(unknown)

Florian Schmid via Toasters <[email protected]> Tue, 17 Oct 2023 13:54:06 +0100
Newsgroups gmane.comp.hardware.netapp
Message-ID <[email protected]>
--===============8480934701629227772==
Content-Type: message/rfc822
Content-Disposition: inline

Received: from mx2-at.ubimet.com (mx2-at.ubimet.com [141.98.226.72])
 by dormouse.teaparty.net (8.14.7/8.14.7) with ESMTP id 39HCs0DA005584
 (version=TLSv1/SSLv3 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO)
 for <[email protected]>; Tue, 17 Oct 2023 13:54:02 +0100
Authentication-Results: dormouse.teaparty.net;
 spf=pass [email protected]
 smtp.helo=mx2-at.ubimet.com
Received: from localhost (localhost [127.0.0.1])
 by mx2-at.ubimet.com (Postfix) with ESMTP id C68F0815EA;
 Tue, 17 Oct 2023 12:53:59 +0000 (UTC)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=ubimet.com;
 s=20200131mdel; t=1697547239;
 bh=ocrzPc+hqHvBXJ/xS4InEPXtb+ERFg0YpbAo9ewvBVk=;
 h=Date:From:To:Cc:In-Reply-To:References:Subject:From;
 b=EevqHx1DweAYasKqN9I6HRJvKtLdSLcWFsp73hwtNbSlFCwdAe+bUkgnpGD2MrEn0
 uhG4aVWtk4KTlkM6Tda/ewm6hbPZx9mTGxwMoU+fLzaleJ1npqkNN1/KDSfQ4hVbAs
 R313oBq9abVI3XSeU6hJhvdLNJ3rKg2deQkEe1JWvUpyz4ntiI7Gf6oebvm6eIrZDa
 GHnuuxxp0XGraaihYIXWZHwbwYcO+bGAzcQC0k44w5wgiuzRoaPpsgumD+J8PcmUqU
 U3CnJJXvkDGsxfJbFQuhyqxJvwcGNiM9StSeVf4hSA48u3EmcSz4Bp4kdafXuX02sv
 sLJ+jqJYQlsYw==
Received: from mx2-at.ubimet.com ([127.0.0.1])
 by localhost (mx02.dmz.dc.at.ubimet.com [127.0.0.1]) (amavisd-new, port 10024)
 with ESMTP id J2WvD0oU3Ka3; Tue, 17 Oct 2023 12:53:59 +0000 (UTC)
Received: from zimbra-mta01.ext.dc.at.ubimet.com (webmail-dc.at.ubimet.com
 [10.1.18.22])
 by mx2-at.ubimet.com (Postfix) with ESMTPS id B482E815E8;
 Tue, 17 Oct 2023 12:53:59 +0000 (UTC)
Received: from localhost (localhost [127.0.0.1])
 by zimbra-mta01.ext.dc.at.ubimet.com (Postfix) with ESMTP id ACDC080621;
 Tue, 17 Oct 2023 12:53:59 +0000 (UTC)
Received: from zimbra-mta01.ext.dc.at.ubimet.com ([127.0.0.1])
 by localhost (zimbra-mta01.ext.dc.at.ubimet.com [127.0.0.1]) (amavis,
 port 10032)
 with ESMTP id F_GKujyQ9mLP; Tue, 17 Oct 2023 12:53:57 +0000 (UTC)
Received: from localhost (localhost [127.0.0.1])
 by zimbra-mta01.ext.dc.at.ubimet.com (Postfix) with ESMTP id 694178050A;
 Tue, 17 Oct 2023 12:53:57 +0000 (UTC)
X-Virus-Scanned: amavis at zimbra-mta01.ext.dc.at.ubimet.com
Received: from zimbra-mta01.ext.dc.at.ubimet.com ([127.0.0.1])
 by localhost (zimbra-mta01.ext.dc.at.ubimet.com [127.0.0.1]) (amavis,
 port 10026)
 with ESMTP id G6dP8EUpzeqA; Tue, 17 Oct 2023 12:53:57 +0000 (UTC)
Received: from zimbra-store02.ext.dc.at.ubimet.com
 (zimbra-store02.ext.dc.at.ubimet.com [10.1.18.23])
 by zimbra-mta01.ext.dc.at.ubimet.com (Postfix) with ESMTP id 45A4880621;
 Tue, 17 Oct 2023 12:53:57 +0000 (UTC)
Date: Tue, 17 Oct 2023 12:53:57 +0000 (UTC)
From: Florian Schmid <[email protected]>
To: "Gislen, Johan" <[email protected]>
Cc: toasters <[email protected]>
Message-ID: <[email protected]>
In-Reply-To: <BYAPR06MB4678C67F27F1647FAA502A54FDD6A@BYAPR06MB4678.namprd06.prod.outlook.com>
References: <BYAPR06MB4678C67F27F1647FAA502A54FDD6A@BYAPR06MB4678.namprd06.prod.outlook.com>
Subject: Re: Question about flash pool maximum SSD size and local tiering
MIME-Version: 1.0
Content-Type: multipart/alternative; 
 boundary="=_7ba12491-e2be-4af7-8823-44c3ee644d03"
X-Originating-IP: [10.15.100.2]
X-Mailer: Zimbra 8.8.15_GA_4562 (ZimbraWebClient - GC117 (Linux)/8.8.15_GA_3)
Thread-Topic: Question about flash pool maximum SSD size and local tiering
Thread-Index: AQHaANFTSYWKFIomukCHnqu6Kg2ylXZfCQk9
X-Greylist: Recipient e-mail whitelisted, not delayed by milter-greylist-4.6.2
 (dormouse.teaparty.net [178.18.123.145]);
 Tue, 17 Oct 2023 13:54:03 +0100 (BST)

