1 <?xml version='1.0' encoding='UTF-8'?><chapter xmlns="http://docbook.org/ns/docbook" xmlns:xl="http://www.w3.org/1999/xlink" version="5.0" xml:lang="en-US" xml:id="upgradinglustre">
2 <title xml:id="upgradinglustre.title">Upgrading a Lustre* File System</title>
3 <para>This chapter describes interoperability between Lustre* software releases. It also provides
4 procedures for upgrading from a Lustre 1.8 release to a Lustre 2.x release, from a Lustre 2.x
5 release to a more recent Lustre 2.x release (major release upgrade), and from a Lustre 2.X.y
6 release to 2.X.y (minor release upgrade). It includes the following sections:</para>
9 <para><xref linkend="dbdoclet.50438205_82079"/></para>
12 <para><xref xmlns:xlink="http://www.w3.org/1999/xlink" linkend="Upgrading_2.x"/></para>
15 <para><xref xmlns:xlink="http://www.w3.org/1999/xlink" linkend="Upgrading_2.x.x"/></para>
18 <section xml:id="dbdoclet.50438205_82079">
20 <primary>Lustre</primary>
21 <secondary>upgrading</secondary>
23 </indexterm><indexterm>
24 <primary>upgrading</primary>
25 </indexterm>Release Interoperability and Upgrade Requirements</title>
26 <para><emphasis role="italic"><emphasis role="bold">Lustre software version 2.x release (major)
27 upgrade:</emphasis></emphasis><itemizedlist>
29 <para>All servers must be upgraded at the same time, while some or all clients may be
33 <para>All servers must be be upgraded to a Linux kernel supported by the Lustre software. See the Linux Test Matrix at <xref
34 xmlns:xlink="http://www.w3.org/1999/xlink" linkend="LustreTestMatrixTable"/> for a
35 list of tested Lustre distributions.</para>
38 <para>Clients to be upgraded to the Lustre 2.4 release or higher must be running a compatible Linux distribution. See the Linux Test Matrix at <xref
39 xmlns:xlink="http://www.w3.org/1999/xlink" linkend="LustreTestMatrixTable"/> for a
40 list of tested Linux distributions.</para>
42 </itemizedlist></para>
43 <para><emphasis role="italic"><emphasis role="bold">Lustre 2.X.y release (minor)
44 upgrade:</emphasis></emphasis></para>
47 <para>All servers must be upgraded at the same time, while some or all clients may be
51 <para>Rolling upgrades are supported for minor releases allowing individual servers and
52 clients to be upgraded without stopping the Lustre file system.</para>
56 <section xml:id="Upgrading_2.x">
58 <primary>upgrading</primary>
59 <secondary>major release (2.x to 2.x)</secondary>
60 </indexterm><indexterm>
61 <primary>wide striping</primary>
62 </indexterm><indexterm>
63 <primary>MDT</primary>
64 <secondary>multiple MDSx</secondary>
65 </indexterm>Upgrading to Lustre Release 2.x (Major Release)</title>
66 <para> The procedure for upgrading a Lustre release 2.x file system to a more recent 2.x release
67 of the Lustre software is described in this section. </para>
69 <para>This procedure can also be used to upgrade Lustre release 1.8.6-wc1 or later to any
70 Lustre release 2.x. To upgrade other versions of 1.8.x, contact your support
74 <para condition="l22">In Lustre release 2.2, a feature has been added that allows striping
75 across up to 2000 OSTs. By default, this "wide striping" feature is disabled. It is
76 activated by setting the <literal>large_xattr</literal> option on the MDT using either
77 <literal>mkfs.lustre</literal> or <literal>tune2fs</literal>. For example after upgrading
78 an existing file system to Lustre release 2.2 or later, wide striping can be enabled by
79 running the following command on the MDT device before mounting
80 it:<screen>tune2fs -O large_xattr</screen>Once the wide striping feature is enabled and in
81 use on the MDT, it is not possible to directly downgrade the MDT file system to an earlier
82 version of the Lustre software that does not support wide striping. To disable wide striping:<orderedlist>
84 <para>Delete all wide-striped files. </para>
