OS Images |
os_Image_1(1)
|
Hardware Description |
hw_1
|
Number of Systems |
1
|
SW Environment |
non-virtual
|
Tuning |
BIOS Settings: - NUMA nodes per socket = NPS4
- Determinism Control = Manual
- Determinism Enable = Performance
- xGMI Link Configuration = 4 xGMI Links
- 4 Link xGMI max speed = 32Gbps
- TDP Control = Manual
- TDP = 500
- Package Power Limit Control = Manual
- Package Power Limit = 500
|
Notes |
None
|
|
JVM Instances |
jvm_Ctr_1(1), jvm_Backend_1(32), jvm_TxInjector_1(32)
|
OS Image Description |
os_1
|
Tuning |
- cpupower -c all frequency-set -g performance
- tuned-adm profile throughput-performance
- ulimit -n 1024000
- echo 960000 > /proc/sys/kernel/sched_rt_runtime_us
- echo 800000000 > /proc/sys/kernel/sched_latency_ns
- echo 40000 > /proc/sys/kernel/sched_migration_cost_ns
- echo 900000000 > /proc/sys/kernel/sched_min_granularity_ns
- echo 700000000 > /proc/sys/kernel/sched_wakeup_granularity_ns
- echo 9000 > /proc/sys/kernel/sched_nr_migrate
- echo 10000 > /proc/sys/vm/dirty_expire_centisecs
- echo 1500 > /proc/sys/vm/dirty_writeback_centisecs
- echo 40 > /proc/sys/vm/dirty_ratio
- echo 10 > /proc/sys/vm/dirty_background_ratio
- echo 10 > /proc/sys/vm/swappiness
- echo 0 > /proc/sys/kernel/numa_balancing
- echo 0 > /proc/sys/vm/numa_stat
- echo always > /sys/kernel/mm/transparent_hugepage/enabled
- echo always > /sys/kernel/mm/transparent_hugepage/defrag
|
Notes |
None
|
Parts of Benchmark |
Controller
|
JVM Instance Description |
jvm_1
|
Command Line |
-Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelGC -XX:ParallelGCThreads=1 -XX:CICompilerCount=2
|
Tuning |
Used numactl to interleave memory on all CPUs
|
Notes |
None
|
Parts of Benchmark |
Backend
|
JVM Instance Description |
jvm_1
|
Command Line |
-Xms31g -Xmx31g -Xmn28g -XX:AllocatePrefetchInstr=2 -XX:+UseParallelGC -XX:ParallelGCThreads=16 -XX:LargePageSizeInBytes=2m -XX:-UseAdaptiveSizePolicy -XX:+AlwaysPreTouch -XX:+UseLargePages -XX:SurvivorRatio=15 -XX:TargetSurvivorRatio=95 -XX:MaxTenuringThreshold=12 -XX:InlineSmallCode=11k -XX:MaxGCPauseMillis=100 -XX:LoopUnrollLimit=200 -XX:+UseTransparentHugePages -XX:TLABAllocationWeight=2 -XX:ThreadStackSize=140 -XX:CompileThresholdScaling=120 -XX:CICompilerCount=4 -XX:AutoBoxCacheMax=32 -XX:OnStackReplacePercentage=100 -XX:-ResizeTLAB -XX:TLABWasteTargetPercent=1 -XX:TLABWasteIncrement=1 -XX:YoungPLABSize=1m -XX:OldPLABSize=1m -XX:+ScavengeBeforeFullGC -XX:PrefetchCopyIntervalInBytes=256 -XX:TLABSize=64k -XX:MinTLABSize=64k
|
Tuning |
Used numactl to affinitize each Backend JVM to 8 Core / 16 Threads - Group1: numactl --physcpubind=0-7,256-263 --localalloc
- Group2: numactl --physcpubind=8-15,264-271 --localalloc
- Group3: numactl --physcpubind=16-23,272-279 --localalloc
- Group4: numactl --physcpubind=24-31,280-287 --localalloc
- Group5: numactl --physcpubind=32-39,288-295 --localalloc
- Group6: numactl --physcpubind=40-47,296-303 --localalloc
- Group7: numactl --physcpubind=48-55,304-311 --localalloc
- Group8: numactl --physcpubind=56-63,312-319 --localalloc
- Group9: numactl --physcpubind=64-71,320-327 --localalloc
- Group10: numactl --physcpubind=72-79,328-335 --localalloc
- Group11: numactl --physcpubind=80-87,336-343 --localalloc
- Group12: numactl --physcpubind=88-95,344-351 --localalloc
