Network B. Welch Internet-Draft B. Halevy Expires: December 11, 2005 Panasas G. Goodson NetApp D. Black EMC A. Adamson CITI June 9, 2005 pNFS Operations draft-welch-pnfs-ops-02.txt Status of this Memo By submitting this Internet-Draft, each author represents that any applicable patent or other IPR claims of which he or she is aware have been or will be disclosed, and any of which he or she becomes aware will be disclosed, in accordance with Section 6 of BCP 79. Internet-Drafts are working documents of the Internet Engineering Task Force (IETF), its areas, and its working groups. Note that other groups may also distribute working documents as Internet- Drafts. Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress." The list of current Internet-Drafts can be accessed at http://www.ietf.org/ietf/1id-abstracts.txt. The list of Internet-Draft Shadow Directories can be accessed at http://www.ietf.org/shadow.html. This Internet-Draft will expire on December 11, 2005. Copyright Notice Copyright (C) The Internet Society (2005). Abstract This Internet-Draft provides a description of the pNFS extension for NFSv4. Welch, et al. Expires December 11, 2005 [Page 1] Internet-Draft pNFS Operations June 2005 The key feature of the protocol extension is the ability for clients to perform read and write operations that go directly from the client to individual storage system elements without funneling all such accesses through a single file server. Of course, the file server must coordinate the client I/O so that the file system retains its integrity. The extension adds operations that query and manage layout information that allows parallel I/O between clients and storage system elements. The layouts are managed in a similar way as delegations in that they have leases and can be recalled by the server, but layout information is independent of delegations. Requirements Language The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in RFC 2119 [1]. Welch, et al. Expires December 11, 2005 [Page 2] Internet-Draft pNFS Operations June 2005 Table of Contents 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 5 2. General Definitions . . . . . . . . . . . . . . . . . . . . . 7 2.1 Metadata Server . . . . . . . . . . . . . . . . . . . . . 7 2.2 Client . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.3 Storage Device . . . . . . . . . . . . . . . . . . . . . . 7 2.4 Storage Protocol . . . . . . . . . . . . . . . . . . . . . 8 2.5 Management Protocol . . . . . . . . . . . . . . . . . . . 8 2.6 Metadata . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.7 Layout . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3. Layouts and Aggregation . . . . . . . . . . . . . . . . . . . 9 3.1 Layout Structure . . . . . . . . . . . . . . . . . . . . . 9 3.1.1 Device IDs . . . . . . . . . . . . . . . . . . . . . . 10 3.1.2 Aggregation Schemes . . . . . . . . . . . . . . . . . 10 3.2 Basic Layout Semantics . . . . . . . . . . . . . . . . . . 10 3.2.1 Layout Iomode . . . . . . . . . . . . . . . . . . . . 11 3.2.2 Operation Sequencing . . . . . . . . . . . . . . . . . 11 3.3 Obtaining a Layout . . . . . . . . . . . . . . . . . . . . 12 3.3.1 Identifying Layouts . . . . . . . . . . . . . . . . . 12 3.3.2 Overlapping Layouts . . . . . . . . . . . . . . . . . 12 3.3.3 Copy-on-write . . . . . . . . . . . . . . . . . . . . 13 3.4 Recalling a Layout . . . . . . . . . . . . . . . . . . . . 13 3.5 Committing a Layout . . . . . . . . . . . . . . . . . . . 13 3.5.1 LAYOUTCOMMIT and EOF . . . . . . . . . . . . . . . . . 14 3.6 Lease Renewals . . . . . . . . . . . . . . . . . . . . . . 15 4. Security Considerations . . . . . . . . . . . . . . . . . . . 15 4.1 File Layout Security . . . . . . . . . . . . . . . . . . . 17 4.2 Object Layout Security . . . . . . . . . . . . . . . . . . 17 4.3 Block Layout Security . . . . . . . . . . . . . . . . . . 18 5. NFSv4 File Layout Type . . . . . . . . . . . . . . . . . . . . 18 5.1 File Striping and Data Access . . . . . . . . . . . . . . 18 5.2 Global Stateid Requirements . . . . . . . . . . . . . . . 22 5.3 The Layout Iomode . . . . . . . . . . . . . . . . . . . . 22 5.4 Storage Device State Propagation . . . . . . . . . . . . . 22 5.4.1 Lock State Propagation . . . . . . . . . . . . . . . . 23 5.4.2 Open-mode Validation . . . . . . . . . . . . . . . . . 23 5.4.3 File Attributes . . . . . . . . . . . . . . . . . . . 24 5.4.4 Access State Propagation . . . . . . . . . . . . . . . 24 5.5 Extending EOF . . . . . . . . . . . . . . . . . . . . . . 24 5.5.1 READs and EOF . . . . . . . . . . . . . . . . . . . . 24 5.5.2 LAYOUTCOMMIT and EOF . . . . . . . . . . . . . . . . . 25 5.6 Security Considerations . . . . . . . . . . . . . . . . . 26 5.7 Alternate Approaches . . . . . . . . . . . . . . . . . . . 26 6. pNFS Typed Data Structures . . . . . . . . . . . . . . . . . . 27 6.1 pnfs_layouttype4 . . . . . . . . . . . . . . . . . . . . . 27 6.2 pnfs_deviceid4 . . . . . . . . . . . . . . . . . . . . . . 27 6.3 pnfs_devaddr4 . . . . . . . . . . . . . . . . . . . . . . 28 Welch, et al. Expires December 11, 2005 [Page 3] Internet-Draft pNFS Operations June 2005 6.4 pnfs_devlist_item4 . . . . . . . . . . . . . . . . . . . . 28 6.5 pnfs_layout4 . . . . . . . . . . . . . . . . . . . . . . . 29 7. pNFS File Attributes . . . . . . . . . . . . . . . . . . . . . 29 7.1 pnfs_layouttype4<> LAYOUT_TYPES . . . . . . . . . . . . . 29 7.2 pnfs_layouttype4 LAYOUT_TYPE . . . . . . . . . . . . . . . 29 7.3 pnfs_layouttypes4 LAYOUT_HINT . . . . . . . . . . . . . . 29 8. pNFS Error Definitions . . . . . . . . . . . . . . . . . . . . 30 9. pNFS Operations . . . . . . . . . . . . . . . . . . . . . . . 30 9.1 LAYOUTGET - Get Layout Information . . . . . . . . . . . . 30 9.2 LAYOUTCOMMIT - Commit writes made using a layout . . . . . 33 9.3 LAYOUTRETURN - Release Layout Information . . . . . . . . 35 9.4 GETDEVICEINFO - Get Device Information . . . . . . . . . . 36 9.5 GETDEVICELIST - Get List of Devices . . . . . . . . . . . 37 10. Callback Operations . . . . . . . . . . . . . . . . . . . . 37 10.1 CB_LAYOUTRECALL . . . . . . . . . . . . . . . . . . . . . 38 10.2 CB_EOFCHANGED . . . . . . . . . . . . . . . . . . . . . . 39 11. Usage Scenarios . . . . . . . . . . . . . . . . . . . . . . 40 11.1 Basic Read Scenario . . . . . . . . . . . . . . . . . . . 40 11.2 Multiple Reads to a File . . . . . . . . . . . . . . . . . 40 11.3 Multiple Reads to a File with Delegations . . . . . . . . 40 11.4 Read with existing writers . . . . . . . . . . . . . . . . 41 11.5 Read with later conflict . . . . . . . . . . . . . . . . . 41 11.6 Basic Write Case . . . . . . . . . . . . . . . . . . . . . 41 11.7 Large Write Case . . . . . . . . . . . . . . . . . . . . . 42 11.8 Create with special layout . . . . . . . . . . . . . . . . 42 12. Layouts and Aggregation . . . . . . . . . . . . . . . . . . 42 12.1 Simple Map . . . . . . . . . . . . . . . . . . . . . . . . 42 12.2 Block Map . . . . . . . . . . . . . . . . . . . . . . . . 43 12.3 Striped Map (RAID 0) . . . . . . . . . . . . . . . . . . . 43 12.4 Replicated Map . . . . . . . . . . . . . . . . . . . . . . 43 12.5 Concatenated Map . . . . . . . . . . . . . . . . . . . . . 43 12.6 Nested Map . . . . . . . . . . . . . . . . . . . . . . . . 44 13. Issues . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 13.1 Storage Protocol Negotiation . . . . . . . . . . . . . . . 44 13.2 Crash recovery . . . . . . . . . . . . . . . . . . . . . . 44 13.3 Storage Errors . . . . . . . . . . . . . . . . . . . . . . 44 14. Normative References . . . . . . . . . . . . . . . . . . . . 44 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . 45 A. Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . 46 Intellectual Property and Copyright Statements . . . . . . . . 