Curve核心组件之chunkserver括读写socket,rpc协议解析等。 ChunkServer架构RPC Service层是对外提供的一些RPC服 务的接口。包含的RPC服务有: • ChunkService。IO相关操作 • CliService。成员变更相关操作 • CopySetService。创建copyset等操 作 • RaftService。Braft内置的service, 完成raft成员之间的选举,日志复制, 安装快照等操作。 from CS1 to CS2的operator给这三个copyset ④ MDS通过RPC在CS2上创建copyset1,2,3这三个copyset ⑤ 假定三个copyset的leader都是CS3,在CS3的下一次心跳的 response中,下发第三步生成的三个operator ⑥ CS3收到change peer from CS1 to CS2的operator,给CS2同步 raft to CS1的operator给 部分copyset,比如copyset1,2,3 ⑤ MDS通过RPC在CS1上创建copyset1,2,3这些copyset ⑥ 假定三个copyset的leader都是CS3,在CS3的下一次心跳的 response中,下发第四步生成的三个operator ⑦ CS3收到change peer from CS2 to CS1的operator,给CS1同步0 码力 | 29 页 | 1.61 MB | 6 月前3
Curve for CNCF MainCurve can backup / sync data to slave cloud • When master cloud failure happens, Database service can move to the slave cloudData apps(middleware/bigdata/ai) • CurveFS can manage different storages plugin for CurveBS • Deploy CurveBS as container service (in Plan) • Config CurveBS by (Cluster and Pool CRDs) in Kubernetes (in Plan) • Support Operator capability level 5 (in Plan) • horizontal / (in Plan) • Deploy CurveFS as container service (in Plan) • Config CurveFS by (cluster and storage pools) CRDs in Kubernetes (in Plan) • Support Operator capability level 5 (in Plan) • now support0 码力 | 21 页 | 4.56 MB | 6 月前3
Curve Detail Introduction for CNCFservices can be configured using CRDs in public cloud and on- premises environments • Use the Curve operator to install, upgrade, backup, and expand CurveBS clusters • Use Curve Discover to discover resource services can be configured using CRDs in public cloud and on- premises environments • Use the Curve operator to install, upgrade, backup, and expand CurveFS clusters • Use Curve Discover to discover resource0 码力 | 23 页 | 6.53 MB | 6 月前3
Curve Cloud Nativehigh performance cloud native file system (Based on CurveBS / S3 compatible Storage)Operator capability Level OPERATOR CAPABILITY LEVEL CURVE COMMENT BASIC INSTALL Y (by Helm) automated application provisioning0 码力 | 9 页 | 2.85 MB | 6 月前3
Curve文件系统元数据持久化方案设计改造 vs 自己实现? redis 中哈希表实现的优点? 参考 前言 根据之前讨论的结果,元数据节点的架构如下图所示,这里涉及到两部分需要持久化/编码的内容: Raft Log:记录 operator log Raft Snapshot:将内存中的数据结构以特定格式 dump 到文件进行持久化© XXX Page 3 of 12 Raft Log +------+-----------0 码力 | 12 页 | 384.47 KB | 6 月前3
Curve文件系统元数据Proto(接口定义)string fsName = 2; } message DeleteFsInfoResponse { required MetaStatusCode statusCode = 1; } service MdsService { // fs interface rpc CreateFs(CreateFsRequest) returns (CreateFsResponse); uint64 inodeId = 2; } message DeleteInodeResponse { required MetaStatusCode statusCode = 1; } service MetaServerService { // dentry interface rpc GetDentry(GetDentryRequest) returns (GetDentryResponse); required uint32 fsId = 1; } message UnInitSpaceResponse { required SpaceStatusCode status = 1; } service SpaceAllocService { // space interface rpc InitSpace(InitSpaceRequest) returns (InitSpaceResponse);0 码力 | 15 页 | 80.33 KB | 6 月前3
CurveFS ChunkID持久化AllocateS3ChunkResponse 的状态码的类型为 FSStatusCode; proto/space.proto/service SpaceAllocService中的 rpc AllocateS3Chunk 复制到 proto/space.proto/service/MdsService中; curvefs/src/mds/mds_services.h MdsServiceImp类中增加0 码力 | 3 页 | 79.38 KB | 6 月前3
OID CND Asia Slide: CurveFSZone is the basic unit of fault isolation Server Indicates a physical server Chunkserver is a service instance on a physical serverCurve metadata organization Curve maps virtual block devices to performance optimizations RAFT protocol Zero data copy pre-created file poolCURVE file system File service middleware Upper-layer applications can access file data in storage pools through interfaces such0 码力 | 24 页 | 3.47 MB | 6 月前3
CurveFS对接S3方案设计message UpdateInodeResponse {© XXX Page 7 of 11 required MetaStatusCode statusCode = 1; } service MetaServerService { rpc UpdateInodeS3Version(UpdateInodeS3VersionRequest) returns (UpdateIno AllocateS3ChunkResponse { required SpaceStatusCode status = 1; // required uint64 chunkId = 2; } service SpaceAllocService { // space interface rpc InitSpace(InitSpaceRequest) returns (InitSpaceResponse);0 码力 | 11 页 | 145.77 KB | 6 月前3
Curve核心组件之snapshotclonedata object data object S3 Snap Task etcd mds client 3.获取快照元数据 datastore metastore http service clone Task user 快照元数据 2.创建内部快照 5.删除内部快照 快照数据 1.发起快照 SnapshotCloneServer 6.删除内部快照数据快照的元数据和数据组织 data object S3 Snap Task etcd MDS client 2.创建克隆卷 3.分配卷空间 7.拷贝数据 datastore metastore http service clone Task user 快照、克隆元数据 SnapshotCloneServer 1.发起克隆 5.8.9.更新元数据克隆卷状态变化 • 初始状态; • 正在安装元数据或拷贝数据中;0 码力 | 23 页 | 1.32 MB | 6 月前3
共 12 条
- 1
- 2













