Request for review of performance advice

classic Classic list List threaded Threaded
7 messages Options
Reply | Threaded
Open this post in threaded view
|

Request for review of performance advice

Vicky Risk
Administrator
A while ago we created a KB article with tips on how to improve your performance with our Kea dhcp server. The tips were fairly obvious to our developers and this was pretty successful. We would like to do something similar for BIND, provide a dozen or so tips for how to maximize your throughput with BIND. However, as usual, everything is more complicated with BIND.

Can those of you who care about performance, who have worked to improve your performance, share some of your suggestions that have the most impact?  Please also comment if you think any of these ideas below are stupid or dangerous. I have combined advice for resolvers and for authoritative servers, I hope it is clear which is which...

The ideas we have fall into four general categories:

System design
1a) Use a load balancer to specialize your resolvers and maximize your cache hit ratio.  A load balancer is traditionally designed to spread the traffic out evenly among a pool of servers, but it can also be used to concentrate related queries on one server to make its cache as hot as possible. For example, if all queries for domains in .info are sent to one server in a pool, there is a better chance that an answer will be in the cache there.

1b) If you have a large authoritative system with many servers, consider dedicating some machines to propagate transfers. These machines, called transfer servers, would not answer client queries, but just send notifies and process IXFR requests.

1c) Deploy ghost secondaries.  If you store copies of authoritative zones on resolvers (resolvers as undelegated secondaries), you can avoid querying those authoritative zones. The most obvious uses of this would be mirroring the root zone locally or mirroring your own authoritative zones on your resolver.

we have other system design ideas that we suspect would help, but we are not sure, so I will wait to see if anyone suggests them.

OS settings and the system environment
2a) Run on bare metal if possible, not on virtual machines or in the cloud. (any idea how much difference this makes? the only reference we can cite is pretty out of date - https://indico.dns-oarc.net/event/19/contributions/234/attachments/217/411/DNS_perf_OARC_Apr_14.pdf )

2b) Consider using with-tuning-large. (https://kb.isc.org/docs/aa-01314) This is a compile time option, so not something you can switch on and off during production. 

2c) Consider which R/W lock choice you want to use - https://kb.isc.org/docs/choosing-a-read-write-lock-implementation-to-use-with-named For the highest tested query rates (> 100,000 queries per second), pthreads read-write locks with hyper-threading enabled seem to be the best-performing choice by far.

2d) Pay attention to your choice of NIC cards. We have found wide variations in their performance. (Can anyone suggest what specifically to look for?)

2e) Make sure your socket send buffers are big enough. (not sure if this is obsolete advice, do we need to tell people how to tell if their buffers are causing delays?)

2f) When the number of CPUs is very large (32 or more), the increase in UDP listeners may not provide any performance improvement and might actually reduce throughput slightly due to the overhead of the additional structures and tasks. We suggest trying different values of -U to find the optimal one for your production environment.


named Features
3a) Minimize logging. Query logging is expensive (can cost you 20% or more of your throughput) so don’t do it unless you are using the logs for something. Logging with dnstap is lower impact, but still fairly expensive. Don’t run in debug mode unless necessary.

3b) Use named.conf option minimal-responses yes; to reduce the amount of work that named needs to do to assemble the query response as well as reducing the amount of outbound traffic

3c) Disable synth-from-dnssec. While this seemed like a good idea, it turns out, in practice it does not improve performance.

3d) Tune your zone transfers. (https://kb.isc.org/docs/aa-00726)

When tuning the behavior of the primary, there are several factors that you can control:

- The rate of notifications of changes to secondary servers (serial-query-rate and notify-delay)

- Limits on concurrent zone transfers (transfers-out, tcp-clients, tcp-listen-queue, reserved-sockets)

- Efficiency/management options (max-transfer-time-out, max-transfer-idle-out, transfer-format)

The most important options to focus on are transfers-out, serial-query-rate, tcp-clients and tcp-listen-queue.

4e) If you use RPZ, consider using qnane-wait-recurse. We have had issues with RPZ transfers impacting query performance in resolvers. In general, more smaller RPZ zones will transfer faster than a few very large RPZ zones. 