- Group13: numactl --physcpubind=96-103,352-359 --localalloc
- Group14: numactl --physcpubind=104-111,360-367 --localalloc
- Group15: numactl --physcpubind=112-119,368-375 --localalloc
- Group16: numactl --physcpubind=120-127,376-383 --localalloc
- Group17: numactl --physcpubind=128-135,384-391 --localalloc
- Group18: numactl --physcpubind=136-143,392-399 --localalloc
- Group19: numactl --physcpubind=144-151,400-407 --localalloc
- Group20: numactl --physcpubind=152-159,408-415 --localalloc
- Group21: numactl --physcpubind=160-167,416-423 --localalloc
- Group22: numactl --physcpubind=168-175,424-431 --localalloc
- Group23: numactl --physcpubind=176-183,432-439 --localalloc
- Group24: numactl --physcpubind=184-191,440-447 --localalloc
- Group25: numactl --physcpubind=192-199,448-455 --localalloc
- Group26: numactl --physcpubind=200-207,456-463 --localalloc
- Group27: numactl --physcpubind=208-215,464-471 --localalloc
- Group28: numactl --physcpubind=216-223,472-479 --localalloc
- Group29: numactl --physcpubind=224-231,480-487 --localalloc
- Group30: numactl --physcpubind=232-239,488-495 --localalloc
- Group31: numactl --physcpubind=240-247,496-503 --localalloc
- Group32: numactl --physcpubind=248-255,504-511 --localalloc
|
Notes |
None
|
Parts of Benchmark |
TxInjector
|
JVM Instance Description |
jvm_1
|
Command Line |
-Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelGC -XX:ParallelGCThreads=1 -XX:CICompilerCount=2
|
Tuning |
Used numactl to affinitize each Transaction Injector JVM to 8 Cores/ 8 Threads - Group1: numactl --physcpubind=0-7 --localalloc
- Group2: numactl --physcpubind=8-15 --localalloc
- Group3: numactl --physcpubind=16-23 --localalloc
- Group4: numactl --physcpubind=24-31 --localalloc
- Group5: numactl --physcpubind=32-39 --localalloc
- Group6: numactl --physcpubind=40-47 --localalloc
- Group7: numactl --physcpubind=48-55 --localalloc
- Group8: numactl --physcpubind=56-63 --localalloc
- Group9: numactl --physcpubind=64-71 --localalloc
- Group10: numactl --physcpubind=72-79 --localalloc
- Group11: numactl --physcpubind=80-87 --localalloc
- Group12: numactl --physcpubind=88-95 --localalloc
- Group13: numactl --physcpubind=96-103 --localalloc
- Group14: numactl --physcpubind=104-111 --localalloc
- Group15: numactl --physcpubind=112-119 --localalloc
- Group16: numactl --physcpubind=120-127 --localalloc
- Group17: numactl --physcpubind=128-135 --localalloc
- Group18: numactl --physcpubind=136-143 --localalloc
- Group19: numactl --physcpubind=144-151 --localalloc
- Group20: numactl --physcpubind=152-159 --localalloc
- Group21: numactl --physcpubind=160-167 --localalloc
- Group22: numactl --physcpubind=168-175 --localalloc
- Group23: numactl --physcpubind=176-183 --localalloc
- Group24: numactl --physcpubind=184-191 --localalloc
- Group25: numactl --physcpubind=192-199 --localalloc
- Group26: numactl --physcpubind=200-207 --localalloc
- Group27: numactl --physcpubind=208-215 --localalloc
- Group28: numactl --physcpubind=216-223 --localalloc
- Group29: numactl --physcpubind=224-231 --localalloc
- Group30: numactl --physcpubind=232-239 --localalloc
- Group31: numactl --physcpubind=240-247 --localalloc
- Group32: numactl --physcpubind=248-255 --localalloc
|
Notes |
None
|
|