Re: ASM Filter Driver Performance
From: Jared Still <jkstill_at_gmail.com>
Date: Fri, 26 Jan 2018 08:29:42 -0800
Message-ID: <CAORjz=M4utg3-92GbsCb=N5LYNbNhZiMSq2eGRUjc1+azgFBFQ_at_mail.gmail.com>
Date: Fri, 26 Jan 2018 08:29:42 -0800
Message-ID: <CAORjz=M4utg3-92GbsCb=N5LYNbNhZiMSq2eGRUjc1+azgFBFQ_at_mail.gmail.com>
Hello Niall,
I should have included the redo stats in the blog article:
On Fri, Jan 26, 2018 at 3:45 AM, Niall Litchfield < niall.litchfield_at_gmail.com> wrote:
> Hi Jared
>
> The AWR reports look a little odd to me. I'd expect a SLOB Update test to
> result in write I/O as well as read I/O. For comparison here's an output
> from a 25% update run I did recently.
>
>
1.56M per second of redo - this is from a test on a small VM.
Statistic Total per Second perTrans
-------------------------------- ------------------ -------------- ------------- redo buffer allocation retries 25 0.0 0.0 redo entries 209,411 347.2 2.1 redo log space requests 37 0.1 0.0 redo ordering marks 14 0.0 0.0 redo size 938,657,620 1,556,388.0 9,427.8 redo size for direct writes 0 0.0 0.0 redo subscn max counts 703 1.2 0.0 redo synch time 0 0.0 0.0 Instance Activity Stats DB/Inst: ASMAFD/asmafd redo synch time (usec) 2,272 3.8 0.0 redo synch time overhead (usec) 228,888 379.5 2.3 redo synch time overhead count ( 8 0.0 0.0 redo synch time overhead count ( 0 0.0 0.0 redo synch time overhead count ( 1 0.0 0.0 redo synch time overhead count ( 1 0.0 0.0 redo synch time overhead count ( 1 0.0 0.0 redo synch writes 11 0.00.0
Jared Still
Certifiable Oracle DBA and Part Time Perl Evangelist
Principal Consultant at Pythian
Pythian Blog http://www.pythian.com/blog/author/still/
Github: https://github.com/jkstill
-- http://www.freelists.org/webpage/oracle-lReceived on Fri Jan 26 2018 - 17:29:42 CET