4f) Consider enabling prefetch on your resolver, unless you are running 9.10 (which is EOL) https://kb.isc.org/docs/aa-01122

Fix your transport network. 
Transport network issues cause BIND to keep retrying, which is a performance drain.
4a) Disable (in some cases, completely remove in order to prevent ongoing interference) outbound firewalls/packet-filters (particularly that maintain state on connections). These are a frequent cause of problems in the DNS that can cause your DNS server to do a lot of extra work.

4b) Set an appropriate MTU for your network. Ensure that your network infrastructure supports EDNS and large UDP responses up to 4096. Ensure that your network infrastructure allows transit for and reassembly of fragmented UDP packets (these will be large query responses if you are DNSSEC signing)

4c) Ensure that your network infrastructure allows DNS over TCP.

4d) Check for, and eliminate any incomplete IPv6 interface set-up (what can go wrong here is that BIND thinks that it can use IPv6 authoritative servers, but actually the sends silently fail, leaving named waiting unnecessarily for responses)

Any further suggestions, corrections or warnings are very welcome.

Thank you!
Vicky

---------

Victoria Risk
Product Manager
Internet Systems Consortium






_______________________________________________
Please visit https://lists.isc.org/mailman/listinfo/bind-users to unsubscribe from this list

ISC funds the development of this software with paid support subscriptions. Contact us at https://www.isc.org/contact/ for more information.


bind-users mailing list
[hidden email]
https://lists.isc.org/mailman/listinfo/bind-users
Vicky Risk
Product Manager,
Internet Systems Consortium
Reply | Threaded
Open this post in threaded view
|

Re: Request for review of performance advice

Bind-Users forum mailing list
Just one quick one before I run off to lunch with regards to section 2:

- Try to avoid crossing NUMA boundaries. At high throughput, the context switching and far memory calls kills performance.

Stuart

From: bind-users <[hidden email]> on behalf of Victoria Risk <[hidden email]>
Date: Wednesday, 8 July 2020 at 11:58
To: bind-users <[hidden email]>
Subject: Request for review of performance advice

A while ago we created a KB article with tips on how to improve your performance with our Kea dhcp server. The tips were fairly obvious to our developers and this was pretty successful. We would like to do something similar for BIND, provide a dozen or so tips for how to maximize your throughput with BIND. However, as usual, everything is more complicated with BIND.

Can those of you who care about performance, who have worked to improve your performance, share some of your suggestions that have the most impact?  Please also comment if you think any of these ideas below are stupid or dangerous. I have combined advice for resolvers and for authoritative servers, I hope it is clear which is which...

The ideas we have fall into four general categories:

System design
1a) Use a load balancer to specialize your resolvers and maximize your cache hit ratio.  A load balancer is traditionally designed to spread the traffic out evenly among a pool of servers, but it can also be used to concentrate related queries on one server to make its cache as hot as possible. For example, if all queries for domains in .info are sent to one server in a pool, there is a better chance that an answer will be in the cache there.

1b) If you have a large authoritative system with many servers, consider dedicating some machines to propagate transfers. These machines, called transfer servers, would not answer client queries, but just send notifies and process IXFR requests.


1c) Deploy ghost secondaries.  If you store copies of authoritative zones on resolvers (resolvers as undelegated secondaries), you can avoid querying those authoritative zones. The most obvious uses of this would be mirroring the root zone locally or mirroring your own authoritative zones on your resolver.

we have other system design ideas that we suspect would help, but we are not sure, so I will wait to see if anyone suggests them.

OS settings and the system environment
2a) Run on bare metal if possible, not on virtual machines or in the cloud. (any idea how much difference this makes? the only reference we can cite is pretty out of date - https://urldefense.com/v3/__https:/indico.dns-oarc.net/event/19/contributions/234/attachments/217/411/DNS_perf_OARC_Apr_14.pdf__;!!N14HnBHF!rk-RfzR0chw8mToGMWAwQAF_WiiXKZM3KXol3WR8YPytPoI_cWyNe5BZ_rsEqdV7T9SIQ1M$ )

2b) Consider using with-tuning-large. (https://urldefense.com/v3/__https:/kb.isc.org/docs/aa-01314__;!!N14HnBHF!rk-RfzR0chw8mToGMWAwQAF_WiiXKZM3KXol3WR8YPytPoI_cWyNe5BZ_rsEqdV7ufSMbnU$) This is a compile time option, so not something you can switch on and off during production. 

