On Sun, 16 Sep 2007, Joerg Delker wrote:
> Hi Joseph,
>
> thanks for your reply.
>
> Although I didn't expect much from your hint, I was really surprised to
> find out, that the firewall *was* cause for this!
get lvs to work first, then add the firewall rules.
> I was unaware of the fact, that L
Hi Joseph,
thanks for your reply.
Although I didn't expect much from your hint, I was really surprised to
find out, that the firewall *was* cause for this!
I was unaware of the fact, that LVS traffic obviously is not subject to
iptables connection tracking and thus doesn't match any ESTABLISHED
On Fri, 14 Sep 2007, Joerg Delker wrote:
> Hi Folks,
>
> I just found this thread in the archives describing my problem.
> So let me tune in so we hopefully can find that bummer.
>
> Symptoms:
> I'm also suffering from very slow connections via the VIPs in contrast to
> accessing the real servers
Hi Folks,
I just found this thread in the archives describing my problem.
So let me tune in so we hopefully can find that bummer.
Symptoms:
I'm also suffering from very slow connections via the VIPs in contrast
to accessing the real servers directly. A wget fetch from a particular
web takes
On Tue, 7 Aug 2007, Dan Baughman wrote:
> Does lvs appropriately forward the 'fragmentation needed' icmp requests back
> to the servers?
do you mean to the client?
No. Linux seems to be the main problem here (it's in the
HOWTO). LVS doesn't fix it. You have to handle it by setting
the mss valu
Does lvs appropriately forward the 'fragmentation needed' icmp requests back
to the servers? Unfortunately I bypassed the load balancer for a quick
solution, in lue of trying more fixes.
On 8/3/07, Joseph Mack NA3T <[EMAIL PROTECTED]> wrote:
>
> On Fri, 3 Aug 2007, Graeme Fowler wrote:
>
> > Try
On Fri, 3 Aug 2007, Graeme Fowler wrote:
> Try tuning your MTU down on both the W2K3 servers *and* the director so
> they're all 400 (you'll have to look up how to do this for your distro,
> but it usually isn't hard).
it's in the LVS-Tun section of the HOWTO
Joe
--
Joseph Mack NA3T EME(B,D), FM
Ok I'll need some time to work through some of these suggestions and report
results. I'll keep ya posted. thx for the suggsetions.
On 8/3/07, Graeme Fowler <[EMAIL PROTECTED]> wrote:
>
> On Fri, 2007-08-03 at 15:16 -0600, Dan Baughman wrote:
> > One, physically separate load balancer. (ubuntu 6.06
On Fri, 2007-08-03 at 15:16 -0600, Dan Baughman wrote:
> One, physically separate load balancer. (ubuntu 6.06). Two physically
> separate real servers. This is all brand spanking new, high end intel
> hardware. Running DR ( with the loopback adapater on the 2k3 servers).
Aha... a thought comes t
On Fri, 3 Aug 2007, Dan Baughman wrote:
> The more hops out
the further away the client, the worse the problem?
> the more the issue presents itself. I am trying to by
> pass the loadbalancer in the problem case to see if it is even the issue.
>>> Just to follow up on this, the packet loss app
One, physically separate load balancer. (ubuntu 6.06). Two physically
separate real servers. This is all brand spanking new, high end intel
hardware. Running DR ( with the loopback adapater on the 2k3 servers).
The real servers are using the same physical interface to respond to the
load balance
On Fri, 2007-08-03 at 09:17 -0600, Dan Baughman wrote:
> Just to follow up on this, the packet loss appeared to be an unrelated
> issue. If I connect directly to a realserver, the page loads fairly fast.
> If I connect through the loadbalancer ( and get the same real server) I see
> a lot of tcp r
Just to follow up on this, the packet loss appeared to be an unrelated
issue. If I connect directly to a realserver, the page loads fairly fast.
If I connect through the loadbalancer ( and get the same real server) I see
a lot of tcp retranmissions and such (as sniffed from the real server). I
can
Well we are getting 1 - 5% packet loss to one of the real servers. We may
have a layer 2 issue here, or perhaps something physical I'll let you know
what we turn up. Thanks for your time and suggestions.
On 8/1/07, Joseph Mack NA3T <[EMAIL PROTECTED]> wrote:
>
> On Wed, 1 Aug 2007, Dan Baughman w
On Wed, 1 Aug 2007, Dan Baughman wrote:
> Thanks for the suggestions so far, here is what the dumps yielded.
>
> I'm using ethereal to look at a side-by-side comparison of
> a healthy conversation and one of the delayed
> conversations. The delayed conversation has two tcp
> packet types that
I guess it might be a version issue, 'ivsadm -v' yields:
ipvsadm v1.24 2003/06/07 (compiled with popt and IPVS v1.2.0)
On 8/1/07, Dan Baughman <[EMAIL PROTECTED]> wrote:
>
> Thanks for the suggestions so far, here is what the dumps yielded.
>
> I'm using ethereal to look at a side-by-side compa
Thanks for the suggestions so far, here is what the dumps yielded.
I'm using ethereal to look at a side-by-side comparison of a healthy
conversation and one of the delayed conversations. The
delayed conversation has two tcp packet types that the normal conversation
doesn't:
1) A lot
Gerry Reno wrote:
> Dan Baughman wrote:
>
>> I am trying to gather a sniffing session from both of my sides of the
>> connection now. So far, they have both been comcast users.
>>
>> On 7/31/07, Joseph Mack NA3T <[EMAIL PROTECTED]> wrote:
>>
>>
>>> On Tue, 31 Jul 2007, Dan Baughman wrote
Dan Baughman wrote:
> I am trying to gather a sniffing session from both of my sides of the
> connection now. So far, they have both been comcast users.
>
> On 7/31/07, Joseph Mack NA3T <[EMAIL PROTECTED]> wrote:
>
>> On Tue, 31 Jul 2007, Dan Baughman wrote:
>>
>>
>>> There are some users t
I am trying to gather a sniffing session from both of my sides of the
connection now. So far, they have both been comcast users.
On 7/31/07, Joseph Mack NA3T <[EMAIL PROTECTED]> wrote:
>
> On Tue, 31 Jul 2007, Dan Baughman wrote:
>
> > There are some users that when acessing my page through
> > th
On Tue, 31 Jul 2007, Dan Baughman wrote:
> There are some users that when acessing my page through
> the load balancer experience a 45 second load time, but
> when going directly to either server takes only ten
> seconds. I'm doing one nic, two network type load
> balancing. (we have one loadb
There are some users that when acessing my page through the load balancer
experience a 45 second load time, but when going directly to either server
takes only ten seconds. I'm doing one nic, two network type load balancing.
(we have one loadbalancer and two real servers)
Again, accessing either s
22 matches
Mail list logo