--=_7ba12491-e2be-4af7-8823-44c3ee644d03
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable

Hi Johan,=20

thank you very much for your help.=20

No, we don't have the disks yet for which the flash-pool should be used.=20
Not all SSDs will be used for flash-pool, only some for cache and the rest =
for fast SSD storage.=20

Regarding HWU, yes, I already thought that and I was hoping that NetApp jus=
t has only not added the bigger ones. But as you said, max is 72 TB and max=
 count is 20 for the 3.8 TB SSDs.=20

I have talked to our new partner and we will clarify this, when we have the=
 final offer.=20

Best regards,=20
Florian Schmid=20





Von: "Gislen, Johan" <[email protected]>=20
An: "Florian Schmid" <[email protected]>, "Sebastian Goetze" <spgoetze@gma=
il.com>, "Michael Fenn" <[email protected]>=20
CC: "toasters" <[email protected]>=20
Gesendet: Dienstag, 17. Oktober 2023 10:27:48=20
Betreff: Re: Re: Question about flash pool maximum SSD size and local tieri=
ng=20



Hi Florian,=20



If you have the NL-SAS aggregate in place already I=E2=80=99d recommend hav=
ing a look at using AWA to figure out what the optimal cache size would be:=
=20

[ https://docs.netapp.com/us-en/ontap/disks-aggregates/determine-flash-pool=
-candidacy-cache-size-task.html | https://docs.netapp.com/us-en/ontap/disks=
-aggregates/determine-flash-pool-candidacy-cache-size-task.html ]=20



That would give you an idea of how much Flash Pool capacity you=E2=80=99d r=
eally benefit from.=20



Regarding 3.8TB vs 7.6 TB =E2=80=93 if the 7.6 TB drives are not listed as =
supported in the HWU, it=E2=80=99s most likely not supported.=20



There=E2=80=99s also a note in the HWU for the 3.8TB drives under =E2=80=9C=
System Cache Limits=E2=80=9D =E2=80=93 =E2=80=9CMax number of Flash Pool Da=
ta SSDs: 20=E2=80=9D (this is excluding RAID parity & hot spares) =E2=80=93=
 if I=E2=80=99m intepreting that note correcly there=E2=80=99d be no point =
in adding more than one shelf of 3.8TB drives.=20



