|
Prev: LACIE problems
Next: restoring system after disaster
From: Mike Ruskai on 3 Jul 2008 20:32 On or about Sat, 28 Jun 2008 17:57:13 +0800 did "Man-wai Chang ToDie (33.6k)" <toylet.toylet(a)gmail.com> dribble thusly: > >Chipset is nForce 570 Ultra. Whatever possessed you to think it would? 3.0Gbps indicates the maximum interface transfer rate for a single drive (which no current SATA drive can meet, much less exceed). It has nothing to do with the speed of an array of drives, each of which has their own connection (it's not like parallel SCSI). At most, you can expect performance of P*N, where P is the performance of one drive, and N is the number of drives.
From: Arno Wagner on 3 Jul 2008 21:01 Previously Mike Ruskai <BUTthannydI(a)dontearthlinklike.netspam> wrote: > On or about Sat, 28 Jun 2008 17:57:13 +0800 did "Man-wai Chang ToDie (33.6k)" > <toylet.toylet(a)gmail.com> dribble thusly: >> >>Chipset is nForce 570 Ultra. > Whatever possessed you to think it would? 3.0Gbps indicates the maximum > interface transfer rate for a single drive (which no current SATA drive can > meet, much less exceed). It has nothing to do with the speed of an array of > drives, each of which has their own connection (it's not like parallel SCSI). > At most, you can expect performance of P*N, where P is the performance of one > drive, and N is the number of drives. Indeed. Another one that looked at the highest number and though that it could be reached. The interface is allways faster than the disk, in order for it to not be a bottleneck. Current disks can reach something like 1Gbps maximum and typically slow down to around half that at the end of the disk. RAID0 is not necessarily that much faster. Arno
From: Man-wai Chang ToDie (33.6k) on 4 Jul 2008 00:20 >> Whatever possessed you to think it would? 3.0Gbps indicates the maximum >> interface transfer rate for a single drive (which no current SATA drive can >> meet, much less exceed). It has nothing to do with the speed of an array of >> drives, each of which has their own connection (it's not like parallel SCSI). > Indeed. Another one that looked at the highest number and though > that it could be reached. The interface is allways faster than the > disk, in order for it to not be a bottleneck. Current disks can > reach something like 1Gbps maximum and typically slow down to > around half that at the end of the disk. RAID0 is not necessarily > that much faster. Is there a way/program that measures the speed of data transfer in the SATA cables? HDTune doesn't seem to do it as the interface of my PC was SATA II. -- @~@ Might, Courage, Vision, SINCERITY. / v \ Simplicity is Beauty! May the Force and Farce be with you! /( _ )\ (Xubuntu 8.04) Linux 2.6.25.10 ^ ^ 12:16:01 up 15:33 0 users load average: 1.00 1.00 1.00 ? ? (CSSA): http://www.swd.gov.hk/tc/index/site_pubsvc/page_socsecu/sub_addressesa/
From: Man-wai Chang ToDie (33.6k) on 4 Jul 2008 07:45 >> Is there a way/program that measures the speed of data transfer in the >> SATA cables? HDTune doesn't seem to do it as the interface of my PC >> was SATA II. > HDTach free version. It really does? -- @~@ Might, Courage, Vision, SINCERITY. / v \ Simplicity is Beauty! May the Force and Farce be with you! /( _ )\ (Xubuntu 8.04) Linux 2.6.25.10 ^ ^ 19:43:01 up 23:00 0 users load average: 1.01 1.03 1.00 ? ? (CSSA): http://www.swd.gov.hk/tc/index/site_pubsvc/page_socsecu/sub_addressesa/
From: Man-wai Chang ToDie (33.6k) on 5 Jul 2008 03:13
>>> HDTach free version. >> It really does? > Yes, it calls it the "Burst Speed". Do you happen to know why HDTune doesn't report 3Gbps burst speed? HDTach really reported burst speed of 3Gbps.... -- @~@ Might, Courage, Vision, SINCERITY. / v \ Simplicity is Beauty! May the Force and Farce be with you! /( _ )\ (Xubuntu 8.04) Linux 2.6.25.10 ^ ^ 15:11:01 up 1 day 18:28 2 users load average: 1.21 1.19 1.25 ? ? (CSSA): http://www.swd.gov.hk/tc/index/site_pubsvc/page_socsecu/sub_addressesa/ |