[root@localhost hdparm-9.12]# /root/iozone3_326/src/current/iozone -b /backup/vusb_iozone.xls -i 0 -i 1 -i 2 -R -t 10 -F /mnt/1 /mnt/2 /mnt/3 /mnt/4 /mnt/5 /mnt/6 /mnt/7 /mnt/8 /mnt/9 /mnt/0 -c
 Iozone: Performance Test of File I/O
         Version $Revision: 3.326 $
  Compiled for 32 bit mode.
  Build: linux

 Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
              Al Slater, Scott Rhine, Mike Wisner, Ken Goss
              Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
              Randy Dunlap, Mark Montague, Dan Million, Gavin Brebner,
              Jean-Marc Zucconi, Jeff Blomberg, Benny Halevy,
              Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root.

 Run began: Thu Jul 23 02:09:45 2009

 Excel chart generation enabled
 Include close in write timing
 Command line used: /root/iozone3_326/src/current/iozone -b /backup/vusb_iozone.xls -i 0 -i 1 -i 2 -R -t 10 -F /mnt/1 /mnt/2 /mnt/3 /mnt/4 /mnt/5 /mnt/6 /mnt/7 /mnt/8 /mnt/9 /mnt/0 -c
 Output is in Kbytes/sec
 Time Resolution = 0.000001 seconds.
 Processor cache size set to 1024 Kbytes.
 Processor cache line size set to 32 bytes.
 File stride size set to 17 * record size.
 Throughput test with 10 processes
 Each process writes a 512 Kbyte file in 4 Kbyte records

 Children see throughput for 10 initial writers  =  307328.47 KB/sec
 Parent sees throughput for 10 initial writers  =   22516.29 KB/sec
 Min throughput per process    =       0.00 KB/sec
 Max throughput per process    =  307328.47 KB/sec
 Avg throughput per process    =   30732.85 KB/sec
 Min xfer      =       0.00 KB

 Children see throughput for 10 rewriters  =  849002.12 KB/sec
 Parent sees throughput for 10 rewriters  =   57476.61 KB/sec
 Min throughput per process    =       0.00 KB/sec
 Max throughput per process    =  849002.12 KB/sec
 Avg throughput per process    =   84900.21 KB/sec
 Min xfer      =       0.00 KB

 Children see throughput for 10 readers   = 1615406.81 KB/sec
 Parent sees throughput for 10 readers   =  113498.94 KB/sec
 Min throughput per process    =  800109.31 KB/sec
 Max throughput per process    =  815297.50 KB/sec
 Avg throughput per process    =  161540.68 KB/sec
 Min xfer      =     512.00 KB

 Children see throughput for 10 re-readers  = 1694048.12 KB/sec
 Parent sees throughput for 10 re-readers  =  113013.27 KB/sec
 Min throughput per process    =  838004.69 KB/sec
 Max throughput per process    =  856043.44 KB/sec
 Avg throughput per process    =  169404.81 KB/sec
 Min xfer      =     512.00 KB

 Children see throughput for 10 random readers  =  998266.44 KB/sec
 Parent sees throughput for 10 random readers  =   58575.28 KB/sec
 Min throughput per process    =       0.00 KB/sec
 Max throughput per process    =  998266.44 KB/sec
 Avg throughput per process    =   99826.64 KB/sec
 Min xfer      =       0.00 KB

 Children see throughput for 10 random writers  =  710241.31 KB/sec
 Parent sees throughput for 10 random writers  =   33684.33 KB/sec
 Min throughput per process    =       0.00 KB/sec
 Max throughput per process    =  710241.31 KB/sec
 Avg throughput per process    =   71024.13 KB/sec
 Min xfer      =       0.00 KB

USB가 저정도 성능이 나와도 되는건가 ;;;

별다른 설정 없이 쓰레드만 10개 돌렸는데..

캐싱을 통한 처리인하여 속도가 비정상적으로 상승한것으로 판단됨