86 <para>Use <literal>lfs_migrate</literal> with the option <literal>-c</literal>
87 <replaceable>stripe_count</replaceable> (set <replaceable>stripe_count</replaceable>
88 to 160) to move the files to another location.</para>
91 <para>Unmount the MDT.</para>
94 <para>Run the following command to turn off the <literal>large_xattr</literal>
95 option:<screen>tune2fs -O ^large_xattr</screen></para>
99 <note condition="l23">
100 <para>To generate a list of all files with more than 160 stripes use <literal>lfs
101 find</literal> with the <literal>--stripe-count</literal>
102 option:<screen>lfs find ${mountpoint} --stripe-count=+160</screen></para>
104 <note condition="l24">
105 <para>In Lustre release 2.4, a new feature allows using multiple MDTs, which can each serve
106 one or more remote sub-directories in the file system. The <literal>root</literal> directory
107 is always located on MDT0. </para>
108 <para>Note that clients running a release prior to the Lustre 2.4 release can only see the
109 namespace hosted by MDT0 and will return an IO error if an attempt is made to access a
110 directory on another MDT.</para>
112 <para>To upgrade a Lustre release 2.x file system to a more recent major release, complete these
116 <para>Create a complete, restorable file system backup. </para>
118 <para>Before installing the Lustre software, back up ALL data. The Lustre software
119 contains kernel modifications that interact with storage devices and may introduce
120 security issues and data loss if not installed, configured, or administered properly. If
121 a full backup of the file system is not practical, a device-level backup of the MDT file
122 system is recommended. See <xref linkend="backupandrestore"/> for a procedure.</para>
126 <para>Shut down the file system by unmounting all clients and servers in the order shown
127 below (unmounting a block device causes the Lustre software to be shut down on that
129 <orderedlist numeration="loweralpha">
131 <para>Unmount the clients. On each client node, run:</para>
132 <screen>umount -a -t lustre</screen>
135 <para>Unmount the MDT. On the MDS node, run:</para>
136 <screen>umount -a -t lustre</screen>
139 <para>Unmount all the OSTs. On each OSS node, run:</para>
140 <screen>umount -a -t lustre</screen>
145 <para>Upgrade the Linux operating system on all servers to a compatible
146 (tested) Linux distribution and reboot. See the Linux Test Matrix at <xref
147 xmlns:xlink="http://www.w3.org/1999/xlink" linkend="LustreTestMatrixTable"/>.</para>
150 <para>Upgrade the Linux operating system on all clients to RHEL 6 or other compatible
151 (tested) distribution and reboot. See the Linux Test Matrix at <xref
152 xmlns:xlink="http://www.w3.org/1999/xlink" linkend="LustreTestMatrixTable"/>.</para>
155 <para>Download the Lustre server RPMs for your platform from the <link
156 xl:href="https://wiki.hpdd.intel.com/display/PUB/Lustre+Releases">Lustre Releases</link>
157 repository. See <xref xmlns:xlink="http://www.w3.org/1999/xlink"
158 linkend="table_cnh_5m3_gk"/> for a list of required packages.</para>
161 <para>Install the Lustre server packages on all Lustre servers (MGS, MDSs, and OSSs).</para>
162 <orderedlist numeration="loweralpha">
164 <para>Log onto a Lustre server as the <literal>root</literal> user</para>
167 <para>Use the <literal>yum</literal> command to install the packages:</para>
169 <screen># yum --nogpgcheck install pkg1.rpm pkg2.rpm ...</screen>
173 <para>Verify the packages are installed correctly:</para>
175 <screen>rpm -qa|egrep "lustre|wc"</screen>
179 <para>Repeat these steps on each Lustre server.</para>
184 <para>Download the Lustre client RPMs for your platform from the <link
185 xl:href="https://wiki.hpdd.intel.com/display/PUB/Lustre+Releases">Lustre Releases</link>
186 repository. See <xref xmlns:xlink="http://www.w3.org/1999/xlink"
