From: Remi Gacogne Date: Thu, 2 Mar 2017 16:36:01 +0000 (+0100) Subject: rec: Reorder the performance tips, clean up the markdown X-Git-Tag: rec-4.1.0-alpha1~211^2 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=39c92a2851301bcdfcec0b289e74f6fd2c0f6908;p=pdns rec: Reorder the performance tips, clean up the markdown --- diff --git a/docs/markdown/recursor/performance.md b/docs/markdown/recursor/performance.md index 0f0222818..862a45110 100644 --- a/docs/markdown/recursor/performance.md +++ b/docs/markdown/recursor/performance.md @@ -1,25 +1,26 @@ # PowerDNS Recursor performance To get the best out of the PowerDNS recursor, which is important if you are doing thousands of queries per second, please consider the following. -- Limit the size of the caches to a sensible value. Cache hit rate does not improve meaningfully beyond 4 million **max-cache-entries** per thread, reducing the memory footprint reduces CPU cache misses. See below for more information about the various caches. -- Compile using g++ 4.1 or later. This compiler really does a good job on PowerDNS, much better than 3.4 or 4.0. -- On AMD/Intel hardware, wherever possible, run a 64-bit binary. This delivers a nearly twofold performance increase. On UltraSPARC, there is no need to run with 64 bits. -- Consider performing a 'profiled build' as described in the README. This is good for a 20% performance boost in some cases. -- When running with >3000 queries per second, and running Linux versions prior to 2.6.17 on some motherboards, your computer may spend an inordinate amount of time working around an ACPI bug for each call to gettimeofday. This is solved by rebooting with 'clock=tsc' or upgrading to a 2.6.17 kernel. - - The above is relevant if dmesg shows **Using pmtmr for high-res timesource** - -- A busy server may need hundreds of file descriptors on startup, and deals with spikes better if it has that many available later on. Linux by default restricts processes to 1024 file descriptors, which should suffice most of the time, but Solaris has a default limit of 256. This can be raised using the ulimit command. FreeBSD has a default limit that is high enough for even very heavy duty use. -- When deploying (large scale) IPv6, please be aware some Linux distributions leave IPv6 routing cache tables at very small default values. Please check and if necessary raise 'sysctl net.ipv6.route.max\_size'. +- A busy server may need hundreds of file descriptors on startup, and deals with spikes better if it has that many available later on. Linux by default restricts processes to 1024 file descriptors, which should suffice most of the time, but Solaris has a default limit of 256. This can be raised using the `ulimit` command or via the `LimitNOFILE` unit directive when `systemd` is used. FreeBSD has a default limit that is high enough for even very heavy duty use. +- Limit the size of the caches to a sensible value. Cache hit rate does not improve meaningfully beyond 4 million `max-cache-entries` per thread, reducing the memory footprint reduces CPU cache misses. See below for more information about the various caches. +- When deploying (large scale) IPv6, please be aware some Linux distributions leave IPv6 routing cache tables at very small default values. Please check and if necessary raise `sysctl net.ipv6.route.max\_size`. - For 3.2 and higher, set `threads` to your number of CPU cores (but values above 8 rarely improve performance). For older versions <3.2: If you need it, try `--fork`, this will fork the daemon into two halves, allowing it to benefit from a second CPU. This feature almost doubles performance, but is a bit of a hack. When running with several threads, you can either ask PowerDNS to start a special thread to dispatch the incoming queries to the workers by setting `pdns-distributes-queries` to true, or let the worker threads handle the incoming queries themselves. The dispatched thread enabled by `pdns-distributes-queries` tries to send the same queries to the same thread to maximize the cache-hit ratio, but it might become a bottleneck if the incoming queries rate is too high to be handled by a single thread. If `pdns-distributes-queries` is set to false and either `SO\_REUSEPORT` support is not available or the `reuseport` directive is set to false, all worker threads share the same listening sockets. This prevents a single thread from having to handle every incoming queries, but can lead to thundering herd issues where all threads are awoken at once when a query arrives. If `SO\_REUSEPORT` support is available and `reuseport` is set to true, separate listening sockets are opened for each worker thread and the query distributions is handled by the kernel, avoiding any thundering herd issue as well as preventing the distributor thread from becoming the bottleneck. -- For best PowerDNS Recursor performance, use a recent version of your operating system, since this generally offers the best event multiplexer implementation available (kqueue, epoll, ports or /dev/poll). +- For best PowerDNS Recursor performance, use a recent version of your operating system, since this generally offers the best event multiplexer implementation available (`kqueue`, `epoll`, `ports` or `/dev/poll`). +- Compile using `g++ 4.1` or later. This compiler really does a good job on PowerDNS, much better than 3.4 or 4.0. +- On AMD/Intel hardware, wherever possible, run a 64-bit binary. This delivers a nearly twofold performance increase. On UltraSPARC, there is no need to run with 64 bits. + +- Consider performing a 'profiled build' by building with `gprof` support enabled, running the recursor a bit then feed that info into the next build. This is good for a 20% performance boost in some cases. +- When running with >3000 queries per second, and running Linux versions prior to 2.6.17 on some motherboards, your computer may spend an inordinate amount of time working around an ACPI bug for each call to gettimeofday. This is solved by rebooting with `clock=tsc` or upgrading to a 2.6.17 kernel. + + The above is relevant if dmesg shows **Using pmtmr for high-res timesource** + - A Recursor under high load puts a severe stress on any stateful (connection tracking) firewall, so much so that the firewall may fail. - Specifically, many Linux distributions run with a connection tracking firewall configured. For high load operation (thousands of queries/second), It is advised to either turn off iptables completely, or use the 'NOTRACK' feature to make sure DNS traffic bypasses the connection tracking. + Specifically, many Linux distributions run with a connection tracking firewall configured. For high load operation (thousands of queries/second), It is advised to either turn off iptables completely, or use the `NOTRACK` feature to make sure DNS traffic bypasses the connection tracking. Sample Linux command lines would be: @@ -47,7 +48,7 @@ ip6tables -I OUTPUT -p udp --sport 53 -j ACCEPT When using FirewallD (Centos 7+ / RedHat 7+ / Fedora 21+) connection tracking can be disabled via direct rules. -The settings can be made permanent by using the --permanent flag. +The settings can be made permanent by using the `--permanent` flag. ``` ## IPv4 firewall-cmd --direct --add-rule ipv4 raw OUTPUT 0 -p udp --dport 53 -j CT --notrack