Dynamic Root Disk: Quick Start & Best Practices

ManualsBrandsHP ManualsSoftwareHP-UX Dynamic Root Disk

Dynamic Root Disk: Quick Start & Best

Practices

August 2010

Technical white paper

Table of Contents

Introduction ......................................................................................................................................... 3

Quick Start ......................................................................................................................................... 3

Installing DRD .................................................................................................................................. 3

Creating a Clone ................................................................................................................................. 4

Overview ........................................................................................................................................ 4

Important Considerations .................................................................................................................. 4

Choosing a Target Disk .................................................................................................................... 4

Checking the Size of the Target Disk .................................................................................................. 5

Performing the Clone Operation ........................................................................................................ 5

Viewing and Accessing the Clone ...................................................................................................... 5

Modifying the Clone ......................................................................................................................... 7

Activating & Booting the Clone .......................................................................................................... 7

After the Clone is Booted .................................................................................................................. 8

Best Practices ...................................................................................................................................... 8

Best Practice 1 (BP1): Basic Maintenance - Patching ............................................................................ 8

BP1: Overview of steps ................................................................................................................ 8

BP1: Additional Considerations ..................................................................................................... 9

Best Practice 2 (BP2): Basic Maintenance – Patching & Security Bulletin Management with DRD and Software

Assistant (SWA) ............................................................................................................................. 12

BP2: Overview of steps .............................................................................................................. 13

BP2: Additional Considerations ................................................................................................... 13

Best Practice 3 (BP3): Basic Maintenance – Updating Within Versions of HP-UX 11i v3 ......................... 14

BP3: Overview of Steps .............................................................................................................. 14

BP3: Additional Considerations ................................................................................................... 14

Best Practice 4 (BP4): Basic Maintenance – Using DRD to Assist an Update from HP-UX 11i v2 to HP-UX 11i

v3 ................................................................................................................................................ 14

BP4: Overview of Steps .............................................................................................................. 15

BP4: Additional Considerations ................................................................................................... 15

Best Practice 5 (BP5): Basic Recovery .............................................................................................. 16

BP5: Overview of Steps .............................................................................................................. 16

BP5: Additional Considerations ................................................................................................... 17

Best Practice 6 (BP6): Basic Provisioning .......................................................................................... 17

BP6: Overview of Steps .............................................................................................................. 17

BP6: Additional Considerations ................................................................................................... 18

Special Considerations for All Best Practices ......................................................................................... 18

Specific Details Regarding Clone Creation ........................................................................................ 18

Mirroring .......................................................................................................................................... 18

Summary of content (27 pages)

PAGE 1
Dynamic Root Disk: Quick Start & Best Practices August 2010 Technical white paper Table of Contents Introduction ......................................................................................................................................... 3 Quick Start ......................................................................................................................................... 3 Installing DRD ............................................................................................
PAGE 2
Using DRD to Expand LVM Logical Volumes and File Systems ................................................................. 19 Extending Files Systems Other Than /stand or / ................................................................................ 19 Extending the /stand or / File System ............................................................................................ 19 Viewing Log Files........................................................................................................
PAGE 3
Introduction Dynamic Root Disk (DRD) provides customers the ability to clone an HP-UX system image to an inactive disk, and then: • Perform system maintenance on the clone while their HP-UX 11i system is online. • Quickly reboot during off-hours—after the desired changes have been made—significantly reducing system downtime. • Utilize the clone for system recovery, if needed.
PAGE 4
Creating a Clone Overview All uses of DRD begin with creating a clone of the root volume group. After discussing clone creation, we will present best practices a system administrator can follow to make software maintenance tasks easier. The drd clone command creates a bootable disk containing a copy of the LVM volume group or VxVM disk group containing the root file system “/". In this white paper, “root group” refers to the LVM volume group or VxVM disk group that contains the root (“/”) file system.
PAGE 5
Checking the Size of the Target Disk A simple mechanism for determining if you have chosen a sufficiently large disk is to run a preview of the drd clone command: # /opt/drd/bin/drd clone -p -v -t /dev/dsk/cxtxdx (legacy device file) # /opt/drd/bin/drd clone -p -v -t /dev/disk/diskx (agile device file) (For further information about options available with the drd clone command, see the manpage drd-clone(1M).
PAGE 6
succeeded. (user=root) (jobid=mesa) On an LVM-based system: • The clone that has been created is not visible (when executing commands such as bdf or vgdisplay) at the completion of the clone operation. This is because the file systems on the clone are unmounted and the clone volume group is exported at completion of the drd clone command. See the information below regarding drd mount to view the clone. • If the root group name is “vgnn”, the clone group is “drdnn”.
PAGE 7
When drd runcmd finds the file systems in the clone already mounted, they will not be unmounted—nor on an LVM-based system will the volume group be vgexported—at the completion of the drd runcmd operation. Modifying the Clone The drd runcmd operation is used to run commands that modify the inactive system image. There are two fundamental requirements for a command run by the drd runcmd operation: • The command must not affect the currently booted system.
PAGE 8
As a best practice, consider creating a shutdown script that runs drd sync so that files changed on the original image after the clone was created will be propagated to the clone when it is activated and booted (see the “DRD sync” section below for more details.) If you need to restore the booted system image to be the primary boot path—that is, “undo” the drd activate command—the drd deactivate command can be used.
PAGE 9
2. Use drd status to view the clone: drd status 3. Install the QPK and PHCO_77777: drd runcmd swinstall \ -s depot_svr:/var/depots/1131 -x patch_match_target=true 4. Ensure the patch and QPK is installed: drd runcmd swlist QPKBASE QPKAPPS \ PHCO_77777 5. Create a shutdown script that runs drd sync so that files changed on the original image after the clone was created will be propagated to the clone (see the “DRD sync” section below for more details) 6.
PAGE 10
are DRD-safe; that is, they can be installed by the drd runcmd command to an inactive image without affecting the booted system. The few patches that are not DRD-safe set the fileset attribute is_drd_safe to false; for example firmware patches fall into this category. In the rare event that a patch is released with the is_drd_safe attribute incorrectly set to true, that patch will be added to the drd_unsafe_patch_list file.
PAGE 11
# /opt/drd/bin/drd runcmd swinstall -p -x patch_match_target\ -s depot_svr:/var/depots/mydepot Each unsafe selection will be rejected with an appropriate message, and the remaining selections will be listed. Planning the Installation of DRD-Unsafe Patches Examine the list of DRD-unsafe patches determined in the section above. For each patch, apply the following logic: 1. Does the patch apply to a product that is not used and for which no use is planned? If so, no action is necessary. 2.
PAGE 12
Patch Planning and Alternative Patch Deployment Schemes The offline patching scenario presents a straightforward progression from clone to boot in a fairly short time period. However, a system administrator might benefit from some time and feedback to craft the exact selection of patches to be applied to an inactive system image that is eventually booted.
PAGE 13
Version of SWA: C.02.26 or later Objective: Perform maintenance on my server, including the identification and repair of security issues, while minimizing downtime. BP2: Overview of steps 1. Use drd status to view the clone: drd status 2. Determine what patches are needed: 3. Mount the clone: drd mount 4. Create an SWA report: swa report -s \ /var/opt/drd/mnts/sysimage_001 5. Download the patches identified by SWA into a depot: swa get \ 6. -t /var/depots/1131swa 7.
PAGE 14
For more information on SWA, go to http://www.hp.com/go/swa. For more information on patching, see the Patch Management User Guide for HP-UX 11.x systems at http://bizsupport1.austin.hp.com/bc/docs/support/SupportManual/c01919407/c01919407.pdf. Best Practice 3 (BP3): Basic Maintenance – Updating Within Versions of HP-UX 11i v3 This best practice focuses on how to reduce downtime while performing an update from an older version of HP-UX 11i v3 to a newer release of HP-UX 11i v3 (update 4 or later.
PAGE 15
update, and providing a quick backup mechanism if you wish to restore the system to HP-UX 11i v2 for any reason. For this scenario, our setup is as follows: Original image: /dev/dsk/c0t0d0 (with HP-UX 11i v2 installed) Clone disk: /dev/dsk/c1t0d0 What to apply: HP-UX 11i v3 Update 4, Virtual Server OE Depot with patches: depot_svr:/var/depots/1131_VSE-OE Version of DRD: B.11.31.A.3.
PAGE 16
same time, verify that System Fault Manager (SFM) and Event Monitoring Service (EMS) are installed and configured properly. Adjusting File System Sizes on the Clone In Step 3 above, the output of the update-ux -p command will identify file systems that need to be expanded, and these changes can be made on the clone prior to activating it and performing the actual update.
PAGE 17
Booting the clone is considerably faster than recovering the system from a network recovery image. Note that any file system changes (for example, application data updates), need to be recovered from the point in time the clone was created, until the time it is booted. BP5: Additional Considerations Ongoing Recovery Failsafe The approach described in this recovery best practice can be used on an ongoing basis by creating a clone regularly—daily or weekly—depending on the volatility of the system.
PAGE 18
ii. hpvmmodify -P drdivm2 -d \ disk:avio_stor:0,1,1:disk:/dev/rdisk/disk75 Note: You might see messages indicating a restart is required due to devices being busy; these can safely be ignored as they only pertain to the original system, not the target for rehosting. iii. hpvmmodify -P drdivm3 -a \ disk:avio_stor:0,1,1:disk:/dev/rdisk/disk75 2. Boot VM3: i. hpvmstart -P drdivm3 ii. hpvmconsole -P drdivm3 iii. From the EFI shell, enter the following: 1. fs0: 2. cd EFI\HPUX 3. hpux.
PAGE 19
Using DRD to Expand LVM Logical Volumes and File Systems Extending Files Systems Other Than /stand or / One of the difficulties in expanding file systems in the root volume group of an LVM-based system is that the file systems are always busy, so a boot to LVM maintenance mode is often needed to complete the size change. Because the entire inactive image created by a drd clone command is not in use, the system administrator has an opportunity to expand file systems on the inactive image.
PAGE 20
This section describes how a system administrator can use an inactive system image created by a drd clone command to expand /stand with a single reboot. The most typical use of Dynamic Root Disk (DRD) is to patch an inactive system image. If desired, the administrator can use the reboot required to boot the patched image to also resize the /stand file system, thus accomplishing both tasks with a single reboot.
PAGE 21
Root: lvol3 Swap: lvol2 Dump: lvol2 on: on: on: /dev/disk/disk6_p2 /dev/disk/disk6_p2 /dev/disk/disk6_p2, 0 Boot Definitions for Volume Group /dev/drd00: Physical Volumes belonging in Root Volume Group: /dev/disk/disk7_p2 -- Boot Disk Boot: lvol1 on: /dev/disk/disk7_p2 Root: lvol3 on: /dev/disk/disk7_p2 Swap: lvol2 on: /dev/disk/disk7_p2 Dump: lvol2 on: /dev/disk/disk7_p2, 0 6.
PAGE 22
# /usr/sbin/lvcreate -L 2048 -C y -r n -n swap drd00 9. Remove the old dump device from drd00: # /usr/sbin/lvrmboot -v -d lvol2 /dev/drd00 10. Create the new dump device: # /usr/sbin/lvlnboot -d /dev/drd00/swap 11. Remove the old swap device: # /usr/sbin/lvrmboot -s /dev/drd00 12. Add the new swap device: # /usr/sbin/lvlnboot -s /dev/drd00/swap 13. Verify the changes: # /usr/sbin/lvlnboot -v 14. Remove /dev/drd00/lvol2: # /usr/sbin/lvremove -f /dev/drd00/lvol2 15.
PAGE 23
20. The old lvol2 must be removed from the device directory of the inactive system image. However, because the device directory on the inactive system image reflects devices when the image is booted, the file to be removed is part of the volume group vg00 on the inactive image: # /usr/bin/rm -f /var/opt/drd/mnts/sysimage_001/dev/vg00/lvol2 21. Create a new character device and a new block device on the inactive system image so that the new swap volume is recognized when it is mounted.
PAGE 24
Boot Definitions for Volume Group /dev/vg00: Physical Volumes belonging in Root Volume Group: /dev/disk/disk6_p2 -- Boot Disk Boot: lvol1 on: /dev/disk/disk6_p2 Root: lvol3 on: /dev/disk/disk6_p2 Swap: lvol2 on: /dev/disk/disk6_p2 Dump: lvol2 on: /dev/disk/disk6_p2, 0 Boot Definitions for Volume Group /dev/drd00: Physical Volumes belonging in Root Volume Group: /dev/disk/disk7_p2 -- Boot Disk Boot: lvol1 on: /dev/disk/disk7_p2 Root: lvol3 on: /dev/disk/disk7_p2 Swap: lvol2 on: /dev/disk/disk7_p2 Dump: lvol2
PAGE 25
• The drd log (/var/opt/drd/drd.log) contains entries that pertain only to the command that was run, including the return code and/or error messages. This log does not contain any log messages from the sw* command itself. • The sw* log file that results from a drd runcmd operation is always on the inactive system image (that is, the clone) and is not appended to the original logs on the booted system (that is, the active system image).
PAGE 26
Maintaining the Integrity of System Logs If system logs are being collected and audited for regulatory, intrusion detection, or forensics purposes, it is desirable to avoid gaps in logs between the creation and boot of the clone. To address this need, the drd sync command was introduced in March 2010. The drd sync command allows you to automatically synchronize the active image and the clone, eliminating the need to manual update files on the clone.
PAGE 27
For More Information To read more about Dynamic Root Disk, go to www.hp.com/go/drd. Call to Action HP welcomes your input. Please give us comments about this white paper, or suggestions for LVM or related documentation, through our technical documentation feedback website: http://docs.hp.com/en/feedback.html © 2010 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice.