Re: better performance with 32 bit ! why?

2011-06-29 Thread lst_hoe02
Zitat von Kevin Oberman kob6...@gmail.com: On Tue, Jun 28, 2011 at 7:32 AM, Ryan Novosielski novos...@umdnj.edu wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 06/28/2011 12:30 PM, David Sparro wrote: On 6/28/2011 11:15 AM, iharrathi@orange-ftgroup.com wrote: Hi all, I'm testing

Re: Named.conf logical blocks

2011-06-29 Thread Phil Mayers
On 06/28/2011 09:54 PM, Stefan Certic wrote: I am more looking for a solution to read data with perl and convert to some native data structure, like hash reference, or multidimenzional array, so i can access and change data in form of: $named_conf_file-{view1}-{zoneblah} = 'somedata' and then

RE: bind-users Digest, Vol 902, Issue 1

2011-06-29 Thread iharrathi.ext
Thanks for the answer, @ Andreas i made the test and i have the same performance as OS 64 bind 64. NB: when i reach the maximum throughput i still have enough free RAM, free CPU, free NIC capacity. So the limit is in Bind. What to do to reach more capacity? Tests: Test1: OS 64 bit, bind 64 bit

Re: better performance with 32 bit ! why?

2011-06-29 Thread iharrathi.ext
-Message d'origine- De : HARRATHI Issam Ext OLNC/DPS Envoyé : mercredi 29 juin 2011 11:04 À : 'novos...@umdnj.edu'; 'lst_ho...@kwsoft.de'; 'kob6...@gmail.com' Cc : 'bind-users@lists.isc.org' Objet : RE: bind-users Digest, Vol 902, Issue 1 Thanks for the answer, @ Andreas i made the

Re: Better solution than making a recursive nameserver authoritative?

2011-06-29 Thread Matus UHLAR - fantomas
On 24.06.11 13:39, David Coulthart wrote: Currently the two recursive caching nameservers for clients on our network are also authoritative for a few zones. In particular, they are authoritative for: 1) our main forward zone (columbia.edu) in order to provide an internal view of the zone

Re: bind-users Digest, Vol 902, Issue 1

2011-06-29 Thread Matus UHLAR - fantomas
On 29.06.11 11:04, iharrathi@orange-ftgroup.com wrote: @ Andreas i made the test and i have the same performance as OS 64 bind 64. NB: when i reach the maximum throughput i still have enough free RAM, free CPU, free NIC capacity. So the limit is in Bind. What to do to reach more

Re: better performance with 32 bit ! why?

2011-06-29 Thread iharrathi.ext
The 64 bit server(server1) is faster than the 32 bit server (server2). Tests: Test1: OS 64 bit, bind 64 bit == 5 qps server1 Test2: OS 32 bit, bind 32 bit == 7 qps server2 Test3: OS 64 bit, bind 32 bit == 5 qps server1 -- Message: 5 Date: Wed, 29 Jun 2011

Re: better performance with 32 bit ! why?

2011-06-29 Thread Eivind Olsen
iharrathi@orange-ftgroup.com wrote: The 64 bit server(server1) is faster than the 32 bit server (server2). Really? I thought you said the 64 bit server had a CPU with 1.6GHz cores, and the 32 bit server had 2.33GHz cores? Regards Eivind Olsen

Re: better performance with 32 bit ! why?

2011-06-29 Thread iharrathi.ext
on server1(64 bit) i have 2 Intel E5310 quad-core 1.6Ghz and on server2(32 bit) i have 2 Intel Xeon dual-core 2.33Ghz. means 8*1.6 Ghz on server1 and 4*2.33 on server2. 8*1.6 is better and faster than 4*2.33, no? Regards Issam Harrathi. The 64 bit server(server1) is faster than the 32 bit

Re: Named.conf logical blocks

2011-06-29 Thread Chris Buxton
On Jun 29, 2011, at 12:21 AM, Phil Mayers wrote: Or use Config::Parser, or adapt the script I sent round (which in fact was the reason I wrote it); tokenisation of the bind config file is easy, and the core grammar is straightforward because everything is ;-terminated, with the form:

Re: better performance with 32 bit ! why?

2011-06-29 Thread Eivind Olsen
Issam Harrathi wrote: on server1(64 bit) i have 2 Intel E5310 quad-core 1.6Ghz and on server2(32 bit) i have 2 Intel Xeon dual-core 2.33Ghz. means 8*1.6 Ghz on server1 and 4*2.33 on server2. 8*1.6 is better and faster than 4*2.33, no? You can only do maths like that if you assume that

Re: better performance with 32 bit ! why?

