- tor-relays - lists.torproject.org

Re: [tor-relays] How to Run High Capacity Tor Relays
by Green Dream 24 Jul '15

24 Jul '15

Pardon the thread necromancy, but I'm wondering if this document ever made its way off this mailing list and onto a blog? Or perhaps there is some other modern doc covering this topic? I've recently setup a relay on a Gb/s fiber connection, and am struggling to understand how to optimize performance. It's not clear 5 years later which if any of the tweaks listed below are still relevant. I'm running a modern debian-based system. Thanks in advance. > After talking to Moritz and Olaf privately and asking them about their > nodes, and after running some experiments with some high capacity > relays, I've begun to realize that running a fast Tor relay is a > pretty black art, with a lot of ad-hoc practice. Only a few people > know how to do it, and if you just use Linux and Tor out of the box, > your relay will likely underperform on 100Mbit links and above. > In the interest of trying to help grow and distribute the network, my > ultimate plan is to try to collect all of this lore, use Science to > divine out what actually matters, and then write a more succinct blog > post about it. > However, that is a lot of work. It's also not totally necessary to do > all this work, when you can get a pretty good setup with a rough > superset of all of the ad-hoc voodoo. This post is thus about that > voodoo. > Hopefully others will spring forth from the darkness to dump their own > voodoo in this thread, as I suspect there is one hell of a lot of it > out there, some (much?) of which I don't yet know. Likewise, if any > blasphemous heretic wishes to apply Science to this voodoo, they > should yell out, "Stand Back, I'm Doing Science!" (at home please, not > on this list) and run some experiments to try to eliminate options > that are useless to Tor performance. Or cite academic research papers. > (But that's not Science, that's computerscience - which is a religion > like voodoo, but with cathedrals). > Anyway, on with the draft: > > == Machine Specs == > First, you want to run your OS in x64 mode because openssl should do > crypto faster in 64bit. > Tor is currently not fully multithreaded, and tends not to benefit > beyond 2 cores per process. Even then, the benefit is still marginal > beyond just 1 core. 64bit Tor nodes require about one 2Ghz Xeon/Core2 > core per 100Mbit of capacity. > Thus, to fill an 800Mbit link, you need at least a dual socket, quad > core cpu config. You may be able to squeeze a full gigabit out of one > of these machines. As far as I know, no one has ever done this with > Tor, on any one machine. > The i7's also just came out in this form factor, and can do > hyperthreading (previous models may list 'ht' in cpuinfo, but actually > don't support it). This should give you a decent bonus if you set > NumCPUs to 2, since ht tends to work better with pure integer math > (like crypto). We have not benchmarked this config yet though, but I > suspect it should fill a gigabit link fairly easily, possibly > approaching 2Gbit. > At full capacity, exit node Tor processes running at this rate consume > about 500M of ram. You want to ensure your ram speed is sufficient, > but most newish hardware is good. Using on this chart: > > https://secure.wikimedia.org/wikipedia/en/wiki/List_of_device_bandwidths#Me… > you can do the math and see that with a dozen memcpys in each > direction, you come out needing DDR2 to be able to push 1Gbit full > duplex. > As far as ethernet cards, the Intel e1000e *should* be theoretically > good, but they seem to fail at properly irq balancing across multiple > CPUs on recent kernels, which can cause you to bottleneck at 100% CPU > on one core. At least that has been Moritz's experience. In our > experiments, the RTL-8169 works fine (once tweaked, see below). > > == System Tweakscript Wibbles and Config Splatters == > First, you want to ensure that you run no more than 2 Tor instances > per IP. Any more than this and clients will ignore them. > Next, paste the following smattering into the shell (or just read it > and make your own script): > # Set the hard limit of open file descriptors really high. > # Tor will also potentially run out of ports. > ulimit -SHn 65000 > # Set the txqueuelen high, to prevent premature drops > ifconfig eth0 txqueuelen 20000 > # Tell our ethernet card (interrupt found from /proc/interrupts) > # to balance its IRQs across one whole CPU socket (4 cpus, mask 0f). > # You only want one socket for optimal ISR and buffer caching. > # > # Note that e1000e does NOT seem to obey this, but RTL-8169 will. > echo 0f > /proc/irq/17/smp_affinity > # Make sure you have auxiliary nameservers. I've seen many ISP > # nameservers fall over under load from fast tor nodes, both on our > # nodes and from scans. Or run caching named and closely monitor it. > echo "nameserver 8.8.8.8" >> /etc/resolv.conf > echo "nameserver 4.2.2.2" >> /etc/resolv.conf > # Load an amalgam of gigabit-tuning sysctls from: > # http://datatag.web.cern.ch/datatag/howto/tcp.html > # http://fasterdata.es.net/TCP-tuning/linux.html > # http://www.acc.umu.se/~maswan/linux-netperf.txt > # http://www.psc.edu/networking/projects/tcptune/#Linux > # and elsewhere... > # We have no idea which of these are needed yet for our actual use > # case, but they do help (especially the nf-contrack ones): > sysctl -p << EOF > net.ipv4.tcp_rmem = 4096 87380 16777216 > net.ipv4.tcp_wmem = 4096 65536 16777216 > net.core.netdev_max_backlog = 2500 > net.ipv4.tcp_no_metrics_save = 1 > net.ipv4.tcp_moderate_rcvbuf = 1 > net.core.rmem_max = 1048575 > net.core.wmem_max = 1048575 > net.ipv4.ip_local_port_range = 1025 61000 > net.ipv4.tcp_synack_retries = 3 > net.ipv4.tcp_tw_recycle = 1 > net.ipv4.tcp_max_syn_backlog = 10240 > net.ipv4.tcp_fin_timeout = 30 > net.ipv4.tcp_keepalive_time = 1200 > net.netfilter.nf_conntrack_tcp_timeout_established=7200 > net.netfilter.nf_conntrack_checksum=0 > net.netfilter.nf_conntrack_max=131072 > net.netfilter.nf_conntrack_tcp_timeout_syn_sent=15 > net.ipv4.tcp_keepalive_time=60 > net.ipv4.tcp_keepalive_time = 60 > net.ipv4.tcp_keepalive_intvl = 10 > net.ipv4.tcp_keepalive_probes = 3 > net.ipv4.ip_local_port_range = 1025 65530 > net.core.netdev_max_backlog=300000 > net.core.somaxconn=20480 > net.ipv4.tcp_max_tw_buckets=2000000 > net.ipv4.tcp_timestamps=0 > vm.min_free_kbytes = 65536 > net.ipv4.ip_forward=1 > net.ipv4.tcp_syncookies = 1 > net.ipv4.tcp_synack_retries = 2 > net.ipv4.conf.default.forwarding=1 > net.ipv4.conf.default.proxy_arp = 1 > net.ipv4.conf.all.rp_filter = 1 > net.ipv4.conf.default.send_redirects = 1 > net.ipv4.conf.all.send_redirects = 0 > EOF > # XXX: ethtool wibbles > # You may also have to tweak some parameters with ethtool, possibly > # also enabling some checksum offloading or irq coalescing options to > # spare CPU, but for us this hasn't been needed yet. > > == Setting up the Torrc == > Basically you can just read through the stock example torrc, but there > are some as-yet undocumented magic options, and options that need new > defaults. > # NumCPUs doesn't provide any benefit beyond 2, and setting it higher > # may cause cache misses. > NumCPUs 2 > # These options have archaic maximums of 2-5Mbyte > BandwidthRate 100 MB > BandwidthBurst 200 MB > > == Waiting for the Bootstrap and Measurement Process == > Perhaps the most frustrating part of this setup is how long it takes > for you to acquire traffic. If you are starting new at an ISP, I would > consider only 200-400Mbit for your first month. Hitting that by the > end of the month may be a challenge, mostly because their may be dips > and total setbacks along the way. > The slow rampup is primarily due to limitations in Tor's ability to > rapidly publish descriptor updates, and to measure relays. > It ends up taking about 2-3 days to hit an observed bandwidth of > 2Mbyte/sec per relay, but it can take well over a week or more (Moritz, do > you have a better number?) to reach 8-9Mbyte/relay. This is for an > Exit node. A middle node will likely gather traffic slower. Also once > you crash, you lose it. This bug is about that issue: > https://trac.torproject.org/projects/tor/ticket/1863 > There is also a potential dip when you get the Guard flag, as our load > balancing formulas try to avoid you, but no clients have chosen you > yet. Changes to the authority voting on Guards in Tor 0.2.2.15 should > make this less drastic. It is also possible that your observed > bandwidth will be greater than without it. However, it will still take > up to 2 months for clients to choose you as their new Guard. > > == Running temporary auxiliary nodes == > One way to shortcut this process and avoid paying for bandwidth you > don't use is to spin up a bunch of temporary nodes to utilize the CPU > and quickly gather that easy first 2MB/sec of observed bandwidth. > But you need the spare IPs to do this. > > == Monitoring == > Personally, I prefer console-based options like nload, top, and > Damian's arm (http://www.atagar.com/arm/) because I don't like the > idea of running extra services to publish my monitoring data to the > world. > Other people have web-based monitoring using things like munin and > mrtg. It would be nice to get a script/howto for that too. > > == Current 1-Box Capacity Record == > Our setup has topped at 450Mbit, but averages between 300-400Mbit. We > are currently having uptime issues due to heat (melting, poorly > ventilated harddrives). It is likely that once we resolve this, we > will continually increase to our CPU ceiling. > I believe Moritz and Olaf also push this much capacity, possibly a bit > more, but with less nodes (4 as opposed to our 8). I hear Jake is also > ramping up some Guard nodes (or maybe I didn't? Did I just betray you > again Jake?) > > == Did I leave anything out? == > Well, did I? > > -- > Mike Perry > Mad Computer Scientist > fscked.org evil labs