47 Welch, et al. Expires December 11, 2005 [Page 4] Internet-Draft pNFS Operations June 2005 1. Introduction The NFSv4 protocol [2] specifies the interaction between a client that accesses files and a server that provides access to files and is responsible for coordinating access by multiple clients. As described in the pNFS problem statement, this requires that all access to a set of files exported by a single NFSv4 server be performed by that server; at high data rates the server may become a bottleneck. The parallel NFS (pNFS) extensions to NFSv4 allow data accesses to bypass this bottleneck by permitting direct client access to the storage devices containing the file data. When file data for a single NFSv4 server is stored on multiple and/or higher throughput storage devices (by comparison to the server's throughput capability), the result can be significantly better file access performance. The relationship among multiple clients, a single server, and multiple storage devices for pNFS (server and clients have access to all storage devices) is shown in this diagram: +-----------+ |+-----------+ +-----------+ ||+-----------+ | | ||| | NFSv4 + pNFS | | +|| Clients |<------------------------------>| Server | +| | | | +-----------+ | | ||| +-----------+ ||| | ||| | ||| Storage +-----------+ | ||| Protocol |+-----------+ | ||+----------------||+-----------+ Management| |+-----------------||| | Protocol| +------------------+|| Storage |------------+ +| Devices | +-----------+ Figure 1 In this structure, the responsibility for coordination of file access by multiple clients is shared among the server, clients, and storage devices, in contrast to NFSv4, by itself, where this is primarily the server's responsibility, some of which can be delegated to clients under strictly specified conditions. The pNFS extension to NFSv4 takes the form of new operations that manage data location information called a "layout". The layout is Welch, et al. Expires December 11, 2005 [Page 5] Internet-Draft pNFS Operations June 2005 managed in a similar fashion as NFSv4 data delegations (e.g., they are recallable and revocable). However, they are distinct abstractions and are manipulated with new operations that are described in Section 9. When a client holds a layout, it has rights to access the data directly using the location information in the layout. There are new attributes that describe general layout characteristics. However, attributes do not provide everything needed to support layouts, hence the use of operations instead. This document specifies both the NFSv4 extensions required to distribute file access coordination between the server and its clients and a NFSv4 file storage protocol that may be used to access data stored on NFSv4 storage devices. Storage protocols used to access a variety of other storage devices are deliberately not specified, these may include: o Block protocols such as iSCSI, parallel SCSI, and FCP (SCSI over Fibre Channel) [refs]. The block protocol support can be independent of the addressing structure of the block protocol used, allowing more than one protocol to access the same file data and enabling extensibility to other block protocols. o Object protocols such as OSD over iSCSI or Fibre Channel [3]. o Other storage protocols, including PVFS and other file systems that are in use in HPC environments. pNFS is designed to accommodate these protocols and be extensible to new classes of storage protocols that may be of interest. The distribution of file access coordination between the server and its clients increases the level of responsibility placed on clients. Clients are already responsible for ensuring that suitable access checks are made to cached data and that attributes are suitably propagated to the server. Generally, a misbehaving client that hosts only a single-user can only impact files accessible to that single user. Misbehavior by a client hosting multiple users may impact files accessible to all of its users. NFSv4 delegations increase the level of client responsibility as a client that carries out actions requiring a delegation without obtaining that delegation will cause its user(s) to see unexpected and/or incorrect behavior. Some uses of pNFS extend the responsibility of clients beyond delegations. In some configurations, the storage devices cannot perform fine grain access checks to ensure that clients are only Welch, et al. Expires December 11, 2005 [Page 6] Internet-Draft pNFS Operations June 2005 performing accesses within the bounds permitted to them by the pNFS operations with the server (e.g., the checks may only be possible at file system granularity rather than file granularity). In situations where this added responsibility placed on clients creates unacceptable security risks, pNFS configurations in which storage devices cannot perform fine-grained access checks SHOULD NOT be used. All pNFS server implementations MUST support NFSv4 access to any file accessible via pNFS in order to provide an interoperable means of file access in such situations. See Section 4 on Security for further discussion. Finally, there are issues about how layouts interact with the existing NFSv4 abstractions of data delegations and byte range locking. These issues (and more) are also discussed here. 2. General Definitions This protocol extension partitions the NFSv4 file system protocol into two parts, the control path and the data path. The control path is implemented by the extended (p)NFSv4 server. When the file system being exported by (p)NFSv4 uses storage devices that are visible to clients over the network, the data path may be implemented by direct communication between the extended (p)NFSv4 file system client and the storage devices. This leads to a few new terms used to describe the protocol extension and some clarifications of some existing terms. 2.1 Metadata Server A pNFS "server" or "metadata server" is a server as defined by RFC3530 [2], with the addition of supporting the pNFS minor extension. When using the pNFS NFSv4 minor extension, the metadata server may hold only the metadata associated with a file, while the data is stored on the storage devices. Note: directory data is always accessed through the metadata server. 2.2 Client A pNFS "client" is a client as defined by RFC3530 [2], with the addition of supporting the pNFS minor extension server protocol and with the addition of supporting at least one storage protocol (for performing I/O directly to storage devices). 2.3 Storage Device This is a device, or server, that controls the file's data, but leaves other metadata management up to the metadata server. A storage device could be another NFS server, or an Object Storage Welch, et al. Expires December 11, 2005 [Page 7] Internet-Draft pNFS Operations June 2005 Device (OSD) or a block device accessed over a SAN (either FiberChannel or iSCSI SAN). The goal of this extension is to allow direct communication between clients and storage devices. 2.4 Storage Protocol This is the protocol between the pNFS client and the storage device used to access the file data. There are three primary types: file protocols (such as NFSv4 or NFSv3), object protocols (OSD), and block protocols (SCSI-block commands, or "SBC"). These protocols are in turn layered over transport protocols such as RPC/TCP/IP or iSCSI/ TCP/IP or FC/SCSI. We anticipate there will be variations on these storage protocols, including new protocols that are unknown at this time or experimental in nature. The details of the storage protocols will be described in other documents so that pNFS clients can be written to use these storage protocols. A NFSv4 file protocol is described in Section 5. 