At 2003-03-12T07:03:59Z, Ron Johnson <ron.l.johnson@cox.net> writes: > 1. Tagged command queuing should order the reads. Yes, but you still have contention in that a larger-than-normal chunk will be read from file1, alternating with a larger-than-normal chunk from file2. > 2. As a DBA, it seems to me that this possibility is irrelevant, since > the DBMS would have sucked those blocks (and their neighbors) into > it's cache after the 1st 1 or 2 db read requests. Work with me here. :) >> Imagine, instead, that file1 and file2 are on a mirror. The RAID system >> could converge on the situation where the first drive is "dedicated" to >> file1, and the second is "dedicated" to file2. > Are controllers smart in that way? I think, more likely, that they'd be stupid in that way. That is, the first drive's heads will be physically closer to a requested block from file1, and similarly for file2 and the second drive. -- Kirk Strauser In Googlis non est, ergo non est.
Attachment:
pgpSH5m3fubCe.pgp
Description: PGP signature