Re: AIX/ORACLE - Raid devices - async I/O [SUMMARY]

In article <Cz9Mto.7wH_at_world.std.com>, lparsons_at_world.std.com (Lee E Parsons) writes:
|>Newsgroups: comp.databases.oracle,comp.unix.aix
|>From: lparsons_at_world.std.com (Lee E Parsons)
|>Subject: AIX/ORACLE - Raid devices - async I/O [SUMMARY]
|>Date: Mon, 14 Nov 1994 16:22:35 GMT
|>

 [...snip...]
|>>
|>> Are not writes to the JFS already async and if so how does the async_io
|>> option increase performance of I/O?
|>

[...snip...]

    Typically writes to JFS are async, since the data is cached. There is     a flag to use on the open() system call (O_SYNC) that will make JFS act     like a write-through cache. This, BTW, would solve the data integrity     issues of running a database on a JFS.

--
Sean Allen                                      AIX/Database Administration
(919)543-6021 Fax 7996                        IBM Personal Computer Company
Internal Zip: D318/B205                    Research Triangle Park, NC 27709
#include<std_disclaimer.h>                   Internet: allensd_at_vnet.ibm.com