2c) Consider which R/W lock choice you want to use - https://urldefense.com/v3/__https:/kb.isc.org/docs/choosing-a-read-write-lock-implementation-to-use-with-named__;!!N14HnBHF!rk-RfzR0chw8mToGMWAwQAF_WiiXKZM3KXol3WR8YPytPoI_cWyNe5BZ_rsEqdV7mVVUg4A$ For the highest tested query rates (> 100,000 queries per second), pthreads read-write locks with hyper-threading enabled seem to be the best-performing choice by far.


2d) Pay attention to your choice of NIC cards. We have found wide variations in their performance. (Can anyone suggest what specifically to look for?)


2e) Make sure your socket send buffers are big enough. (not sure if this is obsolete advice, do we need to tell people how to tell if their buffers are causing delays?)

2f) When the number of CPUs is very large (32 or more), the increase in UDP listeners may not provide any performance improvement and might actually reduce throughput slightly due to the overhead of the additional structures and tasks. We suggest trying different values of -U to find the optimal one for your production environment.




named Features
3a) Minimize logging. Query logging is expensive (can cost you 20% or more of your throughput) so don’t do it unless you are using the logs for something. Logging with dnstap is lower impact, but still fairly expensive. Don’t run in debug mode unless necessary.


3b) Use named.conf option minimal-responses yes; to reduce the amount of work that named needs to do to assemble the query response as well as reducing the amount of outbound traffic


3c) Disable synth-from-dnssec. While this seemed like a good idea, it turns out, in practice it does not improve performance.


3d) Tune your zone transfers. (https://urldefense.com/v3/__https:/kb.isc.org/docs/aa-00726__;!!N14HnBHF!rk-RfzR0chw8mToGMWAwQAF_WiiXKZM3KXol3WR8YPytPoI_cWyNe5BZ_rsEqdV7K_7-VnQ$)
When tuning the behavior of the primary, there are several factors that you can control:
- The rate of notifications of changes to secondary servers (serial-query-rate and notify-delay)
- Limits on concurrent zone transfers (transfers-out, tcp-clients, tcp-listen-queue, reserved-sockets)
- Efficiency/management options (max-transfer-time-out, max-transfer-idle-out, transfer-format)
The most important options to focus on are transfers-out, serial-query-rate, tcp-clients and tcp-listen-queue.
4e) If you use RPZ, consider using qnane-wait-recurse. We have had issues with RPZ transfers impacting query performance in resolvers. In general, more smaller RPZ zones will transfer faster than a few very large RPZ zones. 

4f) Consider enabling prefetch on your resolver, unless you are running 9.10 (which is EOL) https://urldefense.com/v3/__https:/kb.isc.org/docs/aa-01122__;!!N14HnBHF!rk-RfzR0chw8mToGMWAwQAF_WiiXKZM3KXol3WR8YPytPoI_cWyNe5BZ_rsEqdV714AsnkE$

Fix your transport network. 
Transport network issues cause BIND to keep retrying, which is a performance drain.
4a) Disable (in some cases, completely remove in order to prevent ongoing interference) outbound firewalls/packet-filters (particularly that maintain state on connections). These are a frequent cause of problems in the DNS that can cause your DNS server to do a lot of extra work.


4b) Set an appropriate MTU for your network. Ensure that your network infrastructure supports EDNS and large UDP responses up to 4096. Ensure that your network infrastructure allows transit for and reassembly of fragmented UDP packets (these will be large query responses if you are DNSSEC signing)


4c) Ensure that your network infrastructure allows DNS over TCP.


4d) Check for, and eliminate any incomplete IPv6 interface set-up (what can go wrong here is that BIND thinks that it can use IPv6 authoritative servers, but actually the sends silently fail, leaving named waiting unnecessarily for responses)

Any further suggestions, corrections or warnings are very welcome.