Regards, Johan=20





On 2023-10-17, 09:57, "Florian Schmid" <[email protected]> wrote:=20


Hi Sebastian and Michael,=20





thank you very much for your help.=20





We haven't bought the SSD shelves yet.=20


We don't know, if we should take 2 shelves with 3.8 TB or 1 shelf with 7.6 =
TB.=20


I tend to one shelf with 7.6 TB...=20





We are using flash-pool already with Raid-4, exactly for saving space.=20


My problem is now, that I'm concerned about the HWU statement, that there i=
s no SSD listed for using in flash-pool over 3.8 TB.=20


This let me think, that flash-pool is not supported for SSD with 7.6 TB or =
greater.=20





I haven't found anything else about it on NetApp site, only in the HWU for =
system cache limits for FAS 8300=20


Same limits are also for 8700 or 9000 series, no difference here.=20





Really strange.=20





Best regards,=20


Florian=20








----- Urspr=C3=BCngliche Mail -----=20


Von: "Sebastian Goetze" < [ mailto:[email protected] | [email protected] =
] >=20


An: "toasters" < [ mailto:[email protected] | [email protected] ] >=
=20


Gesendet: Montag, 16. Oktober 2023 15:35:36=20


Betreff: Re: Question about flash pool maximum SSD size and local tiering=
=20





Hi Florian,=20








On 16.10.2023 15:01, Fenn, Michael wrote:=20


> FlashPool SSDs (unlike FlashCache) are attached to aggregates as normal R=
AID groups, so you can use as many 3.8 TB drives in RAID-DP as you like to =
hit the maximum FlashPool capacity.=20





Consider using RAID4 for the SSD RaidGroups... More Cache, and for the=20


Write-cached blocks, not really less safety. (SSDs are more reliable,=20


blocks are usually written fairly soon to HDD anyway)=20





Regarding sizes: any size that's supported for the HW should be fine=20


(3.8/15.3TB). Within the Cache-RG, you should use the same size disks,=20


however...=20








>=20


> Note that FlashPool and FabricPool use the same underlying tiering metada=
ta structures, so you can only have one or the other enabled on any given a=
ggregate.=20


>=20


> Thanks,=20


> Michael=20


>=20


> On 10/16/23, 8:03 AM, "Toasters on behalf of Florian Schmid via Toasters"=
 < [ mailto:[email protected] | [email protected] ]=
 <mailto: [ mailto:[email protected] | toasters-bounces@teapart=
y.net ] > on behalf of [ mailto:[email protected] | [email protected]=
et ] <mailto: [ mailto:[email protected] | [email protected] ] >> w=
rote:=20


>=20


>=20


> Hi Alexander,=20


>=20


> this is a very good tip! Tank you very much.=20


> I will have a look on this.=20


>=20


> Best regards,=20


> Florian=20


>=20


> ----- Urspr=C3=BCngliche Mail -----=20


> Von: "Alexander Griesser" < [ mailto:[email protected] | AGriesser@ane=
xia.com ] >=20


> An: "Florian Schmid" < [ mailto:[email protected] | [email protected] ]=
 >, "toasters" < [ mailto:[email protected] | [email protected] ] >=
=20


> Gesendet: Montag, 16. Oktober 2023 12:07:53=20


> Betreff: AW: Question about flash pool maximum SSD size and local tiering=
=20


>=20


> Hi Florian,=20


>=20


> I cannot answer the question with the SSD sizes, I'm not sure if this is =
really a hard requirement or if the slices just may not be bigger than 3.8T=
B (in that case, you could probably manually partition the SSDs), maybe som=
eone else has more insights into this.=20


>=20


> As for your second question: You can spin up OnTap's integrated S3 server=
 on your old boxes and use them as fabric pool targets:=20


> [ https://www.netapp.com/media/17219-tr4814.pdf | https://www.netapp.com/=
media/17219-tr4814.pdf ]=20


