FlashPage: A read cache for low-latency SSDs in web proxy servers
The paper introduces FlashPage, a high-speed SSD caching system designed for ultra-fast media, with the goal of enhancing web page delivery in proxy servers. Traditional SSD caching schemes, designed primarily for slow HDD-based primary storage, encounter difficulties when applied to capacity-class...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Engineering Science and Technology, an International Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215098624000259 |
| _version_ | 1827316523516035072 |
|---|---|
| author | Junhee Ryu Dong Kun Noh Kyungtae Kang |
| author_facet | Junhee Ryu Dong Kun Noh Kyungtae Kang |
| author_sort | Junhee Ryu |
| collection | DOAJ |
| description | The paper introduces FlashPage, a high-speed SSD caching system designed for ultra-fast media, with the goal of enhancing web page delivery in proxy servers. Traditional SSD caching schemes, designed primarily for slow HDD-based primary storage, encounter difficulties when applied to capacity-class SSDs as primary storage. This limits the high-performance capabilities of caching media. To address this issue, FlashPage operates within the Linux virtual filesystem layer, shortening the hit-handling path and minimizing lookup overhead. It incorporates a compact radix tree to fast locate cached data. These approaches reduce the software overhead for a 4kB read hit by over 5 times. FlashPage also employs novel admission and eviction policies to minimize flash wear while maintaining a high hit rate. As a second-level storage cache, FlashPage predicts the hotness of potential demotion candidates in the first-level storage cache (i.e., page cache), achieving a 10.1% higher hit rate and reducing write traffic by 10.4% compared to LRU. Evaluations using Varnish and Squid HTTP caches show its effectiveness, with up to 29.6% and 38.2% faster web request processing compared to Bcache and DM-Cache, state-of-the-art caching schemes in mainline Linux kernels. |
| first_indexed | 2024-03-07T23:39:12Z |
| format | Article |
| id | doaj.art-49945b82cdeb47ef82614ba4d8fe2b3a |
| institution | Directory Open Access Journal |
| issn | 2215-0986 |
| language | English |
| last_indexed | 2024-04-24T23:17:09Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Engineering Science and Technology, an International Journal |
| spelling | doaj.art-49945b82cdeb47ef82614ba4d8fe2b3a2024-03-17T07:54:29ZengElsevierEngineering Science and Technology, an International Journal2215-09862024-03-0151101639FlashPage: A read cache for low-latency SSDs in web proxy serversJunhee Ryu0Dong Kun Noh1Kyungtae Kang2Memory Systems Research, SK hynix, Republic of KoreaSchool of AI Convergence, Soongsil University, Republic of KoreaDepartment of Computer Science and Engineering, Hanyang University ERICA, Republic of Korea; Corresponding author.The paper introduces FlashPage, a high-speed SSD caching system designed for ultra-fast media, with the goal of enhancing web page delivery in proxy servers. Traditional SSD caching schemes, designed primarily for slow HDD-based primary storage, encounter difficulties when applied to capacity-class SSDs as primary storage. This limits the high-performance capabilities of caching media. To address this issue, FlashPage operates within the Linux virtual filesystem layer, shortening the hit-handling path and minimizing lookup overhead. It incorporates a compact radix tree to fast locate cached data. These approaches reduce the software overhead for a 4kB read hit by over 5 times. FlashPage also employs novel admission and eviction policies to minimize flash wear while maintaining a high hit rate. As a second-level storage cache, FlashPage predicts the hotness of potential demotion candidates in the first-level storage cache (i.e., page cache), achieving a 10.1% higher hit rate and reducing write traffic by 10.4% compared to LRU. Evaluations using Varnish and Squid HTTP caches show its effectiveness, with up to 29.6% and 38.2% faster web request processing compared to Bcache and DM-Cache, state-of-the-art caching schemes in mainline Linux kernels.http://www.sciencedirect.com/science/article/pii/S2215098624000259SSD cacheTiered storageWeb cache |
| spellingShingle | Junhee Ryu Dong Kun Noh Kyungtae Kang FlashPage: A read cache for low-latency SSDs in web proxy servers Engineering Science and Technology, an International Journal SSD cache Tiered storage Web cache |
| title | FlashPage: A read cache for low-latency SSDs in web proxy servers |
| title_full | FlashPage: A read cache for low-latency SSDs in web proxy servers |
| title_fullStr | FlashPage: A read cache for low-latency SSDs in web proxy servers |
| title_full_unstemmed | FlashPage: A read cache for low-latency SSDs in web proxy servers |
| title_short | FlashPage: A read cache for low-latency SSDs in web proxy servers |
| title_sort | flashpage a read cache for low latency ssds in web proxy servers |
| topic | SSD cache Tiered storage Web cache |
| url | http://www.sciencedirect.com/science/article/pii/S2215098624000259 |
| work_keys_str_mv | AT junheeryu flashpageareadcacheforlowlatencyssdsinwebproxyservers AT dongkunnoh flashpageareadcacheforlowlatencyssdsinwebproxyservers AT kyungtaekang flashpageareadcacheforlowlatencyssdsinwebproxyservers |