2.5 Management Protocol This is the protocol used by the exported file system between the server and storage devices. This protocol is outside the scope of this draft, and is used for various management activities including the allocation and deallocation of storage and the management of state required by the storage devices to perform client access control. The management protocol should not be confused with protocols used to manage LUNs in a SAN and other sysadmin kinds of tasks. While the pNFS protocol allows for any management protocol, in practice the mangement protocol is closely related to the storage protocol. For example, if the storage devices are NFS servers, then the protocol between the pNFS metadata server and the storage devices is likely to involve NFS operations. Similarly, when object storage devices are used, the pNFS metadata server will likely use iSCSI/OSD commands to manipulate storage. However, this document does not mandate any particular management protocol. Instead, it just describes the requirements on the managment protocol for maintaining attributes like modify time, the change attribute, and the end-of-file position. 2.6 Metadata This is information about a file, like its name, owner, where it stored, and so forth. The information is managed by the exported file system server (server). Metadata also includes lower-level information like block addresses and indirect block pointers. Welch, et al. Expires December 11, 2005 [Page 8] Internet-Draft pNFS Operations June 2005 Depending the storage protocol, block-level metadata may or may not be managed by the metadata server, but is instead managed by Object Storage Devices or other servers acting as a storage device. 2.7 Layout A layout defines how a file's data is organized on one or more storage devices. There are many possible layout types. They vary in the storage protocol used to access the data, and in the aggregation scheme that lays out the file data on the underlying storage devices. Layouts are described in more detail below. 3. Layouts and Aggregation 3.1 Layout Structure The layout is a typed data structure that has variants to handle different storage protocols (block, object, and file). A layout describes a range of a file's contents (e.g., the set of storage devices on which a specific byte range of the file's data reside and a method for identifying the data on those devices). A specific layout structure belongs to a "layout type" (e.g., blocks, objects, files). A metadata server, along with its management protocol, must support at least one layout type. See Section 6.1 for the RPC definition of a layout type. A private sub-range of the layout type name space can be defined through the IANA (e.g., a type with the high bit set to one). This private sub-range can be used for internal testing or experimentation. For example, a file layout type could be an array of tuples (deviceID, file_handle), along with a definition (or aggregation scheme) of how the data is stored across the devices (e.g., striping). A block layout might be an array of tuples that store (deviceID, block_number, block count) along with information about block size and the file offset of the first block. An object layout is an array of tuples (deviceID, objectID) and an additional structure (i.e., the aggregation map) that defines how the logical byte sequence of the file data is serialized into the different objects. This document defines a NFSv4 file layout type using a stripe-based aggregation scheme (see Section 5). Adjunct specifications must exist that precisely define other layout formats (e.g., blocks, objects, or other file-based layouts) to allow interoperability among clients and metadata servers. Welch, et al. Expires December 11, 2005 [Page 9] Internet-Draft pNFS Operations June 2005 3.1.1 Device IDs The "deviceID" is a short name for a storage device. In practice, a significant amount of information may be required to fully identify a storage device. Instead of embedding all that information in a layout, a level of indirection is used. Layouts embed device Ids, and a new op (GETDEVICEINFO) is used to retrieve the complete identity information about the storage device. For example, the identity of a file server or object server could be an IP address and port. The identity of a block device could be a volume label. Due to multipath connectivity in a SAN environment, agreement on a volume label is considered the reliable way to locate a particular storage device. Another operation, GETDEVICELIST, has been added to allow clients to fetch the mappings of multiple storage devices attached to a metadata server. Clients SHOULD NOT expect the mapping between deviceID and storage device address to exist across metadata server reboots (i.e., clients should fetch new mappings upon startup or upon detection of a metadata server reboot). If data are reorganized from a storage device with a given deviceID to a different storage device, the layout describing the data SHOULD be recalled rather than assigning the new storage device to the old deviceID. 3.1.2 Aggregation Schemes Aggregation schemes can describe layouts like simple one-to-one mapping, concatenation, and striping. A general aggregation scheme allows nested maps so that more complex layouts can be compactly described. The canonical aggregation type for this extension is striping, which allows a client to access storage devices in parallel. Even a one-to-one mapping is useful for a file server that wishes to distribute its load among a set of other file servers. There are also experimental aggregation types such as writable mirrors and RAID. 3.2 Basic Layout Semantics Layouts delegate to the client the ability to access data out of band. The layout guarantees the holder that the layout will be recalled when the state encapsulated by the layout becomes invalid (e.g., through some operation that directly or indirectly modifies the layout) or, possibly, when a conflicting layout is requested, as determined by the layout's iomode. Holding a layout does not guarantee that a user of the layout has the rights to access the data represented by the layout. All user access rights MUST be obtained through the appropriate open and lock commands. However, if a valid layout for a file is not held by the client, the storage device may reject all I/Os to that file's byte Welch, et al. Expires December 11, 2005 [Page 10] Internet-Draft pNFS Operations June 2005 range that originate from that client. In summary, layouts and ordinary file access controls are independent. The act of modifying a file for which a layout is held, does not necessarily conflict with the holding of the layout (that describes the file being modified). However, with certain layout types (e.g., block layouts), the layout's iomode must agree with the type of I/O being performed. 3.2.1 Layout Iomode When requesting a layout (through LAYOUTGET), the client MUST request a layout pertaining to an "iomode" of either READ or READ/WRITE. The iomode indicates to the metadata server the client's intent to perform either READ-ONLY or READ/WRITE I/O to the storage devices using the requested layout. For certain layout types, it is useful for a client to specify this intent at LAYOUTGET time. E.g., for block based protocols, block allocation could occur when a READ/WRITE iomode is specified. A storage device may validate I/O with regards to the iomode; this is dependent upon storage device implementation. Thus, if the client's layout iomode differs from the I/O being performed the storage device may reject the client's I/O with an error indicating a new layout with the correct I/O mode should be fetched. E.g., if a client gets a layout with a READ iomode and performs a WRITE to a storage device, the storage device is allowed to reject that WRITE. The iomode does not conflict with OPEN share modes or lock requests, and these are the preferred method for restricting user access to data files. E.g., an OPEN of read, deny-write does not conflict with a LAYOUTGET containing an iomode of READ/WRITE performed by another client. Applications that depend on writing into the same file concurrently SHOULD use byte range locking to serialize their accesses. 