Lenovo Global Technology ThinkSystem SD535 V3 1447998 SPECjbb2015-Distributed max-jOPS
1324145 SPECjbb2015-Distributed critical-jOPS
Tested by: Lenovo Global Technology Test Sponsor: Lenovo Global Technology Test location: Beijing, China Test date: Apr 11, 2024
SPEC license #: 9017 Hardware Availability: May-2024 Software Availability: Jan-2024 Publication: Thu May 2 14:51:39 EDT 2024
Benchmark Results Summary
 
Overall Throughput RT curve
Overall SUT (System Under Test) Description
VendorLenovo Global Technology
Vendor URLhttp://www.lenovo.com
System SourceSingle Supplier
System DesignationServer Rack
Total Systems1
All SUT Systems IdenticalYES
Total Nodes4
All Nodes IdenticalYES
Nodes Per System4
Total Chips4
Total Cores384
Total Threads768
Total Memory Amount (GB)3072
Total OS Images4
SW EnvironmentNon-virtual
 
Hardware hw_1
NameThinkSystem SD535 V3
VendorLenovo Global Technology
Vendor URLhttp://www.lenovo.com
AvailableMay-2024
ModelThinkSystem SD535 V3
Form Factor2U
CPU NameAMD EPYC 9684X
CPU Characteristics96 core, 2.55 GHz, 1152 MB L3 Cache (Max Boost Clock up to 3.70 GHz)
Number of Systems1
Nodes Per System4
Chips Per System4
Cores Per System384
Cores Per Chip96
Threads Per System768
Threads Per Core2
VersionQPE103H
CPU Frequency (MHz)2550
Primary Cache32KB(I)+32KB(D) on chip per core
Secondary Cache1MB (I+D) on chip per core
Tertiary Cache1152MB (I+D) on chip per chip
Other CacheNone
Disk4 x 960GB M.2 NVME SSD
File SystemXFS
Memory Amount (GB)3072
# and size of DIMM(s)48 x 64 GB
Memory Details64 GB 2Rx4 PC5-4800B-R
# and type of Network Interface Cards (NICs)4 x 10/25 GbE OCP NIC
Power Supply Quantity and Rating (W)2 x 2700W
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 SP5
VendorSUSE
Vendor URLhttp://suse.com/
Version5.14.21-150500.53-default
AvailableJun-2023
Bitness64
NotesNone
Java Virtual Machine jvm_1
NameOracle Java SE 17.0.10
VendorOracle Corporation
Vendor URLhttp://oracle.com/
VersionJava HotSpot 64-Bit Server VM, version 17.0.10
AvailableJan-2024
Bitness64
NotesNone
Other Software other_1
NameNone
VendorNone
Vendor URLNone
VersionNone
AvailableNone
BitnessNone
NotesNone
Hardware hw_2
NameThinkSystem SR665 V3
VendorLenovo Global Technology
Vendor URLhttp://www.lenovo.com
AvailableDec-2023
ModelThinkSystem SR665 V3
Form Factor2U
CPU NameAMD EPYC 9684X
CPU Characteristics96 core, 2.55 GHz, 1152 MB L3 Cache (Max Boost Clock up to 3.70 GHz)
Number of Systems1
Nodes Per System1
Chips Per System2
Cores Per System192
Cores Per Chip96
Threads Per System384
Threads Per Core2
VersionKAE117M
CPU Frequency (MHz)2550
Primary Cache32KB(I)+32KB(D) on chip per core
Secondary Cache1MB (I+D) on chip per core
Tertiary Cache1152MB (I+D) on chip per chip
Other CacheNone
Disk1 x 960GB SATA SSD
File SystemXFS
Memory Amount (GB)1536
# and size of DIMM(s)24 x 64 GB
Memory Details64 GB 2Rx4 PC5-4800B-R
# and type of Network Interface Cards (NICs)1 x 10/25 GbE PCIE NIC
Power Supply Quantity and Rating (W)1 x 1800W
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_2
NameNone
VendorNone
Vendor URLNone
VersionNone
AvailableNone
BitnessNone
NotesNone
Operating System os_2
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_2
NameOracle Java SE 17.0.10
VendorOracle Corporation
Vendor URLhttp://oracle.com/
VersionJava HotSpot 64-Bit Server VM, version 17.0.10
AvailableJan-2024
Bitness64
NotesNone
Other Software other_2
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 BIOS Configuration:
  • Choose Operating Mode set to Maximum Performance and then set to Custom Mode
  • NUMA Nodes per Socket set to NPS2
  • L2 Stream HW Prefetcher set to Disabled
