SPECsfs97_R1.v3 Result =============================================================================== DataChorus Co. Ltd : ClusStor SG C7000 (Failover Cluster) SPECsfs97_R1.v3 = 30024 Ops/Sec (Overall Response Time = 1.80 msec) =============================================================================== Throughput Response ops/sec msec 3060 0.5 6124 0.8 9045 1.1 12113 1.4 15067 1.8 18081 2.1 21042 2.4 24033 2.8 27030 3.3 30024 3.8 =============================================================================== Server Configuration and Availability Vendor DataChorus Co. Ltd Hardware Available Jan 2004 Software Available Jan 2004 Date Tested Dec 2004 SFS License number 2974 Licensee Location Seoul Korea CPU, Memory and Power Model Name ClusStor SG C7000 (Failover Cluster) Processor Intel Xeon 3.06 Ghz # of Processors 4 cores, 4 chips, 1 core/chip (2 cores per node) Primary Cache Execution Trace Cache 12KB + Data Cache 8KB on chip Secondary Cache 512KB (I+D) on chip Other Cache N/A UPS N/A Other Hardware N/A Memory Size 4 GB (2 GB per node) NVRAM Size 8 GB (4 GB per RAID controller) NVRAM Type Battery backed RAM NVRAM Description See notes Server Software OS Name and Version ClusStor 3.3 Other Software N/A File System DCFS NFS version 3 Server Tuning Buffer Cache Size Dynamic # NFS Processes 256 Fileset Size 290.1 GB Network Subsystem Network Type Gigabit Ethernet (MTU 1500 bytes) Network Controller Desc. Intel PRO/1000 1000BASE-T Number Networks 2 (N1 - Service, N2 - Cluster) Number Network Controllers 4 (2 per node: See notes) Protocol Type UDP Switch Type Nortel BayStack 380-24T Bridge Type N/A Hub Type N/A Other Network Hardware N/A Disk Subsystem and Filesystems Number Disk Controllers 4 (2 per node) Number of Disks 80 Number of Filesystems 2 File System Creation Ops default File System Config 10 RAID LUNs per file system Disk Controller QLogic QLA2300 # of Controller Type 4 (2 per node) Number of Disks 80 Disk Type Hitachi 36GB 10K RPM File Systems on Disks F1,F2 Special Config Notes RAID Level 0+1 with 4 disks, total 20 LUNs Load Generator (LG) Configuration Number of Load Generators 2 Number of Processes per LG 40 Biod Max Read Setting 2 Biod Max Write Setting 2 LG Type LG1 LG Model Intel SE7501WV2 Number and Type Processors 2 x Xeon 2.8 Ghz Memory Size 1 GB Operating System Linux RedHat 9.0 Compiler gcc 3.2.2 Compiler Options default Network Type Intel PRO/1000 1000BASE-T Testbed Configuration LG # LG Type Network Target File Systems Notes ---- ------- ------- ------------------- ----- 1 LG1 N1 F1,F2 N/A 2 LG1 N1 F1,F2 N/A =============================================================================== Notes and Tuning <> DataChorus ClusStor SG C7000 was configured as Active-Standby cluster with heartbeat/hardware monitoring and failover software. <> There are two gigabit ports per server: one is used for file service, the other is used for clustering (administration/heartbeat communication). <> ClusStor SG C7000 has two RAID controllers as active-active configuration. <> NVRAM: Each RAID controller has 4GB write-back disk cache (72 hours battery-backed). <> The RAID is comprised of 20 LUNs. Each LUN has 4 disks with RAID 0+1 and the stripe size is 64 KB. <> Each RAID controller serves 10 LUNs, respectively. <> For failover, each NAS server and each RAID controller were connected with 2 ports through 2 Gbps FC link. <> Each server has onboard Adaptec Ultra320 SCSI controller for OS disks. <> OS disks in each server are mirrored with software RAID 1 for failure protection. <> Uniform Access Rule: <> Each node has 1 network port(N1) for NFS service. <> Each node has 1 network port(N2) for cluster operation. <> There are 20 LUNs in RAID storage. There are two file systems (F1 and F2): each file system consists of 10 LUNs. <> Each LG has 40 processes: 20 processes access F1 and the other 20 processes access F2. <> Stable Storage: <> NFS share in ClusStor SG C7000 was configured to "Synchronous write". NFS write request is acknowledged after data is written to disk cache in RAID controller. <> Battery-backed disk cache in RAID controller preserves unwritten data for 72 hours in case of unexpected power outage. <> If active server fails, the standby server takes over all services and data without any loss. =============================================================================== Generated on Thu Feb 17 15:57:42 EST 2005 by SPEC SFS97 ASCII Formatter Copyright (c) 1997-2004 Standard Performance Evaluation Corporation