Re: analyzing, visualizing, understanding and rating I/O latency
From: Martin Berger <martin.a.berger_at_gmail.com>
Date: Sun, 30 Sep 2012 20:18:52 +0200
Message-ID: <CALH8A92KDcnotXjM-2bMnQBd_xzeTc-Xk4=cCgqi7jnpzFRT3Q_at_mail.gmail.com>
that's what histograms are for.
sometimes it even helps to calculate mean/median/mode so at least you can 'reasonable guess' there are such effects. But still I prefer histograms.
Date: Sun, 30 Sep 2012 20:18:52 +0200
Message-ID: <CALH8A92KDcnotXjM-2bMnQBd_xzeTc-Xk4=cCgqi7jnpzFRT3Q_at_mail.gmail.com>
that's what histograms are for.
sometimes it even helps to calculate mean/median/mode so at least you can 'reasonable guess' there are such effects. But still I prefer histograms.
On Sun, Sep 30, 2012 at 12:22 PM, goran bogdanovic <goran00_at_gmail.com> wrote:
>> I'm generally looking into latency - for most of system disk queue
>> size and queuing time is a good indicator of performance
>> problems.
>
> ... what if SAN caching fake this values?
>
>
> --
> http://www.freelists.org/webpage/oracle-l
-- http://www.freelists.org/webpage/oracle-lReceived on Sun Sep 30 2012 - 20:18:52 CEST