>=20


> Best,=20


>=20


> Alexander Griesser=20


> Head of Systems Operations=20


>=20


> ANEXIA Internetdienstleistungs GmbH=20


>=20


> E-Mail: [ mailto:[email protected] | [email protected] ]=20


> Web: [ https://www.anexia.com/ | https://www.anexia.com ]=20


>=20


> Anschrift Hauptsitz Klagenfurt: Feldkirchnerstra=C3=9Fe 140, 9020 Klagenf=
urt=20


> Gesch=C3=A4ftsf=C3=BChrer: Alexander Windbichler=20


> Firmenbuch: FN 289918a | Gerichtsstand: Klagenfurt | UID-Nummer: AT U6321=
6601=20


>=20


> -----Urspr=C3=BCngliche Nachricht-----=20


> Von: Florian Schmid < [ mailto:[email protected] | [email protected] ] =
>=20


> Gesendet: Montag, 16. Oktober 2023 11:53=20


> An: [ mailto:[email protected] | [email protected] ]=20


> Betreff: Question about flash pool maximum SSD size and local tiering=20


>=20


> Hi,=20


>=20


> I have checked NetApp HWU for a FAS 8300 and system cache limits.=20


>=20


> Ok, so far, max flash-pool is 72 TB, which is a way more than I want to u=
se, but I haven't seen usable SSDs greater than 3.8 TB.=20


>=20


> Is that really true, that I can't use a 7.6 TB or 15.3 TB SSD for flash-p=
ool?=20


>=20


> It would be nice, if someone has here a deeper understanding than I have =
about this and can give me here some clarifications.=20


>=20


> May I ask a second question?=20


> Is flash-pool still the way to go for speeding up NL-SAS aggregates?=20


> I had a look on fabric-pool tiering, but it seems like, that this only wo=
rks to S3 storage, which we don't have.=20


> We have plenty of NL-SAS storage and also of SSDs and it would be great t=
o have a tiering between them or at least use them for caching.=20


>=20


> Best regards,=20


> Florian=20


>=20


>=20


>=20


> _______________________________________________=20


> Toasters mailing list=20


> [ mailto:[email protected] | [email protected] ]=20


> [ https://www.teaparty.net/mailman/listinfo/toasters |=20
https://www.teaparty.net/mailman/listinfo/toasters ]=20


_______________________________________________=20


Toasters mailing list=20


[ mailto:[email protected] | [email protected] ]=20


[ https://www.teaparty.net/mailman/listinfo/toasters | https://www.teaparty=
.net/mailman/listinfo/toasters ]=20








--=_7ba12491-e2be-4af7-8823-44c3ee644d03
Content-Type: text/html; charset=utf-8
Content-Transfer-Encoding: quoted-printable

<html><body><div style=3D"font-family: arial, helvetica, sans-serif; font-s=
ize: 12pt; color: #000000"><div>Hi Johan,</div><div><br data-mce-bogus=3D"1=
"></div><div>thank you very much for your help.</div><div><br data-mce-bogu=
s=3D"1"></div><div>No, we don't have the disks yet for which the flash-pool=
 should be used.</div><div>Not all SSDs will be used for flash-pool, only s=
ome for cache and the rest for fast SSD storage.</div><div><br data-mce-bog=
us=3D"1"></div><div>Regarding HWU, yes, I already thought that and I was ho=
ping that NetApp just has only not added the bigger ones. But as you said, =
max is 72 TB and max count is 20 for the 3.8 TB SSDs.</div><div><br data-mc=
e-bogus=3D"1"></div><div>I have talked to our new partner and we will clari=
fy this, when we have the final offer.</div><div><br data-mce-bogus=3D"1"><=
/div><div>Best regards,</div><div>Florian Schmid</div><div data-marker=3D"_=
_SIG_PRE__"><div><p style=3D"margin-bottom: 0cm;"><br></p></div></div><div>=
<br></div><hr id=3D"zwchr" data-marker=3D"__DIVIDER__"><div data-marker=3D"=
__HEADERS__"><b>Von: </b>"Gislen, Johan" &lt;[email protected]&gt;<br=
><b>An: </b>"Florian Schmid" &lt;[email protected]&gt;, "Sebastian Goetze"=
 &lt;[email protected]&gt;, "Michael Fenn" &lt;Michael.Fenn@DEShawResearch=
.com&gt;<br><b>CC: </b>"toasters" &lt;[email protected]&gt;<br><b>Gesen=
det: </b>Dienstag, 17. Oktober 2023 10:27:48<br><b>Betreff: </b>Re: Re: Que=
stion about flash pool maximum SSD size and local tiering<br></div><div><br=
><style><!--