3.2.2 Operation Sequencing As with other stateful operations, pNFS requires the correct sequencing of layout operations. This proposal assumes that sessions will precede pNFS into NFSv4.x and thus, pNFS will require the use of sessions. If the sessions proposal does not precede pNFS, then this proposal must be modified to provide for the correct sequencing of pNFS layout operations. One main issue with operation sequencing concerns callbacks. The protocol must defend against races between the reply to a LAYOUTGET operation and a subsequent CB_LAYOUTRECALL. It MUST not be possible for a client to process the CB_LAYOUTRECALL for a layout that it has not received in a reply message to a LAYOUTGET. Welch, et al. Expires December 11, 2005 [Page 11] Internet-Draft pNFS Operations June 2005 3.3 Obtaining a Layout The metadata server will give out layouts of a particular type (block, object, or file) and aggregation. A client obtains a layout through a new operation (LAYOUTGET). The layout returned to the client may not line up exactly with the requested byte range. However, at least a single byte overlap MUST exist between the requested layout and the layout returned by the metadata server. The storage protocol used by the client to access the data on the storage device is determined by the layout's type. The client needs to select a "layout driver" that understands how to interpret and use that layout. The API used by the client to talk to its drivers is outside the scope of the pNFS extension. The storage protocol between the client's layout driver and the actual storage is covered by other protocols specifications such as SBC (block storage), OSD (object storage) or NFS (file storage). Although, the metadata server is in control of the layout for a file, the pNFS client can provide hints to the server when a file is opened or created about preferred layout type. The pNFS extension introduces a LAYOUT_HINT attribute that the client can query at anytime, and can set with a compound SETATTR after OPEN to provide a hint to the server for new files. 3.3.1 Identifying Layouts A layout is identified by the following tuple: (ClientID, FH, offset, length); the FH refers to the FH of the file on the metadata server, the offset and length specify the byte range of the file the layout covers. Since there is a desire to manage layouts as sub-dividable entities, layouts are range-based and are identified in such a manner. Sub-dividable layouts have the benefit of being returnable/ recallable or committable in smaller chunks without having to return, recall, or commit the entire layout. E.g., this may be useful when the layout is very large and a client is only actively using a small range of the layout, thus the client may not want to commit the entire layout, rather it could commit just the range of the layout it is using. 3.3.2 Overlapping Layouts A metadata server may hand-out layouts that overlap, as long as the overlapping regions specify the same storage device/file mapping; i.e., the records within the overlapping layouts should specify the same storage device mapping for the same byte ranges they represent. If two overlapping layouts differ, the old layout should be recalled. Welch, et al. Expires December 11, 2005 [Page 12] Internet-Draft pNFS Operations June 2005 3.3.3 Copy-on-write For block-based protocols it is useful to have the ability to direct a client to read data from one group of blocks, but write to a different group; e.g., to implement a snapshotting blocks system. The client can not make the choice of where to place data, it requires help by the metadata server, most probably communicated through the layout. A single layout with the ability to mark (and re-mark) portions read-only vs. read/write is sufficient for this to work. 3.4 Recalling a Layout Since a layout protects a client's access to a file via a direct client-data-server path, a layout need only be recalled when it is semantically unable to serve this function. Typically, this occurs when the layout no longer encapsulates the true location of the file over the byte range it represents. Any operation that changes the layout will result in a recall of the layout. A REMOVE operation may cause the metadata server to recall the layout to prevent the client from accessing a non-existent file and to reclaim state stored on the client. Since a REMOVE may be delayed until the last close of the file has occurred, the recall may also be delayed until this time. As well, once the file has been removed (after the last reference), the client SHOULD no longer be able to perform I/O using the layout (e.g., with file-based layouts an error such as ESTALE could be returned). Once a layout has been recalled, the client should no longer issue I/Os to the storage devices for the file and byte range represented by the recalled layout, even though the client may still have valid stateids for that file (except to flush dirty data before returning the layout). If a client does issue an I/O to a storage device for which it does not hold a layout, the storage device SHOULD reject the I/O. This can be verified by the storage device by mapping the stateid used for I/O to the client instance and validating that the client instance has a valid layout. 3.5 Committing a Layout Due to the nature of the protocol, the file attributes that exist on the metadata storage device may become inconsistent in relation to the data stored on the storage devices; e.g., when WRITEs occur before a layout has been committed (e.g., between a LAYOUTGET and a LAYOUTCOMMIT). Thus, it is necessary to occasionally re-sync this state and make it visible to other clients through the metadata server. Welch, et al. Expires December 11, 2005 [Page 13] Internet-Draft pNFS Operations June 2005 The LAYOUTCOMMIT operation is responsible for committing the modified layout to the metadata server. Note: the data should be written (and committed) to the appropriate storage devices before the LAYOUTCOMMIT occurs. The scope of this operation depends on the storage protocol in use. For block-based layouts, it may require updating the block list that comprises the file and committing this layout to stable storage. While, for file-layouts it requires the synchronization of attributes between the metadata and storage devices (mainly the size/ EOF). The management protocol is free to sync this state before it receives a LAYOUTCOMMIT, however upon successful completion of a LAYOUTCOMMIT, state that exists on the metadata server that describes the file MUST be in sync with the state existing on the storage devices that comprises that file (assuming no intervening operations). Thus, a client that queries the size of a file between a WRITE to a storage device and the LAYOUTCOMMIT may not observe a size that reflects the actual data written. The change attribute and mtime may be updated, by the server, at LAYOUTCOMMIT time; since for some layout protocols, the change attribute can not be updated by a WRITE operation performed at a storage device. However, for some layout protocols the change attribute and mtime may be updated at or after the time of the WRITE (e.g., if the storage device is able to communicate these attributes to the metadata server). If, upon receiving a LAYOUTCOMMIT, the server implementation is able to determine that the file did not change since the last time the change attribute was updated (e.g., no WRITEs or over-writes occurred), the implementation need not update the change attribute (file-based protocols may have enough state to make this determination or may update the change attribute upon each file modification). This also applies for mtime; if the server implementation is able to determine that the file has not been modified since the last mtime update, the server need not update mtime at LAYOUTCOMMIT time. Once LAYOUTCOMMIT completes, the new change attribute and mtime should be visible if that file was modified since the latest previous LAYOUTCOMMIT or LAYOUTGET. If a client prefers to set a new mtime, it should do so through the SETATTR operation. 3.5.1 LAYOUTCOMMIT and EOF As well, the file's EOF may be updated at LAYOUTCOMMIT time. The LAYOUTCOMMIT operation takes an EOF flag and length as arguments. If the EOF flag is set, a new EOF SHOULD be specified by the client. The EOF length may be used as a hint to the metadata server. The metadata server may validate the EOF against state that exists on the storage devices. The metadata server may either: update the file's EOF based on the client specified length, it may ignore the EOF flag, or it may use a value computed by querying the storage devices (e.g., Welch, et al. Expires December 11, 2005 [Page 14] Internet-Draft pNFS Operations June 2005 through the management protocol). The method chosen to update EOF may depend on the storage device's and/or the management protocol's implementation. For example, if the storage devices are block devices with no knowledge of EOF, then the metadata server must rely on the client to set the EOF appropriately. An EOF flag and length are also returned in the results of a LAYOUTCOMMIT. This union indicates whether a new EOF was set, and to what length it was set. The server may return a new EOF regardless of whether the client set the neweof field in the request, however if the EOF flag was set in the request, the neweof MUST be returned. The EOF flag SHOULD not be used to truncate or grow the file sparsely; the SETATTR operation must be used to do so. The metadata server in conjunction with the management protocol SHOULD ensure that a new EOF is reflected by the storage device immediately upon return of the LAYOUTCOMMIT operation; e.g., a READ up to the new EOF should succeed on the storage devices (assuming no intervening truncations). Since client layout holders may be unaware of changes made to EOF (through LAYOUTCOMMIT or SETATTR) by other clients, an additional callback/notification has been added for pNFS. CB_EOFCHANGED is a notification that the metadata server sends to layout holders to notify them of an EOF change to the file. This is preferred over issuing CB_LAYOUTRECALL to each of the layout holders. 3.6 Lease Renewals The current NFSv4 specification allows for implicit lease renewals to occur upon receiving an I/O. However, due to the disjoint pNFS architecture, implicit lease renewals are limited to operations performed at the metadata server (including I/O performed through the metadata server). So, READ and WRITE I/O to storage devices do not implicitly renew lease state. It is suggested that explicit lease renewal is used instead of relying on implicit renewals. The impact on lease renewals and storage devices needs to be better defined. For now it is left up to the management protocol to manage leases that may exist on storage devices. 4. Security Considerations The pNFS extension partitions the NFSv4 file system protocol into two parts, the control path and the data path (storage protocol). The control path contains all the new operations described by this extension; all existing NFSv4 security mechanisms and features apply to the control path. The combination of components in a pNFS system (see Figure 1) is required to preserve the security properties of NFSv4 with respect to an entity accessing data via a client, Welch, et al. Expires December 11, 2005 [Page 15] Internet-Draft pNFS Operations June 2005 including security countermeasures to defend against threats that NFSv4 provides defenses for in environments where these threats are considered significant. In some cases, the security countermeasures for connections to storage devices may take the form of physical isolation or a recommendation not to use pNFS in an environment. For example, it is currently infeasible to provide confidentiality protection for some storage device access protocols to protect against eavesdropping; in environments where eavesdropping on such protocols is of sufficient concern to require countermeasures, physical isolation of the communication channel (e.g., via direct connection from client(s) to storage device(s)) and/or a decision to forego use of pNFS (e.g., and fall back to NFSv4) may be appropriate courses of action. In full generality where communication with storage devices is subject to the same threats as client-server communication, the protocols used for that communication need to provide security mechanisms comparable to those available via RPSEC_GSS for NFSv4. Many situations in which pNFS is likely to be used will not be subject to the overall threat profile for which NFSv4 is required to provide countermeasures. pNFS implementations MUST NOT remove NFSv4's access controls. The combination of clients, storage devices, and the server are responsible for ensuring that all client to storage device file data access respects NFSv4 ACLs and file open modes. This entails performing both of these checks on every access in the client, the storage device, or both. If a pNFS configuration performs these checks only in the client, the risk of a misbehaving client obtaining unauthorized access is an important consideration in determining when it is appropriate to use such a pNFS configuration. Such configurations SHOULD NOT be used when client- only access checks do not provide sufficient assurance that NFSv4 access control is being applied correctly. The following subsections describe security considerations specifically applicable to each of the three major storage device protocol types supported for pNFS. [Additional security info - the object protocol needs this, but it may be out-of-band; the OSD experts will know for sure. For Block and File an approach of the client being expected to know what it needs when it sees what it's being asked to access probably suffices, although we might be able to help (e.g., pass iSCSI CHAP authentication identities, but NOT secrets, via pNFS). For File in particular, defaulting to the NFSv4 principal is probably a good idea, although it's not strictly necessary.] Welch, et al. Expires December 11, 2005 [Page 16] Internet-Draft pNFS Operations June 2005 [Requiring strict equivalence to NFSv4 security mechanisms is the wrong approach. Will need to lay down a set of statements that each protocol has to make starting with access check location/properties.] 4.1 File Layout Security A NFSv4 file layout type is defined in Section 5; see Section 5.6 for additional security considerations and details. In summary, the NFSv4 file layout type requires that all I/O access checks MUST be performed by the storage devices, as defined by the NFSv4 specification. If another file layout type is being used, additional access checks may be required. But in all cases, the access control performed by the storage devices must be at least as strict as that specified by the NFSv4 protocol. 