Thank you!
Vicky


---------


Victoria Risk
Product Manager
Internet Systems Consortium
mailto:[hidden email]





_______________________________________________
Please visit https://lists.isc.org/mailman/listinfo/bind-users to unsubscribe from this list

ISC funds the development of this software with paid support subscriptions. Contact us at https://www.isc.org/contact/ for more information.


bind-users mailing list
[hidden email]
https://lists.isc.org/mailman/listinfo/bind-users
Reply | Threaded
Open this post in threaded view
|

Re: Request for review of performance advice

John Thurston
In reply to this post by Vicky Risk

On 7/7/2020 5:57 PM, Victoria Risk wrote:
> A while ago we created a KB article with tips on how to improve your
> performance with our Kea dhcp server. The tips were fairly obvious to
> our developers and this was pretty successful. We would like to do
> something similar for BIND, provide a dozen or so tips for how to
> maximize your throughput with BIND. However, as usual, everything is
> more complicated with BIND.

This is an excellent idea.

If it comes to fruition, I ask there be some guidance offered on when
such optimizations are useful. I've seen places where such a guide-sheet
is followed when the guidelines were suitable for a business with 10X or
100X the traffic the customer sees.

That is, a configuration which benefits an organization seeing 100,000
qps may be excessively complex (or brittle) for one seeing 100 qps.

--
Do things because you should, not just because you can.

John Thurston    907-465-8591
[hidden email]
Department of Administration
State of Alaska