8 11

Running a relay in the Netherlands
by TorOps 24 Jul '15

24 Jul '15

Hello, I am about to move to the Netherlands and will, as part of the move, decommission the server my relay is currently running on. I'd like to be able to continue to help, though, so I wonder how the legal climate is for Tor relays and/or exit nodes in the Netherlands? On a related topic, how smart/efficient/possible is it to run a relay/exit on a Raspberry Pi? Thanks for any info. -- Regards, StairNetTor Operator

6 7

The ultimate DMCA culprit
by I 24 Jul '15

24 Jul '15

2 1

[warn] Content-Length is less than zero; it looks like someone is trying to crash us
by Toralf Förster 24 Jul '15

24 Jul '15

4 6

Fwd: Tor family graphs
by Virgil Griffith 23 Jul '15

23 Jul '15

Hello tor-relays@ We are still working on your nice relay incentive as and part of that we've been looking at how to partition relays into different families with it's not 100% obvious what that groupings should be. For those that are interested in the family connections, I have some pretty PDFs for you. I present three graphs of all Tor relays (nodes) with at least one family connection (edge). (1) only symmetric edges shown (black) -- http://dl.dropbox.com/u/3308162/sym.pdf (2) only asymmetric edges shown (red) -- http://dl.dropbox.com/u/3308162/asym.pdf (3) both symmetric (black) and asymmetric (red) shown -- http://dl.dropbox.com/u/3308162/both.pdf Notes: * A node is colored red if and only if it is the origin of an asymmetric connection. Ergo, every red node has at least one red edge, and vice-versa. * Blue edges are self-connections. I presume the Tor directory authorities should be excluding should these edges from the consensus---unless you all like being cute? Unfortunately you cannot click to see where you are in the graph. Hopefully in a future version you'll be able to click-around using D3.js or some such. -V

