| Oracle FAQ | Your Portal to the Oracle Knowledge Grid | |
 |
 | |||
| Oracle FAQ | Your Portal to the Oracle Knowledge Grid | |
|
| |||
Home -> Community -> Mailing Lists -> Oracle-L -> RE: aio on sun ufs problem
David is right, -t just filters out specfic calls otherwise
the truss output can be a bit too much some times.
Richard
-----Original Message-----
From: David Green [mailto:thump_at_cosmiccooler.org] Sent: Tue 5/4/2004 11:27 PM To: oracle-l_at_freelists.org Cc: Subject: RE: aio on sun ufs problem
-----Original Message-----
From: oracle-l-bounce_at_freelists.org =
[mailto:oracle-l-bounce_at_freelists.org]
On Behalf Of zhu chao
Sent: Tuesday, May 04, 2004 5:00 AM
To: oracle-l_at_freelists.org
Subject: aio on sun ufs problem
Hi friends:
While reading the following paper:
http://de.sun.com/Partner/Softwarepartner/Oracle/Technik/pdf/oracle_on_su=
n.p
df
It says for oracle 8.1.7/ufs, aio is by default disabled. We must =
enable
it explictly with _filesystemio_options=3Dasynch. Is it true? For aio on =
raw
device/QuickIO, we can see truss -t kaio -p dbwr to verify it, for aio =
on
filesystem, how to verify it then?
---
Aio on solaris is enabled by default if you use disk_asynch_io =3D true. =
You
will see a failed system call to kaio and then pread pwrite processes =
spawn
to simulate aio via light weight threaded processing.
You can verify this in the same way using truss against dbwr. I'm not =
sure
what -t does, but if you just truss on dbwr process you will see the
behavior. I personally feel that dbwr_io_slaves when weighed against =
these
facts are better suted at simulating aio than the light weight threaded
processes.
- David
 |
 |