201220076 六、發明說明: 【發明所屬之技術領域】 本發明係關於一種取得儲存裝置狀態訊號的方法,特別是 種利用基板管理控制器(BaseboardManagement ContiOllei·, BMC)取得儲存裝置狀態訊號的方法。 【先前技術】 隨著電腦的普及與網路技術的快速發展’僅由普通電腦或 设備所能提供的服務以不敷使用,故發展出了伺服器的技術。 伺服器係為一種善於處理網路技術之電腦平台,其可連結至各 種網路系統.,並對透過網路系統相連結的電腦提供各種的應用 服務。伺服器大多具有大容量的儲存裝置,以提供諸如多媒體 播放、網路硬碟或是企業用資料庫等服務。由此可知,儲存裝 置疋飼服器中相當重要的一個元件,一但發生故障就會對伺服 器乃至提供給客戶的服務造成嚴重的不良影響。 而為了管理伺服器,智慧型平台管理介面(201220076 VI. Description of the Invention: [Technical Field] The present invention relates to a method for obtaining a status signal of a storage device, and more particularly to a method for obtaining a storage device status signal by using a Baseboard Management ContiOllei (BMC). [Prior Art] With the popularity of computers and the rapid development of network technologies, the services provided by ordinary computers or devices are not enough, so the technology of the server has been developed. The server is a computer platform that is good at handling network technology. It can be connected to various network systems. It provides various application services for computers connected through the network system. Servers mostly have large-capacity storage devices to provide services such as multimedia playback, network hard drives, or enterprise databases. It can be seen that the storage device is a very important component in the feeding device, and once it fails, it will have a serious adverse effect on the server and even the service provided to the customer. In order to manage the server, the intelligent platform management interface (
Platform Management Interface ’ IPMI)的技術應運而生。管理 者可以透過IPMI以及配置於伺服器中的基板管理控制器 (Baseboard Management Controller,BMC)監控飼服器。但 是目前的伺服器在儲存裝置故障後,係透過獨立運作的硬體發 出代表故障的狀態訊號再點亮伺服器上的燈號,而不會通知管 理員。也就是說,習知的狀態訊號係直接由硬體解碼控制。因 此造成習知的伺服器無法整合並行的故障信號與管理機制,亦 201220076 無法有效率地通知管理員故障事件的問題。 【發明内容】 為了解決上述問題’提供—種利用基板管理控制器 (Baseboard Management Contr〇ller,BMC)取得儲存裝置狀 ' 齡·方法。侧BMC崎齡裝錄H峨的方法適用 _ 於具有_ BMC以及一儲存震置的-伺服器。利用BMC取得 儲存裝置狀態訊號的方法包括:輸人輸出擴展器 _ (mput/output expander,1/0 expander)接收對應於儲存裝置的 -儲存裝置控制器產生的-電訊號;以及產生—系統管理中斷 (systemmanagementinterrupt,SMI),以觸發一基本輸入輸出 系統(baSiCinput/outputSyStem,m〇s)的一 SM處理程序。 其中SMI處理程序包括:讀取電訊號;以及依據電訊號,發 送'錯誤事件給BMC。 其中在「利用一輸入輸出擴展器接收對應於儲存裝置的— 籲儲存裝置控制器的一電訊號」的步驟中,可以從一複雜可程式 邏輯裝置(C〇mplex ProgrammableL〇gic Device,cpLD)接收 電訊號。此外,可以由輸入輸出擴展器產生SMI,以觸發BI0S 的SMI處理各序。上述SMI並可以透過内部整合電路匯流排 (inter mtegrated circuit bus,此 bus)觸發 m〇s 的細處理程 序。 儲存裝置控制器可以監測儲存裝置的狀態,並透過序列式 通用型輸入輪出(serial general pUrp0se inpm/output,SGpi(^ 201220076 據以發送電訊號給CPLD。 根據-實mi例, BMC轉儲錄置祕訊號的方 法另可包括:令CPLD依據電職點亮對應於儲存裝置的一發 光二極體(light emitting diode,LED)組。其中儲存裝置可包 括多個儲存單元,而電訊號係對應於這些儲存單元。 根據另-實施範例’利用BMC取得儲縣置狀態訊號的 方法亦包括:令BMC依據f訊號執行―館存裝置管理程序。 其中儲存裝置管理程序可以包括:通知it過智能平台管理匯流 排(Intelligent Platform Management —,細)與腿 連的-遠端管雜序。齡健f理程核是可以包括:依據 電訊號暫停儲存裴置的至少一儲存單元。 1不上所述’利用BMC取得儲存農置狀態訊號的方法產生 電訊號後,點亮對應的LED組並透過SMI以及讀處理程序 。知BMC目此由硬體控制的故障點燈機制被整合入 管理的事件之中,使管理介面得以統—而增進管理效率。 【實施方式】 以下在員施方式中詳細敛述本發明之詳細特徵以及優 點’其内*足以使任何熟習細技藝者了解本發明之技術内容 並據以實施’且根縣說明書所揭露之内容、帽專利範圍及 圖式’任何Μ相關技藝者可輕易地理解本發明相關之目的及 優點。 