Sponsored Content
Special Forums Hardware Filesystems, Disks and Memory Optimizing the system reliability Post 32976 by Deepa on Wednesday 11th of December 2002 10:09:19 PM
Old 12-11-2002
Thanks Perderabo!

As you said, "Reliability will require duplicate servers, preferably in different cities", we do have a duplicate sun box geographically located in different cities, which has the same configuration and with the same number of processes running on it.

But the secondary machine is used only when the primary machine goes for a toss.

I am trying to find out the number of parallel instances of each process to be running in each machine, to attain a better reliability.

As u rightly said, we have to benchmark for gaining performance. I happened to hear about the genetic algorithm which can be applied for similar type of scenario. But still, we have to define the performance calculation of each process (considering the CPU load, memory usage, database accessing, IPC access etc) and provide it as one of the input to genetic algorithm.

I am not sure if any of our forum members are aware of this genetic algorithm(GA) concept. If anyone knows a good GA site/forum from where we can grab some information, pls let me know.

Thanks
 

7 More Discussions You Might Find Interesting

1. Shell Programming and Scripting

Optimizing for a Speed-up

How would one go about optimizing this current .sh program so it works at a more minimal time. Such as is there a better way to count what I need than what I have done or better way to match patterns in the file? Thanks, #declare variables to be used. help=-1 count=0 JanCount=0 FebCount=0... (3 Replies)
Discussion started by: switch
3 Replies

2. UNIX and Linux Applications

Optimizing query

Hi All, My first thread to this sub-forum and first thread of this sub-forum :) Here it is, Am trying to delete duplicates from a table retaining just 1 duplicate value out of the duplicate records for example : from n records of a table out of which x are duplicates, I want to remove x... (15 Replies)
Discussion started by: matrixmadhan
15 Replies

3. High Performance Computing

High reliability web server - cluster, redundancy, etc

Hi. I am IT manager/developer for a small organization. I have been doing as-needed linux server administration for several years and am by no means an expert. I've built several of my own servers, and our org is currently using hosting services for our servers and I am relatively happy. We... (3 Replies)
Discussion started by: bsaadmin
3 Replies

4. AIX

MPIO reliability

Hi, we have a vew boxes using MPIO and they are connected to some virtualization software managing some disk subsystems, offering volumes to the AIX boxes. Sometimes when a cable has been plugged out for a test or when a real problem occurs, using lspath to show the state of the paths shows... (8 Replies)
Discussion started by: zaxxon
8 Replies

5. Shell Programming and Scripting

Optimizing the code

Hi, I have two files in the format listed below. I need to find out all values from field 12 to field 20 present in file 2 and list them in file3(format as file2) File1 : FEIN,CHRISTA... (2 Replies)
Discussion started by: nua7
2 Replies

6. Solaris

Reasons for NOT using LDOMs? reliability?

Dear Solaris Experts, We are upgrading from sun4u to T4 systems and one proposal is to use LDOMs and also zones within LDOMs. Someone advised using only zones and not LDOMs because the new machines have fewer chips and if a chip or a core fails then it doesn't impact the zones, but impacts... (3 Replies)
Discussion started by: User121
3 Replies

7. Web Development

Optimizing JS and CSS

Yes. Got few suggestions. - How about minifying resources - mod_expires - Service workers setup https://www.unix.com/attachments/web-programming/7709d1550557731-sneak-preview-new-unix-com-usercp-vuejs-demo-screenshot-png (8 Replies)
Discussion started by: Akshay Hegde
8 Replies
numa_policy(5)							File Formats Manual						    numa_policy(5)