4.2 Object Layout Security The object storage protocol relies on a cryptographically secure capability to control accesses at the object storage devices. Capabilities are generated by the metadata server, returned to the client, and used by the client as described below to authenticate their requests to the Object Storage Device (OSD). Capabilities therefore achieve the required access and open mode checking. They allow the file server to define and check a policy (e.g., open mode) and the OSD to check and enforce that policy without knowing the details (e.g., user IDs and ACLs). Each capability is specific to a particular object, an operation on that object, a byte range w/in the object, and has an explicit expiration time. The capabilities are signed with a secret key that is shared by the object storage devices (OSD) and the metadata managers. clients do not have device keys so they are unable to forge capabilities. The details of the security and privacy model for Object Storage are out of scope of this document and will be specified in the Object Storage version of the storage protocol definition. However, the following sketch of the algorithm should help the reader understand the basic model. LAYOUTGET returns {CapKey = MAC(CapArgs), CapArgs} The client uses CapKey to sign all the requests it issues for that object using the respective CapArgs. In other words, the CapArgs appears in the request to the storage device, and that request is signed with the CapKey as follows: Welch, et al. Expires December 11, 2005 [Page 17] Internet-Draft pNFS Operations June 2005 ReqMAC = MAC(Req, Nonceln) The following is sent to the OSD: {CapArgs, Req, Nonceln, ReqMAC}. The OSD uses the SecretKey it shares with the metadata server to compare the ReqMAC the client sent with a locally computed MAC(CapArgs)>(Req, Nonceln) and if they match the OSD assumes that the capabilities came from an authentic metadata server and allows access to the object, as allowed by the CapArgs. Therefore, if the server LAYOUTGET reply, holding CapKey and CapArgs, is snooped by another client, it can be used to generate valid OSD requests (within the CapArgs access restriction). To provide the required privacy requirements for the capabilities returned by LAYOUTGET, the GSS-API can be used, e.g. by using a session key known to the file server and to the client to encrypt the whole layout or parts of it. Two general ways to provide privacy in the absence of GSS-API that are independent of NFSv4 are either an isolated network such as a VLAN or a secure channel provided by IPsec. 4.3 Block Layout Security Block protocols rely on clients to enforce file access checks, as the storage devices are generally unaware of the files they are storing (and in particular are unaware of which block belongs to which file). In environments where access control is important and client-only access checks provide insufficient assurance of access control enforcement (e.g., there is concern about a malicious client skipping the access check), the storage devices will generally be unable to compensate for these client deficiencies. In such threat environments, Block protocols SHOULD NOT be used with pNFS; NFSv4 without pNFS may be a more suitable means of accessing files in the presence of such threats. Storage-device/protocol-specific methods (e.g., LUN masking/mapping) may be available to prevent malicious or high-risk clients from directly accessing storage devices. 5. NFSv4 File Layout Type This section describes the semantics and format of NFSv4 file-based layouts. 5.1 File Striping and Data Access The file layout specifies an ordered array of (deviceID, start_offset, filehandle) tuples, as well as the stripe_size, skip and the file's current EOF (current as of LAYOUTGET time). Devices Welch, et al. Expires December 11, 2005 [Page 18] Internet-Draft pNFS Operations June 2005 and filehandles may be repeated multiple times within the device list (dev_list). Data MUST be distributed in a round-robin fashion across the list of devices in increments of stripe_size bytes. A data file stored on a storage device MUST map to a single file as defined by the metadata server; i.e., data from two files as viewed by the metadata server MUST NOT be stored within the same data file on any storage device. struct pnfs_nfsv4_file_layout { pnfs_deviceid4 dev_id; offset4 start_offset; nfs_fh4 fh; }; struct pnfs_nfsv4_file_layouttype4 { uint64_t skip; uint64_t stripe_size; length4 eof; pnfs_nfsv4_file_layout dev_list<>; }; The "start_offset" field indicates the initial byte offset in the file represented by the filehandle "fh" on the device indicated by "dev_id". The "skip" field indicates the number of bytes to skip between the stripes on a particular storage device. This representation allows for a variety of storage device file layouts. The two data file layouts anticipated to be most common are "sparse file-layouts" and "dense file-layouts". For example: Welch, et al. Expires December 11, 2005 [Page 19] Internet-Draft pNFS Operations June 2005 Sparse file-layout ------------------ The following layout: stripe_size=4KB, skip=8KB and dev_list: [{dev_id: 0, start_offset: 0}, {dev_id: 1, start_offset: 4KB}, {dev_id: 2, start_offset: 8KB}] Is represented by the following file layout on the storage devices: Offset ID:0 ID:1 ID:2 0 +--+ +--+ +--+ +--+ indicates a |//| | | | | |//| stripe that 4KB +--+ +--+ +--+ +--+ contains data | | |//| | | 8KB +--+ +--+ +--+ | | | | |//| 12KB +--+ +--+ +--+ |//| | | | | 16KB +--+ +--+ +--+ | | |//| | | +--+ +--+ +--+ The sparse file-layout has holes for the byte ranges not exported by that storage device. This allows clients to access data using the real offset into the file, regardless of the storage device's position within the stripe. However, if a client writes to one of these holes (e.g., offset 4-12KB on device 1), then an error MUST be returned by the storage device. This requires that the storage device have knowledge of the layout for each file. Welch, et al. Expires December 11, 2005 [Page 20] Internet-Draft pNFS Operations June 2005 Dense/packed file-layout ------------------------ The following layout: stripe_size=4KB, skip=0 and dev_list: [{dev_id: 0, start_offset: 0}, {dev_id: 1, start_offset: 0}, {dev_id: 2, start_offset: 0}] Is represented by the following file layout on the storage devices: Offset ID:0 ID:1 ID:2 0 +--+ +--+ +--+ |//| |//| |//| 4KB +--+ +--+ +--+ |//| |//| |//| 8KB +--+ +--+ +--+ |//| |//| |//| 12KB +--+ +--+ +--+ |//| |//| |//| 16KB +--+ +--+ +--+ |//| |//| |//| +--+ +--+ +--+ The dense or packed file-layout does not leave holes on the storage devices. Each stripe unit is spread in a round-robin fashion across the storage devices. As such, the storage devices need not know the file's layout since the client is allowed to write to any offset. Regardless of the layout, the calculation to determine the index into the device array is the same: dev_idx = floor(file_offset / stripe_size) mod dev_list_num The calculation to determine the byte offset within the data file (on the storage device referenced by the device index) is: dev_offset = (floor(floor(file_offset / stripe_size) / dev_list_num) * (stripe_size + skip)) + (file_offset mod stripe_size) + dev_list[dev_idx].start_offset [NOTE: I have no problem simplifying this layout scheme. It seems there is a desire for sparse and dense layouts. We can always simplify this by adding a flag which indicates the type of layout (sparse or dense).] Clients MUST use the filehandle described within the layout when accessing data on the storage devices. The client MUST only issue READ, WRITE, and COMMIT operations to the storage devices. In Welch, et al. Expires December 11, 2005 [Page 21] Internet-Draft pNFS Operations June 2005 response to a WRITE or COMMIT, a storage device may return a writeverf unique to that storage device. GETATTR and SETATTR MUST be directed to the metadata server. In the case of a SETATTR of the size attribute, the management protocol is responsible for propagating size updates/truncations to the storage devices. In the case of extending WRITEs to the storage devices, the new size must be visible on the metadata server once a LAYOUTCOMMIT has completed (see Section 3.5.1, Section 5.5.2). All size attribute updates MUST be effective on the storage devices immediately (by the time the metadata operation returns), so that READs past EOF can be recognized. As described in Section 3.2, a client MUST NOT issue I/Os to storage devices for which it does not hold a valid layout. The storage devices SHOULD reject such requests. 