IPP Software Navigation Tools IPP Links Communication Pan-STARRS Links

Changeset 5050


Ignore:
Timestamp:
Sep 13, 2005, 5:24:45 PM (21 years ago)
Author:
jhoblitt
Message:

fix typos

Location:
trunk
Files:
3 edited

Legend:

Unmodified
Added
Removed
  • trunk/Nebulous-Server/docs/design.txt

    r5045 r5050  
    11# Copyright (C) 2004-2005  Joshua Hoblitt
    22#
    3 # $Id: design.txt,v 1.3 2005-09-14 00:46:58 jhoblitt Exp $
     3# $Id: design.txt,v 1.4 2005-09-14 03:24:45 jhoblitt Exp $
     4
     5Abstract
     6--
     7
     8Nebulous is a user-space distributed object (file) storage system.  It is much
     9more a database of where objects are stored then a filesystem in the
     10traditional sense.  Nebulous is considered distributed because of it's data
     11storage model, where objects are stored across a number of storage volumes and
     12may have redundant copies.  While IPC is done in the traditional client/server
     13model with a single[1] centralized server containing all storage object
     14meta-data.  This system was designed, unlike most distributed filesystems,
     15specifically so that clients have the option of hosting one or more storage
     16volumes.  Although, if you so choose, clients and storage volumes can reside
     17on independent hardware.  Above all else, Nebulous is designed to make
     18efficient use of both disk and network bandwidth.
     19
    420
    521Overview
    622--
    723
    8 Nebulous is a user-space distributed object (file) storage system.  The system
    9 is distributed in the sense of it's data storage model where objects are stored
    10 across a number of storage volumes and may have redundant copies.  While IPC
    11 is done in the traditional client/server model with a single[1] centralized
    12 server containing all storage object meta-data.  This system was designed,
    13 unlike most distributed filesystems, specifically so that Nebulous clients
    14 could also host one or more storage volumes. Although, there is no requirement
    15 that clients also provide storage space.  If you so choose, clients and the
    16 storage volumes can reside on independent hardware.
    17 
    1824There are 4 principle components required for a working Nebulous system;
    19 server, client, data transport, and data storage.  The Nebulous system only
    20 provides the server and the client software.  Data transport[2] and Data
    21 storage are left to 3rd party software packages.  As this function is typically
    22 included with most operation system it is unlikely that those specific
    23 technologies can be improved upon.
    24 
    25 A centralized server model was used to allow efficient use of 'like' searches
    26 on storage object names.  The current 'best' technique for a distributed
    27 metadata store is with distributed hash tables.  Unfortunately, no widely
    28 available DHT implementation allows 'like' searches on key names.
     25server, client, data transport, and data storage.  The Nebulous software
     26distribution provides only the server and the client software.  Data
     27transport[2] and Data storage are left to 3rd party software packages.  As
     28those functionalities are typically included with most operation system.
     29Instead, Nebulous build upon and benfits from advances made in those
     30technologies.
     31
     32Server
     33--
     34
     35The server is responsible for keeping track of storage objects, all instances
     36of that object, and enforcing locking semantics.  Extensive logging and
     37tracing support is provided for debug and to allow for statics generation and
     38possible X<hotspot> optimization.
     39
     40Nebulous uses a centralized server model.  This model was choosen because it
     41allows efficient X<pattern matching> of storage object names.  The current
     42'best' technique for a distributed metadata store is with distributed hash
     43tables.  Unfortunately, no widely available DHT implementation allows efficent
     44I<pattern matching> of key names.
     45
    2946
    3047[1] Multiple Nebulous servers should be possible via database replication.
  • trunk/Nebulous/docs/design.txt

    r5045 r5050  
    11# Copyright (C) 2004-2005  Joshua Hoblitt
    22#
    3 # $Id: design.txt,v 1.3 2005-09-14 00:46:58 jhoblitt Exp $
     3# $Id: design.txt,v 1.4 2005-09-14 03:24:45 jhoblitt Exp $
     4
     5Abstract
     6--
     7
     8Nebulous is a user-space distributed object (file) storage system.  It is much
     9more a database of where objects are stored then a filesystem in the
     10traditional sense.  Nebulous is considered distributed because of it's data
     11storage model, where objects are stored across a number of storage volumes and
     12may have redundant copies.  While IPC is done in the traditional client/server
     13model with a single[1] centralized server containing all storage object
     14meta-data.  This system was designed, unlike most distributed filesystems,
     15specifically so that clients have the option of hosting one or more storage
     16volumes.  Although, if you so choose, clients and storage volumes can reside
     17on independent hardware.  Above all else, Nebulous is designed to make
     18efficient use of both disk and network bandwidth.
     19
    420
    521Overview
    622--
    723
    8 Nebulous is a user-space distributed object (file) storage system.  The system
    9 is distributed in the sense of it's data storage model where objects are stored
    10 across a number of storage volumes and may have redundant copies.  While IPC
    11 is done in the traditional client/server model with a single[1] centralized
    12 server containing all storage object meta-data.  This system was designed,
    13 unlike most distributed filesystems, specifically so that Nebulous clients
    14 could also host one or more storage volumes. Although, there is no requirement
    15 that clients also provide storage space.  If you so choose, clients and the
    16 storage volumes can reside on independent hardware.
    17 
    1824There are 4 principle components required for a working Nebulous system;
    19 server, client, data transport, and data storage.  The Nebulous system only
    20 provides the server and the client software.  Data transport[2] and Data
    21 storage are left to 3rd party software packages.  As this function is typically
    22 included with most operation system it is unlikely that those specific
    23 technologies can be improved upon.
    24 
    25 A centralized server model was used to allow efficient use of 'like' searches
    26 on storage object names.  The current 'best' technique for a distributed
    27 metadata store is with distributed hash tables.  Unfortunately, no widely
    28 available DHT implementation allows 'like' searches on key names.
     25server, client, data transport, and data storage.  The Nebulous software
     26distribution provides only the server and the client software.  Data
     27transport[2] and Data storage are left to 3rd party software packages.  As
     28those functionalities are typically included with most operation system.
     29Instead, Nebulous build upon and benfits from advances made in those
     30technologies.
     31
     32Server
     33--
     34
     35The server is responsible for keeping track of storage objects, all instances
     36of that object, and enforcing locking semantics.  Extensive logging and
     37tracing support is provided for debug and to allow for statics generation and
     38possible X<hotspot> optimization.
     39
     40Nebulous uses a centralized server model.  This model was choosen because it
     41allows efficient X<pattern matching> of storage object names.  The current
     42'best' technique for a distributed metadata store is with distributed hash
     43tables.  Unfortunately, no widely available DHT implementation allows efficent
     44I<pattern matching> of key names.
     45
    2946
    3047[1] Multiple Nebulous servers should be possible via database replication.
  • trunk/Nebulous/lib/Nebulous/Client/QuickStart.pod

    r5047 r5050  
    33=head1 NAME
    44
    5 Nebulous::Server::QuickStart- Nebulous QuickStart Guide
     5Nebulous::Server::QuickStart - Nebulous QuickStart Guide
    66
    77=head1 Perl CLIENT
     
    7777    PKG_CHECK_MODULES([NEBCLIENT], [nebclient >= 0.0.1])
    7878
    79 This Will setup the variables C<NEBLCLIENT_CFLAGS> and C<NEBCLIENT_LIBS> for
     79This will setup the variables C<NEBLCLIENT_CFLAGS> and C<NEBCLIENT_LIBS> for
    8080you and C<AC_SUBST()> them.
    8181
Note: See TracChangeset for help on using the changeset viewer.