本發明係關於一種利用基板管理控制器(Baseboard 201220076The technology of Platform Management Interface ’ IPMI came into being. The administrator can monitor the feeder through IPMI and a Baseboard Management Controller (BMC) configured in the server. However, after the storage device fails, the current server sends a signal indicating the fault through the independently operating hardware to illuminate the signal on the server without notifying the administrator. That is to say, the conventional status signal is directly controlled by hardware decoding. As a result, the conventional server cannot integrate the parallel fault signal and management mechanism, and 201220076 cannot effectively notify the administrator of the fault event. SUMMARY OF THE INVENTION In order to solve the above problems, a storage device-like age method is obtained by using a substrate management controller (Baseboard Management Contr〇ller, BMC). The method of side BMC ageing H峨 is applicable to the server with _BMC and a storage. The method for obtaining the storage device status signal by using the BMC includes: the input output expander_(mput/output expander, 1/0 expander) receives the -electric signal generated by the storage device controller corresponding to the storage device; and generates - system management A systemmanagement interrupt (SMI) to trigger an SM handler for a basic input/output system (baSiCinput/outputSyStem, m〇s). The SMI processing program includes: reading the electrical signal; and sending an 'error event to the BMC according to the electrical signal. The step of "receiving a signal corresponding to the storage device by using an input/output expander" can be received from a complex programmable logic device (C〇mplex Programmable L〇gic Device, cpLD). Telecommunications signal. In addition, the SMI can be generated by the input and output expanders to trigger the SMI processing of the BIOS. The above SMI can trigger a fine processing of m〇s through an inter-mated circuit bus (this bus). The storage device controller can monitor the status of the storage device and send it through the serial general-purpose input (serial general pUrp0se inpm/output, SGpi (^ 201220076 to send the electrical signal to the CPLD. According to the real-mi example, BMC transfer record) The method of the secret signal may further include: causing the CPLD to illuminate a light emitting diode (LED) group corresponding to the storage device according to the electric job. The storage device may include a plurality of storage units, and the electrical signal system corresponds to According to another embodiment, the method for obtaining a state signal by using the BMC includes: causing the BMC to execute a library management program according to the f signal. The storage device management program may include: notifying the IT platform The management platform (Intelligent Platform Management -, fine) and the leg-to-leg tube miscellaneous sequence. The age-fighting core can include: at least one storage unit that suspends the storage device according to the electrical signal. 'Using the BMC to obtain the signal for storing the farm status signal, the corresponding LED group is illuminated and the SMI and the read processing program are transmitted. The hardware-controlled fault lighting mechanism is integrated into the management event, so that the management interface can be unified to improve management efficiency. [Embodiment] The following detailed description of the features and advantages of the present invention will be described in detail. 'Inside* is sufficient for any skilled artisan to understand the technical content of the present invention and to implement the contents disclosed in the 'Gen County Manual, Cap Patent Range and Drawing'. Any relevant artisan can easily understand the present invention. The purpose and advantages of the present invention relate to a substrate management controller (Baseboard 201220076)