4 8

OpenBSD: tor rc script: don't kill unrelated tor instances (patch)
by nusenu 23 Jul '15

23 Jul '15

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 Hi Pascal, what do you think of changing OpenBSD's tor rc script to require perfect process matches when sending signals to them instead of the current "kill everything that starts with..." approach? I've put tor-relays on CC so people can speak up if this change is not desired or breaks anyone's environment - I believe it fixes them. Problem: /etc/rc.d/tor stop might kill all (including unrelated) tor instances instead of the intended daemon only. /etc/rc.d/tor start might never start the intended daemon if another tor instance is already running (rc_check believes tor is already running). /etc/rc.d/tor restart might kill all tor instances and starts only one. references: http://article.gmane.org/gmane.os.openbsd.misc/222896 One line "patch" for /etc/rc.d/tor to address this issue: (tested with and without custom daemon_flags) 8a9,10 > pexp="${daemon}${daemon_flags:+ ${daemon_flags}}$" > (this line is a complete copy from rc.subr with the addition of one char: $ ) thanks, nusenu https://github.com/nusenu/ansible-relayor/issues/40 -----BEGIN PGP SIGNATURE----- iQIcBAEBCgAGBQJViSx3AAoJEFv7XvVCELh0y8UQAJgb6JVbKde/xf79YJJr8LW1 t+Rji8A5zZ9VsjcW4Pguf/OZsQEN3MEIkjzTM3kw0q9S8CPnDbF3IYOaZj4ewYkX 8OoNmHfFbcQCC0YCJBlbUJMBtNJqi8pg7qRY4o+qY9KKa9ekUhPer7kzUt4N1A+T an4z44lh3ytAcehyFxo6hpDGZHHGGsACEIql9Rav6v+DPCBSJnCZsmlT0OeTeV5k 5WEy9nTVzdkX4mKs1xXv8YJFggCrb1uur3q91/5ZGhpKADfRj6T+1i/9622Bcki9 17ADc4ZI73dP3ZelKvpZ+FXhaiZLn6tugdj2dcqnXU8Zras6jKToupFi2nB8xfTV f70qSdkMP6WOJReCP+KTAGHiCkapyoc9V+8569iZIjUXuD7GbbSpP6I1rOoqSLYH rao6WpqHVfSMQ5jCaECHBbZY62qBhHH83B/um3nG+WXvvWDPpzjkbEx56RxH3UUo yZ4naGenbxQzCXsGXhEOAmUkJjSmW+Hw75EyObBLAp00+Q8zAXkHnFOqRGbRuxdl IKqAYsfGNLr7kPBvz9pxfnOJMfyIBDQ2P2WNyKXvYLME3wKbYMazVxd7cXzmAV5g QthMuFJ/JhWYI9Lb1U+IQq7LOX+pEWU6u/L2xqjTDj7VMn4UF1WZ6UHhnaLMAotZ lfiTKPnopA62t+X05ztR =ysgm -----END PGP SIGNATURE-----

3 5

Re: [tor-relays] Running a relay in the Netherlands
by Jan Hendrik den Besten 22 Jul '15

22 Jul '15

> Date: Tue, 21 Jul 2015 00:13:19 +0200 > From: t0reo(a)t0reo.eu > To: tor-relays(a)lists.torproject.org > Subject: Re: [tor-relays] Running a relay in the Netherlands > > Hello All ! > > About running a relay in the NL, what host company would you guys > recommend ? > > I also have that idea of running first a relay then an exit node, and > would like some basic information or recommendation about host > providers, like price /month, bandwidth included, satisfaction or > quality, level of tor friendliness, whatever... > > Thx for any help you can provide, > tOreo I have my node running here in The Netherlands at UPC, now merged with Ziggo. I contacted them once: back then they did not have a problem running even an exit node. BR, JH

4 3

[Relay] Hibernation Reset
by Tor Operator 22 Jul '15

22 Jul '15

Hi gents, I rencetly had one of my relay fall into hibernation. It seems that simply restarting the service doesn't change the hibernation status since Tor is still thinking that the BW limits have been overrun. Is the proper method to reset the status of the node is simply to delete the "state" file in "/var/lib/tor/". For now, I just set back to 0 the "AccountingBytesReadInInterval" and "AccountingBytesWrittenInInterval" counters and the node was able to wake up but that doesn't seem like a very elegant way to do it. Thanks,

2 3

BWauth's / TorFlow seem better
by starlight.2015q2＠binnacle.cx 22 Jul '15

22 Jul '15

Over the last week it seems to me that some improvement has gone into TorFlow and the BWauths are performing better. In particular the weightings calculated by each BWauth have stabilized and become less erratic. Several relays in the same region of a large network as my relay are now showing a roughly matching pattern of ascending measures, from smallest to largest: longclaw, gabelmoo, maatuska, moria1. One would expect this but it was not true in the past. One fast relay I watch, 'pixelminer' had a tendency to be yanked from one extreme to another (e.g. 10k to 120k and back) and now has a placid consensus running in the middle of the range (still apparent in the {presumably stabilized} component values).

1 1

Boosting throughput with own DNS resolvers
by Tim Semeijn 21 Jul '15

21 Jul '15

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 Recently I noticed my Tor Exit nodes were showing nameserver errors in the tor log and I decided to set up two private DNS resolvers (pdns-recursor). Since I use those I have seen an increase of traffic throughput on my Exit nodes to approx. 150%. I feel I am finally utilizing the resources available. All bigger Tor relay operators will probably already do it this way, but as I myself have long been using Google DNS or other privacy-aware DNS resolvers on my nodes I just wanted to throw this out in the open. How many of you are already using private DNS resolvers for your nodes? Any feedback/ideas about this? - -- Tim Semeijn Babylon Network pgp 0x5B8A4DDF -----BEGIN PGP SIGNATURE----- Version: GnuPG/MacGPG2 v2.0.19 (Darwin) Comment: GPGTools - http://gpgtools.org iQIcBAEBCgAGBQJVrAzLAAoJEIZioqpbik3fmkcP/R5DXaKoVHUY6SjiSJi0n8ug 6NMF2KTXNP3f7vFbuzjWdqdo4Hfj2Zj6SyKc+i99/pJFiISQiGsMfeWjwdGGqaxR hlCNxYAsnV2kFd8UK435kOv2LclPFDMPjFk9OLr+DDQ8ZFmkpF80+95fqwzKaPr0 XtltMNBDxO8uCC4zsNYpT2BlO4EwhMTB5/79lNJ44MlWaSaPd6BAqoDfExyBjZfV v7bvQxqSNxF5jZvoNBRw1/t1jc8AXZF7UxkkR62ff7cBiQsDo16QK4sRcDTNRziM y5fm8Tt9W+19gsf0CNPo7lj7j/T7yHj3gClBi7TmhSxsIO7ylpeuX6L9hsAkzOJm o9TMgkO11T6h0e5EiCJh6P0ov21pqUJ61ScN/D0qiHVJC42UM/diGqVFgev3AT3u NImaA7IPUXvDC+Z+EQulnBP4XdIuukozU/4DJFF4x5tDhyTTXhCInrVsaMB4rOIU lLfQLZiCCC39uxIBs+xvS+rN1+wAVq4VH4Wbd5w4tH7e2Ic0BLBaI71z00RoTiF/ i8TK5IDP+gfykBemXtAcZeyyTkuzf6fFZg3NKfCPGbOqvpLEGEk26Mp8ANv+csTb HQXbmFtPX/SUhxm2zdMzA2uq8gzHOllxmEKriYyon499ZfCImbmBU+1kTKo+v2p7 lOMSGXcjkCVgAwtnZNKw =YekJ -----END PGP SIGNATURE-----

5 6