Hi Viktor, On 23/05/18 01:45, Viktor Dukhovni via Unbound-users wrote: > > I have 8 threads configured, anyone know why unbound would > do all the work in just one thread?
Previously people that asked this, had a usage that one thread could satisfy. Perhaps the other cpu cores are running some other process. It it the systems scheduler for delivering packets to the listening network socket that determines which thread gets the content. so-reuseport: yes reportedly improves distribution between threads on Linux. Best regards, Wouter > > Build info: > > # /usr/local/sbin/unbound -h > [...] > Version 1.7.1 > linked libs: libevent 2.1.8-stable (it uses kqueue), OpenSSL 1.0.2o 27 Mar > 2018 > linked modules: dns64 respip validator iterator > [...] > > Configuration below my signature, stats below (the machine is > running the DANE adoption survey, so yes, ~3.5 billion queries with > a low cache hit rate is right): > > # /usr/local/sbin/unbound-control stats_noreset | egrep -v '=0$' > thread0.recursion.time.avg=0.000000 > thread1.recursion.time.avg=0.000000 > thread2.recursion.time.avg=0.000000 > thread3.recursion.time.avg=0.000000 > thread4.recursion.time.avg=0.000000 > thread5.recursion.time.avg=0.000000 > thread6.recursion.time.avg=0.000000 > thread7.num.queries=3478975092 > thread7.num.cachehits=1422530 > thread7.num.cachemiss=3477552562 > thread7.num.recursivereplies=3477552317 > thread7.requestlist.avg=257.029 > thread7.requestlist.max=1266 > thread7.requestlist.current.all=245 > thread7.requestlist.current.user=245 > thread7.recursion.time.avg=0.220082 > thread7.recursion.time.median=0.0963222 > total.num.queries=3478975092 > total.num.cachehits=1422530 > total.num.cachemiss=3477552562 > total.num.recursivereplies=3477552317 > total.requestlist.avg=257.029 > total.requestlist.max=1266 > total.requestlist.current.all=245 > total.requestlist.current.user=245 > total.recursion.time.avg=0.220082 > total.recursion.time.median=0.0120403 >
signature.asc
Description: OpenPGP digital signature