Management Controller,BMC)取得儲存裝置狀態訊號的方 法,其適用於具有一基板管理控制器(BMC)以及一儲存裴 置的一伺服器。 請參照「第1圖」,其係為一實施範例之伺服器之示意圖。 伺服器20包括BMC 21、儲存裝置22以及一中央處理器 (central processor unit ’ CPU) 23。中央處理器 23 透過一儲存 裝置控制器232與儲存裝置22電性相連,並運行一基本輸入 鲁輸出系統(basic input/output system,BIOS ) 234。其中儲存裝 置控制器232可位於中央處理器23的一南橋(未繪示)之中。 儲存裝置22可以例如是各種大容量的硬碟,或是磁碟陣列 (redundant array of ineXpensive disk,RAID )系統。伺服器 2〇 並可透過網路與一遠端計算機(rem〇tec〇mpmer) 3〇相連,而 逖端計算機30則可藉由一遠端管理程序32以及BMC 21管理 伺服器20。 • 飼服器20可支持智慧型平台管理介面(Intelligent PlatformManagement Controller (BMC) A method of obtaining a storage device status signal suitable for a server having a Baseboard Management Controller (BMC) and a storage device. Please refer to "FIG. 1", which is a schematic diagram of a server of an embodiment. The server 20 includes a BMC 21, a storage device 22, and a central processor unit (CPU) 23. The central processing unit 23 is electrically coupled to the storage device 22 via a storage device controller 232 and operates a basic input/output system (BIOS) 234. The storage device controller 232 can be located in a south bridge (not shown) of the central processing unit 23. The storage device 22 can be, for example, a variety of large-capacity hard disks or a redundant array of ineXpensive disk (RAID) system. The server 2A can be connected to a remote computer (rem〇tec〇mpmer) via the network, and the terminal computer 30 can manage the server 20 by a remote management program 32 and the BMC 21. • Feeder 20 supports smart platform management interface (Intelligent Platform
ManagementInterface,IpMI),並藉由上述硬體運行一作業系 統。其中伺服器20可使用Unix的Linux、FreeBSD或是微軟 (Microsoft)的 Wind〇ws (窗口操作系統)8_γ2〇〇3 等作業 系、先亦可為磁碟作業系統(Disk Operating System,DOS) 或疋了伸勃體;丨面(可擴展固件接口,Extensible Firmware Interface ’ EFI)的系、統。且飼服器2〇亦可各種廠牌之各種祠 服器產品,本發明並不對其限制。ManagementInterface, IpMI), and run a job system with the above hardware. The server 20 can use Unix Linux, FreeBSD or Microsoft (Wind) ws (window operating system) 8_γ2〇〇3 operating system, first can also be Disk Operating System (DOS) or疋 伸 丨 丨; 丨 ( (Extensible Firmware Interface, Extensible Firmware Interface 'EFI) system, system. Moreover, the feeding device 2 can also be used for various products of various brands, and the invention is not limited thereto.
S 7 201220076 更詳細地說,智慧型平台管理介面是一種伺服器管理平台 的標準架構,它包含BMC21、系統介面(SystemInterface)、 非揮發性儲存單元(Non-volatile Storage )、智能平台管理匯流 排(Intelligent Platform Management Bus,ΓΡΜΒ )以及智慧型 機箱管理匯流排(Intelligent Chassis Management Bus,ICMB ) 等5項元件。而其中最重要的就是bmC 21。BMC 21就像是 一台獨立的電腦,包括自己的處理器以及記憶體等資源。且 BMC 21的運作均使用自己具有的資源,而不會佔用伺服器2〇 之硬體模組的其他資源。舉例而言,遠端計算機3〇可使用惠 普(HP)公司的iL〇系統、.戴爾DELL公司的iDRAC系统, 或是英特爾(Intel)公司的ESB2系統。 請配合「第1圖」並參照「第2圖」,「第2圖」係為—實 施範例之_ BMC取_存健狀態織的方狀流程圖。 首先利用一輸入輸出擴展器(bput/〇mput expander, expander) 25接收對應於儲存裝置22的儲存裝置控制器幻2 產生的-電訊號(步驟sl〇〇)。其中輸入輸出擴展器乃可將 收到的電訊號存於一輸入暫存器(未繪示)。 