JVM Options:
 -server -Xms3g -Xmx3g -Xmn1g -Xss128k -XX:+AggressiveHeap
 -XX:+UseParallelGC -XX:ParallelGCThreads=8 -XX:PermSize=128m
 -XX:LargePageSizeInBytes=4m -XX:+UseParallelOldGC
 -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamp
WLS Options:
 -Dweblogic.SocketReaders=4 -Dweblogic.StuckThreadMaxTime=1200
 -Dweblogic.diagnostics.debug.DebugLogger.DISABLED=true
Java process started in FX class using /usr/bin/priocntl -e -c FX
Java process started with LD_PRELOAD_32=/usr/lib/libumem.so

JVM Options:
 -d64 server -Xms16g -Xmx16g -Xmn12g -Xss256k -XX:+AggressiveHeap
 -XX:+UseParallelGC -XX:ParallelGCThreads=32
 -XX:LargePageSizeInBytes=4m -XX:MaxTenuringThreshold=3
 -XX:SurvivorRatio=20 -verbose:gc -XX:+PrintGCDetails
 -XX:+PrintGCTimeStamps -XX:-TraceClassUnloading
 -XX:PermSize=96m -XX:MaxPermSize=512M -XX:+UseCompressedOops
WLS Options:
 -Dweblogic.SocketReaders=4 -Dsun.net.inetaddr.ttl=0 -Dnetworkaddress.cache.ttl=0
Java process started in FX class using /usr/bin/priocntl -e -c FX
Java process started with LD_PRELOAD_64=/usr/lib/sparc64/libumem.so

 db_name                         = specdb
 control_files                   = /specdb/cntrlspecdb
 _db_writer_flush_imu            = FALSE
 _db_cache_pre_warm              = FALSE
 _collect_undo_stats             = FALSE
 _imu_pools                      = 2000
 _in_memory_undo                 = true
 _smm_advice_enabled             = FALSE
 _undo_autotune                  = FALSE
 _ksmg_granule_size              = 33554432
 compatible                      = 11.1.0.6.0
 cursor_space_for_time           = TRUE
 aq_tm_processes                 = 0
 db_cache_size                   = 50G
 db_cache_advice                 = off
 db_8k_cache_size                = 12G
 db_4k_cache_size                = 10G
 db_keep_cache_size              = 4096M
 db_block_size                   = 2048
 db_block_checksum               = FALSE
 db_block_checking               = FALSE
 db_file_multiblock_read_count   = 128
 db_files                        = 256
 db_writer_processes             = 8
 dml_locks                       = 1000
 disk_asynch_io                  = TRUE
 log_buffer                      = 100663296
 log_checkpoint_interval         = 0
 log_checkpoints_to_alert        = TRUE
 open_cursors                    = 2000
 parallel_max_servers            = 100
 processes                       = 3300
 query_rewrite_enabled           = false
 replication_dependency_tracking = false
 sessions                        = 3300
 shared_pool_size                = 8G
 statistics_level                = BASIC
 timed_statistics                = false
 trace_enabled                   = FALSE
 transactions                    = 33000
 transactions_per_rollback_segment = 1
 undo_management                 = AUTO
 undo_retention                  = 300
 undo_tablespace                 = undo_ts
 cpu_count                       = 216
 _array_update_vector_read_enabled = true
 _diag_adr_enabled               = false
 _fg_sync_sleep_usecs            = 3000
 _global_hang_analysis_interval  = 0
 _hang_detection                 = 0
 _ktc_control                    = 4
 _library_cache_advice           = false
 _local_hang_analysis_interval_secs = 0
 _global_hang_analysis_interval_secs = 0
 _resource_manager_always_off    = true
 _two_pass                       = false
 _log_event_queues               = 4

Oracle processes run in 4 processor sets containing 28 cores in all, using psrset -b pset pid
and each process run in the FX class using /usr/bin/priocntl -s -c FX -i pid
Oracle Log Writer run in a processor set containing 4 HW strands
using psrset -b pset pid and run in the RT class using
/usr/bin/priocntl -s -c RT -p 1 -i pid.
One processor set configured with 3 HW strands executing the OS clock
thread (HW strand 0) and the 2 e1000g interrupt threads.
The remaining cores were used for network and disk interrupt handling.
Four ST2540 and ST2501 storage array pairs configured as one ASM diskgroup for
the database files. Two ST2540 storage arrays configured with three ASM diskgroups
for the redo logs. The ASM configuration is in the FDA.

