<div dir="ltr"><div>Anand,</div><div><br></div>yeah. I capture stats every minute as well -- which profoundly aggravates the problem. Anything that forks -- nsd-control [reconfig|reload|stats], etc will trip on this. <div>
<br></div><div>have you confirmed that you have an affected kernel? I can send you the test program we used to spot the issue, if you like...</div><div><br></div><div>WBSP</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">
On Tue, Aug 5, 2014 at 1:45 AM, Anand Buddhdev <span dir="ltr"><<a href="mailto:anandb@ripe.net" target="_blank">anandb@ripe.net</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="">On 05/08/2014 10:24, Will Pressly wrote:<br>
<br>
> addendum:<br>
> 1. this problem apparently started with 2.6.34.<br>
> 2. In my last line that should have read: " but we definitely have to<br>
</div>> periodically *restart* NSD until this issue is addressed."<br>
<br>
Very interesting. We have the exact same issue, and our symptoms are<br>
also the same. We periodically have to restart NSD to alleviate server<br>
load. Wouter Wijngaards and I have been trying to find the problem for<br>
ages, and we both thought it was in NSD. I've been trying various<br>
patches he made, but nothing has helped, and now it seems clear why,<br>
because the bug isn't in NSD. Of course, NSD's frequent forking probably<br>
makes this worse, and on our server with several thousand zones, the<br>
zone refresh rate is quite high.<br>
<span class="HOEnZb"><font color="#888888"><br>
Anand<br>
</font></span></blockquote></div><br></div>