、 更沣細地說,儲存裝置控制器 隨呀監測儲存裝置 的狀態;而當儲存裝置22發生故障時,儲存裝置控制哭汉 2狄纽障錢麵—齡裝置《職給—硬 又4。硬體編碼手段24再將儲存裝置控制器Μ2發 存裝置狀態訊號轉軸魏號。也就是說,電訊號就是表示錯 201220076 存裝置22的狀態的狀態訊號。 其中硬體編碼手段24可以是-複雜可程式邏輯裝置 (Complex Programmable Logic Device,CPLD )。CPLD 中可 包3夕個可私式邏輯陣列(pr〇grammabieArrayi^gie,pAy, 並用來只現各種運算和組合邏輯(c〇mbinati〇nal㈣c)。各個 PAL間的互接連線也可以進行程雜的_以及燒錄。CAD 運用讀乡合-(A11_IlK)ne)的整合作法,使其能實現數千 φ 個途輯閘’甚至數十萬個邏輯閘才能構成的電路。而在本實施 fe例中CPLD被程式化以執行硬體編碼手段24所需的功能。 例如CPLD可接收儲存裝置控制器232透過序列式通用型輸入 輸出(serial general purpose input/output,SGPIO)發送的電訊 號’再將其重新編碼為電訊號。 需注意的是,即使儲存裝置22沒有發生故障,儲存裝置 控 232仍可持續發出表示正常的儲存裝置狀態訊號以表 # 示目前狀況正常。CPLD亦對應地將表示正常的儲存裝置狀態 訊號轉換為表示正常的電訊號,例如全由二進位「〇」表示的 訊號。 接者输入輸出擴展 u & 土 τ 所 I system managemenuntemipt ’ SMI),以觸發 BI〇s 234 的一 $⑽處理 程序236 (步驟S110 )。SMI會使得中央處理器23進入稱^系 統管理模式(System Management mode ’ SMM)的執行模式。 SMM底下包括事蚊義好的SMI處理程序236,並H發 201220076 時執行。例如SMM可以聽處理例如記㈣錯料系統事 件;或是在中央處理器23溫度過高時_關機以維護饲服器 20的安全。 根據一實施範例,當輸入輸出擴展器25收到不是表示正 常的電訊號(表示正常的電訊號例如是全由二進位「〇」表示 的訊號)時,以軟體模擬的方式發出SMI,以觸發见〇8 的SMI處理程序236。 睛參照「第3 ®」’其係為-實施範例之SMJ處理程序之 流程圖。SMI處理程序236被執行時先讀取電訊號(步驟 S200)。SMI處理程序236可透過連接中央處理器23的一南橋 (未繪示)與輸入輸出擴展器25的内部整合電路匯流排(inter mtegrated circuit bus,I2C bus)讀取輸入輸出擴展器乃的輸入 暫存裔的值,以確定有發生儲存裝置22錯誤的情形。例如當 儲存裝置22包括多個儲存單元時,可以藉由電訊號得知故障 的是哪一個儲存單元。 SMI處理程序236並依據電訊號,發送一錯誤事件給bmc 21 (步驟S210)。根據一實施範例,SMI處理程序236可將電 訊號夠過_事先絲的格式纟!ρΜ㈣辭面通知bmc 21。系統介面例如可以是知識中心支援系統 (Knowledge-Centered Supp〇rt ’ KCS)或是伺服器管理介面 (Server Management Interface Chip » SMIC ) ° 請參照「第4圖」’其係為另一實施範例之利用BMC取 201220076 得儲存裝置狀態訊號的方法之流程圖。利用BMC取得儲存裝 置狀態訊號的方法另可以令CPLD依據電訊號點亮對應於儲 存裝置 22 的一發光二極體(light emitting diode,LED)組 26 (步驟 S120)。 請配合參照「第5圖」,其係為另一實施範例之伺服器之 示思圖。儲存裝置22可包括多個儲存單元222,例如儲存單 元222a、儲存單元222b以及儲存單元222c ;而LED組26則 • 可包括與儲存單元222數量相同的多個LED燈號262,例如 LED燈號262a、LED燈號262b以及LED燈號262c。經重新 編瑪的電訊號係對應這些儲存單元222,並用以點亮LED燈 號 262。 此外’錯誤事件中除了指出儲存裝置22的故障狀況外, 並可包括需要由BMC 21執行的工作。當BMC21接收到的錯 誤事件之後,利用BMC取得儲存裝置狀態訊號的方法並可令 籲 BMC 21依據電訊號執行一儲存裝置管理程序(步驟si3〇)。 BMC 21可紀雜存裝置a發生故_事件,並依照儲存裝 置管理程序進行後續處置。而儲存裂置管理程序可以依據電訊 號暫停儲存裝置22的至少一個故障的儲存單元222,或是通 知透過IPMB與BMC 21相連的遠端計算機3〇的遠端管理程 序32。因此透過步驟sll〇以及_處理程序说,可以使得 BMC η能_鬆轉域縣置22的故轉況,以及需要 進行的處理方法。S 7 201220076 In more detail, the intelligent platform management interface is a standard architecture of the server management platform, which includes BMC21, system interface (SystemInterface), non-volatile storage unit (Non-volatile Storage), intelligent platform management bus (Intelligent Platform Management Bus, ΓΡΜΒ) and Intelligent Chassis Management Bus (ICMB) and other five components. The most important of these is bmC 21. The BMC 21 is like a standalone computer with resources such as its own processor and memory. And the operation of the BMC 21 uses its own resources, and does not occupy other resources of the hardware module of the server. For example, the remote computer 3 can use HP's iL system, Dell DELL's iDRAC system, or Intel's ESB2 system. Please refer to "Figure 1" and refer to "Figure 2". "Second Picture" is a square flow chart of the implementation example. First, an electric signal generated by the storage device controller corresponding to the storage device 22 is received by an input/output expander (bput/〇mput expander, expander) 25 (step sl1). The input/output expander can store the received electrical signal in an input register (not shown). More specifically, the