5.2 Global Stateid Requirements Note, there are no stateids returned embedded within the layout. The client MUST use the stateid representing open or lock state as returned by an earlier metadata operation (e.g., OPEN, LOCK) to perform I/O on the data-servers (as would be used in regular NFSv4). Special stateids may be used when accessing data files on the storage devices. Special stateid usage for I/O is subject to the NFSv4 protocol specification. The stateid used for I/O MUST have the same affect and be subject to the same validation on storage device as it would if the I/O was being performed on the metadata server itself (in the absence of pNFS). This has the implication that stateids are globally valid on both the metadata and storage devices. This requires the metadata server to propagate changes in lock and open state to the data-servers, so that the data-servers may validate I/O accesses. This is discussed further in Section 5.4. 5.3 The Layout Iomode The layout iomode is not used by the metadata server when servicing NFSv4 file-based layouts. As such, the client SHOULD set the iomode to READ/WRITE at LAYOUTGET time. If an iomode of READ/WRITE is not specified, the metadata server may return an error. The iomode need not be checked by the storage devices when clients perform I/O. However, the storage devices SHOULD still validate that the client holds a valid layout and return an error if the client does not. 5.4 Storage Device State Propagation Since the metadata server, which handles lock and open-mode state changes, as well as ACLs, may not be collocated with the storage devices (where I/O access is validated), the server implementation Welch, et al. Expires December 11, 2005 [Page 22] Internet-Draft pNFS Operations June 2005 MUST take care of propagating changes of this state to the storage devices. Once the propagation to the storage devices is complete, the full effect of those changes must be in effect at the storage devices. However, some state changes need not be propagated immediately, although all changes SHOULD be propagated promptly. These state propagations have an impact on the design of the management protocol, even though the management protocol is outside of the scope of this specification. 5.4.1 Lock State Propagation Mandatory locks MUST be made effective at the storage devices before the request that establishes them returns to the caller. Thus, mandatory lock state MUST be synchronously propagated to the storage devices. On the other hand, since advisory lock state is not used for checking I/O accesses at the storage devices, there is no semantic reason for propagating advisory lock state to the storage devices. However, since all lock, unlock, open downgrades and upgrades affect the sequence ID stored within the stateid, the stateid changes which may cause difficulty if this state is not propagated. Thus, when a client uses a stateid on a storage device for I/O with a newer sequence number than the one the storage device has, the storage device should query the metadata server and get any pending updates to that stateid. Since updates to advisory locks neither confer nor remove privileges, these changes need not be propagated immediately, and may not need to be propagated promptly. The updates to advisory locks need only be propagated when the storage device needs to resolve a question about a stateid. In fact, if byte-range locking is not mandatory (is advisory) the clients are advised not to use the lock-based stateids for I/O at all. The ones returned by open are sufficient and eliminate overhead for this kind of state propagation. 5.4.2 Open-mode Validation Open-mode validation MUST be performed against the open mode(s) held by the storage devices. However, the server implementation may not always require the immediate propagation of changes. Reduction in access because of CLOSEs or DOWNGRADEs do not have to be propagated immediately, but SHOULD be propagated promptly (whereas changes due to revocation MUST be propagated immediately). On the other hand, changes that expand access (e.g., new OPEN's and upgrades) don't have to be propagated immediately but the storage device SHOULD NOT reject a request because of mode issues without making sure that the upgrade is not in flight. Welch, et al. Expires December 11, 2005 [Page 23] Internet-Draft pNFS Operations June 2005 5.4.3 File Attributes Since the SETATTR operation has the ability to modify state that is visible on the both the metadata and storage devices (e.g., the size), care must be taken to ensure that the resultant state (across the set of storage devices) is consistent; especially when truncating or growing the file. As described earlier, the LAYOUTCOMMIT operation is used to ensure that the metadata is synced with changes made to the storage devices. For the file-based protocol, it is necessary to re-sync state such as the size attribute, and the setting of mtime/atime. The management protocol is free to sync this state before it receives a LAYOUTCOMMIT, however upon successful completion of a LAYOUTCOMMIT the size attribute MUST be in sync (across the metadata server and storage devices, baring any intervening operations). 5.4.4 Access State Propagation Any changes to the state of a file that controls access as reflected by ACCESS calls or READs and WRITEs on the metadata server, MUST be propagated to the storage devices for enforcement on READ and WRITE I/O calls. If the changes made on the metadata server result in more restrictive access permissions for any user, those changes MUST be propagated to the storage devices synchronously. Recall, the NFSv4 protocol [2] specifies that: ...since the NFS version 4 protocol does not impose any requirement that READs and WRITEs issued for an open file have the same credentials as the OPEN itself, the server still must do appropriate access checking on the READs and WRITEs themselves. This also includes changes to ACLs. The propagation of ACLs may be asynchronous only if the server implementation is able to determine that the updated ACL is not more restrictive for any user specified in the old ACL. Due to the relative infrequency of ACL updates, it is suggested that they are propagated synchronously. 5.5 Extending EOF 5.5.1 READs and EOF A potential problem exists when a data file on a particular storage device is grown past EOF; it exists for both dense and sparse layouts. Imagine the following scenario: a client creates a new file (EOF == 0) and writes to byte 128KB; the client then seeks to the beginning of the file and reads byte 100. The client should receive Welch, et al. Expires December 11, 2005 [Page 24] Internet-Draft pNFS Operations June 2005 0s back as a result of the read. However, if the read falls on a different storage device to the client's original write, the storage device servicing the READ may still believe that the EOF is at 0 and return no data (with the EOF flag set). The storage device can only return 0s if it knows that the EOF has been extended. This would require the immediate propagation of EOF to all storage devices, which is potentially very costly, instead another approach is outlined below. First, the EOF is returned within the layout by LAYOUTGET. This EOF must reflect the latest EOF at the metadata server as set by the most recent of either the last LAYOUTCOMMIT or SETATTR; however, it may be more recent. Second, if a