NAME
numa_policy - physical memory allocation policy on cellular HP-UX servers VALUES
Default Allowed values Integer values or DESCRIPTION
HP-UX treats large servers as if they are built from componment blocks. Each component block is referred to as a locality and can contain memory, CPUs and peripherals. HP-UX constructs these component blocks in such a way as to optimize resource alignment. If a machine has only one locality, it is considered to be an UMA (Unform Memory Architecture) machine. UMA is also a synonym for Symmet- ric Multiprocessor (SMP). Large servers use Non-Uniform Memory Access (NUMA) protocols. An application thread can experience variable memory latency depending on whether it is accessing memory from the same locality upon which it is executing or from a different locality. HP-UX implements a number of memory allocation features to optimize performance. Users can divide the memory on the system into two classes of memory: Interleaved and Cell-local. Interleaved memory delivers uniform latency. It makes multiple localities look like a single bank of uniform memory, delivering the same average latency for all applications across all CPUs. This is very useful in spreading the memory load across all the localities. Cell-local memory delivers low latency (high performance) to a process running in the same cell as the memory it accesses. Conversely, references from a remote cell will have a much higher latency. Users can configure cell-local memory using the HP-UX command or The dynamic kernel tunable allows users to define how interleaved and cell-local memory are utilized. There are five possible values for this tunable: This is the default value. HP-UX will autosense the right policy based on the mode in which HP-UX is operating. See for more details on mode. This is the default policy in LORA mode. This policy directs HP-UX to use memory from the locality closest to the allocating CPU for user memory allocations. It will select the locality by first honoring any locality policies specified in or If no locality policies are specified, then all memory is allocated from the locality closest to the allocating CPU. See mpsched(1) for more information. This policy directs HP-UX to override any locality policies supplied via or and allocate all memory from the interleaved. Cell-local memory is allocated when there is insufficient interleaved mem- ory. This policy is like setting to except that all text and library data segments are allocated from the interleaved domain. This setting is useful for servers running highly threaded applications. This setting has a similar effect to the command's +id option (this option is only available on Integrity systems), but on a system wide basis. This is the default policy in SMP mode. In a machine configured with a mix of cell-local memory and interleaved memory, HP-UX makes intelligent decisions on how to use the memory by distinguishing between private memory and shared memory. For example, Memory allocated to private objects (stack, heap, private files, and so on) is likely to come from cell-local memory. Memory allocated to shared objects (shared files, System V shared memory) is allocated from interleaved memory unless the user specifies otherwise using for files or uses one of the memory options in Restrictions on Changing Changes to this tunable take effect on memory allocated subsequent to the change. Any memory created before the change will not be affected. When Should the Value of This Tunable Be Changed to 1? should be set to 1 only if all performance-sensitive applications on the system have a high degree of locality of access. That is, if the majority of references to shared memory are from processes running on the same cell where the memory has been allocated, then setting will have a positive effect on performance. Changing the value to 1 should be done after sufficient memory has been designated as cell-local using and the machine has been rebooted. When Should the Value of This Tunable Be Changed to 2? can be set to 2 if the workload has a low degree of locality to a cell and it is not possible to change the source code. Changing the value to 2 should be done after sufficient memory has been designated as interleaved using and the machine has been rebooted. Setting the tunable to 2 only makes sense in a mixed environment in which some applications can benefit from cell-local memory, and others cannot. When Should the Value of This Tunable Be Changed to 3? can be set to 3 if the all the performance-sensitive applications on the system have a high degree of locality of access and if the work- load is threaded. Changing the value to 3 should be done after sufficient memory has been designated as cell-local using and the machine has been rebooted. WARNINGS
All HP-UX kernel tunable parameters are release specific. This parameter may be removed or have its meaning changed in future releases of HP-UX. Installation of optional kernel software, from HP or other vendors, may cause changes to tunable parameter values. After installation, some tunable parameters may no longer be at the default or recommended values. For information about the effects of installation on tun- able values, consult the documentation for the kernel software being installed. For information about optional kernel software that was factory installed on your system, see at AUTHOR
was developed by HP. SEE ALSO
chatr_ia(1), mpsched(1), parmodify(1M), fadvise(2), shmget(2). Tunable Kernel Parameters numa_policy(5)
All times are GMT -4. The time now is 06:17 AM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy