Re: IO statistics of the ARCH process

From: Tanel Poder <tanel_at_tanelpoder.com>
Date: Fri, 16 Mar 2012 23:01:07 +0000
Message-ID: <CAMHX9JKBgpVfD0QANd3cfQgMBEs6McuDZzZ2jtBt=vS9BwE0AQ_at_mail.gmail.com>

Snapper can show it as arch processes have sessions (and populate V$SESSION) like most other background processes...

---

    SID, USERNAME , TYPE, STATISTIC
, DELTA, HDELTA/SEC, %TIME, GRAPH

---

    122, (ARC0)    , STAT, recursive calls


          ,             2,        .33,

    122, (ARC0)    , STAT, non-idle wait time
         ,             8,       1.33,
    122, (ARC0)    , STAT, non-idle wait count


          ,           350,      58.33,

    122, (ARC0)    , STAT, in call idle wait time
         ,          8400,       1.4k,
    122, (ARC0)    , STAT, messages sent


          ,             1,        .17,

    122, (ARC0)    , STAT, messages received


          ,             2,        .33,

    122, (ARC0)    , STAT, session pga memory
         ,      12255232,      2.04M,
    122, (ARC0)    , STAT, session pga memory max
         ,      12255232,      2.04M,
    122, (ARC0)    , STAT, enqueue waits


          ,             1,        .17,

    122, (ARC0)    , STAT, enqueue requests
         ,            49,       8.17,
    122, (ARC0)    , STAT, enqueue conversions


          ,             2,        .33,

    122, (ARC0)    , STAT, enqueue releases
         ,            49,       8.17,
    122, (ARC0)    , STAT, physical read total IO requests


          ,            83,      13.83,

    122, (ARC0)    , STAT, physical read total multi block requests
         ,             2,        .33,
*    122, (ARC0)    , STAT, physical read total bytes
          ,       3145728,    524.29k,*
    122, (ARC0)    , STAT, physical write total IO requests
         ,            46,       7.67,
*    122, (ARC0)    , STAT, physical write total bytes
           ,        721920,    120.32k,*
    122, (ARC0)    , STAT, cell physical IO interconnect bytes
          ,       3867648,    644.61k,
    122, (ARC0)    , STAT, max cf enq hold time
         ,            10,       1.67,
    122, (ARC0)    , STAT, total cf enq hold time
         ,            40,       6.67,
    122, (ARC0)    , STAT, total number of cf enq holders
         ,             6,          1,
    122, (ARC0)    , STAT, calls to kcmgcs


          ,             4,        .67,

    122, (ARC0)    , TIME, background cpu time


          ,         32996,      5.5ms,      .5%, |_at_         |

    122, (ARC0)    , TIME, background elapsed time


          ,         61308,    10.22ms,     1.0%, |_at_         |

    122, (ARC0)    , WAIT, rdbms ipc message
          ,       4999912,   833.32ms,    83.3%, |_at_@@@@@@@@ |
    122, (ARC0)    , WAIT, Disk file operations I/O
         ,          3534,      589us,      .1%, |          |
    122, (ARC0)    , WAIT, Log archive I/O


          ,           240,       40us,      .0%, |          |

    122, (ARC0)    , WAIT, control file sequential read
         ,         13620,     2.27ms,      .2%, |          |
    122, (ARC0)    , WAIT, control file parallel write


          ,          3281,   546.83us,      .1%, |          |

    122, (ARC0)    , WAIT, log file sequential read
         ,          2744,   457.33us,      .0%, |          |
    122, (ARC0)    , WAIT, kfk: async disk IO
         ,          1889,   314.83us,      .0%, |          |
    122, (ARC0)    , WAIT, events in waitclass Other


          ,         47288,     7.88ms,      .8%, |_at_         |

--
*Tanel Poder*
Enkitec Europe
+372 56 956 181
http://www.enkitec.com/
Expert Oracle Exadata book:
http://www.apress.com/9781430233923




On Fri, Mar 16, 2012 at 7:20 PM, Hameed, Amir <Amir.Hameed_at_xerox.com> wrote:

> Folks,
> Is there a statistic that can be used to estimate how much IO/sec the
> ARCH process is doing when archiving redo log files? I was planning to
> use "Log archive I/O" event but the description of this event states
> that:
>
> "When the archiving process exhausts its I/O buffers because all of them
> are being used for on-going I/O's, the wait for an available I/O buffer
> is captured in this system wait event."
>
>
>
> Thank you
>
> Amir
>
>
> --
> http://www.freelists.org/webpage/oracle-l
>
>
>


--
http://www.freelists.org/webpage/oracle-l

Received on Fri Mar 16 2012 - 18:01:07 CDT