嵌入式網路通訊裝置評比技術與工具之研發---子計畫四：嵌入式網路通訊裝置儲存裝置效能評比基準與工具之研發(中心分項)(I)

Abstract

由於快閃記憶體的良好物理特性，如非揮發性，耐震，以及省電，使得它一向是嵌 入式系統中儲存媒體的最好選擇。作為一個儲存媒體，目前評比快閃記憶體為基礎 的儲存系統效能的方法，還是援用設計給以磁碟為基礎之儲存系統的既有方法。這 些方法固然可以測出一些表面的效能瓶頸，但是卻無法深入發掘導致效能低落的問 題所在，而這些問題往往是與快閃記憶體的特殊管理議題有關。舉例來說，快閃記 憶體上面的可用空間是由垃圾回收方法所產生的，這種內部動作，會不時產生冗長 的停頓時間。而垃圾回收則會磨損快閃記憶體。而為了平均地磨損快閃記憶體，又 有了平均磨損的議題。因此，除了典型之回應時間與資料吞吐量，欲佈署快閃記憶 體在嵌入式系統中以為儲存媒體，測試評比之對象，還必須包含快閃記憶體的壽命 問題，即時應用程式支援能力，時間以及空間計算資源之成本，快閃記憶體的空間 利用率，快閃記憶體傳輸介面之頻寬利用率等等。 本研究計畫的目的，在於針對快閃記憶體為基礎之儲存系統，設計與實作出完整之 效能評比程序，工具，以及技術。測試對象有二：快閃記憶體檔案系統，以及固態 硬碟。工作項目包括：作業系統核心與韌體之事件擷取機制，標準測試程序之建立， 測試標竿之設計，完整之批次測試工具，以及虛擬平台技術。本計畫提案分為兩年， 而前期已有連續性的計畫執行中。已執行的計畫中，已經針對既有的儲存裝置，利 用既有的工具，做了大規模的評比測試。本計劃提案的第一年，則開發整合我們自 行開發的測試工具，持續精進至可進行in-lab test 的水準，並且將測試的角度， 由以往完全黑箱測試，延伸至可部分知道，或者全部知道待測物內部狀況的測試方 法。本年度搭配虛擬平台技術的開發，讓固態硬碟廠商可以在不需要公開原始碼的 狀況下，能夠做所謂的白箱測試。第二年，則延續第一年開發之工具與技術，產出 可逕付廠商做out-lab之測試工具與測試程序。而本年度的技術議題則延伸至自動診 斷技術，用以發現待測物的效能瓶頸與弱點，給固態硬碟設計者一些技術上可改良 的建議。

Flash memory is widely deployed in embedded computing systems because of its non-volatility, shock-resistance, and power conservation. To test the performance of flash-memory-based storage systems, currently benchmark suites for disk-based storage systems are used. The ordinary benchmark suites may identify the commonly existing performance bottleneck, the source that causes the performance degradation is not easy to identify, though. That is because the physical characteristics and geometry of flash memory impose many constraints on its management. For example, newly written data are dispatched to garbage-collected space. Garbage collection would involve intensive internal data movement and then introduce lengthy delay. Furthermore, garbage collection would wear portions of the flash memory out. So to lengthen the overall lifespan of flash memory, wear-leveling activities would then be performed. By the above discussions we may found that to test a flash-memory-based storage system is very different from to test a disk-based ones. Besides response and throughput, to test flash-memory-based embedded storage systems we have to include the lifetime issue, the support of real-time applications, the computational-resource costs of time and space, flash-memory space utilization, and bandwidth utilization. The objective of this research project is to design and implement the tools, procedures and methods of benchmark for flash-memory-based storage systems. Working items include the methods to capture and to analyze kernel/firmware events, design of test procedures and performance indexes, implementation of batch test tools, and platform-surrogating techniques. Our proposal is for a two-year project, and we have developed many benchmark tools for black-box tests in the last NSC project which is still running. For the first year of this proposal, the tools must have the quality for in-lab tests. Despite black-box tests, this year we are concerned with gray-box tests and white-box tests. A technical issue of this project year is platform surrogating. It is to provide abstraction model of hardware and related software interface. With platform surrogating, vendors may transfer their firmware/driver source code to the virtual platform for white-box tests without disclosing their code. For the second year of this project, our benchmark tools should reach a quality that they can be used for out-lab tests. The technique issue of this year is to develop an auto-pilot diagnosing procedure. It is to automatically target and to identify the design weak points pertaining to performance degradation. By jointly using the benchmark tools and the platform-surrogating technique, the cycle of test, debug, and benchmark of their algorithms can be significantly shortened.