@font-face
=09{font-family:"Cambria Math";
=09panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
=09{font-family:Calibri;
=09panose-1:2 15 5 2 2 2 4 3 2 4;}

p.MsoNormal, li.MsoNormal, div.MsoNormal
=09{margin:0cm;
=09font-size:11.0pt;
=09font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
=09{mso-style-priority:99;
=09color:blue;
=09text-decoration:underline;}
span.EmailStyle18
=09{mso-style-type:personal-reply;
=09font-family:"Calibri",sans-serif;
=09color:windowtext;}
.MsoChpDefault
=09{mso-style-type:export-only;
=09font-size:10.0pt;
=09mso-ligatures:none;}
@page WordSection1
=09{size:612.0pt 792.0pt;
=09margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
=09{page:WordSection1;}
--></style></div><div data-marker=3D"__QUOTED_TEXT__">






<div class=3D"WordSection1">
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">Hi Florian,</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">&nbsp;</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">If you have the NL-SAS aggregate in place already I=E2=80=99d recomme=
nd having a look at using AWA to figure out what the optimal cache size wou=
ld be:</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US"><a href=3D"https://docs.netapp.com/us-en/ontap/disks-aggregates/deter=
mine-flash-pool-candidacy-cache-size-task.html" target=3D"_blank">https://d=
ocs.netapp.com/us-en/ontap/disks-aggregates/determine-flash-pool-candidacy-=
cache-size-task.html</a></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">&nbsp;</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">That would give you an idea of how much Flash Pool capacity you=E2=80=
=99d really benefit from.</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">&nbsp;</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">Regarding 3.8TB vs 7.6 TB =E2=80=93 if the 7.6 TB drives are not list=
ed as supported in the HWU, it=E2=80=99s most likely not supported.</span><=
/p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">&nbsp;</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">There=E2=80=99s also a note in the HWU for the 3.8TB drives under =E2=
=80=9CSystem Cache Limits=E2=80=9D &nbsp;=E2=80=93 =E2=80=9CMax number of F=
lash Pool Data SSDs: 20=E2=80=9D (this is excluding RAID parity &amp; hot s=
pares) =E2=80=93 if I=E2=80=99m intepreting
 that note correcly there=E2=80=99d be no point in adding more than one she=
lf of 3.8TB drives.</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">&nbsp;</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">Regards, Johan</span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"mso-fareast-language:E=
N-US">&nbsp;</span></p>
<p class=3D"MsoNormal"><span style=3D"mso-fareast-language:EN-US">&nbsp;</s=
pan></p>
<p class=3D"MsoNormal" style=3D"margin-bottom:12.0pt">On 2023-10-17, 09:57,=
 "Florian Schmid" &lt;[email protected]&gt; wrote:</p>
<div>
<p class=3D"MsoNormal">Hi Sebastian and Michael,</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">thank you very much for your help.</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">We haven't bought the SSD shelves yet.</p>
</div>
<div>
<p class=3D"MsoNormal">We don't know, if we should take 2 shelves with 3.8 =
TB or 1 shelf with 7.6 TB.</p>
</div>
<div>
<p class=3D"MsoNormal">I tend to one shelf with 7.6 TB...</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">We are using flash-pool already with Raid-4, exactly=
 for saving space.</p>
</div>
<div>
<p class=3D"MsoNormal">My problem is now, that I'm concerned about the HWU =
statement, that there is no SSD listed for using in flash-pool over 3.8 TB.=
</p>
</div>
<div>
<p class=3D"MsoNormal">This let me think, that flash-pool is not supported =
for SSD with 7.6 TB or greater.</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">I haven't found anything else about it on NetApp sit=
e, only in the HWU for system cache limits for FAS 8300</p>
</div>
<div>
<p class=3D"MsoNormal">Same limits are also for 8700 or 9000 series, no dif=
ference here.</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">Really strange.</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">Best regards,</p>
</div>
<div>
<p class=3D"MsoNormal">Florian</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">----- Urspr=C3=BCngliche Mail -----</p>
</div>
<div>
