Vdbench-For-Linux簡(jiǎn)明操作手冊(cè).doc

Vdbench For Linux簡(jiǎn)明操作手冊(cè)Vdbench is a disk and tape I/O workload generator for verifying data integrity and measuring performance of direct attached and network connected storage on Windows, Solaris, Linux, AIX, OS/X and HP/UX. 目 錄一、運(yùn)行環(huán)境3二、Vdbench目錄說明3三、Vdbench基本命令介紹3四、Vdbench 腳本參數(shù)解釋41、存儲(chǔ)定義（Storage definition）42、工作負(fù)荷定義（Workload definition）53、測(cè)試運(yùn)行定義（Run definition）64、腳本示例6一、運(yùn)行環(huán)境 二、Vdbench目錄說明1、 執(zhí)行程序文件#./vdbench2、 軟件操作說明文件#vdbench.pdf3、 示例腳本文件，及腳本說明#cd examples三、Vdbench基本命令介紹1、 進(jìn)入Vdbench目錄，給Vdbench執(zhí)行文件賦予“777”權(quán)限。#cd /vdbench#chmod 777 vdbench2、 執(zhí)行Vdbench測(cè)試命令。#./vdbench -f ./test/seq_read_sdb -o /testlog/seq_read_sdb_1命令解釋：命 令描 述備 注./vdbench測(cè)試的執(zhí)行文件-f指定測(cè)試腳本參數(shù)./test/seq_read_sdb測(cè)試腳本文件路徑-o指定測(cè)試輸入?yún)?shù)/testlog/seq_read_sdb_1測(cè)試結(jié)果輸入路徑四、Vdbench 腳本參數(shù)解釋1、 存儲(chǔ)定義（Storage definition）u raw:裸盤測(cè)試。示例：sd=sd1,lun=/dev/sdb,threads=32,openflags=o_direct描述：定義一個(gè)存儲(chǔ)過程（sd），測(cè)試磁盤裸設(shè)備（/dev/sdb）。lun=/dev/sdb：指定測(cè)試的盤符，裸盤路徑。threads=32：設(shè)置測(cè)試進(jìn)程隊(duì)列深度，常用有1、2、4、8、16、32、64等，數(shù)值越高表示對(duì)磁盤的壓力越大。openflags=o_direct：處理緩存的方法?！皁_direct”使用Linux的“O_DIRECT”選項(xiàng)不使用緩存直接寫入磁盤。注意：測(cè)試過程組合有：sd、wd、rdu filesys:文件系統(tǒng)測(cè)試。1、測(cè)試單個(gè)文件示例1：sd=sd1,lun=/dir/a.file,size=100m,openflags=o_direct描述：定義一個(gè)存儲(chǔ)過程（sd），測(cè)試“/div/a.file”文件，設(shè)定文件大小為100MB。lun=/dir/a.file：指定測(cè)試一個(gè)文件完整路徑。注意：測(cè)試過程組合有：sd、wd、rd2、測(cè)試多個(gè)文件示例2：fsd=fsd1,anchor=/dir,depth=1,width=1,files=15,size=128k,openflags=o_direct描述：定義的是文件存儲(chǔ)過程（fsd），指定存儲(chǔ)路徑為“/dir”。depth=1：路徑的深度，數(shù)值代表文件夾的級(jí)別。width=1：每層文件夾下子文件夾數(shù)。files=15：測(cè)試最后一層文件夾中將自動(dòng)生成的文件個(gè)數(shù)。size=128k：每個(gè)測(cè)試文件的大小。例：depth=3,width=2,files=15,size=1m測(cè)試最后一層一共生成23=8個(gè)文件夾，每個(gè)文件夾下生成15個(gè)文件，共有8*15*1=120MB的文件數(shù)據(jù)。注意：測(cè)試過程組合有：fsd、fwd、rdfsd參數(shù)詳細(xì)說明：fsd=nameUnique name for this File System Definition.fsd=defaultAll parameters used will serve as default for all the following fsds.count=(nn,mm)Creates a sequence of FSD parameters.anchor=/dir/The name of the directory where the directory structure will be created.shared=yes/noDefault no: See FSD sharingwidth=nnHow many directories to create in each new directory.depth=nnHow many levels of directories to create under the anchor.files=nnHow many files to create in the lowest level of directories.sizes=(nn,nn,.)Specifies the size(s) of the files that will be created.distribution=allDefault bottom, creates files only in the lowest directories. allcreatesFiles in all directories.openflags=(flag,.)Pass extra flags to (Solaris) file system open request (See: man open)total_size=nnnStop after a total of nnn bytes of files have been created.workingsetsize=nnwss=nnCauses Vdbench to only use a subset of the total amount of files defined In the file structure. See workingsetsize.2、 工作負(fù)荷定義（Workload definition）u 測(cè)試裸盤，或測(cè)試單個(gè)文件示例：wd=wd1,sd=sd*,seekpct=seq,rdpct=100,xfersize=2m描述：定義一個(gè)工作量過程。