track back from Robert Scoble's blog:
Having attended PDC's 2001 and 2003 I can't really find any good reason to justify going. Whidbey? Read quite a bit and I am waiting for beta 2. Unless there are late additions like Indigo into Whidbey I don't think I'm going.
Thursday, March 10, 2005
Wednesday, March 09, 2005
scalability
Comment from Larry Osterman's weblog:
"you can't speed up hard disk copies by throwing more threads or overlapped I/O at the problem, because file copy speed is ultimately limited by the physical speed of the underlying media - and with only one spindle, it can only read or write to the drive one operation at a time."
I thought with RAID, byte striping, SAN and the like you can't really assume what your underlying physical reality is anymore. I once heard this from a technical staff of a high-end RAID provider: "that anything you can throw into the SCSI bus, their RAID box will be able to write". Not really sure if it were true but their disks are really fast.
"you can't speed up hard disk copies by throwing more threads or overlapped I/O at the problem, because file copy speed is ultimately limited by the physical speed of the underlying media - and with only one spindle, it can only read or write to the drive one operation at a time."
I thought with RAID, byte striping, SAN and the like you can't really assume what your underlying physical reality is anymore. I once heard this from a technical staff of a high-end RAID provider: "that anything you can throw into the SCSI bus, their RAID box will be able to write". Not really sure if it were true but their disks are really fast.
Subscribe to:
Posts (Atom)
Posts
