latency_ns=16000000
- sched_min_granularity_ns=6000000
- sched_wakeup_granularity_ns=15000000
- dirty_expire_centisecs=10000
- dirty_writeback_centisecs=1500
- dirty_ratio=40
- dirty_background_ratio=10
- swappiness=10
|
Notes |
None
|
Parts of Benchmark |
Controller
|
JVM Instance Description |
jvm_1
|
Command Line |
-server -Xmn1536m -Xms2g -Xmx2g -XX:+UseLargePages -XX:LargePageSizeInBytes=2m -XX:+UseParallelOldGC -XX:ParallelGCThreads=2
|
Tuning |
None
|
Notes |
None
|
Parts of Benchmark |
Backend
|
JVM Instance Description |
jvm_1
|
Command Line |
-server -Xms30g -Xmx30g -Xmn28g -XX:SurvivorRatio=28 -XX:TargetSurvivorRatio=95 -XX:-UseAdaptiveSizePolicy -XX:ParallelGCThreads=28 -XX:AllocatePrefetchInstr=2 -XX:-UsePerfData -XX:+AlwaysPreTouch -XX:+UseParallelOldGC -XX:-UseBiasedLocking -XX:+UseLargePages -XX:LargePageSizeInBytes=2m -XX:MaxTenuringThreshold=15 -XX:+UseRTMLocking -XX:+UseRTMDeopt -XX:InlineSmallCode=10k -XX:InitialCodeCacheSize=25m
|
Tuning |
to affinitize each Backend JVM to a single memory numa node with numactl, e.g.: - numactl --cpunodebind=$gnum --localalloc
|
Notes |
None
|
Parts of Benchmark |
TxInjector
|
JVM Instance Description |
jvm_1
|
Command Line |
-server -Xmn1536m -Xms2g -Xmx2g -XX:+UseLargePages -XX:LargePageSizeInBytes=2m -XX:+UseParallelOldGC -XX:ParallelGCThreads=2
|
Tuning |
to affinitize each TxInjector JVM to a single memory numa node with numactl, e.g.: - numactl --cpunodebind=$gnum --localalloc
|
Notes |
None
|