2011-06-29 Thread Ryan Novosielski
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Not necessarily. They are not apples to apples. Multi-core machines only excel at multi-threaded computational loads. I don't know how BIND does or does not qualify. I suspect, however, there may be some other differences between the two chips anyhow

Re: better performance with 32 bit ! why?

2011-06-29 Thread lst_hoe02
Zitat von iharrathi@orange-ftgroup.com: on server1(64 bit) i have 2 Intel E5310 quad-core 1.6Ghz and on server2(32 bit) i have 2 Intel Xeon dual-core 2.33Ghz. means 8*1.6 Ghz on server1 and 4*2.33 on server2. 8*1.6 is better and faster than 4*2.33, no? This would only apply for

Re: better performance with 32 bit ! why?

2011-06-29 Thread Mats Dufberg
It would be interesting to hear what kind of lookup that you did for your test. Did the servers just answer from configured zones? Would recursion make any difference on the utilization of the cores? And validation? Or is four fast cores always better than many slower cores? Mats

Re: Named.conf logical blocks

2011-06-29 Thread Phil Mayers
On 06/29/2011 02:37 PM, Chris Buxton wrote: Not entirely. There is at least one construct that looks like this (using your terms): thing+ block thing block semicolon For example, within the controls statement: inet * allow { trusted; } keys { some.key; }; Good point.

Re: better performance with 32 bit ! why?

2011-06-29 Thread Sven Eschenberg
Not neccessarily. It really depends on many many things. How well does the OS kernel+NIC driver scale, how good do they work in balancing among all CPUs+cores. I do not know the inner workings of bind, but depending on the algorithmic problems, distributed/parallel processing can even degrade

Re: better performance with 32 bit ! why?

2011-06-29 Thread iharrathi.ext
When i start Bind on server2 i do it with -n 4 ( to use 4 thread) and on server1 i start bind with -n 8. And i see then on munin that the load is shared on all cores. For the load-server it's another server let's call it server 3. I know that tcpreplay is monothread so i lunch 2*25000 qps for

Re: better performance with 32 bit ! why?

2011-06-29 Thread Matus UHLAR - fantomas
On 29.06.11 15:33, iharrathi@orange-ftgroup.com wrote: on server1(64 bit) i have 2 Intel E5310 quad-core 1.6Ghz and on server2(32 bit) i have 2 Intel Xeon dual-core 2.33Ghz. means 8*1.6 Ghz on server1 and 4*2.33 on server2. 8*1.6 is better and faster than 4*2.33, no? It was already

Re: better performance with 32 bit ! why?

2011-06-29 Thread Fajar A. Nugraha
On Wed, Jun 29, 2011 at 8:33 PM, iharrathi@orange-ftgroup.com wrote: on server1(64 bit) i have 2 Intel E5310 quad-core 1.6Ghz and on server2(32 bit) i have 2 Intel Xeon dual-core 2.33Ghz. means 8*1.6 Ghz on server1 and 4*2.33 on server2. 8*1.6 is better and faster than 4*2.33, no?

RE: Re: better performance with 32 bit ! why?

2011-06-29 Thread iharrathi.ext
As asked, i will made a test with os 32 bit on the same server as the the 64 bit, and will post this result here. Thanks for all for your answers. Regards. Issam Harrathi. De : HARRATHI Issam Ext OLNC/DPS Envoyé : mercredi 29 juin 2011 16:17 À :

Re: better performance with 32 bit ! why?

2011-06-29 Thread Michael Graff
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 6/29/11 8:19 AM, Eivind Olsen wrote: Really? I thought you said the 64 bit server had a CPU with 1.6GHz cores, and the 32 bit server had 2.33GHz cores? Benchmarking on different machine types, even if they are identical speed, can be affected by

Large number of small zones in BIND? We have something for you to try.

2011-06-29 Thread Michael Graff
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 We've been working on the start-up time of BIND 9, when many many zones are configured. By many, I mean in the 10k to 1m range. If you are someone who has a large number of zones loaded into BIND 9, and would like to try out some test code to see if

Re: better performance with 32 bit ! why?