storage device controller monitors the state of the storage device; when the storage device 22 fails, the storage device controls the crying device. The hardware encoding means 24 then stores the device controller Μ2 to store the device status signal. That is to say, the telecommunication signal is a status signal indicating the status of the device 201222. The hardware encoding means 24 may be a Complex Programmable Logic Device (CPLD). In CPLD, there can be a private logic array (pr〇grammabieArrayi^gie, pAy, and used to display only various operations and combinational logic (c〇mbinati〇nal(4)c). Interconnection between PALs can also be performed. Miscellaneous _ and burning. CAD uses the whole cooperation method of reading xianghe-(A11_IlK)ne, so that it can realize thousands of φ roads and even hundreds of thousands of logic gates. In the present embodiment, the CPLD is programmed to perform the functions required by the hardware encoding means 24. For example, the CPLD can receive the electrical signal transmitted by the storage device controller 232 through the serial general purpose input/output (SGPIO) and re-encode it into an electrical signal. It should be noted that even if the storage device 22 fails, the storage device control 232 can continue to send a status signal indicating that the storage device is normal to indicate that the current status is normal. The CPLD also correspondingly converts the normal storage device status signal into a normal electrical signal, such as a signal represented by the binary "〇". The receiver input and output extension u & τ is I system managemenuntemipt ’ SMI) to trigger a $(10) processing procedure 236 of BI〇s 234 (step S110). The SMI causes the central processing unit 23 to enter an execution mode called System Management Mode (SMM). Under the SMM, the SMI processing program 236 is included, and is executed at 201220076. For example, the SMM can listen to, for example, a (four) wrong system event; or when the CPU 23 is too hot, the power is turned off to maintain the safety of the feeder 20. According to an embodiment, when the input/output expander 25 receives a signal that does not indicate a normal signal (indicating that the normal electrical signal is, for example, a signal represented by a binary "〇"), the SMI is sent in a software simulation manner to trigger See S8's SMI handler 236. Refer to the "3rd ®" as a flowchart of the SMJ processing procedure for the implementation example. When the SMI handler 236 is executed, the electrical signal is first read (step S200). The SMI processing program 236 can read the input and output expander input through a south bridge (not shown) connected to the central processing unit 23 and an internal integrated circuit bus (I2C bus) of the input/output expander 25. The value of the survivor is determined to determine if there is an error in the storage device 22. For example, when the storage device 22 includes a plurality of storage units, it is possible to know which storage unit is faulty by the electrical signal. The SMI handler 236 sends an error event to bmc 21 based on the electrical signal (step S210). According to an embodiment, the SMI handler 236 can pass the signal number