Sponsored Content
Special Forums News, Links, Events and Announcements Software Releases - RSS News lustre 1.6.6 (Development branch) Post 302274574 by Linux Bot on Thursday 8th of January 2009 01:00:06 AM
Old 01-08-2009
lustre 1.6.6 (Development branch)

Lustre is a novel storage and filesystem architecture and implementation suitable for very large clusters. It is a next-generation cluster filesystem that is currently running on clusters that have tens of thousands of nodes, petabytes of storage, and move hundreds of GB/sec. License: GNU General Public License (GPL) Changes:
This release adds support for downgrading pools-striped files. Distribution kernel support has been updated to RHEL5 kernel-2.6.18-92.1.10.el5 and SLES10 SP2 kernel-2.6.16.60-0.27. There are numerous bugfixes, including fixes for 8 TB systems with more than 65536 groups, machines with more than 1GB of RAM, and issues when mounting filesystems with the flock option. Image

Image

More...
 
clm order(1)							  USER COMMANDS 						      clm order(1)

  NAME
      clm order - reorder clusterings conformal to inclusion structure

      clmorder	is  not  in  actual  fact  a program. This manual page documents the behaviour and options of the clm program when invoked in mode
      order. The options -h, --apropos, --version, -set, --nop are accessible in all clm modes. They are described in the clm manual page.

  SYNOPSIS
      clm order [-prefix <string> (file multiplex prefix)] [-o <fname> (concatenated output in single file)] <cluster|stack>+

  DESCRIPTION
      Given a set of input clusterings clm order first transform it into a stack of strictly nesting clusterings. It does this by splitting  clus-
      ters  where  necessary.  It then reorders the coarsest (i.e. level-one) clustering, from large to small clusters. After that it reorders the
      second coarsest clustering conformally such that the first batch among its reordered clusters covers the level-one largest cluster, the sec-
      ond batch covers the level-one second largest cluster, and so on. Within these constraints, each batch of second-level clusters (correspond-
      ing to a single first-level cluster) is again ordered from larger to smaller clusters. This process is applied  recursively  throughout  the
      entire stack of input clusters.

      The input can be specified in multiple files, and a single file may contain multiple clusterings. The output is by default written as a con-
      catenation of matrix files, the so-called stack format. Use the -o option to specify the output file. The stacked format can be converted to
      Newick format using mcxdump(1). The output can be written to multiple files, one for each projected clustering, by using the -prefix option.
      By example, -prefix P leads to output in files named P1, P2, ..PN, where N is the number of clusters in the input,  P1  is  the  most  fine-
      grained ordered clustering, and PN is the coarsest clustering.

  OPTIONS
      -prefix (<string>)
      -o (<fname>)
	As decribed above.

  AUTHOR
      Stijn van Dongen.

  SEE ALSO
      mclfamily(7) for an overview of all the documentation and the utilities in the mcl family.

  clm order 12-068						      8 Mar 2012							clm order(1)
All times are GMT -4. The time now is 04:58 AM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy