Re: exadata flash cache and flash disk metrics

From: Karl Arao <karlarao_at_gmail.com>
Date: Thu, 24 Jan 2019 12:53:47 -0500
Message-ID: <CACNsJncV8CEfWJUKbh-2CxOWC3AF35A+MYvzGaauuXrs1_MX2A_at_mail.gmail.com>



is your WBFC enabled ? starting cell version 12.2.1.1.0, if WBFC is enabled temp writes also goes to FD

https://docs.oracle.com/en/engineered-systems/exadata-database-machine/dbmso/whats-new-oracle-exadata-database-machine-12c-release-2-12.2.1.1.0.html#GUID-FFFDCB63-308F-4B08-A917-D635686920E6

check this (
https://github.com/karlarao/cellmetricstoolkit/blob/master/1_gen_scl.sh) as a reference on how you can breakdown the IO further, start from CG up to the CD.

CG - consumer group
DB - database
FC and FL - flash
CD - cell disk

Then correlate that with your perf hub Exadata Section. Then you'll be able to see patterns and and numbers to chase and workload periods

On Thu, Jan 24, 2019 at 11:31 AM Ls Cheng <exriscer_at_gmail.com> wrote:

> Hi all
>
> Does anyone know the differece between these two metrics in Exadata Cells?
>
>
> 1. DB_FC_IO_RQ_SM_SEC => The number of small I/O requests issued by a
> database to flash cache per second.
> 2. DB_FD_IO_RQ_SM_SEC => The number of small I/O requests issued by a
> database to flash disks per second.
>
>
> The difference between flash disk and flash cache precisely.
>
> Our is 1/8 X6 Rack with HC disks with Flash Cache however when I run LIST
> METRICCURRENT DB_FD_IO_RQ_SM_SEC I actually see some values which is quite
> confusing because we are using flash cache and not flash disk (instead we
> have HC disks).
>
> Any lights?
>
> Thanks
>
>
>
>
>
>
> <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail> Virus-free.
> www.avast.com
> <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail>
> <#m_-5391896866109542471_DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>
>

--
http://www.freelists.org/webpage/oracle-l
Received on Thu Jan 24 2019 - 18:53:47 CET

Original text of this message