<p class=3D"MsoNormal">Von: "Sebastian Goetze" &lt;<a href=3D"mailto:spgoet=
[email protected]" target=3D"_blank">[email protected]</a>&gt;</p>
</div>
<div>
<p class=3D"MsoNormal">An: "toasters" &lt;<a href=3D"mailto:toasters@teapar=
ty.net" target=3D"_blank">[email protected]</a>&gt;</p>
</div>
<div>
<p class=3D"MsoNormal">Gesendet: Montag, 16. Oktober 2023 15:35:36</p>
</div>
<div>
<p class=3D"MsoNormal">Betreff: Re: Question about flash pool maximum SSD s=
ize and local tiering</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">Hi Florian,</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">On 16.10.2023 15:01, Fenn, Michael wrote:</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; FlashPool SSDs (unlike FlashCache) are attached=
 to aggregates as normal RAID groups, so you can use as many 3.8 TB drives =
in RAID-DP as you like to hit the maximum FlashPool capacity.</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">Consider using RAID4 for the SSD RaidGroups... More =
Cache, and for the
</p>
</div>
<div>
<p class=3D"MsoNormal">Write-cached blocks, not really less safety. (SSDs a=
re more reliable,
</p>
</div>
<div>
<p class=3D"MsoNormal">blocks are usually written fairly soon to HDD anyway=
)</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">Regarding sizes: any size that's supported for the H=
W should be fine
</p>
</div>
<div>
<p class=3D"MsoNormal">(3.8/15.3TB). Within the Cache-RG, you should use th=
e same size disks,
</p>
</div>
<div>
<p class=3D"MsoNormal">however...</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Note that FlashPool and FabricPool use the same=
 underlying tiering metadata structures, so you can only have one or the ot=
her enabled on any given aggregate.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Thanks,</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Michael</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; On 10/16/23, 8:03 AM, "Toasters on behalf of Fl=
orian Schmid via Toasters" &lt;<a href=3D"mailto:toasters-bounces@teaparty.=
net" target=3D"_blank">[email protected]</a> &lt;mailto:<a href=
=3D"mailto:[email protected]" target=3D"_blank">toasters-bounce=
[email protected]</a>&gt;
 on behalf of <a href=3D"mailto:[email protected]" target=3D"_blank">to=
[email protected]</a> &lt;mailto:<a href=3D"mailto:[email protected]"=
 target=3D"_blank">[email protected]</a>&gt;&gt; wrote:</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Hi Alexander,</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; this is a very good tip! Tank you very much.</p=
>
</div>
<div>
<p class=3D"MsoNormal">&gt; I will have a look on this.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Best regards,</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Florian</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; ----- Urspr=C3=BCngliche Mail -----</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Von: "Alexander Griesser" &lt;<a href=3D"mailto=
:[email protected]" target=3D"_blank">[email protected]</a>&gt;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; An: "Florian Schmid" &lt;<a href=3D"mailto:fsch=
[email protected]" target=3D"_blank">[email protected]</a>&gt;, "toasters" &l=
t;<a href=3D"mailto:[email protected]" target=3D"_blank">toasters@teapa=
rty.net</a>&gt;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Gesendet: Montag, 16. Oktober 2023 12:07:53</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Betreff: AW: Question about flash pool maximum =
SSD size and local tiering</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Hi Florian,</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; I cannot answer the question with the SSD sizes=
, I'm not sure if this is really a hard requirement or if the slices just m=
ay not be bigger than 3.8TB (in that case, you could probably manually part=
ition the SSDs), maybe someone else has
 more insights into this.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; As for your second question: You can spin up On=
Tap's integrated S3 server on your old boxes and use them as fabric pool ta=
rgets:</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; <a href=3D"https://www.netapp.com/media/17219-t=
r4814.pdf" target=3D"_blank">https://www.netapp.com/media/17219-tr4814.pdf<=