to the _ prior silk format! Μ Μ (4) to inform bmc 21. The system interface can be, for example, a Knowledge Center Support System (Knowledge-Centered Supp〇rt 'KCS) or a Server Management Interface Chip (SMIC). Please refer to FIG. 4, which is another embodiment. A flow chart of a method for taking a storage device status signal from 201220076 using the BMC. The method for obtaining the storage device status signal by using the BMC may further cause the CPLD to illuminate a light emitting diode (LED) group 26 corresponding to the storage device 22 according to the electrical signal (step S120). Please refer to "Figure 5" for a description of the server of another embodiment. The storage device 22 can include a plurality of storage units 222, such as a storage unit 222a, a storage unit 222b, and a storage unit 222c; and the LED group 26 can include a plurality of LED lights 262 of the same number as the storage unit 222, such as LED lights. 262a, LED light number 262b, and LED light number 262c. The re-coded telecommunication numbers correspond to the storage units 222 and are used to illuminate the LED lights 262. Furthermore, in addition to indicating a fault condition of the storage device 22, the error event may include work that needs to be performed by the BMC 21. After the BMC21 receives the error event, the BMC obtains the storage device status signal and can cause the BMC 21 to execute a storage device management program according to the electrical signal (step si3). The BMC 21 miscellaneous device a occurs and is subsequently disposed in accordance with the storage device management program. The storage splice management program may suspend at least one failed storage unit 222 of the storage device 22 according to the electrical signal, or notify the remote management program 32 of the remote computer connected to the BMC 21 via the IPMB. Therefore, through the steps sll 〇 and _ the processing procedure, it is possible to make the BMC η _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
S 11 201220076 S130的執行順序並 需注意的是,對於步驟S120以及步驟 沒有限制。 態訊號的方法實際運 以下係為彻取得儲存裝置狀 作時的一實施範例。 例如當儲存單元222b發生故障時,儲存裝置控制器说 會據以發⑽存灯故_號。cpLD躲_存裝置故障信 號後將其觀為電峨。例如可以相的二進位碼對應表示所 有的儲存單元222,且以「〇本+ 「 以G」表不正常時’「_」的電訊號 辨識表示現在只有儲存單元㈣發生故障。硬體編碼手段^ 接著將電訊號傳送給輸人輸出擴展器25,並依據「_」的電 訊號將LED燈號勘點亮為紅燈。而沒發生故障的儲存單元 222a以及222b所對應之LED燈號262a以及纖可以不點燈 亦可以維持點亮綠燈以表示正常狀態。 由於輸入輸出擴展器25收到與代表正常的「〇〇〇」不同之 電訊號「010」’其便產生SMI以觸發BI0S 234的SMI處理程 序236。接著BIOS 234將電訊號以及儲存裝置管理程序作為 錯誤事件發送給BMC 2卜而當BMC 21收到錯誤事件後,便 執行儲存裝置管理程序以經由網路以及通知遠端計算機通 知管理人。如此一來,管理人便可即時前往維修或更換故障的 儲存單元222b。 綜上所述,利用BMC取得儲存裝置狀態訊號的方法利用 硬體編碼手段產生電訊號後’不但用以點亮對應的LED組, 12 201220076 亦透過SMI以及SMI處理程序告知BMC。也就是說,原先獨 立由硬體控制的故障點燈機制被整合入BMC管理的事件之 中,使管理介面得以統一。如此一來,可以解決習知技術像多 頭馬車並行般的雜亂的管理方式,而能以更簡潔且有效率的方 法管理伺服器,並有效率地再發生故障事件時通知管理員。 【圖式簡單說明】 ' 第1圖係為一實施範例之伺服器之示意圖。 第2圖係為一實施範例之利用基板管理控制器取得儲存 裝置狀態訊號的方法之流程圖。 第3.圖係為一實施範例iSMI處理程序之流程圖。 第4圖係為另-實施範例之利用基板管理控制器取得錯 存裝置狀態訊號的方法之流程圖。 ' 第5圖係為另一實施範例之伺服器之示意圖。 