IPP Software Navigation Tools IPP Links Communication Pan-STARRS Links

Changeset 5045


Ignore:
Timestamp:
Sep 13, 2005, 2:46:58 PM (21 years ago)
Author:
jhoblitt
Message:

update

Location:
trunk
Files:
4 edited

Legend:

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

    r4943 r5045  
    11# Copyright (C) 2004-2005  Joshua Hoblitt
    22#
    3 # $Id: design.txt,v 1.2 2005-09-02 04:20:29 jhoblitt Exp $
     3# $Id: design.txt,v 1.3 2005-09-14 00:46:58 jhoblitt Exp $
    44
    55Overview
     
    2323technologies can be improved upon.
    2424
     25A centralized server model was used to allow efficient use of 'like' searches
     26on storage object names.  The current 'best' technique for a distributed
     27metadata store is with distributed hash tables.  Unfortunately, no widely
     28available DHT implementation allows 'like' searches on key names.
     29
    2530[1] Multiple Nebulous servers should be possible via database replication.
    2631[2] A future version of Nebulous may include it's own data transport layer
     
    3136
    3237The Nebulous Server and clients communicate via the SOAP protocol.  Since SOAP
    33 is platform independent this allows native Nebulous client to be written in a
     38is platform independent this allows native Nebulous clients to be written in a
    3439variety of languages.  With in the Nebulous Server itself the IPC mechanism is
    3540abstracted to allow ether multi-protocol support or complete replacement of
  • trunk/Nebulous-Server/docs/requirements.txt

    r2785 r5045  
    11# Copyright (C) 2004  Joshua Hoblitt
    22#
    3 # $Id: requirements.txt,v 1.1.1.1 2004-12-22 02:16:23 jhoblitt Exp $
     3# $Id: requirements.txt,v 1.2 2005-09-14 00:46:01 jhoblitt Exp $
    44
    55- store all image data aquired during the first two years of PS1's
     
    77
    88- injest new data from the summit at the same rate it is produced when
    9   operating at a cadence of 40s between integrations.  Approximately 400Mb/s.
     9  operating at a cadence of 40s between integrations.  Approximately 400Mb/s
     10  and 64 files/integration.
    1011
    1112- support phase 1 & 2 processing. x files per t_min
     
    1415
    1516- support accessing small blocks of a file (ie., seek)
     17
     18- tolerate partal system failures without data loss
     19
     20- execeedly efficent use of both disk and network I/O
    1621
    1722what are the science drivers for these 3?
  • trunk/Nebulous/docs/design.txt

    r4943 r5045  
    11# Copyright (C) 2004-2005  Joshua Hoblitt
    22#
    3 # $Id: design.txt,v 1.2 2005-09-02 04:20:29 jhoblitt Exp $
     3# $Id: design.txt,v 1.3 2005-09-14 00:46:58 jhoblitt Exp $
    44
    55Overview
     
    2323technologies can be improved upon.
    2424
     25A centralized server model was used to allow efficient use of 'like' searches
     26on storage object names.  The current 'best' technique for a distributed
     27metadata store is with distributed hash tables.  Unfortunately, no widely
     28available DHT implementation allows 'like' searches on key names.
     29
    2530[1] Multiple Nebulous servers should be possible via database replication.
    2631[2] A future version of Nebulous may include it's own data transport layer
     
    3136
    3237The Nebulous Server and clients communicate via the SOAP protocol.  Since SOAP
    33 is platform independent this allows native Nebulous client to be written in a
     38is platform independent this allows native Nebulous clients to be written in a
    3439variety of languages.  With in the Nebulous Server itself the IPC mechanism is
    3540abstracted to allow ether multi-protocol support or complete replacement of
  • trunk/Nebulous/docs/requirements.txt

    r2785 r5045  
    11# Copyright (C) 2004  Joshua Hoblitt
    22#
    3 # $Id: requirements.txt,v 1.1.1.1 2004-12-22 02:16:23 jhoblitt Exp $
     3# $Id: requirements.txt,v 1.2 2005-09-14 00:46:01 jhoblitt Exp $
    44
    55- store all image data aquired during the first two years of PS1's
     
    77
    88- injest new data from the summit at the same rate it is produced when
    9   operating at a cadence of 40s between integrations.  Approximately 400Mb/s.
     9  operating at a cadence of 40s between integrations.  Approximately 400Mb/s
     10  and 64 files/integration.
    1011
    1112- support phase 1 & 2 processing. x files per t_min
     
    1415
    1516- support accessing small blocks of a file (ie., seek)
     17
     18- tolerate partal system failures without data loss
     19
     20- execeedly efficent use of both disk and network I/O
    1621
    1722what are the science drivers for these 3?
Note: See TracChangeset for help on using the changeset viewer.