> I never asked, but before your change how was the > single LUn that was > presented tot he LDom configured on the EMC box? > Was it striped over many physical disks? I assumed > it was, but if it > was not could help explain the speedup. > SANS admin was only able to give me hypers so there is no striping on the backend. My old config was 1 x 67Gbyte hyper + 1 x 33Gbyte hyper presented to the LDOM through the io domain. inside the LDOM: zpool create poolname disk1 disk2
new setting is: disk1 = 1 x 16Gbyte hyper disk2 = 1 x 16Gbyte hyper disk3 = 1 x 16Gbyte hyper disk4 = 1 x 16Gbyte hyper disk5 = 1 x 16Gbyte hyper disk6 = 1 x 16Gbyte hyper disk7 = 1 x 16Gbyte hyper disk8 = 1 x 16Gbyte hyper disk1 - disk8 presented to LDOM inside LDOM: zpool create poolname disk1 disk2 disk3 disk4 disk5 disk6 disk7 disk8 Application admin has finished testing and the full run time for 8000 reports went from 1 hour 36 minutes down to 23 minutes. which is now acceptable times but we would like to shave some more time off of it. -- This message posted from opensolaris.org _______________________________________________ ldoms-discuss mailing list [email protected] http://mail.opensolaris.org/mailman/listinfo/ldoms-discuss
