keepalived high cpu usage / Vyatta VC6.2 / many VLANs with VRRP

Aitor Ibarra <[email protected]> Tue, 10 May 2011 17:26:03 +0100
Newsgroups gmane.linux.keepalived.announce
Message-ID <C06E537F3FC8644AB284935CEA557B240213E988F8D1@VMHOTEL-SBS2008.vmhotelltd.local>
--===============1170031708484561369==
Content-Language: en-US
Content-Type: multipart/alternative;
	boundary="_000_C06E537F3FC8644AB284935CEA557B240213E988F8D1VMHOTELSBS2_"

--_000_C06E537F3FC8644AB284935CEA557B240213E988F8D1VMHOTELSBS2_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

Hi,

I'm running into a cpu usage issue with keepalived as included in Vyatta VC=
6.2 - wondering if this has been addressed with more recent releases not ye=
t integrated into Vyatta... I'm an absolute newbie when it comes to both VR=
RP and Vyatta, so please forgive any naivety.

Basically, the more VLANs I set up (each running a subnet with a VRRP insta=
nce) the longer keepalived (the parent process) spends at a high CPU level.=
 Keepalived seems to be single threaded, and with about 500 VLANs on a 1.8G=
Hz quad core xeon, I see keepalived run at about 70% of a core for several =
minutes until the VRRP virtual ips for all the subnets come up. If I push i=
t to 1000 VLANs, it stays stuck at 100% and the virtual ips NEVER come up. =
Is it just plain unrealistic to run so many instances? What's the largest n=
umber of VRRP instances tested?

The VLANS are running on a bonded pair of Ethernet interfaces. I can run wi=
th no VRRP without issue (and neglible CPU usage), but I need an HA solutio=
n.

Thanks,

Aitor

--_000_C06E537F3FC8644AB284935CEA557B240213E988F8D1VMHOTELSBS2_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:=
//www.w3.org/TR/REC-html40"><head><meta http-equiv=3DContent-Type content=
=3D"text/html; charset=3Dus-ascii"><meta name=3DGenerator content=3D"Micros=
oft Word 12 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
	{font-family:"Cambria Math";
	panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
	{font-family:Calibri;
	panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
	{font-family:Tahoma;
	panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0cm;
	margin-bottom:.0001pt;
	font-size:11.0pt;
	font-family:"Calibri","sans-serif";}
a:link, span.MsoHyperlink
	{mso-style-priority:99;
	color:blue;
	text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
	{mso-style-priority:99;
	color:purple;
	text-decoration:underline;}
p.MsoAcetate, li.MsoAcetate, div.MsoAcetate
	{mso-style-priority:99;
	mso-style-link:"Balloon Text Char";
	margin:0cm;
	margin-bottom:.0001pt;
	font-size:8.0pt;
	font-family:"Tahoma","sans-serif";}
span.EmailStyle17
	{mso-style-type:personal-compose;
	font-family:"Calibri","sans-serif";
	color:windowtext;}
span.BalloonTextChar
	{mso-style-name:"Balloon Text Char";
	mso-style-priority:99;
	mso-style-link:"Balloon Text";
	font-family:"Tahoma","sans-serif";}
.MsoChpDefault
	{mso-style-type:export-only;}
@page WordSection1
	{size:612.0pt 792.0pt;
	margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
	{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext=3D"edit" spidmax=3D"1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext=3D"edit">
<o:idmap v:ext=3D"edit" data=3D"1" />
</o:shapelayout></xml><![endif]--></head><body lang=3DEN-GB link=3Dblue vli=
nk=3Dpurple><div class=3DWordSection1><p class=3DMsoNormal>Hi,<o:p></o:p></=
p><p class=3DMsoNormal><o:p>&nbsp;</o:p></p><p class=3DMsoNormal>I&#8217;m =
running into a cpu usage issue with keepalived as included in Vyatta VC6.2 =
&#8211; wondering if this has been addressed with more recent releases not =
yet integrated into Vyatta... I&#8217;m an absolute newbie when it comes to=
 both VRRP and Vyatta, so please forgive any naivety.<o:p></o:p></p><p clas=
s=3DMsoNormal><o:p>&nbsp;</o:p></p><p class=3DMsoNormal>Basically, the more=
 VLANs I set up (each running a subnet with a VRRP instance) the longer kee=
palived (the parent process) spends at a high CPU level. Keepalived seems t=
o be single threaded, and with about 500 VLANs on a 1.8GHz quad core xeon, =
I see keepalived run at about 70% of a core for several minutes until the V=
RRP virtual ips for all the subnets come up. If I push it to 1000 VLANs, it=
 stays stuck at 100% and the virtual ips NEVER come up. Is it just plain un=
realistic to run so many instances? What&#8217;s the largest number of VRRP=
 instances tested?<o:p></o:p></p><p class=3DMsoNormal><o:p>&nbsp;</o:p></p>=
<p class=3DMsoNormal>The VLANS are running on a bonded pair of Ethernet int=
erfaces. I can run with no VRRP without issue (and neglible CPU usage), but=
 I need an HA solution.<o:p></o:p></p><p class=3DMsoNormal><o:p>&nbsp;</o:p=
></p><p class=3DMsoNormal>Thanks,<o:p></o:p></p><p class=3DMsoNormal><o:p>&=
nbsp;</o:p></p><p class=3DMsoNormal>Aitor<o:p></o:p></p></div></body></html=
>=

--_000_C06E537F3FC8644AB284935CEA557B240213E988F8D1VMHOTELSBS2_--


--===============1170031708484561369==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

------------------------------------------------------------------------------
Achieve unprecedented app performance and reliability
What every C/C++ and Fortran developer should know.
Learn how Intel has extended the reach of its next-generation tools
to help boost performance applications - inlcuding clusters.
http://p.sf.net/sfu/intel-dev2devmay
--===============1170031708484561369==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Keepalived-announce mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/keepalived-announce

--===============1170031708484561369==--