通過“sd”參數(shù)指定前面所定義的存儲(chǔ)過程，“sd*”表示所有“sd”開頭的存儲(chǔ)過程。seekpct：random(100) or sequential(0)* 100% random : seekpct=100* 100% sequential : seekpct=0* 20% random : seekpct=20rdpct：read(100) or write(0)* 100% read : rdpct=100* 100% write : rdpct=0* 70% read : rdpct=70xfersize：Data transfer size,default 4ku 測(cè)試多個(gè)文件示例：fwd=fwd1,fsd=fsd1,operation=read,xfersize=256k,fileio=sequential,fileselect=sequential,threads=6fwd參數(shù)詳細(xì)說明：fwd=nameUnique name for this Filesystem Workload Definition.fwd=defaultAll parameters used will serve as default for all the following fwds.fsd=(xx,.)Name(s) of Filesystem Definitions to usehost=host_labelWhich host this workload to run on.fileio=randomHow file I/O will be done: random or sequentialfileio=sequentialHow file I/O will be done: random or sequentialfileio=(seq,delete)Sequential I/O: When opening for writes, first delete the filestopafter=nnnFor random I/O: stop and close file after nnn reads or writes. Default 100 for random I/O.fileselect=random/ sequentialHow to select file names or directory names for processing.xfersizes=nnSpecifies the data transfer size(s) to use for read and write operations.operation=xxxxSpecifies a single file system operation that must be done for this workload.rdpct=nnFor read and write only. This allows a mix and read and writes against a single file.skew=nnThe percentage of the total amount of work for this FWDthreads=nnHow many concurrent threads to run for this workload. (Make sure you have at least one file for each thread).3、 測(cè)試運(yùn)行定義（Run definition）u 示例：rd=rd1,wd=wd*,elapsed=1800,interval=1,iorate=max描述：elapsed：Time of this run in seconds,default 30 secondsinterval：Reporting interval in secondsiorate：Run an uncontrolled workload4、 腳本示例* example1:sd=sd1,lun=/dev/sdb,threads=32,openflags=o_directwd=wd1,sd=sd*,seekpct=seq,rdpct=100,xfersize=2mrd=rd1,wd=wd*,elapsed=600,interval=1,iorate=max*說明* 測(cè)試磁盤設(shè)備（/dev/sdb），隊(duì)列深度為32，采用2MB塊大小，順序讀，測(cè)試時(shí)長(zhǎng)為600秒。* example2:sd=sd1,lun=/dir/a.file, size=100m,openflags=o_directwd=wd1,sd=sd*,seekpct=seq,rdpct=100,xfersize=2mrd=rd1,wd=wd*,elapsed=600,interval=1,iorate=max*說明* 測(cè)試讀出文件/dir/a.file，設(shè)置文件大小為100MB，以2MB塊大小順序讀出，測(cè)試時(shí)長(zhǎng)為600秒。* example3:fsd=fsd1,anchor=/dir,depth=1,width