/a></p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Best,</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Alexander Griesser</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Head of Systems Operations</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; ANEXIA Internetdienstleistungs GmbH</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; E-Mail: <a href=3D"mailto:[email protected]"=
 target=3D"_blank">[email protected]</a></p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Web: <a href=3D"https://www.anexia.com" target=
=3D"_blank">https://www.anexia.com</a></p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Anschrift Hauptsitz Klagenfurt: Feldkirchnerstr=
a=C3=9Fe 140, 9020 Klagenfurt</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Gesch=C3=A4ftsf=C3=BChrer: Alexander Windbichle=
r</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Firmenbuch: FN 289918a | Gerichtsstand: Klagenf=
urt | UID-Nummer: AT U63216601</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; -----Urspr=C3=BCngliche Nachricht-----</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Von: Florian Schmid &lt;<a href=3D"mailto:fschm=
[email protected]" target=3D"_blank">[email protected]</a>&gt;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Gesendet: Montag, 16. Oktober 2023 11:53</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; An: <a href=3D"mailto:[email protected]" ta=
rget=3D"_blank">[email protected]</a></p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Betreff: Question about flash pool maximum SSD =
size and local tiering</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Hi,</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; I have checked NetApp HWU for a FAS 8300 and sy=
stem cache limits.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Ok, so far, max flash-pool is 72 TB, which is a=
 way more than I want to use, but I haven't seen usable SSDs greater than 3=
.8 TB.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Is that really true, that I can't use a 7.6 TB =
or 15.3 TB SSD for flash-pool?</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; It would be nice, if someone has here a deeper =
understanding than I have about this and can give me here some clarificatio=
ns.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; May I ask a second question?</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Is flash-pool still the way to go for speeding =
up NL-SAS aggregates?</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; I had a look on fabric-pool tiering, but it see=
ms like, that this only works to S3 storage, which we don't have.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; We have plenty of NL-SAS storage and also of SS=
Ds and it would be great to have a tiering between them or at least use the=
m for caching.</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Best regards,</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Florian</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt;&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; _______________________________________________=
</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; Toasters mailing list</p>
</div>
<div>
<p class=3D"MsoNormal">&gt; <a href=3D"mailto:[email protected]" target=
=3D"_blank">[email protected]</a></p>
</div>
<div>
<p class=3D"MsoNormal">&gt; <a href=3D"https://www.teaparty.net/mailman/lis=
tinfo/toasters" target=3D"_blank">
https://www.teaparty.net/mailman/listinfo/toasters</a></p>
</div>
<div>
<p class=3D"MsoNormal">_______________________________________________</p>
</div>
<div>
<p class=3D"MsoNormal">Toasters mailing list</p>
</div>
<div>
<p class=3D"MsoNormal"><a href=3D"mailto:[email protected]" target=3D"_=
blank">[email protected]</a></p>
</div>
<div>
<p class=3D"MsoNormal"><a href=3D"https://www.teaparty.net/mailman/listinfo=
/toasters" target=3D"_blank">https://www.teaparty.net/mailman/listinfo/toas=
ters</a></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp;</p>
</div>
</div><br></div></div></body></html>
--=_7ba12491-e2be-4af7-8823-44c3ee644d03--

--===============8480934701629227772==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Toasters mailing list
[email protected]
https://www.teaparty.net/mailman/listinfo/toasters
--===============8480934701629227772==--