Disk Load Balancing, Fault Tolerance, and Configuration Limits for NonStop Systems

ManualsBrandsHP ManualsServerHP Integrity NonStop Service Information

Table of contents

Summary.......................................................................................................................................2

Introduction ...................................................................................................................................2

Processors and memory...................................................................................................................3

ServerNet......................................................................................................................................4

Adapters, SACs, CLIMs, and configuration limits..................................................................................5

I/O buses .....................................................................................................................................7

Examples......................................................................................................................................7

Glossary.......................................................................................................................................9

References...................................................................................................................................10

Disk Load Balancing, Fault Tolerance, and

Configuration Limits for NonStop Systems

Technical brief

Summary of content (10 pages)

PAGE 1
Disk Load Balancing, Fault Tolerance, and Configuration Limits for NonStop Systems Technical brief Table of contents Summary....................................................................................................................................... 2 Introduction ................................................................................................................................... 2 Processors and memory ................................................................................
PAGE 2
Summary A frequently asked question about disk load balancing is "how can I balance the load of FCSAattached disk I/O across the X and Y ServerNet fabrics?" The short answer is that it is done automatically by SCS (T8456), which is used for all I/O to FCSA-attached devices. SCS also automatically balances the ServerNet I/O to CLIM-attached devices.
PAGE 3
• NB-series systems, characterized by processors and ServerNet switches in a c-7000 enclosure and running J-series RVUs. – NB-series I/O consists of CLIMs connected to ESS (HP XP) and MSA70 disk enclosures containing SAS disks. The I/O buses are Fibre Channel and SAS. – NB-series systems support a backward-compatible I/O generation by replacing some CLIMs with IOAME enclosures. – NB-series systems support another backward-compatible I/O generation by replacing some CLIMs with S-series I/O enclosures.
PAGE 4
The amount of memory each volume consumes is application-dependent, but can be limited by usercontrollable disk attributes such as: CBPOOLLEN, AUDITRAILBUFFER/SQLMXBUFFER, LKIDLONGPOOLLEN, LKTABLESPACELEN, and cache size. In general, the largest consumer of memory is cache. At a minimum, DP2 memory is required for stack space, internal buffers for both DP2 FM and I/O Driver, control blocks, lock tables, work pools, etc. The minimum consumption for these areas in most S-series systems is about 31 MB.
PAGE 5
In any system with IOAMEs or CLIMs, I/O traffic to any FCSA or CLIM is automatically distributed across both ServerNet fabrics by SCS (T8456). This provides both fault tolerance and load balancing. SCS automatically rebalances the load after failure and restoration of a ServerNet fabric.
PAGE 6
number of IOPs which can be launched in a processor. See the explanation in the preceding “Processors and memory” section.
PAGE 7
I/O buses The most common issue at this level in the architecture is bandwidth. For all bus types (SCSI, Fibre Channel, and SAS domains), multiple devices share the bandwidth of a single backplane, cable, or expander. For this reason, it is best to spread the devices evenly across the available I/O buses. An I/O bus is also a potential point of failure, so the primary and mirror drives of a mirrored disk volume should not be configured on the same I/O bus.
PAGE 8
Example 1 Volume CPUs –P SAC –B SAC –M SAC –MB SAC $D1 0,1 (110,2,1) 1 (110,3,1) 1 (110,3,2) 1 (110,2,2) 1 $D2 1,0 (110,2,1) 1 (110,3,1) 1 (110,3,2) 1 (110,2,2) 1 $D3 2,3 (110,2,1) 1 (110,3,1) 1 (110,3,2) 1 (110,2,2) 1 $D4 3,2 (110,2,1) 1 (110,3,1) 1 (110,3,2) 1 (110,2,2) 1 $D5 0,1 (110,2,1) 2 (110,3,1) 2 (110,3,2) 2 (110,2,2) 2 $D6 1,0 (110,2,1) 2 (110,3,1) 2 (110,3,2) 2 (110,2,2) 2 $D7 2,3 (110,2,1) 2 (110,3,1) 2 (110,3,2) 2 (11
PAGE 9
Glossary Acronym Meaning CLIM Cluster I/O Machine. DP2 Disk Process 2. The IOP used for disk devices. DP2 FM The File Management part of the DP2 process. ESS Enterprise Storage System. F-PIC Fiber Plug-In Card. Used with an SNDA adapter. FCDM Fibre Channel Disk Module. Contains disk drives. FCSA Fibre Channel ServerNet Adapter. FRU Field Replaceable Unit. HP XP The model name of a Hewlett Packard ESS product. IOAME I/O Adapter Module Enclosure. Contains adapters like the FCSA.
PAGE 10
References Configuration: S-series system (pre-G06.05) with S-series I/O enclosures Document: Support Note S97086A on G-series Disk Load Balancing Configuration: S-series system (G06.05-G06.