From 14a9628f0552d3818cd58fb085e7544cdbb3b5eb Mon Sep 17 00:00:00 2001
From: Rob Austein <sra@hactrn.net>
Date: Wed, 3 Aug 2016 18:27:49 +0000
Subject: Dump of rpki.net Wiki, to capture content not linked into the manual.

---
 doc/wiki-dump/doc%2FRPKI%2FRP%2FHierarchicalRsync | 103 ++++++++++++++++++++++
 1 file changed, 103 insertions(+)
 create mode 100644 doc/wiki-dump/doc%2FRPKI%2FRP%2FHierarchicalRsync

(limited to 'doc/wiki-dump/doc%2FRPKI%2FRP%2FHierarchicalRsync')

diff --git a/doc/wiki-dump/doc%2FRPKI%2FRP%2FHierarchicalRsync b/doc/wiki-dump/doc%2FRPKI%2FRP%2FHierarchicalRsync
new file mode 100644
index 00000000..6727b073
--- /dev/null
+++ b/doc/wiki-dump/doc%2FRPKI%2FRP%2FHierarchicalRsync
@@ -0,0 +1,103 @@
+[[TracNav(doc/RPKI/TOC)]]
+[[PageOutline]]
+
+= Running a hierarchical rsync configuration =
+
+Having every relying party on the Internet contact every publication
+service is not terribly efficient.  In many cases, it may make more
+sense to use a hierarchical configuration in which a few "gatherer"
+relying parties contact the publication servers directly, while a
+collection of other relying parties get their raw data from the
+gatherers.
+
+ Note:: The relying parties in this configuration still perform their
+   own validation, they just let the gatherers do the work of
+   collecting the unvalidated data for them.
+
+A gatherer in a configuration like this would look just like a
+stand-alone relying party as discussed [[#cronjob|above]].  The only
+real difference is that a gatherer must also make its unauthenticated
+data collection available to other relying parties.  Assuming the
+standard configuration, this will be the directory
+`/var/rcynic/data/unauthenticated` and its subdirectories.
+
+There are two slightly different ways to do this with rsync:
+
+1. Via unauthenticated rsync, by configuring an `rsyncd.conf`
+   "module", or
+
+2. Via rsync over a secure transport protocol such as ssh.
+
+Since the downstream relying party performs its own validation in any
+case, either of these will work, but using a secure transport such as
+ssh makes it easier to track problems back to their source if a
+downstream relying party concludes that it's been receiving bad
+data.
+
+Script for a downstream relying party using ssh might look like this:
+
+{{{
+#!sh
+#!/bin/sh -
+
+PATH=/usr/bin:/bin:/usr/local/bin
+umask 022
+eval `/usr/bin/ssh-agent -s` >/dev/null
+/usr/bin/ssh-add /root/rpki_ssh_id_rsa 2>&1 | /bin/fgrep -v 'Identity added:'
+hosts='larry.example.org moe.example.org curly.example.org'
+for host in $hosts
+do
+  /usr/bin/rsync --archive --update --safe-links rpkisync@${host}:/var/rcynic/data/unauthenticated/ /var/rcynic/data/unauthenticated.${host}/
+done
+eval `/usr/bin/ssh-agent -s -k` >/dev/null
+for host in $hosts
+do
+  /usr/sbin/chroot -u rcynic -g rcynic /var/rcynic /bin/rcynic -c /etc/rcynic.conf -u /data/unauthenticated.${host}
+  /var/rcynic/bin/rcynic-html /var/rcynic/data/rcynic.xml /usr/local/www/data/rcynic.${host}
+done
+cd /var/rcynic/rpki-rtr
+/usr/bin/su -m rcynic -c '/usr/local/bin/rpki-rtr cronjob /var/rcynic/data/authenticated'
+}}}
+
+where /root/rpki_ssh_id_rsa is an SSH private key authorized to log in
+as user "rpkisync" on the gatherer machines.  If you want to lock this
+down a little tighter, you could use ssh's `command="..."`
+mechanism as described in the sshd documentation to restrict the
+rpkisync user so that it can only run this one rsync command.
+
+If you prefer to use insecure rsync, perhaps to avoid allowing the
+downstream relying parties any sort of login access at all on the
+gatherer machines, the configuration would look more like this:
+
+{{{
+#!sh
+#!/bin/sh -
+
+PATH=/usr/bin:/bin:/usr/local/bin
+umask 022
+hosts='larry.example.org moe.example.org curly.example.org'
+for host in $hosts
+do
+  /usr/bin/rsync --archive --update --safe-links rsync://${host}/unauthenticated/ /var/rcynic/data/unauthenticated.${host}/
+done
+for host in $hosts
+do
+  /usr/sbin/chroot -u rcynic -g rcynic /var/rcynic /bin/rcynic -c /etc/rcynic.conf -u /data/unauthenticated.${host}
+  /var/rcynic/bin/rcynic-html /var/rcynic/data/rcynic.xml /usr/local/www/data/rcynic.${host}
+done
+cd /var/rcynic/rpki-rtr
+/usr/bin/su -m rcynic -c '/usr/local/bin/rpki-rtr cronjob /var/rcynic/data/authenticated'
+}}}
+
+where "unauthenticated" here is an rsync module pointing at
+`/var/rcynic/data/unauthenticated` on each of the gatherer
+machines.  Configuration for such a module would look like:
+
+{{{
+#!ini
+[unauthenticated]
+    read only           = yes
+    transfer logging    = yes
+    path                = /var/rcynic/data/unauthenticated
+    comment             = Unauthenticated RPKI data
+}}}
-- 
cgit v1.2.3