>
> Can those of you who care about performance, who have worked to improve
> your performance, share some of your suggestions that have the most
> impact?  Please also comment if you think any of these ideas below are
> stupid or dangerous. I have combined advice for resolvers and for
> authoritative servers, I hope it is clear which is which...
>
> The ideas we have fall into four general categories:
>
> System design
> 1a) Use a load balancerto specialize your resolvers and maximize your
> cache hit ratio.  A load balancer is traditionally designed to spread
> the traffic out evenly among a pool of servers, but it can also be used
> to concentrate related queries on one server to make its cache as hot as
> possible. For example, if all queries for domains in .info are sent to
> one server in a pool, there is a better chance that an answer will be in
> the cache there.
>
> 1b) If you have a large authoritative system with many servers, consider
> dedicating some machines to propagate transfers. These machines, called
> transfer servers, would not answer client queries, but just send
> notifies and process IXFR requests.
>
> 1c) Deploy ghost secondaries.  If you store copies of authoritative
> zones on resolvers (resolvers as undelegated secondaries), you can avoid
> querying those authoritative zones. The most obvious uses of this would
> be mirroring the root zone locally or mirroring your own authoritative
> zones on your resolver.
>
> we have other system design ideas that we suspect would help, but we are
> not sure, so I will wait to see if anyone suggests them.
>
> OS settings and the system environment
> 2a) Run on bare metal if possible, not on virtual machines or in the
> cloud. (any idea how much difference this makes? the only reference we
> can cite is pretty out of date -
> https://indico.dns-oarc.net/event/19/contributions/234/attachments/217/411/DNS_perf_OARC_Apr_14.pdf 
> <https://urldefense.com/v3/__https://indico.dns-oarc.net/event/19/contributions/234/attachments/217/411/DNS_perf_OARC_Apr_14.pdf__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYfEBpbu8w$>
> )
>
> 2b) Consider using with-tuning-large. (https://kb.isc.org/docs/aa-01314 
> <https://urldefense.com/v3/__https://kb.isc.org/docs/aa-01314__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYdvKmJFZQ$>)
> This is a compile time option, so not something you can switch on and
> off during production.
>
> 2c) Consider which R/W lock choice you want to use -
> https://kb.isc.org/docs/choosing-a-read-write-lock-implementation-to-use-with-named 
> <https://urldefense.com/v3/__https://kb.isc.org/docs/choosing-a-read-write-lock-implementation-to-use-with-named__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYftHIt-qg$>
> For the highest tested query rates (> 100,000 queries per second),
> pthreads read-write locks with hyper-threading /enabled/seem to be the
> best-performing choice by far.
>
> 2d) Pay attention to your choice of NIC cards. We have found wide
> variations in their performance. (Can anyone suggest what specifically
> to look for?)
>
> 2e) Make sure your socket send buffers are big enough. (not sure if this
> is obsolete advice, do we need to tell people how to tell if their
> buffers are causing delays?)
>
> 2f) When the number of CPUs is very large (32 or more), the increase in
> UDP listeners may not provide any performance improvement and might
> actually reduce throughput slightly due to the overhead of the
> additional structures and tasks. We suggest trying different values of
> -U to find the optimal one for your production environment.
>
>
> named Features
> 3a) Minimize logging. Query logging is expensive (can cost you 20% or
> more of your throughput) so don’t do it unless you are using the logs
> for something. Logging with dnstap is lower impact, but still fairly
> expensive. Don’t run in debug mode unless necessary.
>
> 3b) Use named.conf option minimal-responses yes; to reduce the amount of
> work that named needs to do to assemble the query response as well as
> reducing the amount of outbound traffic
>
> 3c) Disable synth-from-dnssec. While this seemed like a good idea, it
> turns out, in practice it does not improve performance.
>
> 3d) Tune your zone transfers. (https://kb.isc.org/docs/aa-00726 
> <https://urldefense.com/v3/__https://kb.isc.org/docs/aa-00726__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYe98KMFqg$>)
>
> When tuning the behavior of the primary, there are several factors that
> you can control:
>
> - The rate of notifications of changes to secondary servers
> (serial-query-rate and notify-delay)
>
> - Limits on concurrent zone transfers (transfers-out, tcp-clients,
> tcp-listen-queue, reserved-sockets)
>
> - Efficiency/management options (max-transfer-time-out,
> max-transfer-idle-out, transfer-format)
>
> The most important options to focus on are transfers-out,
> serial-query-rate, tcp-clients and tcp-listen-queue.
>
> 4e) If you use RPZ, consider using qnane-wait-recurse. We have had
> issues with RPZ transfers impacting query performance in resolvers. In
> general, more smaller RPZ zones will transfer faster than a few very
> large RPZ zones.
>
> 4f) Consider enabling prefetch on your resolver, unless you are running
> 9.10 (which is EOL) https://kb.isc.org/docs/aa-01122 
> <https://urldefense.com/v3/__https://kb.isc.org/docs/aa-01122__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYcf-H7ZBg$>
>
> Fix your transport network.
> Transport network issues cause BIND to keep retrying, which is a
> performance drain.
> 4a) Disable (in some cases, completely remove in order to prevent
> ongoing interference) outbound firewalls/packet-filters (particularly
> that maintain state on connections). These are a frequent cause of
> problems in the DNS that can cause your DNS server to do a lot of extra
> work.
>
> 4b) Set an appropriate MTU for your network. Ensure that your network
> infrastructure supports EDNS and large UDP responses up to 4096. Ensure
> that your network infrastructure allows transit for and reassembly of
> fragmented UDP packets (these will be large query responses if you are
> DNSSEC signing)
>
> 4c) Ensure that your network infrastructure allows DNS over TCP.
>
> 4d) Check for, and eliminate any incomplete IPv6 interface set-up (what
> can go wrong here is that BIND thinksthat it can use IPv6 authoritative
> servers, but actually the sends silently fail, leaving named waiting
> unnecessarily for responses)
>
> Any further suggestions, corrections or warnings are very welcome.
>
> Thank you!
> Vicky
>
> ---------
>
> Victoria Risk
> Product Manager
> Internet Systems Consortium
> [hidden email] <mailto:[hidden email]>
>
>
>
>
>
>
> _______________________________________________
> Please visit https://urldefense.com/v3/__https://lists.isc.org/mailman/listinfo/bind-users__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYflfQafZw$  to unsubscribe from this list
>
> ISC funds the development of this software with paid support subscriptions. Contact us at https://urldefense.com/v3/__https://www.isc.org/contact/__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYd9ITf9ow$  for more information.
>
>
> bind-users mailing list
> [hidden email]
> https://urldefense.com/v3/__https://lists.isc.org/mailman/listinfo/bind-users__;!!J2_8gdp6gZQ!7sRXGLQDm9waSVfgufc44e2-G1iYoLGoT_iBOLgmPYx3xAW8jKIAFbCB5OVJYYflfQafZw$
>
_______________________________________________
Please visit https://lists.isc.org/mailman/listinfo/bind-users to unsubscribe from this list

