Quanta Cloud Technology, QuantaGrid S44NL-1U 319411 SPECjbb2015-MultiJVM max-jOPS
308527 SPECjbb2015-MultiJVM critical-jOPS
Tested by: Quanta Computer Inc. Test Sponsor: Quanta Computer Inc. Test location: Taoyuan, TW, R.O.C Test date: Aug 14, 2023
SPEC license #: 9050 Hardware Availability: Aug-2023 Software Availability: Apr-2023 Publication: Thu Aug 24 13:28:06 EDT 2023
Benchmark Results Summary
 
Overall Throughput RT curve
Overall SUT (System Under Test) Description
VendorQuanta Cloud Technology
Vendor URLhttp://qct.io
System SourceSingle Supplier
System DesignationServer Rack
Total Systems1
All SUT Systems IdenticalYES
Total Nodes1
All Nodes IdenticalYES
Nodes Per System1
Total Chips1
Total Cores96
Total Threads192
Total Memory Amount (GB)768
Total OS Images1
SW EnvironmentNon-virtual
 
Hardware hw_1
NameQuantaGrid S44NL-1U
VendorQuanta Cloud Technology
Vendor URLhttp://qct.io
AvailableAug-2023
ModelQuantaGrid S44NL-1U
Form Factor1U
CPU NameAMD EPYC 9654
CPU Characteristics96 core, 2.4GHz, 384MB L3 Cache (Max. Boost Clock up to 3.7GHz)
Number of Systems1
Nodes Per System1
Chips Per System1
Cores Per System96
Cores Per Chip96
Threads Per System192
Threads Per Core2
Version3A08 released Jun-2023
CPU Frequency (MHz)2400
Primary Cache32 KB I + 32 KB D on chip per core
Secondary Cache1024 KB I+D on chip per core
Tertiary Cache384 MB (I+D) on chip per chip
Other CacheNone
Disk1 x 960 GB NVMe SSD
File SystemXFS
Memory Amount (GB)768
# and size of DIMM(s)12 x 64 GB
Memory Details64GB 2Rx4 PC5-38400R , running at 4800 MHz
# and type of Network Interface Cards (NICs)Intel 10 Gigabit Ethernet X710-AT2 2-port
Power Supply Quantity and Rating (W)1 x 1600
Other HardwareNone
Cabinet/Housing/EnclosureNone
Shared DescriptionNone
Shared CommentNone
Notes
  • NA: The test sponsor attests, as of date of publication, that CVE-2017-5754 (Meltdown) is mitigated in the system as tested and documented.
  • Yes: The test sponsor attests, as of date of publication, that CVE-2017-5753 (Spectre variant 1) is mitigated in the system as tested and documented.
  • Yes: The test sponsor attests, as of date of publication, that CVE-2017-5715 (Spectre variant 2) is mitigated in the system as tested and documented.
Other Hardware network_1
NameNone
VendorNone
Vendor URLNone
VersionNone
AvailableNone
BitnessNone
NotesNone
Operating System os_1
NameSUSE Linux Enterprise Server 15 SP4
VendorSUSE
Vendor URLhttp://suse.com/
Version5.14.21-150400.22-default
AvailableJun-2022
Bitness64
NotesNone
Java Virtual Machine jvm_1
NameOracle Java SE 17.0.7
VendorOracle
Vendor URLhttp://www.oracle.com
VersionJava HotSpot 64-bit Server VM, version 17.0.7
AvailableApr-2023
Bitness64
NotesNone
Other Software other_1
NameNone
VendorNone
Vendor URLNone
VersionNone
AvailableNone
BitnessNone
NotesNone
Hardware
OS Images os_Image_1(1)
Hardware Description hw_1
Number of Systems 1
SW Environment non-virtual
Tuning
  • L1 Stream HW Prefetcher : Disabled
  • L2 Stream HW Prefetcher : Disabled
  • NUMA Nodes Per Socket : NPS2
  • Determinism Slider : Power Determinism
  • ACPI CST C2 Latency : 18
  • PPT Control : 400
Notes None
OS Image os_Image_1
JVM Instances jvm_Ctr_1(1), jvm_Backend_1(6), jvm_TxInjector_1(6)
OS Image Description os_1
Tuning
  • echo 950000 > /proc/sys/kernel/sched_rt_runtime_us
  • echo 150000000 > /proc/sys/kernel/sched_latency_ns
  • echo 80000 > /proc/sys/kernel/sched_migration_cost_ns
  • echo 300000 > /proc/sys/kernel/sched_min_granularity_ns
  • echo 300000 > /proc/sys/kernel/sched_wakeup_granularity_ns
  • 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/vm/numa_stat
  • echo 0 > /proc/sys/kernel/numa_balancing
  • UserTasksMax=970000
  • DefaultTasksMax=970000
  • echo always > /sys/kernel/mm/transparent_hugepage/enabled
  • echo always > /sys/kernel/mm/transparent_hugepage/defrag

  • ulimit -n 1024000
Notes None
JVM Instance jvm_Ctr_1
Parts of Benchmark Controller
JVM Instance Description jvm_1
Command Line -Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelGC -XX:ParallelGCThreads=2 -XX:CICompilerCount=4
Tuning