Notes None
OS Image os_Image_1
JVM Instances jvm_Backend_1(24)
OS Image Description os_1
Tuning
  • cpupower frequency-set -g performance
  • tuned-adm profile throughput-performance
  • echo 950000 > /proc/sys/kernel/sched_rt_runtime_us
  • echo 20000000 > /proc/sys/kernel/sched_latency_ns
  • echo 40000 > /proc/sys/kernel/sched_migration_cost_ns
  • echo 200000 > /proc/sys/kernel/sched_min_granularity_ns
  • echo 40000 > /proc/sys/kernel/sched_wakeup_granularity_ns
  • echo 128 > /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 always > /sys/kernel/mm/transparent_hugepage/defrag
  • echo always > /sys/kernel/mm/transparent_hugepage/enabled
  • ulimit -n 1024000
  • UserTasksMax=970000
  • DefaultTasksMax=970000
Notes None
JVM Instance jvm_Backend_1
Parts of Benchmark Backend
JVM Instance Description jvm_1
Command Line -Xms103g -Xmx103g -Xmn100g -server -XX:MetaspaceSize=512m -XX:AllocatePrefetchInstr=2 -XX:-UsePerfData -XX:-UseAdaptiveSizePolicy -XX:+AlwaysPreTouch -XX:+UseParallelGC -XX:SurvivorRatio=100 -XX:TargetSurvivorRatio=95 -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 JVM (3 Groups) to one NUMA node in every node in SUT
  • Group1: numactl --cpunodebind=0 --localalloc
  • Group2: numactl --cpunodebind=0 --localalloc
  • Group3: numactl --cpunodebind=0 --localalloc
  • Group4: numactl --cpunodebind=1 --localalloc
  • Group5: numactl --cpunodebind=1 --localalloc
  • Group6: numactl --cpunodebind=1 --localalloc
Notes None
Hardware
OS Images os_Image_2(1)
Hardware Description hw_2
Number of Systems 1
SW Environment non-virtual
Tuning BIOS Configuration:
  • Choose Operating Mode set to Maximum Performance and then set to Custom Mode
  • NUMA Nodes per Socket set to NPS2
  • L2 Stream HW Prefetcher set to Disabled
Notes None
OS Image os_Image_2
JVM Instances jvm_Ctr_1(1), jvm_TxInjector_1(24)
OS Image Description os_2
Tuning
  • cpupower frequency-set -g performance
  • tuned-adm profile throughput-performance
  • echo 950000 > /proc/sys/kernel/sched_rt_runtime_us
  • echo 20000000 > /proc/sys/kernel/sched_latency_ns
  • echo 40000 > /proc/sys/kernel/sched_migration_cost_ns
  • echo 200000 > /proc/sys/kernel/sched_min_granularity_ns
  • echo 40000 > /proc/sys/kernel/sched_wakeup_granularity_ns
  • echo 128 > /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 always > /sys/kernel/mm/transparent_hugepage/defrag
  • echo always > /sys/kernel/mm/transparent_hugepage/enabled
  • ulimit -n 1024000
  • UserTasksMax=970000
  • DefaultTasksMax=970000
Notes None
JVM Instance jvm_Ctr_1
Parts of Benchmark Controller
JVM Instance Description jvm_2
Command Line -Xms4g -Xmx4g -Xmn3g -XX:+UseParallelGC -XX:ParallelGCThreads=8 -XX:CICompilerCount=4
Tuning
  • numactl --interleave=all
Notes None
JVM Instance jvm_TxInjector_1
Parts of Benchmark TxInjector
JVM Instance Description jvm_2
Command Line -Xms4g -Xmx4g -Xmn3g -XX:+UseParallelGC -XX:ParallelGCThreads=8 -XX:CICompilerCount=4
Tuning Used numactl to affinitize six TxInjector JVM (6 Groups) to one NUMA node
  • Group1: numactl --cpunodebind=0 --localalloc
  • Group2: numactl --cpunodebind=0 --localalloc
  • Group3: numactl --cpunodebind=0 --localalloc
  • Group4: numactl --cpunodebind=0 --localalloc
  • Group5: numactl --cpunodebind=0 --localalloc
  • Group6: numactl --cpunodebind=0 --localalloc
  • Group7: numactl --cpunodebind=1 --localalloc
  • Group8: numactl --cpunodebind=1 --localalloc
  • Group9: numactl --cpunodebind=1 --localalloc
  • Group10: numactl --cpunodebind=1 --localalloc
  • Group11: numactl --cpunodebind=1 --localalloc
  • Group12: numactl --cpunodebind=1 --localalloc
