<html><head></head><body>Hi David,<br>
<br>
We are aware of this. 3.4 will have a fix for this. Thank you for your very complete report!<br>
<br>
Peter<br>
-- <br>
Sent from my Android phone with K-9 Mail. Please excuse my brevity.<br><br><div class="gmail_quote">"GAVARRET, David" <david.gavarret@sfr.com> wrote:<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<pre style="white-space: pre-wrap; word-wrap:break-word; font-family: monospace">Hello,<br /><br />we have just upgraded some more production servers with version 3.4-pre of pdns_recursor.<br />Over time (in our case, after about 18 hours), reading of statistics via the command "rec_control get-all" takes more and more time, up to 5 seconds. These 5 seconds also seem to be a timeout limit, and so when it is reached, the command fails with the following error :<br />" Fatal: Unable to receive message over control channel: Success " <br /><br />In the log file, the message is a bit longer :<br />" Error dealing with control socket request: Unable to send message over control channel '/var/run/powerdns//lsockcaf2V2': No such file or directory "<br /><br />With version 3.3, statistics are always returned within 10 ms, even after hundreds of days running.<br />The settings are identical on the servers running 3.3 and servers running 3.4 version. The CPU and load average are also q
uite
the same.<br /><br />It seems that the "cache-bytes" statistic is the one taking so much time. Here is the measure time for getting each statistic with unitary command "rec_control get" :<br /><br />$ for id in `sudo rec_control --socket-dir=/var/run/powerdns/ get-all | cut -f 1`; do echo "$id : " ; time sudo rec_control --socket-dir=/var/run/powerdns/ get $id ; done<br />all-outqueries :<br />41460979<br /><br />real 0m0.007s<br />user 0m0.000s<br />sys 0m0.000s<br />dlg-only-drops :<br />0<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />dont-outqueries :<br />151500<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.000s<br />max-mthread-stack :<br />36264<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.004s<br />outgoing-timeouts :<br />1776957<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.000s<br />tcp-outqueries :<br />49713<br /><br />real 0m0.006s<br />user 0m0.004s<br
/>sys
0m0.004s<br />throttled-out :<br />418136<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />throttled-outqueries :<br />418136<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.004s<br />unreachables :<br />226341<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />answers-slow :<br />899924<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.004s<br />answers0-1 :<br />17180424<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.000s<br />answers1-10 :<br />8097358<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.004s<br />answers10-100 :<br />12337003<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.004s<br />answers100-1000 :<br />8438958<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />case-mismatches :<br />0<br /><br />real 0m0.005s<br />user 0m0.000s<br />sys 0m0.008s<br />chain-resends :<br />150
757<br
/><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.000s<br />client-parse-errors :<br />23334<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />edns-ping-matches :<br />0<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />edns-ping-mismatches :<br />0<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br />ipv6-outqueries :<br />0<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br />no-packet-error :<br />146612428<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br />noedns-outqueries :<br />41506921<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.008s<br />noerror-answers :<br />251917785<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />noping-outqueries :<br />0<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />nsset-invalidations :<br />84551<br /><br />real 0m0.00
6s<br
/>user 0m0.000s<br />sys 0m0.008s<br />nxdomain-answers :<br />12293232<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.008s<br />over-capacity-drops :<br />0<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />qa-latency :<br />26<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.012s<br />questions :<br />267200911<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br />resource-limits :<br />1<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.008s<br />server-parse-errors :<br />2<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br />servfail-answers :<br />2964254<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.008s<br />spoof-prevents :<br />0<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.000s<br />tcp-client-overflow :<br />0<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br
/>tcp-questions :<br />11471<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.004s<br />unauthorized-tcp :<br />0<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br />unauthorized-udp :<br />0<br /><br />real 0m0.005s<br />user 0m0.000s<br />sys 0m0.008s<br />unexpected-packets :<br />183889<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />cache-bytes :<br />1467740916<br /><br />real 0m4.875s <<<<<<<br />user 0m0.000s<br />sys 0m0.008s<br />cache-entries :<br />12811541<br /><br />real 0m0.009s<br />user 0m0.004s<br />sys 0m0.000s<br />cache-hits :<br />16743327<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.008s<br />cache-misses :<br />30214506<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />concurrent-queries :<br />111<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />malloc-bytes
:<br
/>0<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />negcache-entries :<br />1600262<br /><br />real 0m0.007s<br />user 0m0.000s<br />sys 0m0.008s<br />nsspeeds-entries :<br />48068<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />packetcache-bytes :<br />53881659<br /><br />real 0m0.119s<br />user 0m0.000s<br />sys 0m0.004s<br />packetcache-entries :<br />502387<br /><br />real 0m0.006s<br />user 0m0.000s<br />sys 0m0.004s<br />packetcache-hits :<br />220244614<br /><br />real 0m0.005s<br />user 0m0.000s<br />sys 0m0.004s<br />packetcache-misses :<br />46970437<br /><br />real 0m0.006s<br />user 0m0.004s<br />sys 0m0.000s<br />sys-msec :<br />8463024<br /><br />real 0m0.005s<br />user 0m0.000s<br />sys 0m0.004s<br />tcp-clients :<br />0<br /><br />real 0m0.005s<br />user 0m0.004s<br />sys 0m0.000s<br />throttle-entries :<br />14957<br /><br />real
0m0.005s<br />user 0m0.004s<br />sys 0m0.000s<br />uptime :<br />64397<br /><br />real 0m0.005s<br />user 0m0.000s<br />sys 0m0.004s<br />user-msec :<br />20958557<br /><br />real 0m0.005s<br />user 0m0.008s<br />sys 0m0.000s<br /><br /><br /><br />Here is our recursor.conf file:<br /><br />setuid=20100<br />setgid=20100<br />socket-owner=pdns<br />socket-group=pdns<br />socket-mode=770<br />socket-dir=/var/run/powerdns<br />allow-from-file=/etc/powerdns/dns-resolver-allow-from<br />forward-zones-file=/etc/powerdns/dns-resolver-forward-zones<br />local-address=...<br />max-cache-entries=16000000<br />stack-size=250000<br />threads=4<br />logging-facility=0<br />version-string=3.4-pre<br /><br />I can provide any other information if needed,<br /><br />Kind Regards,<br /><br />-- <br />David Gavarret<br /><hr /><br />Pdns-users mailing list<br />Pdns-users@mailman.powerdns.com<br /><a
href="http://mailman.powerdns.com/mailman/listinfo/pdns-users">http://mailman.powerdns.com/mailman/listinfo/pdns-users</a><br /></pre></blockquote></div></body></html>