diff options
| -rw-r--r-- | ceph.spec.in | 3 | ||||
| -rw-r--r-- | debian/ceph-test.install | 1 | ||||
| -rw-r--r-- | debian/ceph.install | 1 | ||||
| -rw-r--r-- | debian/librados-dev.install | 1 | ||||
| -rw-r--r-- | doc/faq.rst | 35 | ||||
| -rw-r--r-- | doc/start/quick-cephfs.rst | 13 | ||||
| -rw-r--r-- | doc/start/quick-rbd.rst | 9 |
7 files changed, 55 insertions, 8 deletions
diff --git a/ceph.spec.in b/ceph.spec.in index 4724dbb9e95..a260d32e0f7 100644 --- a/ceph.spec.in +++ b/ceph.spec.in @@ -345,6 +345,7 @@ fi %{_bindir}/rbd %{_bindir}/ceph-debugpack %{_bindir}/ceph-coverage +%{_bindir}/ceph_mon_store_converter %{_initrddir}/ceph /sbin/mkcephfs /sbin/mount.ceph @@ -417,6 +418,7 @@ fi %{_includedir}/rados/buffer.h %{_includedir}/rados/page.h %{_includedir}/rados/crc32c.h +%{_includedir}/rados/rados_types.h %dir %{_includedir}/rbd %{_includedir}/rbd/librbd.h %{_includedir}/rbd/librbd.hpp @@ -570,6 +572,7 @@ fi %{_bindir}/ceph_test_rados_open_pools_parallel %{_bindir}/ceph_test_rados_watch_notify %{_bindir}/ceph_test_signal_handlers +%{_bindir}/ceph_test_store_tool %{_bindir}/ceph_test_timers %{_bindir}/ceph_tpbench %{_bindir}/ceph_xattr_bench diff --git a/debian/ceph-test.install b/debian/ceph-test.install index 1aba361ee9a..63cb379e156 100644 --- a/debian/ceph-test.install +++ b/debian/ceph-test.install @@ -56,6 +56,7 @@ usr/bin/ceph_test_rados_list_parallel usr/bin/ceph_test_rados_open_pools_parallel usr/bin/ceph_test_rados_watch_notify usr/bin/ceph_test_signal_handlers +usr/bin/ceph_test_store_tool usr/bin/ceph_test_timers usr/bin/ceph_tpbench usr/bin/ceph_xattr_bench diff --git a/debian/ceph.install b/debian/ceph.install index fb70d9b9380..b942679fd73 100644 --- a/debian/ceph.install +++ b/debian/ceph.install @@ -6,6 +6,7 @@ usr/bin/ceph-run usr/bin/ceph-mon usr/bin/ceph-osd usr/bin/ceph-debugpack +usr/bin/ceph_mon_store_converter sbin/ceph-disk-prepare usr/sbin/ sbin/ceph-disk-activate usr/sbin/ sbin/ceph-create-keys usr/sbin/ diff --git a/debian/librados-dev.install b/debian/librados-dev.install index ecc29c7cf36..876382b0a3c 100644 --- a/debian/librados-dev.install +++ b/debian/librados-dev.install @@ -6,5 +6,6 @@ usr/include/rados/librados.hpp usr/include/rados/buffer.h usr/include/rados/page.h usr/include/rados/crc32c.h +usr/include/rados/rados_types.h usr/bin/librados-config usr/share/man/man8/librados-config.8 diff --git a/doc/faq.rst b/doc/faq.rst index e702b22377f..cec5808d7e8 100644 --- a/doc/faq.rst +++ b/doc/faq.rst @@ -51,6 +51,40 @@ Ceph also runs on Fedora and Enterprise Linux derivates (RHEL, CentOS) using You can also download Ceph source `tarballs`_ and build Ceph for your distribution. See `Installation`_ for details. +.. _try-ceph: + +How Can I Give Ceph a Try? +========================== + +Follow our `Quick Start`_ guides. They will get you up an running quickly +without requiring deeper knowledge of Ceph. Our `Quick Start`_ guides will also +help you avoid a few issues related to limited deployments. If you choose to +stray from the Quick Starts, there are a few things you need to know. + +We recommend using at least two hosts, and a recent Linux kernel. In older +kernels, Ceph can deadlock if you try to mount CephFS or RBD client services on +the same host that runs your test Ceph cluster. This is not a Ceph-related +issue. It's related to memory pressure and needing to relieve free memory. +Recent kernels with up-to-date ``glibc`` and ``syncfs(2)`` reduce this issue +considerably. However, a memory pool large enough to handle incoming requests is +the only thing that guarantees against the deadlock occuring. When you run Ceph +clients on a Ceph