Method and system for distributed LVM
A centralized orchestrator configured to be the only resource managing the distributed LVMs whereby orchestrator is further configured to queue parallel operations on the distributed LVM, making sure only one operation is performed at a time, without a cluster.
1 . A data storage system, comprising:
(i) at least two servers that comprise a direct attached logical volume manager (LVM) storage volume and configured to run operating systems on each of said servers designated to host data accessible and exposable over a data plane (DP) network, and
(ii) at least one orchestrator configured to interact with each of said servers and designated to control a control plane (CP) of said DP network,
wherein synchronization between the servers is conducted using the orchestrator and without need for clustering,
wherein the orchestrator is configured to queue parallel operations and ensure that only a direct attached storage volume which belongs to one server will conduct an operation in a given time, and
wherein the orchestrator is designated to orchestrate the storage stack components (SS) and the standard storage stack (SSS) embedded within said servers.
2 . The system of claim 1 , wherein the orchestrator is configured to send at least one allocation command to the LVM regarding the servers sharing direct attached storage and LVM, in order to ensure cached metadata will be consistent across all the servers.
3 . The system of claim 1 , wherein the direct attached storage volume comprises Redundant Array of Independent Disks (RAID) components.
4 . The system of claim 1 , wherein the orchestrator is configured to only use parts of one or more direct attached media storage within the storage system.
5 . The system of claim 1 , wherein the orchestrator is configured to allocate new hot spare disk from a storage pool in case of failure.
6 . The system of claim 1 , wherein the orchestrator is configured to instruct each server to add a selected spare storage media to each direct attached storage volume.
7 . The system of claim 1 , wherein the orchestrator is configured to add a selected spare disk to direct attached shared storage volume.
8 . The system of claim 1 , wherein the orchestrator is configured to instruct each server to dismiss a failed disk in each shared direct attached storage volume and rebuild a new spare drive chunk with valid data.
9 . The system of claim 1 , wherein connection between the servers is conducted using a multipath connection.
10 . The system of claim 1 , wherein the orchestrator is configured to provide alerts and handle failures for remote block device connection between servers.
11 . The system of claim 1 , wherein multiple initiators are configured to be created per network path to each server.
12 . The system of claim 1 , wherein coordination between the servers is conducted using a CP orchestrator installed on each server.
13 . The system of claim 1 , wherein communication between the servers and the orchestrator is done using a designated software component installed on each of said servers.
14 . The system of claim 1 , wherein the server is configured to utilize a redundant array of independent disks (RAID) storage stack component (SSC) configured to provide data redundancy originated from multiple designated portions of the direct attached storage volume at multiple servers.
15 . The system of claim 14 , wherein the RAID SSC is configured to provide data redundancy originated from combined multiple initiator paths originated from the designated portion of the direct attached storage volume of at least two servers.
16 . The system of claim 15 , wherein the servers are located at different locations and wherein the orchestration is allocated across different resiliency domains.
17 . The system of claim 16 , wherein the orchestration allocated while considering different resiliency domains also considers maintaining system balance.
18 . The system of claim 1 , wherein the orchestrator is configured to interact with the servers using an administration protocol.
19 . The system of claim 1 , wherein a designated portion of the direct attached storage volume is allocated using a LVM storage stack component (SSC).
20 . A method for orchestrating and storing data, comprising:
(i) enabling at least two servers that comprise a direct attached logical volume manager (LVM) storage volume and configured to run an operating system on each of said servers to host data accessible and exposable over a data plane (DP) network, and
(ii) enabling at least one orchestrator to interact with each of said servers to control a control plane (CP) of said DP network,
wherein synchronization between the servers is conducted using the orchestrator and without need for clustering,
wherein the orchestrator is configured to queue parallel operations and ensure that only a direct attached storage volume which belongs to one server will conduct an operation in a given time, and
wherein the orchestrator is designated to orchestrate the storage stack components (SS) and the standard storage stack (SSS) of the operating system embedded within said servers.