187 linkend="table_j3r_ym3_gk"/> for a list of required packages.</para>
189 <para>The version of the kernel running on a Lustre client must be the same as the version
190 of the <literal>lustre-client-modules-</literal><replaceable>ver</replaceable> package
191 being installed. If not, a compatible kernel must be installed on the client before the
192 Lustre client packages are installed.</para>
196 <para>Install the Lustre client packages on each of the Lustre clients to be
198 <orderedlist numeration="loweralpha">
200 <para>Log onto a Lustre client as the <literal>root</literal> user.</para>
203 <para>Use the <literal>yum</literal> command to install the packages:</para>
205 <screen># yum --nogpgcheck install pkg1.rpm pkg2.rpm ...</screen>
209 <para>Verify the packages were installed correctly:</para>
211 <screen># rpm -qa|egrep "lustre|kernel"</screen>
215 <para>Repeat these steps on each Lustre client.</para>
220 <para condition="l22">(Optional) For upgrades to Lustre release 2.2 or higher, to enable
221 wide striping on an existing MDT, run the following command on the MDT
222 :<screen>mdt# tune2fs -O large_xattr <replaceable>device</replaceable></screen></para>
225 <para condition="l24">(Optional) For upgrades to Lustre release 2.4 or higher, to format an
226 additional MDT, complete these steps:<orderedlist numeration="loweralpha">
228 <para>Determine the index used for the first MDT (each MDT must have unique index).
229 Enter:<screen>client$ lctl dl | grep mdc
230 36 UP mdc lustre-MDT0000-mdc-ffff88004edf3c00 4c8be054-144f-9359-b063-8477566eb84e 5</screen></para>
231 <para>In this example, the next available index is 1.</para>
234 <para>Add the new block device as a new MDT at the next available index by entering
236 line):<screen>mds# mkfs.lustre --reformat --fsname=<replaceable>filesystem_name</replaceable> --mdt \
237 --mgsnode=<replaceable>mgsnode</replaceable> --index <replaceable>1</replaceable> <replaceable>/dev/mdt1_device</replaceable>
240 </orderedlist></para>
243 <para>(<?oxy_comment_start author="lbeberne" timestamp="20130815T140026-0700" comment="Have James test"?>Optional<?oxy_comment_end?>)
244 If you are upgrading to Lustre software release 2.3 or higher from Lustre software version 2.2 or earlier
245 and want to enable the quota feature, complete these steps: <orderedlist
246 numeration="loweralpha">
248 <para>Before setting up the file system, enter on both the MDS and
249 OSTs:<screen>tunefs.lustre --quota</screen></para>
252 <para>When setting up the file system,
253 enter:<screen>conf_param $FSNAME.quota.mdt=$QUOTA_TYPE
254 conf_param $FSNAME.quota.ost=$QUOTA_TYPE</screen></para>
256 </orderedlist></para>
259 <para>Start the Lustre file system by starting the components in the order shown in the
260 following steps:</para>
261 <orderedlist numeration="loweralpha">
263 <para>Mount the MGT. On the MGS, run<screen>mgs# mount -a -t lustre</screen></para>
266 <para>Mount the MDT(s). On each MDT, run:<screen>mds# mount -a -t lustre</screen></para>
269 <para>Mount all the OSTs. On each OSS node, run:</para>
270 <screen>oss# mount -a -t lustre</screen>
272 <para>This command assumes that all the OSTs are listed in the
273 <literal>/etc/fstab</literal> file. OSTs that are not listed in the
274 <literal>/etc/fstab</literal> file, must be mounted individually by running the
275 mount command:</para>
276 <screen> mount -t lustre <replaceable>/dev/block_device</replaceable> <replaceable>/mount_point</replaceable> </screen>
280 <para>Mount the file system on the clients. On each client node, run:</para>
281 <screen>client# mount -a -t lustre</screen>
287 <para>The mounting order described in the steps above must be followed for the intial mount
288 and registration of a Lustre file system after an upgrade. For a normal start of a Lustre
289 file system, the mounting order is MGT, OSTs, MDT(s), clients.</para>
