Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@cassandra.apache.org
MIME-Version: 1.0
References: <CAEcKvja5MAjhyrBZJii8VW7KhGAbqGDi5St6_EG15Dxbur57tw@mail.gmail.com>
In-Reply-To: <CAEcKvja5MAjhyrBZJii8VW7KhGAbqGDi5St6_EG15Dxbur57tw@mail.gmail.com>
From: Eric Stevens <mightye@gmail.com>
Date: Mon, 30 May 2016 14:55:36 +0000
Message-ID: <CAORswtzgD0gmbdC1oo570BwGFpJB_7VjLy+wow1=MatUkoSz3g@mail.gmail.com>
Subject: Re: Per node limit for Disk Space
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=001a113d30b282d07005341073f5
archived-at: Mon, 30 May 2016 14:55:50 -0000

--001a113d30b282d07005341073f5
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

Those are rough guidelines, actual effective node size is going to depend
on your read/write workload and the compaction strategy you choose.  The
biggest reason data density per node usually needs to be limited is due to
data grooming overhead introduced by compaction.  Data at rest essentially
becomes I/O debt.  If you're using Leveled compaction, the interest rate on
that debt is higher.

If you're writing aggressively you'll find that you run out of I/O capacity
for smaller data at rest.  If you use compaction strategies that allow for
data to eventually stop compacting (Date Tiered, Time Windowed), you may be
able to have higher data density per node assuming that some of your data
is going into the no-longer-compacting stages.

Beyond that it'll be hard to say what the right size for you is.  Target
the recommended numbers and if you find that you're not running out of I/O
as you approach them you can probably go bigger.  Just remember to leave
~50% disk capacity free to leave room for compaction to happen.

On Fri, May 27, 2016 at 1:52 PM Anshu Vajpayee <anshu.vajpayee@gmail.com>
wrote:

> Hi All,
> I have question regarding max disk space limit  on a node.
>
> As per Data stax, We can have 1TB max disk space for rotational disks and
> up to 5 TB for SSDs on a node.
>
> Could you please suggest per your experience what would be limit for spac=
e
> on a single node with out causing so much stress on a  node?
>
>
>
>
>
> *=E2=80=8BThanks,=E2=80=8B*
>
>

--001a113d30b282d07005341073f5
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Those are rough guidelines, actual effective node size is =
going to depend on your read/write workload and the compaction strategy you=
 choose.=C2=A0 The biggest reason data density per node usually needs to be=
 limited is due to data grooming overhead introduced by compaction.=C2=A0 D=
ata at rest essentially becomes I/O debt.=C2=A0 If you&#39;re using Leveled=
 compaction, the interest rate on that debt is higher. =C2=A0<div><br></div=
><div>If you&#39;re writing aggressively you&#39;ll find that you run out o=
f I/O capacity for smaller data at rest.=C2=A0 If you use compaction strate=
gies that allow for data to eventually stop compacting (Date Tiered, Time W=
indowed), you may be able to have higher data density per node assuming tha=
t some of your data is going into the no-longer-compacting stages.</div><di=
v><br></div><div>Beyond that it&#39;ll be hard to say what the right size f=
or you is.=C2=A0 Target the recommended numbers and if you find that you=
9;re not running out of I/O as you approach them you can probably go bigger=
.=C2=A0 Just remember to leave ~50% disk capacity free to leave room for co=
mpaction to happen.</div></div><br><div class=3D"gmail_quote"><div dir=3D"l=
tr">On Fri, May 27, 2016 at 1:52 PM Anshu Vajpayee &lt;<a href=3D"mailto:an=
shu.vajpayee@gmail.com">anshu.vajpayee@gmail.com</a>&gt; wrote:<br></div><b=
lockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1px =
#ccc solid;padding-left:1ex"><div dir=3D"ltr"><div class=3D"gmail_default" =
style=3D"font-family:verdana,sans-serif">Hi All,</div><div class=3D"gmail_d=
efault" style=3D"font-family:verdana,sans-serif">I have question regarding =
max disk space limit =C2=A0on a node.</div><div class=3D"gmail_default" sty=
le=3D"font-family:verdana,sans-serif"><br></div><div class=3D"gmail_default=
" style=3D"font-family:verdana,sans-serif">As per Data stax, We can have 1T=
B max disk space for rotational disks and up to 5 TB for SSDs on a node.</d=
iv><div class=3D"gmail_default" style=3D"font-family:verdana,sans-serif"><b=
r></div><div class=3D"gmail_default" style=3D"font-family:verdana,sans-seri=
f">Could you please suggest per your experience what would be limit for spa=
ce on a single node with out causing so much stress on a =C2=A0node?=C2=A0<=
/div><div class=3D"gmail_default" style=3D"font-family:verdana,sans-serif">=
<br></div><div class=3D"gmail_default" style=3D"font-family:verdana,sans-se=
rif"><br></div><div class=3D"gmail_default" style=3D"font-family:verdana,sa=
ns-serif"><br></div><div><br></div><div data-smartmail=3D"gmail_signature">=
<div dir=3D"ltr"><div><font face=3D"verdana, sans-serif"><b><div class=3D"g=
mail_default" style=3D"font-family:verdana,sans-serif;display:inline">=E2=
=80=8BThanks,=E2=80=8B</div><br></b></font><div><div><span style=3D"font-si=
ze:13px;border-collapse:collapse;color:rgb(136,136,136)"></span><br></div><=
/div></div></div></div>
</div>
</blockquote></div>

--001a113d30b282d07005341073f5--