2011-06-29 Thread Michael Graff
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 6/29/11 9:08 AM, Sven Eschenberg wrote: Maybe some bind developer can shed a light on this: Does bind use epoll()? AIO (as in Posix RT extensions) BIND 9 uses epoll() I believe, but AFAIK does not touch AIO. I've not touched that code

Re: better performance with 32 bit ! why?

2011-06-29 Thread Michael Graff
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 6/29/11 9:16 AM, iharrathi@orange-ftgroup.com wrote: Do i have to use bind compiled and running on 32 bit server to have better performance rather than bind compiled and running on 64 bit server? No matter what, what gets you the best

RE: better performance with 32 bit ! why?

2011-06-29 Thread Lightner, Jeff
I'm not sure I agree with that - multiple single threaded processes can be distributed across cores/CPUs. That is to say ONE single thread process doesn't gain from multiple cores but more than one can because they don't have to compete against each other on the same core. -Original

Re: better performance with 32 bit ! why?

2011-06-29 Thread Sven Eschenberg
Thanks for that insight. I already considered something like the 'single core per udp socket' problem. One thing that just popped up my mind: Does it increase performance, when you, let's say, bind multiple IPs to the same NIC and make bind listen to all of those IPs, while of course taking care

Single nameserver doesn't show signed SOA-RRs

2011-06-29 Thread Stefan Foerster
Hello world, I'm having a problem with a single authoritative server that seems to not receive a signed zone. I used www.zonecheck.fr to check the zones incertum.net and billigmail.org and it complains that ns3.wars-nicht.de doesn't have a signed SOA. I already tried increasing the serial for

Re: better performance with 32 bit ! why?

2011-06-29 Thread Michael Graff
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 6/29/11 3:00 PM, Sven Eschenberg wrote: One thing that just popped up my mind: Does it increase performance, when you, let's say, bind multiple IPs to the same NIC and make bind listen to all of those IPs, while of course taking care to fix the

RE: better performance with 32 bit ! why?

2011-06-29 Thread Sven Eschenberg
That is, if all of those threads have work to do, because the task can be distributed accordingly. Which is not easy even if you know the number of cores (threads for that matter) and the whole task is known a priori. Unfortunately Queries to a DNS-Server like bind do not follow parameters known

Re: better performance with 32 bit ! why?

2011-06-29 Thread Michael Graff
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 6/29/11 4:28 PM, Sven Eschenberg wrote: P.S.: If all parts of bind were optimized towards multicore processing and the pattern of queries fits, yes, then the 8 core machine could probably outrun the 4 core machine, even when having a slower

Re: better performance with 32 bit ! why?

2011-06-29 Thread Eivind Olsen
Michael Graff wrote: We hope to improve this in 9.9 or at the latest 9.10, and have something that can saturate all CPUs. And no, we're not cracking RSA keys on the extra CPUs just to keep them busy! Pre-populating a small /56 IPv6 prefix with PTRs? :-) I'm looking forward to what you're

Re: Single nameserver doesn't show signed SOA-RRs

2011-06-29 Thread Zenon Panoussis
On 06/29/2011 10:57 PM, Stefan Foerster wrote: ...it complains that ns3.wars-nicht.de doesn't have a signed SOA. It complains that the SOA of wars-nicht.de itself is not signed, or that ns3.wars-nicht.de does not have a signed SOA for billigmail.org and incertum.net? I already tried

Re: Single nameserver doesn't show signed SOA-RRs

2011-06-29 Thread Mark Andrews
Contact the adminstrator of the server and request that they stop disabling dnssec. dnssec-enable yes; is the default for all version except 9.3.x. % grep dnssec-enable 9.?.x/bin/named/config.c 9.3.x/bin/named/config.c: dnssec-enable no; /* Make yes for 9.4. */ \n\

Re: Single nameserver doesn't show signed SOA-RRs

2011-06-29 Thread Stefan Foerster
* Mark Andrews ma...@isc.org: Contact the adminstrator of the server and request that they stop disabling dnssec. dnssec-enable yes; is the default for all version except 9.3.x. Are you sure that 88.198.26.233 has DNSSEC disabled? The admin told me he had added dnssec-enable yes; to the

Re: Single nameserver doesn't show signed SOA-RRs

2011-06-29 Thread Mark Andrews
In message 20110630031511.gn14...@mail.incertum.net, Stefan Foerster writes: * Mark Andrews ma...@isc.org: Contact the adminstrator of the server and request that they stop disabling dnssec. dnssec-enable yes; is the default for all version except 9.3.x. Are you sure that 88.198.26.233