東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Reducing Garbage Collection Costs Using Application-Specific Information.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Reducing Garbage Collection Costs Using Application-Specific Information./
Author:	Nunez, Diogenes Antonio.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	115 p.
Notes:	Source: Dissertations Abstracts International, Volume: 82-05, Section: B.
Contained By:	Dissertations Abstracts International82-05B.
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28089213
ISBN:	9798684655272

Reducing Garbage Collection Costs Using Application-Specific Information.
Nunez, Diogenes Antonio.

Reducing Garbage Collection Costs Using Application-Specific Information. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 115 p.

Source: Dissertations Abstracts International, Volume: 82-05, Section: B.

Thesis (Ph.D.)--Tufts University, 2020.

This item must not be sold to any third party vendors.

Applications running on multiple environments are all supported by garbage collectors. Modern garbage collectors rely on two assumptions to perform well: the collector will reclaim enough memory to avoid frequent failed allocations and most memory allocated for the application soon becomes garbage. These assumptions are broken by modern applications. For instance, applications that rely on an application-level key-value store, or software cache, reduce run time by increasing memory use. However, that breaks the first assumption. When they are broken, garbage collector performance degrades. To reduce this performance loss, garbage collectors should be supplied application-specific information.In this thesis, we support this hypothesis with three projects. First, we hypothesized Haskell programs violate the first assumption. The violation is thanks to the implementation of lazy evaluation which evaluates expressions only as needed. This can be circumvented with annotations, but the annotations can prove difficult to place correctly. We present Autobahn as a solution. Autobahn is a tool that uses a genetic algorithm to add strictness annotations to Haskell programs and improve their runtime.Next, we hypothesized software caches violate both assumptions. The violation comes from conflicting goals. The goal of the cache is to maximize the amount of space used to improve runtime. The goal of the garbage collector is to minimize the amount of space used to allow future allocations to succeed and keep time spent collection low. We present prioritized garbage collection as a solution. The prioritized garbage collector lets a programmer supply the garbage collector with data about objects to relieve memory-pressure and improve the robustness of software caching applications.Finally, we hypothesized applications with long-lived data structures violate the second assumption. These data structures are visited every collection, resulting in repeated work and lost time. We present a design for a deferred garbage collector. The deferred garbage collector lets a programmer supply information about long-lived data structures to reduce garbage collection time.

ISBN: 9798684655272Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Garbage collection

Reducing Garbage Collection Costs Using Application-Specific Information.
LDR:03386nmm a2200397 4500 001 2346344
005 20230315102144.5
006 m o d
007 cr#unu||||||||
008 241004s2020 ||||||||||||||||| ||eng d
020 $a 9798684655272
035 $a (MiAaPQ)AAI28089213
035 $a AAI28089213
040 $a MiAaPQ $c MiAaPQ
100 1 $a Nunez, Diogenes Antonio. $3 3685424
245 1 0 $a Reducing Garbage Collection Costs Using Application-Specific Information.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 115 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-05, Section: B.
500 $a Advisor: Guyer, Samuel Z.
502 $a Thesis (Ph.D.)--Tufts University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Applications running on multiple environments are all supported by garbage collectors. Modern garbage collectors rely on two assumptions to perform well: the collector will reclaim enough memory to avoid frequent failed allocations and most memory allocated for the application soon becomes garbage. These assumptions are broken by modern applications. For instance, applications that rely on an application-level key-value store, or software cache, reduce run time by increasing memory use. However, that breaks the first assumption. When they are broken, garbage collector performance degrades. To reduce this performance loss, garbage collectors should be supplied application-specific information.In this thesis, we support this hypothesis with three projects. First, we hypothesized Haskell programs violate the first assumption. The violation is thanks to the implementation of lazy evaluation which evaluates expressions only as needed. This can be circumvented with annotations, but the annotations can prove difficult to place correctly. We present Autobahn as a solution. Autobahn is a tool that uses a genetic algorithm to add strictness annotations to Haskell programs and improve their runtime.Next, we hypothesized software caches violate both assumptions. The violation comes from conflicting goals. The goal of the cache is to maximize the amount of space used to improve runtime. The goal of the garbage collector is to minimize the amount of space used to allow future allocations to succeed and keep time spent collection low. We present prioritized garbage collection as a solution. The prioritized garbage collector lets a programmer supply the garbage collector with data about objects to relieve memory-pressure and improve the robustness of software caching applications.Finally, we hypothesized applications with long-lived data structures violate the second assumption. These data structures are visited every collection, resulting in repeated work and lost time. We present a design for a deferred garbage collector. The deferred garbage collector lets a programmer supply information about long-lived data structures to reduce garbage collection time.
590 $a School code: 0234.
650 4 $a Computer science. $3 523869
650 4 $a Environmental health. $3 543032
650 4 $a Systems science. $3 3168411
650 4 $a Information science. $3 554358
653 $a Garbage collection
653 $a Lazy evaluation
653 $a Memory management
653 $a Programming languages
690 $a 0984
690 $a 0723
690 $a 0470
690 $a 0790
710 2 $a Tufts University. $b Computer Science. $3 1026183
773 0 $t Dissertations Abstracts International $g 82-05B.
790 $a 0234
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28089213