【主要元件符號說明】 20 伺服器 21 基板管理控制器(BMC) 212 偵測器 22 儲存裝置 222, 222a, 222b, 222c 儲存單元 23 中央處理器 232 儲存裝置控制器 234 基本輸入輸出系統(BIOS) 201220076 236 SMI處理程序 24 硬體編碼手段 25 輸入輸出擴展器 26 發光二極體組(LED組) 262, 262a, 262b, 262c 發光二極體燈號(LED燈號) 30 遠端計算機 32 遠端管理程序 14S 11 201220076 S130 execution order and it should be noted that there is no limitation for step S120 and the steps. The method of the signal signal is actually carried out. The following is an example of the implementation of the storage device. For example, when the storage unit 222b fails, the storage device controller says that it will send (10) the lamp _ number. After cpLD hides the device fault signal, it views it as power. For example, the binary code of the phase can correspond to all the storage units 222, and the signal identification of "〇" + "when G is abnormal" and "_" indicates that only the storage unit (4) has failed. The hardware encoding means ^ then transmits the electrical signal to the input output expander 25, and lights the LED light number to a red light according to the "_" signal number. The LED lights 262a and the fibers corresponding to the non-faulty storage units 222a and 222b may not be lit, and the green light may be maintained to indicate a normal state. Since the input/output expander 25 receives an electrical signal "010" which is different from the normal "〇〇〇", it generates an SMI to trigger the SMI processing program 236 of the BI0S 234. The BIOS 234 then sends the telecommunication signal and the storage device management program as an error event to the BMC 2b. When the BMC 21 receives the error event, it executes the storage device management program to notify the remote computer of the administrator via the network. In this way, the manager can immediately go to repair or replace the failed storage unit 222b. In summary, the method of obtaining the state signal of the storage device by using the BMC is to use the hardware encoding means to generate the electrical signal, and then not only to illuminate the corresponding LED group, 12 201220076 also informs the BMC through the SMI and the SMI processing program. In other words, the previously independent hardware-controlled fault lighting mechanism was integrated into the BMC-managed events to unify the management interface. In this way, it is possible to solve the messy management method of the conventional technology like a parallel carriage, and to manage the server in a more concise and efficient manner, and notify the administrator when the fault event occurs again effectively. [Simple description of the drawing] 'The first figure is a schematic diagram of a server of an embodiment. Figure 2 is a flow diagram of a method for obtaining a storage device status signal using a substrate management controller in an embodiment. Figure 3. is a flow chart of an example iSMI handler. Figure 4 is a flow diagram of a method for obtaining a faulty device status signal using a substrate management controller in another embodiment. Figure 5 is a schematic diagram of a server of another embodiment. [Main component symbol description] 20 Server 21 Baseboard Management Controller (BMC) 212 Detector 22 Storage Device 222, 222a, 222b, 222c Storage Unit 23 Central Processing Unit 232 Storage Device Controller 234 Basic Input Output System (BIOS) 201220076 236 SMI processing program 24 Hardware coding means 25 Input and output expander 26 Light-emitting diode group (LED group) 262, 262a, 262b, 262c Light-emitting diode (LED light) 30 Remote computer 32 Remote Management program 14