Used numactl to interleave memory on all CPUs

  • numactl --interleave=all
Notes "Notes here"
JVM Instance jvm_Backend_1
Parts of Benchmark Backend
JVM Instance Description jvm_1
Command Line -Xms120g -Xmx120g -Xmn119g -server -XX:MetaspaceSize=256m -XX:AllocatePrefetchInstr=2 -XX:LargePageSizeInBytes=2m -XX:-UsePerfData -XX:-UseAdaptiveSizePolicy -XX:+AlwaysPreTouch -XX:+UseLargePages -XX:+UseParallelGC -XX:SurvivorRatio=90 -XX:TargetSurvivorRatio=90 -XX:ParallelGCThreads=32 -XX:MaxTenuringThreshold=15 -XX:InitialCodeCacheSize=25m -XX:InlineSmallCode=10k -XX:MaxGCPauseMillis=200 -XX:+UseCompressedOops -XX:ObjectAlignmentInBytes=32 -XX:+UseTransparentHugePages -XX:TLABAllocationWeight=55 -XX:ThreadStackSize=512 -XX:CompileThresholdScaling=120
Tuning

Used numactl to affinitize three Backend JVMs to a NUMA node

  • numactl --cpunodebind=0 --localalloc
  • numactl --cpunodebind=0 --localalloc
  • numactl --cpunodebind=0 --localalloc
  • numactl --cpunodebind=1 --localalloc
  • numactl --cpunodebind=1 --localalloc
  • numactl --cpunodebind=1 --localalloc
Notes None
JVM Instance jvm_TxInjector_1
Parts of Benchmark TxInjector
JVM Instance Description jvm_1
Command Line -Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelGC -XX:ParallelGCThreads=2 -XX:CICompilerCount=4
Tuning

Used numactl to affinitize three Transaction Injector JVMs to a NUMA node

  • numactl --cpunodebind=0 --localalloc
  • numactl --cpunodebind=0 --localalloc
  • numactl --cpunodebind=0 --localalloc
  • numactl --cpunodebind=1 --localalloc
  • numactl --cpunodebind=1 --localalloc
  • numactl --cpunodebind=1 --localalloc
Notes None
max-jOPS = jOPS passed before the First Failure
Pass/Fail Pass Pass Fail Fail Fail
jOPS 315153 319411 323670 327929 332188
critical-jOPS = Geomean ( jOPS @ 10000; 25000; 50000; 75000; 100000; SLAs )
Response time percentile is 99-th
SLA (us) 10000 25000 50000 75000 100000 Geomean
jOPS 287470 304505 313023 319411 319411 308527
  Percentile
  10-th 50-th 90-th 95-th 99-th 100-th
500us - / 4259 - / 4259 - / 4259 - / 4259 - / 4259 - / 4259
1000us 285341 / 289600 4259 / 8518 - / 4259 - / 4259 - / 4259 - / 4259
5000us 319411 / - 319411 / - 293859 / 298117 276823 / 281082 229976 / 225717 4259 / 8518
10000us 319411 / - 319411 / - 319411 / - 319411 / - 285341 / 289600 42588 / 17035
25000us 319411 / - 319411 / - 319411 / - 319411 / - 302376 / 306635 42588 / 17035
50000us 319411 / - 319411 / - 319411 / - 319411 / - 310894 / 315153 42588 / 17035
75000us 319411 / - 319411 / - 319411 / - 319411 / - 319411 / - 174612 / 17035
100000us 319411 / - 319411 / - 319411 / - 319411 / - 319411 / - 238494 / 34071
200000us 319411 / - 319411 / - 319411 / - 319411 / - 319411 / - 310894 / 315153
500000us 319411 / - 319411 / - 319411 / - 319411 / - 319411 / - 319411 / -
1000000us 319411 / - 319411 / - 319411 / - 319411 / - 319411 / - 319411 / -
Probes jOPS / Total jOPS
Request Mix Accuracy
Note
(Actual % in the Mix - Expected % in the Mix) must be within:
'Main Tx' limit of +/-5.0% for the requests whose expected % in the mix is >= 10.0%
'Minor Tx' limit of +/-1.0% for the requests whose expected % in the mix is < 10.0%
There were no non-critical failures in Response Time curve building
Delay between status pings
IR/PR Accuracy
This section lists properties only set by user
Property Name Default Controller Group1.Backend.beJVM Group1.TxInjector.txiJVM1 Group2.Backend.beJVM Group2.TxInjector.txiJVM1 Group3.Backend.beJVM Group3.TxInjector.txiJVM1 Group4.Backend.beJVM Group4.TxInjector.txiJVM1 Group5.Backend.beJVM Group5.TxInjector.txiJVM1 Group6.Backend.beJVM Group6.TxInjector.txiJVM1
specjbb.comm.connect.client.pool.size 256 256 120 120 120 120 120 120 120 120 120 120 120 120
specjbb.comm.connect.selector.runner.count 0 8 4 4 4 4 4 4 4 4 4 4 4 4
specjbb.comm.connect.worker.pool.max 256 256 120 120 120 120 120 120 120 120 120 120 120 120
specjbb.comm.connect.worker.pool.min 1 1 24 24 24 24 24 24 24 24 24 24 24 24
specjbb.controller.handshake.period 5000 20000
specjbb.controller.handshake.timeout 600000 900000
specjbb.forkjoin.workers 192 {Tier1=121, Tier2=1, Tier3=5}
specjbb.group.count 1 6
specjbb.heartbeat.period 10000 2000
specjbb.heartbeat.threshold 100000 9000000
specjbb.mapreducer.pool.size 192 16
specjbb.txi.pergroup.count 1 1
View table in csv format
 
Level: COMPLIANCE
Check Agent Result
Check properties on compliance All PASSED
 
Level: CORRECTNESS
Check Agent Result
Compare SM and HQ Inventory All PASSED
High-bound (max attempted) is 425882 IR
High-bound (settled) is 355001 IR