ISC funds the development of this software with paid support subscriptions. Contact us at https://www.isc.org/contact/ for more information.


bind-users mailing list
[hidden email]
https://lists.isc.org/mailman/listinfo/bind-users
Reply | Threaded
Open this post in threaded view
|

Re: Request for review of performance advice

Chuck Aurora
In reply to this post by Vicky Risk
On 2020-07-07 20:57, Victoria Risk wrote:
> A while ago we created a KB article with tips on how to improve your
> performance with our Kea dhcp server. The tips were fairly obvious to
> our developers and this was pretty successful. We would like to do
> something similar for BIND, provide a dozen or so tips for how to
> maximize your throughput with BIND. However, as usual, everything is
> more complicated with BIND.
[big snip]
> Any further suggestions, corrections or warnings are very welcome.

Vicky, I'd suggest separating these performance tips into two separate
articles: authoritative and recursive.  Lumping both together is going
to create more confusion.

_______________________________________________
Please visit https://lists.isc.org/mailman/listinfo/bind-users to unsubscribe from this list

ISC funds the development of this software with paid support subscriptions. Contact us at https://www.isc.org/contact/ for more information.


bind-users mailing list
[hidden email]
https://lists.isc.org/mailman/listinfo/bind-users
Reply | Threaded
Open this post in threaded view
|

Re: Request for review of performance advice

Bind-Users forum mailing list
In reply to this post by Vicky Risk
> OS settings and the system environment
...
> 2e) Make sure your socket send buffers are big enough. (not
>     sure if this is obsolete advice, do we need to tell people how
>     to tell if their buffers are causing delays?)

2e#1) Make sure your UDP socket *receive* buffers are big enough.
      If on BSD, monitor for "dropped due to full socket buffers"
      count in "netstat -s" output, and tune accordingly.  Note that
      this may be a symptom of mis-tuning of other parts of BIND,
      causing excessive CPU usage, which may contribute to this
      problem.
     
BTW, unbound has configuration options ("so-rcvbuf" / "so-sndbuf")
to tune these for only the name server; when I earlier looked for
something similar in BIND I could not find a corresponding option,
so had to do a system-wide tuning via sysctl, which isn't ideal, but
solved the problem in my case.

> named Features
> 3a) Minimize logging. Query logging is expensive (can cost you
>     20% or more of your throughput) so don't do it unless you
>     are using the logs for something. Logging with dnstap is
>     lower impact, but still fairly expensive.  Don't run in
>     debug mode unless necessary.

3a#1) Do not configure BIND with --enable-querytrace.  It most
      probably doesn't do what you might think it does, and is a
      major drag on performance.
     
See above under the new "2e#1" for a possible symptom...

> 4b) Set an appropriate MTU for your network. Ensure that your
>     network infrastructure supports EDNS and large UDP responses up
>     to 4096.  Ensure that your network infrastructure allows transit
>     for and reassembly of fragmented UDP packets (these will be
>     large query responses if you are DNSSEC signing)

Well, isn't the major goal of DNS Flag Day 2020 to eliminate
fragmentation for various reasons (some of them security-related),
and recommends to set EDNS buffer size to 1232 instead of letting it
be the present default of BIND of 4096?

Best regards,

- Håvard
_______________________________________________
Please visit https://lists.isc.org/mailman/listinfo/bind-users to unsubscribe from this list

ISC funds the development of this software with paid support subscriptions. Contact us at https://www.isc.org/contact/ for more information.


bind-users mailing list
[hidden email]
https://lists.isc.org/mailman/listinfo/bind-users
Reply | Threaded
Open this post in threaded view
|

Re: Request for review of performance advice

Timothe Litt
In reply to this post by Vicky Risk

These suggestions - like most performance articles - are oriented toward achieving the highest performance with large configurations.  E.g. "How big can/should you go to support big loads?"