291 <para>If you have a problem upgrading a Lustre file system, see <xref
292 xmlns:xlink="http://www.w3.org/1999/xlink" linkend="dbdoclet.50438198_30989"/> for some ways
295 <section xml:id="Upgrading_2.x.x">
297 <primary>upgrading</primary>
298 <secondary>2.X.y to 2.X.y (minor release)</secondary>
299 </indexterm><indexterm/>Upgrading to a Lustre Release 2.X.y (Minor Release)</title>
300 <para>Rolling upgrades are supported for upgrading from any Lustre release 2.X.y to a more
301 recent 2.X.y release. This allows the Lustre file system to continue to run while individual
302 servers (or their failover partners) and clients are upgraded one at a time. The procedure for
303 upgrading a Lustre release 2.X.y file system to a more recent minor release is described in
305 <para>To upgrade Lustre release 2.X.y to a more recent minor release, complete these
309 <para>Create a complete, restorable file system backup. </para>
311 <para>Before installing the Lustre software, back up ALL data. The Lustre software
312 contains kernel modifications that interact with storage devices and may introduce
313 security issues and data loss if not installed, configured, or administered properly. If
314 a full backup of the file system is not practical, a device-level backup of the MDT file
315 system is recommended. See <xref linkend="backupandrestore"/> for a procedure.</para>
319 <para>Download the Lustre server RPMs for your platform from the <link
320 xl:href="https://wiki.hpdd.intel.com/display/PUB/Lustre+Releases">Lustre Releases</link>
321 repository. See <xref xmlns:xlink="http://www.w3.org/1999/xlink"
322 linkend="table_cnh_5m3_gk"/> for a list of required packages.</para>
325 <para>For a rolling upgrade, complete any procedures required to keep the Lustre file system
326 running while the server to be upgraded is offline, such as failing over a primary server
327 to its secondary partner. </para>
330 <para>Unmount the Lustre server to be upgraded (MGS, MDS, or OSS)</para>
333 <para>Install the Lustre server packages on the Lustre server.</para>
334 <orderedlist numeration="loweralpha">
336 <para>Log onto the Lustre server as the <literal>root</literal> user</para>
339 <para>Use the <literal>yum</literal> command to install the packages:</para>
341 <screen># yum --nogpgcheck install pkg1.rpm pkg2.rpm ...</screen>
345 <para>Verify the packages are installed correctly:</para>
347 <screen>rpm -qa|egrep "lustre|wc"</screen>
351 <para>Mount the Lustre server to restart the Lustre software on the
352 server:<screen>server# mount -a -t lustre</screen></para>
355 <para>Repeat these steps on each Lustre server.</para>
360 <para>Download the Lustre client RPMs for your platform from the <link
361 xl:href="https://wiki.hpdd.intel.com/display/PUB/Lustre+Releases">Lustre Releases</link>
362 repository. See <xref xmlns:xlink="http://www.w3.org/1999/xlink"
363 linkend="table_j3r_ym3_gk"/> for a list of required packages.</para>
366 <para>Install the Lustre client packages on each of the Lustre clients to be
368 <orderedlist numeration="loweralpha">
370 <para>Log onto a Lustre client as the <literal>root</literal> user.</para>
373 <para>Use the <literal>yum</literal> command to install the packages:</para>
375 <screen># yum --nogpgcheck install pkg1.rpm pkg2.rpm ...</screen>
379 <para>Verify the packages were installed correctly:</para>
381 <screen># rpm -qa|egrep "lustre|kernel"</screen>
385 <para>Mount the Lustre client to restart the Lustre software on the
386 client:<screen>client# mount -a -t lustre</screen></para>
389 <para>Repeat these steps on each Lustre client.</para>
394 <para>If you have a problem upgrading a Lustre file system, see <xref
395 xmlns:xlink="http://www.w3.org/1999/xlink" linkend="dbdoclet.50438198_30989"/> for some
396 suggestions for how to get help.</para>