  • Group13: numactl --cpunodebind=2 --localalloc
  • Group14: numactl --cpunodebind=2 --localalloc
  • Group15: numactl --cpunodebind=2 --localalloc
  • Group16: numactl --cpunodebind=2 --localalloc
  • Group17: numactl --cpunodebind=2 --localalloc
  • Group18: numactl --cpunodebind=2 --localalloc
  • Group19: numactl --cpunodebind=3 --localalloc
  • Group20: numactl --cpunodebind=3 --localalloc
  • Group21: numactl --cpunodebind=3 --localalloc
  • Group22: numactl --cpunodebind=3 --localalloc
  • Group23: numactl --cpunodebind=3 --localalloc
  • Group24: numactl --cpunodebind=3 --localalloc
Notes None
max-jOPS = jOPS passed before the First Failure
Pass/Fail Pass Pass Fail Fail Fail
jOPS 1430963 1447998 1465033 1482068 1499104
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 1149880 1269127 1354304 1422445 1447998 1324145
  Percentile
  10-th 50-th 90-th 95-th 99-th 100-th
500us 306635 / 289600 17035 / 34071 - / 17035 - / 17035 - / 17035 - / 17035
1000us 1413927 / 1430963 681411 / 698446 119247 / 136282 102212 / 119247 34071 / 51106 - / 17035
5000us 1447998 / - 1447998 / - 1345786 / 1362822 1192469 / 1175434 953975 / 868799 119247 / 17035
10000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1141363 / 1158398 119247 / 17035
25000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1260610 / 1277645 119247 / 17035
50000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1345786 / 1362822 289600 / 34071
75000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1413927 / 1430963 732517 / 34071
100000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1447998 / - 936940 / 272564
200000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1362822 / 902869
500000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1447998 / 902869
1000000us 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1447998 / - 1447998 / 902869
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 Group10.Backend.beJVM Group10.TxInjector.txiJVM1 Group11.Backend.beJVM Group11.TxInjector.txiJVM1 Group12.Backend.beJVM Group12.TxInjector.txiJVM1 Group13.Backend.beJVM Group13.TxInjector.txiJVM1 Group14.Backend.beJVM Group14.TxInjector.txiJVM1 Group15.Backend.beJVM Group15.TxInjector.txiJVM1 Group16.Backend.beJVM Group16.TxInjector.txiJVM1 Group17.Backend.beJVM Group17.TxInjector.txiJVM1 Group18.Backend.beJVM Group18.TxInjector.txiJVM1 Group19.Backend.beJVM Group19.TxInjector.txiJVM1 Group2.Backend.beJVM Group2.TxInjector.txiJVM1 Group20.Backend.beJVM Group20.TxInjector.txiJVM1 Group21.Backend.beJVM Group21.TxInjector.txiJVM1 Group22.Backend.beJVM Group22.TxInjector.txiJVM1 Group23.Backend.beJVM Group23.TxInjector.txiJVM1 Group24.Backend.beJVM Group24.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 Group7.Backend.beJVM Group7.TxInjector.txiJVM1 Group8.Backend.beJVM Group8.TxInjector.txiJVM1 Group9.Backend.beJVM Group9.TxInjector.txiJVM1
specjbb.comm.connect.client.pool.size 256 256 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140
specjbb.comm.connect.selector.runner.count 0 4
specjbb.comm.connect.worker.pool.max 256 256 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140 150 140
specjbb.comm.connect.worker.pool.min 1 1 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 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.controller.host localhost 192.168.10.40
specjbb.forkjoin.workers 480 {Tier1=99, Tier2=3, Tier3=7}
specjbb.group.count 1 24
specjbb.heartbeat.period 10000 2000
specjbb.heartbeat.threshold 100000 9000000
specjbb.mapreducer.pool.size 480 4
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 1703527 IR
High-bound (settled) is 1530418 IR