svn commit: r50196 - head/en_US.ISO8859-1/htdocs/news/status
Benjamin Kaduk
bjk at FreeBSD.org
Sun Apr 23 03:15:50 UTC 2017
Author: bjk
Date: Sun Apr 23 03:15:49 2017
New Revision: 50196
URL: https://svnweb.freebsd.org/changeset/doc/50196
Log:
Add 2017Q1 Ceph entry from Willem Jan Withagen
Modified:
head/en_US.ISO8859-1/htdocs/news/status/report-2017-01-2017-03.xml
Modified: head/en_US.ISO8859-1/htdocs/news/status/report-2017-01-2017-03.xml
==============================================================================
--- head/en_US.ISO8859-1/htdocs/news/status/report-2017-01-2017-03.xml Sat Apr 22 18:07:25 2017 (r50195)
+++ head/en_US.ISO8859-1/htdocs/news/status/report-2017-01-2017-03.xml Sun Apr 23 03:15:49 2017 (r50196)
@@ -1045,4 +1045,143 @@
etc.</task>
</help>
</project>
+
+ <project cat='proj'>
+ <title>Ceph on &os;</title>
+
+ <contact>
+ <person>
+ <name>
+ <given>Willem Jan</given>
+ <common>Withagen</common>
+ </name>
+ <email>wjw at digiware.nl</email>
+ </person>
+ </contact>
+
+ <links>
+ <url href="http://ceph.com">Ceph Main Site</url>
+ <url href="https://github.com/ceph/ceph">Main Repository</url>
+ <url href="https://github.com/wjwithagen/ceph">My &os; Fork </url>
+ </links>
+
+ <body>
+ <p>Ceph is a distributed object store and file system designed to provide
+ excellent performance, reliability and scalability.</p>
+
+ <ul>
+ <li><p>Object Storage</p>
+
+ <p>Ceph provides seamless access to objects using native
+ language bindings or <tt>radosgw</tt>, a REST interface
+ that is compatible with applications written for S3 and
+ Swift.</p></li>
+
+ <li><p>Block Storage</p>
+
+ <p>Ceph’s RADOS Block Device (RBD) provides access to block
+ device images that are striped and replicated across the
+ entire storage cluster.</p></li>
+
+ <li><p>File System</p>
+
+ <p>Ceph provides a POSIX-compliant network file system that
+ aims for high performance, large data storage, and maximum
+ compatibility with legacy applications.</p></li>
+ </ul>
+
+ <p>I started looking into Ceph, because the HAST solution with
+ CARP and <tt>ggate</tt> did not really do what I was looking
+ for. But I aim to run a Ceph storage cluster of storage nodes
+ that are running ZFS. User stations would be running
+ <tt>bhyve</tt> on RBD disk that are stored in Ceph.</p>
+
+ <p>The &os; build will build most of the tools in Ceph.</p>
+
+ <p>The most notable progress since the last report:</p>
+
+ <ul>
+ <li>The most important change is that a port has been
+ submitted: <tt>net/ceph-devel</tt>. However, it does not
+ yet contain <tt>ceph-fuse</tt>.</li>
+
+ <li>Regular updates to the <tt>ceph-devel</tt> port are
+ expected, with the next one coming in April.</li>
+
+ <li><tt>ceph-fuse</tt> works, allowing one to mount a CephFS
+ filesystem on a &os; system and perform normal operations.</li>
+
+ <li><tt>ceph-disk prepare</tt> and <tt>activate</tt> work for
+ FileStore on ZFS, allowing for easy creation of OSDs.</li>
+
+ <li>RBD is actually buildable and can be used to manage RADOS BLOCK
+ DEVICEs.</li>
+
+ <li>Most of the awkward dependancies on Linux-isms are deleted
+ — only <tt>/bin/bash</tt> is here to stay.</li>
+ </ul>
+
+ <p>To get things running on a &os; system, run <tt>pkg install
+ net/ceph-devel</tt> or clone <a
+ href="https://github.com/wjwithagen/ceph">https://github.com/wjwithagen/ceph</a>
+ and build manually by running <tt>./do_freebsd.sh</tt> in the
+ checkout root.</p>
+
+ <p>Parts not (yet) included:</p>
+
+ <ul>
+ <li>KRBD: Kernel Rados Block Devices are implemented in the
+ Linux kernel, but not yet in the &os; kernel. It is possible
+ that <tt>ggated</tt> could be used as a template, since it
+ does similar things, just between two disks. It also has a
+ userspace counterpart, which could ease development.</li>
+
+ <li>BlueStore: &os; and Linux have different AIO APIs, and
+ that incompatibility needs to resolved somehow. Additionally,
+ there is discussion in &os; about <tt>aio_cancel</tt> not
+ working for all devicetypes.</li>
+
+ <li>CephFS as native filesystem: though <tt>ceph-fuse</tt>
+ works, it can be advantageous to have an in-kernel
+ implementation for heavy workloads. Cython tries to access
+ an internal field in <tt>struct dirent</tt>, which does not
+ compile.</li>
+ </ul>
+ </body>
+
+ <help>
+ <task>Run integration tests to see if the &os; daemons will work
+ with a Linux Ceph platform.</task>
+
+ <task>Compile and test the userspace RBD (Rados Block Device).
+ This currently works but testing has been limitted.</task>
+
+ <task>Investigate and see if an in-kernel RBD device could be
+ developed akin to <tt>ggate</tt>.</task>
+
+ <task>Investigate the keystore, which can be embedded in the
+ kernel on Linux and currently prevents building Cephfs and
+ some other parts. The first question is whether it is really
+ required, or only KRBD requires it.</task>
+
+ <task>Scheduler information is not used at the moment, because the
+ schedulers work rather differently between Linux and &os;.
+ But at a certain point in time, this will need some attention
+ (in src/common/Thread.cc).</task>
+
+ <task>Improve the &os; initscripts in the Ceph stack, both for
+ testing purposes and for running Ceph on production machines.
+ Work on <tt>ceph-disk</tt> and <tt>ceph-deploy</tt> to make it
+ more &os;- and ZFS- compatible.</task>
+
+ <task>Build a test cluster and start running some of the
+ teuthology integration tests on it. Teuthology wants to build
+ its own <tt>libvirt</tt> and that does not quite work with all
+ the packages &os; already has in place. There are many
+ details to work out here.</task>
+
+ <task>Design a vitual disk implementation that can be used with
+ <tt>bhyve</tt> and attached to an RBD image.</task>
+ </help>
+ </project>
</report>
More information about the svn-doc-all
mailing list