SPECjbb2015 Report for jbb2015-20160510-00082 : 186968 max-jOPS ; 114609 critical-jOPS

Hardware hw_1
Name	ProLiant DL580 Gen9
Vendor	Hewlett Packard Enterprise
Vendor URL	http://hpe.com/
Available	May-2016
Model	ProLiant DL580 Gen9
Form Factor	4U Rack
CPU Name	Intel Xeon E7-8890 v4
CPU Characteristics	24 Core, 2.20 GHz, 60 MB L3 Cache (Turbo Boost Technology up to 3.4 GHz)
Number of Systems	1
Nodes Per System	1
Chips Per System	4
Cores Per System	96
Cores Per Chip	24
Threads Per System	192
Threads Per Core	2
Version	U17 04/26/2016
CPU Frequency (MHz)	2200
Primary Cache	32 KB I + 32 KB D on chip per core
Secondary Cache	256 KB I+D on chip per core
Tertiary Cache	60 MB I+D on chip per chip
Other Cache	None
Disk	1 x 400 GB SSD SAS
File System	XFS
Memory Amount (GB)	512
# and size of DIMM(s)	64 x 32768 MB
Memory Details	32 GB 2Rx4 PC4-2400T-R, running at 1600MHz
# and type of Network Interface Cards (NICs)	HP Ethernet 1Gb 4-port
Power Supply Quantity and Rating (W)	4 x 1500
Other Hardware	None
Cabinet/Housing/Enclosure	None
Shared Description	None
Shared Comment	None
Notes	None
Other Hardware network_1
Name	None
Vendor	None
Vendor URL	None
Version	None
Available	None
Bitness	None
Notes	None

Operating System os_1
Name	SUSE Linux Enterprise Server 12 SP1
Vendor	SUSE
Vendor URL	https://www.suse.com/
Version	3.12.49-11-default
Available	Dec-2015
Bitness	64
Notes	None
Java Virtual Machine jvm_1
Name	Oracle Java SE 8u92
Vendor	Oracle
Vendor URL	http://oracle.com/
Version	Java HotSpot 64-bit Server VM, version 1.8.0_92
Available	Apr-2016
Bitness	64
Notes	None
Other Software other_1
Name	None
Vendor	None
Vendor URL	None
Version	None
Available	None
Bitness	None
Notes	None

Hardware
OS Images	os_Image_1(1)
Hardware Description	hw_1
Number of Systems	1
SW Environment	Non-virtual
Tuning	Hyper Threading=Enabled QPI Snoop Configuration=Home Snoop Thermal Configuration=Maximum Cooling Power Profile=Maximum Performance Collaborative Power Control=Disabled Processor Power and Utilization Monitoring=Disabled Memory Patrol Scrub=Disabled
Notes	None

OS Image os_Image_1
JVM Instances	jvm_Ctr_1(1), jvm_Backend_1(4), jvm_TxInjector_1(4)
OS Image Description	os_1
Tuning	tuned-adm profile=throughput-performance echo 16000000 > /proc/sys/kernel/sched_latency_ns echo 6000000 > /proc/sys/kernel/sched_min_granularity_ns echo 990000 > /proc/sys/kernel/sched_rt_runtime_us echo 1000 > /proc/sys/kernel/sched_migration_cost_ns echo 1 > /proc/sys/kernel/sched_compat_yield
Notes	None
JVM Instance jvm_Ctr_1
Parts of Benchmark	Controller
JVM Instance Description	jvm_1
Command Line	-Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelOldGC
Tuning	None
Notes	None
JVM Instance jvm_Backend_1
Parts of Benchmark	Backend
JVM Instance Description	jvm_1
Command Line	-Xms470g -Xmx470g -XX:-UsePerfData -XX:-UseAdaptiveSizePolicy -XX:-UseBiasedLocking -XX:+UseParallelOldGC -XX:SurvivorRatio=28 -XX:TargetSurvivorRatio=95 -XX:ParallelGCThreads=36 -XX:MaxTenuringThreshold=15 -server -Xmn430g -XX:LargePageSizeInBytes=2m -XX:+UseLargePages -XX:+AlwaysPreTouch -XX:+AggressiveOpts -XX:+DisableExplicitGC
Tuning	Used numactl to affinitize each Backend JVM to NUMA node. numactl --cpunodebind=0 --localalloc numactl --cpunodebind=1 --localalloc numactl --cpunodebind=2 --localalloc numactl --cpunodebind=3 --localalloc
Notes	None
JVM Instance jvm_TxInjector_1
Parts of Benchmark	TxInjector
JVM Instance Description	jvm_1
Command Line	-Xms2g -Xmx2g -Xmn1536m -XX:+UseParallelOldGC
Tuning	None
Notes	None

max-jOPS = jOPS passed before the First Failure
Pass/Fail	Pass	Pass	Fail	Fail	Fail
jOPS	184601	186968	189334	191701	194068

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	67450	117150	130956	136084	140423	114609

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

This section lists properties only set by user

Property Name	Default	Controller
specjbb.comm.connect.selector.runner.count	0	4
specjbb.comm.connect.timeouts.connect	60000	600000
specjbb.comm.connect.timeouts.read	60000	600000
specjbb.comm.connect.timeouts.write	60000	600000
specjbb.comm.connect.worker.pool.max	256	64
specjbb.controller.maxir.maxFailedPoints	3	3
specjbb.forkjoin.workers	192	{Tier1=170, Tier2=85, Tier3=35}
specjbb.group.count	1	4
specjbb.txi.pergroup.count	1	1


Level: COMPLIANCE
Check	Agent	Result
Check properties on compliance	All	PASSED

High-bound (max attempted) is 236668 IR

High-bound (settled) is 198484 IR

SPECjbb2015 Version: [SPECjbb2015 1.00, June 24, 2015]

Hewlett Packard Enterprise ProLiant DL580 Gen9	186968 SPECjbb2015-MultiJVM max-jOPS 114609 SPECjbb2015-MultiJVM critical-jOPS
Tested by: Hewlett Packard Enterprise	Test Sponsor: Hewlett Packard Enterprise	Test location: Houston, TX	Test date: May 9, 2016
SPEC license #: 3	Hardware Availability: May-2016	Software Availability: Apr-2016	Publication: Jun 06, 2016


SPECjbb2015-MultiJVM: Multiple JVMs/Single Host (# of groups: 4) Overall SUT Description SUT Description max-jOPS and critical-jOPS Details Number of probes Request Mix Accuracy Rate Of Non-Critical Failures Delay between performance status pings IR/PR Accuracy Topology SUT Configuration Properties Validation Details Link to Full Disclosure	Overall Throughput RT curve