SPECsfs97_R1.v3 Result

Performance

Throughput (ops/sec) Response (msec) 2536 0.6 5072 0.6 7643 0.7 10177 0.8 12743 0.8 15346 1.0 17884 1.2 20517 1.4 23161 2.1 25382 5.1

Configuration

LG Type	LG1
LG Model	NEC Express5800/120Rb-1
Number and Type Processors	1 GHz Pentium III
Memory Size	1 GB
Operating System	Red Hat Linux 7.2, Linux Kernel 2.4.21-rc1
Compiler
Compiler Options
Network Type	Alteon AceNIC Gigabit Ethernet

LG Type	LG2
LG Model	NEC Express5800/120Rc-1
Number and Type Processors	2.4 GHz Xeon
Memory Size	1 GB
Operating System	Red Hat Linux 7.2, Linux Kernel 2.4.21-rc1
Compiler
Compiler Options
Network Type	Intel Pro/1000 Network Connection

Testbed Configuration
LG #	LG Type	Network	Target File Systems	Notes
1,2,3,4,5,6,7,8	LG1	N1	F1	N/A
9,10,11,12	LG2	N1	F1	N/A

Other Notes

• The system was equipped with two array controllers and seven disk enclosures.
• Each array controller activated two FC loops.
• The first four disk enclosures were connected to an array controller and the rest were connected to the other.
• Each disk enclosure contains fifteen disks and 105 disks in total were used.
• The first four disks of the first disk enclosure are reserved for the Operating System and each disk enclosure has one spare disk.
• The fourteen user disks of each disk enclosre formed a RAID 1+0 group, except for the first enclosure which housed ten user disks.
• The single filesystem was comprised of the total 94 user disks.
• With UPS, the content of the NVRAM is saved into the reserved area of the disk within a limited time.
• The TOE handles segmenting and assembling of small Ethernet frames and Jumbo Frame is therefore not used.
• The two Gigabit switches were connected together via an uplink to increase the number of Gigabit ports.
• The following NFS and filesystem options were used; maximum journal size, no quota, no atime, no subtreecheck, no root squash, no privileged port check.
• In the event of system crash, the data is held in the memory (NVRAM). The part of memory is backed-up by battery and protected by the short power interruption and/or system crash.
• In the event of short power interruption, the memory controller goes into the self refresh mode, so that it keeps data. The rebooting system checks if the data is held in the NVRAM area and use it at recovery phase.
• The battery lasts only a few hours. The SPEC requires 72hour data protection. Our system is equipped with UPS. The UPS can enough energy to keep the controller and the first disk enclosure operational for a couple of minutes. The UPS detects power failure and singnal the system with SNMP protocol.
• Once the system detects power failure, it goes into the special mode which is similar to the panic dump. Like panic dump, it stops any further I/O service and dump the NVRAM area into the special partition in the OS disk.
• The OS disk is mirrored and guaranteed the power. Max 2GB NVRAM is saved sequentally within a limited time.
• At the next reboot with power coming back, the system checks if the data is saved in the special area and runs the special restoring program automatically. The program loads the special OS disk partition and restores the NVRAM area, before starting the usual OS. The usual OS sees the same NVRAM area as the system crash.

Generated on Tue Jul 8 23:47:11 2003 by SPEC SFS97 HTML Formatter
Copyright © 1997-2002 Standard Performance Evaluation Corporation