JVM Options:
 -server -XX:+AggressiveHeap -XX:+UseParallelGC
 -XX:LargePageSizeInBytes=4m -XX:-TraceClassUnloading
 -Xms2g -Xmx2g -Xmn600m -XX:+DisableExplicitGC -Xbatch
 -Xss128k -Dsun.net.inetaddr.ttl=0 -Dnetworkaddress.cache.ttl=0
 -Dweblogic.ThreadPoolSize=50 -Dweblogic.ThreadPoolPercentSocketReaders=50

System Tuning in /etc/system:
set ip:ip_soft_rings_cnt = 16
Network Tuning:
ndd -set /dev/tcp tcp_conn_req_max_q 16384
ndd -set /dev/tcp tcp_conn_req_max_q0 16384
ndd -set /dev/tcp tcp_xmit_hiwat 131072
ndd -set /dev/tcp tcp_recv_hiwat 131072
ndd -set /dev/tcp tcp_naglim_def 1
Network configuration:
1x XAUI 10Gbit NIC, 1x onboard 1Gbit NIC
Disk and File system configuration:
2x 146GB SAS disks for OS and application software using UFS.
2x 32GB SSD disks for logs and JMS persistence filestore using ZFS.
Configuration notes:
Four application server instances were hosted in 4 separate Solaris Containers.
Three Containers were bound to separate processor sets where each pset
consisted of 4 cores (32 HW threads) using resource pools.
The fourth container used the default processor set.
The Solaris Container and Resouce Pool configuration is in the FDA.
Interrupts were enabled on one HW strand per core.
Each Container on the system was connected to 2 subnets.
The first subnet in each container was used for driver access and
connected to the 10 GbE switch.
All 4 containers shared one 10Gbit NIC for this subnet
The second subnet in each container was used for database access
where all 4 containers shared a 1GBit NIC for this subnet.

System Tuning in /etc/system:
set kernel_cage_enable=0
set ip:ip_soft_rings_cnt = 8
set hires_tick = 1
Network Tuning:
ndd -set /dev/tcp tcp_conn_req_max_q 16384
ndd -set /dev/tcp tcp_conn_req_max_q0 16384
ndd -set /dev/tcp tcp_xmit_hiwat 131072
ndd -set /dev/tcp tcp_recv_hiwat 131072
ndd -set /dev/tcp tcp_naglim_def 1
Shared memory settings in /etc/project:
user.oracle:101:Oracle DBA:::project.max-shm-memory=(privileged,137438953472,deny)
Network configuration
1x 10 GbE XAUI card, 2x 1GBit oboard NIC, and 1x Dual Port 1Gbit NIC
Disk configuration
3x 4Gb Dual Port PCI-E Fiber Channel card
6 Sun StorageTek 2540 Array (12 x 146GB SAS Array)
4 Sun StorageTek 2501 Expansion Array (12 x 146GB SAS Array)
The Processor Set configuration is in the FDA.

System Tuning in /etc/system:
set ip:ip_soft_rings_cnt = 16
Network Tuning:
ndd -set /dev/tcp tcp_conn_req_max_q 16384
ndd -set /dev/tcp tcp_conn_req_max_q0 16384
ndd -set /dev/tcp tcp_xmit_hiwat 131072
ndd -set /dev/tcp tcp_recv_hiwat 131072
ndd -set /dev/tcp tcp_naglim_def 1
ndd -set /dev/tcp tcp_time_wait_interval 10000
Blade Chassis Configuration:
Sun Blade 6000 Chassis configured with
10 Sun Blade T6300 Server Modules and
10 10Gbit PCIe Express Modules

Network Tuning:
ndd -set /dev/tcp tcp_conn_req_max_q 16384
ndd -set /dev/tcp tcp_conn_req_max_q0 16384
ndd -set /dev/tcp tcp_xmit_hiwat 131072
ndd -set /dev/tcp tcp_recv_hiwat 131072
ndd -set /dev/tcp tcp_naglim_def 1
ndd -set /dev/tcp tcp_time_wait_interval 10000

Network Tuning:
ndd -set /dev/tcp tcp_conn_req_max_q 16384
ndd -set /dev/tcp tcp_conn_req_max_q0 16384
ndd -set /dev/tcp tcp_xmit_hiwat 131072
ndd -set /dev/tcp tcp_recv_hiwat 131072
ndd -set /dev/tcp tcp_naglim_def 1
The DNS named process run in the RT class using /usr/bin/priocntl -s -c RT -p 1 -i pid PID