That's useful for many users.  But there are also many people who run smaller operations, where the goal is to provide adequate (or even exceptional) performance with a minimum footprint. When BIND is one of many services, overall performance can be improved by minimizing BIND's resource requirements.  This is also true in embedded applications, where footprint matters.

So a discussion about how to optimize for the smaller cases - what do you trade-off?  What knobs can one turn down - and how far? would be a useful part of or complement to the proposed article.  E.g. "How small can/should you go when your loads are smaller?"

FWIW, a wizard - even just a spreadsheet - that encapsulates known performance results might also be useful.  E.g. Given a processor, number/size of zones, query rate, & type, produce a memory size, disk & network I/O rates, and starting configuration parameters... Obviously, this could become arbitrarily complicated, but a simple spreadsheet with configuration (hardware & software) and performance data that's searchable would give people a good starting point.  Especially if it's real-world. (It can be challenging to map artificial "performance"/stress tests done in a development/verification environment to the real world...)  While full automation can be fun, it's amazing how much one can get out of a spreadsheet with/autofilter.  (For the next level, pivot tables and/or charts...)

Timothe Litt
ACM Distinguished Engineer
--------------------------
This communication may not represent the ACM or my employer's views,
if any, on the matters discussed. 
On 07-Jul-20 21:57, Victoria Risk wrote:
A while ago we created a KB article with tips on how to improve your performance with our Kea dhcp server. The tips were fairly obvious to our developers and this was pretty successful. We would like to do something similar for BIND, provide a dozen or so tips for how to maximize your throughput with BIND. However, as usual, everything is more complicated with BIND.

Can those of you who care about performance, who have worked to improve your performance, share some of your suggestions that have the most impact?  Please also comment if you think any of these ideas below are stupid or dangerous. I have combined advice for resolvers and for authoritative servers, I hope it is clear which is which...

The ideas we have fall into four general categories:

System design
1a) Use a load balancer to specialize your resolvers and maximize your cache hit ratio.  A load balancer is traditionally designed to spread the traffic out evenly among a pool of servers, but it can also be used to concentrate related queries on one server to make its cache as hot as possible. For example, if all queries for domains in .info are sent to one server in a pool, there is a better chance that an answer will be in the cache there.

1b) If you have a large authoritative system with many servers, consider dedicating some machines to propagate transfers. These machines, called transfer servers, would not answer client queries, but just send notifies and process IXFR requests.
1c) Deploy ghost secondaries.  If you store copies of authoritative zones on resolvers (resolvers as undelegated secondaries), you can avoid querying those authoritative zones. The most obvious uses of this would be mirroring the root zone locally or mirroring your own authoritative zones on your resolver.

we have other system design ideas that we suspect would help, but we are not sure, so I will wait to see if anyone suggests them.

OS settings and the system environment
2a) Run on bare metal if possible, not on virtual machines or in the cloud. (any idea how much difference this makes? the only reference we can cite is pretty out of date - https://indico.dns-oarc.net/event/19/contributions/234/attachments/217/411/DNS_perf_OARC_Apr_14.pdf )

2b) Consider using with-tuning-large. (https://kb.isc.org/docs/aa-01314) This is a compile time option, so not something you can switch on and off during production. 

2c) Consider which R/W lock choice you want to use - https://kb.isc.org/docs/choosing-a-read-write-lock-implementation-to-use-with-named For the highest tested query rates (> 100,000 queries per second), pthreads read-write locks with hyper-threading enabled seem to be the best-performing choice by far.

2d) Pay attention to your choice of NIC cards. We have found wide variations in their performance. (Can anyone suggest what specifically to look for?)

2e) Make sure your socket send buffers are big enough. (not sure if this is obsolete advice, do we need to tell people how to tell if their buffers are causing delays?)

