Disaggregated Memory Benefits for Server Consolidation

 
Thread Tools Search this Thread
Special Forums News, Links, Events and Announcements UNIX and Linux RSS News Disaggregated Memory Benefits for Server Consolidation
# 1  
Old 03-08-2011
Disaggregated Memory Benefits for Server Consolidation

HPL-2011-31 Disaggregated Memory Benefits for Server Consolidation - Lim, Kevin; Turner, Yoshio; Chang, Jichuan; Santos, Jose Renato; Ranganathan, Parthasarathy
Keyword(s): disaggregated memory, virtual machines, consolidation, hypervisor
Abstract: Recent architecture research has introduced a new building block - a memory blade - which provides disaggregated memory capacity expansion and sharing for an ensemble of blade servers. In this paper, we examine the systems implications of this new architectural building block. We build a software-ba ...
Full Report

More...
Login or Register to Ask a Question

Previous Thread | Next Thread

4 More Discussions You Might Find Interesting

1. UNIX for Dummies Questions & Answers

RRDtool consolidation not going as expected

Hello all, I am new to RRDtool and have made a RRDtool database with one data-source. Information of this data-source is stored in four different RRA's with different intervals for different time spans. Database create command: rrdtool create /root/mde.rrd --step 300 \... (2 Replies)
Discussion started by: ArtOfLosing
2 Replies

2. UNIX for Dummies Questions & Answers

Code Consolidation

My code currently looks like this: #!/usr/bin/ksh clear while true do clear echo "Menu" echo " 1. WPPHA1" echo " 2. WPPHA2" echo " 3. WPPHA3" echo " 4. WPPHB1" echo " 5. WPPHB2" echo " 6. WPPHC0" echo " 7. WPPHD0" echo " 8. WPPHD1" echo " 9. WPPHD2" echo "10. WPPHD3" (1 Reply)
Discussion started by: misterpinkey
1 Replies

3. UNIX for Dummies Questions & Answers

What are some benefits of the UNIX hierarchical file structure?

What are some benefits of the UNIX hierarchical file structure? I am new to UNIX and researching some information about it for a class so please help if you can. Thanks. (1 Reply)
Discussion started by: 88923JJJSDK
1 Replies

4. UNIX for Advanced & Expert Users

V890 Benefits over V880

Hello, Need to know all benefits\differences for V890 over V880. We are really keen to know about this. Can anybody please take out some time and get us the information. Regards, Narinder (4 Replies)
Discussion started by: narinderd
4 Replies
Login or Register to Ask a Question
CHI::Driver::Memory(3pm)				User Contributed Perl Documentation				  CHI::Driver::Memory(3pm)

NAME
CHI::Driver::Memory - In-process memory based cache VERSION
version 0.54 SYNOPSIS
use CHI; my $hash = {}; my $cache = CHI->new( driver => 'Memory', datastore => $hash ); my $cache = CHI->new( driver => 'Memory', global => 1 ); DESCRIPTION
This cache driver stores data on a per-process basis. This is the fastest of the cache implementations, but data can not be shared between processes. Data will remain in the cache until cleared, expired, or the process dies. To maintain the same semantics as other caches, references to data structures are deep-copied on set and get. Thus, modifications to the original data structure will not affect the data structure stored in the cache, and vica versa. See CHI::Driver::RawMemory for a faster memory cache that sacrifices this behavior. CONSTRUCTOR OPTIONS
When using this driver, the following options can be passed to CHI->new() in addition to the CHI. One of datastore or global must be specified, or else a warning (possibly an error eventually) will be thrown. datastore [HASHREF] A reference to a hash to be used for storage. Within the hash, each namespace is used as a key to a second-level hash. This hash may be passed to multiple CHI::Driver::Memory constructors. global [BOOL] Use a standard global datastore. Multiple caches created with this flag will see the same data. Before 0.21, this was the default behavior; now it must be specified explicitly (to avoid accidentally sharing the same datastore in unrelated code). DISCARD POLICY
For CHI/SIZE AWARENESS caches, this driver implements an 'LRU' policy, which discards the least recently used items first. This is the default policy. SEE ALSO
CHI::Driver::RawMemory, CHI AUTHOR
Jonathan Swartz <swartz@pobox.com> COPYRIGHT AND LICENSE
This software is copyright (c) 2011 by Jonathan Swartz. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. perl v5.14.2 2012-05-30 CHI::Driver::Memory(3pm)