On Mon, 26 Mar 2001, Mihai RUSU wrote:
> On Mon, 26 Mar 2001, Matei Conovici wrote:
>
> > bind
> > ----
> >
> > Run Resolved Failed Queries/sec
> > 1 61063 4473 28.00
> > 2 61056 7 1221.00
> > 3 61049 0 1650.00
> > 4 61049 0 1650.00
> > 5 61049 0 1696.00
> > 6 61049 0 1650.00
> > 7 61049 0 1696.00
> > 8 61049 0 1696.00
> > 9 61049 0 1696.00
> > 10 61049 0 1650.00
> >
> > Average rate (all runs) : 1463.30 queries/sec
> > Average rate (error free runs): 1673.00 queries/sec
> >
> > dnscache
> > --------
> >
> > Run Resolved Failed Queries/sec
> > 1 64662 874 36.00
> > 2 64661 1 965.00
> > 3 64660 0 1026.00
> > 4 64660 0 979.00
> > 5 64660 0 1010.00
> > 6 64660 0 1010.00
> > 7 64660 0 979.00
> > 8 64660 0 950.00
> > 9 64660 0 950.00
> > 10 64658 2 702.00
> >
> > Average rate (all runs) : 860.70 queries/sec
> > Average rate (error free runs): 986.29 queries/sec
am mai citit odata mesajul mai atent si cred ca am o posibila explicatie.
precum vezi si la bind si la dnscache la inceput s-au resolvat foarte
putine cereri pe secunda (deoarece se construia in memorie cache-ul pentru
diferite root-uri si tld-uri). apoi dnscache urca pana la o anumita
valoare "limitata" dupa parerea mea (IMHO) de dimensiunea cache-ului in
memorie (500000).
pe cand la bind creste si la un moment dat se opreste (IMHO tot din cauza
memoriei, fie isi impune bind o limita fie nu duce mai mult...)
----------------------------
Mihai RUSU
RoEduNet Network Engineer
"... and what if this is as good as it gets ?"
---
Send e-mail to '[EMAIL PROTECTED]' with 'unsubscribe rlug' to
unsubscribe from this list.