2f) When the number of CPUs is very large (32 or more), the increase in UDP listeners may not provide any performance improvement and might actually reduce throughput slightly due to the overhead of the additional structures and tasks. We suggest trying different values of -U to find the optimal one for your production environment.
named Features
3a) Minimize logging. Query logging is expensive (can cost you 20% or more of your throughput) so don’t do it unless you are using the logs for something. Logging with dnstap is lower impact, but still fairly expensive. Don’t run in debug mode unless necessary.
3b) Use named.conf option minimal-responses yes; to reduce the amount of work that named needs to do to assemble the query response as well as reducing the amount of outbound traffic
3c) Disable synth-from-dnssec. While this seemed like a good idea, it turns out, in practice it does not improve performance.
3d) Tune your zone transfers. (https://kb.isc.org/docs/aa-00726)

When tuning the behavior of the primary, there are several factors that you can control:

- The rate of notifications of changes to secondary servers (serial-query-rate and notify-delay)

- Limits on concurrent zone transfers (transfers-out, tcp-clients, tcp-listen-queue, reserved-sockets)

- Efficiency/management options (max-transfer-time-out, max-transfer-idle-out, transfer-format)

The most important options to focus on are transfers-out, serial-query-rate, tcp-clients and tcp-listen-queue.

4e) If you use RPZ, consider using qnane-wait-recurse. We have had issues with RPZ transfers impacting query performance in resolvers. In general, more smaller RPZ zones will transfer faster than a few very large RPZ zones. 

4f) Consider enabling prefetch on your resolver, unless you are running 9.10 (which is EOL) https://kb.isc.org/docs/aa-01122

Fix your transport network. 
Transport network issues cause BIND to keep retrying, which is a performance drain.
4a) Disable (in some cases, completely remove in order to prevent ongoing interference) outbound firewalls/packet-filters (particularly that maintain state on connections). These are a frequent cause of problems in the DNS that can cause your DNS server to do a lot of extra work.
4b) Set an appropriate MTU for your network. Ensure that your network infrastructure supports EDNS and large UDP responses up to 4096. Ensure that your network infrastructure allows transit for and reassembly of fragmented UDP packets (these will be large query responses if you are DNSSEC signing)
4c) Ensure that your network infrastructure allows DNS over TCP.
4d) Check for, and eliminate any incomplete IPv6 interface set-up (what can go wrong here is that BIND thinks that it can use IPv6 authoritative servers, but actually the sends silently fail, leaving named waiting unnecessarily for responses)

Any further suggestions, corrections or warnings are very welcome.
Thank you!
Vicky
---------
Victoria Risk
Product Manager
Internet Systems Consortium






_______________________________________________
Please visit https://lists.isc.org/mailman/listinfo/bind-users to unsubscribe from this list

ISC funds the development of this software with paid support subscriptions. Contact us at https://www.isc.org/contact/ for more information.


bind-users mailing list
[hidden email]
https://lists.isc.org/mailman/listinfo/bind-users

signature.asc (499 bytes) Download Attachment
Reply | Threaded
Open this post in threaded view
|

Re: Request for review of performance advice

Niall O'Reilly
In reply to this post by Bind-Users forum mailing list

On 9 Jul 2020, at 21:25, Havard Eidnes via bind-users wrote:

2e#1) Make sure your UDP socket *receive* buffers are big enough.
If on BSD, monitor for "dropped due to full socket buffers"
count in "netstat -s" output, and tune accordingly. Note that
this may be a symptom of mis-tuning of other parts of BIND,
causing excessive CPU usage, which may contribute to this
problem.

I'm seeing some instances of "dropped due to no socket" on my FreeBSD
systems where my resolvers run.

I'm wondering

  • whether and how I can address this with tuning, and also
  • whether I'm wandering out of scope for this list.

Thanks in anticipation and/or apologies.
Niall


_______________________________________________
Please visit https://lists.isc.org/mailman/listinfo/bind-users to unsubscribe from this list

ISC funds the development of this software with paid support subscriptions. Contact us at https://www.isc.org/contact/ for more information.


bind-users mailing list
[hidden email]
https://lists.isc.org/mailman/listinfo/bind-users