cluster machine, loopback NFS can experience a similar problem +related to buffer cache management in the kernel. You can avoid these scenarios +entirely by using a separate client host, which is more realistic for deployment +scenarios anyway. + +We recommend using at least two OSDs with at least two replicas of the data. +OSDs report other OSDs to the monitor, and also interact with other OSDs when +replicating data. If you have only one OSD, a second OSD cannot check its +heartbeat. Also, if an OSD expects another OSD to tell it which placement groups +it should have, the lack of another OSD prevents this from occurring. So a +placement group can remain stuck "stale" forever. These are not likely +production issues. + +Finally, `Quick Start`_ guides are a way to get you up and running quickly. To +build performant systems, you'll need a drive for each OSD, and you will likely +benefit by writing the OSD journal to a separate drive from the OSD data. + How Many OSDs Can I Run per Host? ================================= @@ -346,3 +380,4 @@ Documentation for the build procedure. .. _Striping: ../architecture##how-ceph-clients-stripe-data .. _https://github.com/ceph/ceph/blob/master/doc/faq.rst: https://github.com/ceph/ceph/blob/master/doc/faq.rst .. _Filesystem Recommendations: ../rados/configuration/filesystem-recommendations +.. _Quick Start: ../start
\ No newline at end of file diff --git a/doc/start/quick-cephfs.rst b/doc/start/quick-cephfs.rst index 6674087f922..5e17c4d39a4 100644 --- a/doc/start/quick-cephfs.rst +++ b/doc/start/quick-cephfs.rst @@ -5,8 +5,6 @@ To use this guide, you must have executed the procedures in the `5-minute Quick Start`_ guide first. Execute this quick start on the client machine. -.. important:: Mount the CephFS filesystem on the client machine, - not the cluster machine. Kernel Driver ============= @@ -15,7 +13,12 @@ Mount Ceph FS as a kernel driver. :: sudo mkdir /mnt/mycephfs sudo mount -t ceph {ip-address-of-monitor}:6789:/ /mnt/mycephfs - + + +.. note:: Mount the CephFS filesystem on the client machine, + not the cluster machine. See `FAQ`_ for details. + + Filesystem in User Space (FUSE) =============================== @@ -24,6 +27,7 @@ Mount Ceph FS as with FUSE. Replace {username} with your username. :: sudo mkdir /home/{username}/cephfs sudo ceph-fuse -m {ip-address-of-monitor}:6789 /home/{username}/cephfs + Additional Information ====================== @@ -33,4 +37,5 @@ details on running CephFS in a production environment. .. _5-minute Quick Start: ../quick-start .. _CephFS: ../../cephfs/ -.. _Inktank: http://inktank.com
\ No newline at end of file +.. _Inktank: http://inktank.com +.. _FAQ: ../../faq#try-ceph diff --git a/doc/start/quick-rbd.rst b/doc/start/quick-rbd.rst index e7561ec9dd6..7300547e5ea 100644 --- a/doc/start/quick-rbd.rst +++ b/doc/start/quick-rbd.rst @@ -5,9 +5,6 @@ To use this guide, you must have executed the procedures in the `5-minute Quick Start`_ guide first. Execute this quick start on the client machine. -.. important:: Mount the block device on the client machine, - not the server machine. - #. Create a block device image. :: rbd create foo --size 4096 @@ -29,7 +26,11 @@ Quick Start`_ guide first. Execute this quick start on the client machine. sudo mkdir /mnt/myrbd sudo mount /dev/rbd/rbd/foo /mnt/myrbd +.. note:: Mount the block device on the client machine, + not the server machine. See `FAQ`_ for details. + See `block devices`_ for additional details. .. _5-minute Quick Start: ../quick-start -.. _block devices: ../../rbd/rbd
\ No newline at end of file +.. _block devices: ../../rbd/rbd +.. _FAQ: ../../faq#try-ceph |