client performs a read that is returned short (i.e., is fully within EOF, but the storage device indicates EOF and returns partial or no data), the client must assume that it is a hole and substitute 0s for the data not read (up until its known local EOF). If a client extends the file, it must update its local EOF. Third, if the metadata server receives a SETATTR of the size or a LAYOUTCOMMIT that alters the EOF, the metadata server MUST send out CB_EOFCHANGED messages with the new EOF to clients holding layouts (it need not send a notification to the client that performed the operation that resulted in EOF changing). Upon reception of the CB_EOFCHANGED notification, clients must update their local EOF. As well, if a new EOF is returned as a result to LAYOUTCOMMIT, the client must update their local EOF. 5.5.2 LAYOUTCOMMIT and EOF Another complication can arise due to EOF. If a file has been grown by a set of WRITEs prior to a LAYOUTCOMMIT, the management protocol must ensure that the corresponding file on each storage device is grown (possibly sparsely) up until the offset represented by the EOF length before LAYOUTCOMMIT returns. For example: Imagine a file is striped across four storage devices, using a sparse file layout, with 64KB on each storage device. A WRITE of 64KB occurs starting at offset 192KB (the first stripe on the 4th storage device) followed by a LAYOUTCOMMIT. The new EOF offset is now at 256KB, however the corresponding file size on the first three storage devices is 0, since they did not service any WRITE operations. Immediately upon completion of LAYOUTCOMMIT, the server implementation MUST ensure that READs to any of the storage devices, at an offset below EOF, succeed; indeed, in this example, a read to any of the first three storage devices (below EOF) must return all 0s. The easiest way to accomplish this is to set the file size on each of the storage devices to EOF. Note, this only need occur at LAYOUTCOMMIT time or upon the reception of a SETATTR that modifies the size. Welch, et al. Expires December 11, 2005 [Page 25] Internet-Draft pNFS Operations June 2005 5.6 Security Considerations The NFSv4 file layout type MUST adhere to the security considerations outlined in Section 4. More specifically, storage devices must make all of the required access checks on each READ or WRITE I/O as determined by the NFSv4 protocol [2]. This impacts the management protocol and the propagation of state from the metadata server to the storage devices; see Section 5.4 for more details. 5.7 Alternate Approaches Two alternate approaches exist for file-based layouts and the method used by clients to obtain stateids used for I/O. Both approaches embed stateids within the layout. However, before examining these approaches it is important to understand the distinction between clients and owners. Delegations belong to clients, while locks (record and share reservations) are held by owners (who belong to a specific client). As such, delegations can only protect against inter-client conflicts, not intra-client conflicts. Layouts are held by clients and SHOULD NOT be associated with state held by owners. Therefore, if stateids used for data access are embedded within a layout, these stateids can only act as delegation stateids, protecting against inter-client conflicts; stateids pertaining to an owner can not be embedded within the layout. This has the implication that the client MUST arbitrate among all intra-client conflicts (such as arbitrating among lock requests by different processes) before issuing pNFS operations. Using the stateids stored within the layout, storage devices can only arbitrate between clients (not owners). The first alternate approach is to do away with global stateids (stateids returned by OPEN/LOCK that are valid on the metadata server and storage devices) and use only stateids embedded within the layout. This approach has the drawback that the stateids used for I/O access can not be validated against per owner state (rather they are validated against per client state), since they are only associated with the client holding the layout. It breaks the semantics of tieing a stateid used for I/O to an open instance. This has the implication that clients must delegate per owner lock and open requests internally, rather than push the work onto the storage devices. The storage devices can still arbitrate and enforce inter- client lock and open state. [Comment: What goes wrong when the stateids are not used as expected? Is it that byte range locks are not honored? Does it matter in the world of advisory locks?] Welch, et al. Expires December 11, 2005 [Page 26] Internet-Draft pNFS Operations June 2005 The second approach is a hybrid approach. This approach allows for stateids to be embedded with the layout, but also allows for the possibility of global stateids. If the stateid embedded within the layout is a special stateid of all zeros, then the stateid referring to the last successful OPEN/LOCK should be used (as a global stateid presented earlier in the proposal). This approach is recommended if it is decided that using NFSv4 as a management protocol is required. This proposal suggests the global stateid approach due to the cleaner semantics it provides regarding the relationship between stateids used for I/O and their corresponding open instance (or lock state). However, it does have a profound impact on the management protocol's implementation and the state propagation that is required (as described in Section 5.4). 6. pNFS Typed Data Structures 6.1 pnfs_layouttype4 enum pnfs_layouttype4 { LAYOUT_NFSV4_FILES = 1 }; A layout type specifies the layout being used. The implication is that clients have "layout drivers" that support one or more layout types. The file server advertises the layout types it supports through the LAYOUT_TYPES file system attribute. A client asks for layouts of a particular type in LAYOUTGET, and passes those layouts to its layout driver. The set of well known layout types must be defined through IANA. A private range of layout types should exist as defined through IANA. This would allow custom installations to introduce new layout types. The LAYOUT_NFSV4_FILES enumeration specifies that the NFSv4 file layout type is to be used. 6.2 pnfs_deviceid4 uint32_t pnfs_deviceid4; /* 32-bit device ID */ Layout information includes device IDs that specify a storage device through a compact handle. Addressing and type information is obtained with the GETDEVICEINFO operation. Device IDs may not be valid across metadata server reboots. See Section 3.1.1 for more details. Welch, et al. Expires December 11, 2005 [Page 27] Internet-Draft pNFS Operations June 2005 6.3 pnfs_devaddr4 enum pnfs_devaddrtypes4 { DEVADDR_SERVER_PORT = 1 }; union pnfs_devaddr4 switch (pnfs_devaddrtypes4 type) { case DEVADDR_SERVER_PORT: string r_netid<>; /* network ID */ string r_addr<>; /* universal address */ default: opaque devaddr<>; /* For other layouts */ }; This structure is used to set up a communication channel with the storage device. Different layout types will require different types of structures to define how they communicate with storage devices. The pnfs_devaddrtypes4 enumeration should list the types of structures required by the different layout types. The pnfs_devaddr4 union switches of this enumeration. Currently, DEVADDR_SERVER_PORT has been defined to identify a storage device by network IP address and port number. This is sufficient for the NFSv4 file layout storage driver to communicate with the NFSv4 storage devices, and for object-based storage drivers to communicate with iSCSI/OSD devices. Again, the pnfs_devaddrtypes4 should be defined through IANA. 6.4 pnfs_devlist_item4 struct pnfs_devlist_item4 { pnfs_deviceid4 id; pnfs_deviceaddr4 addr; }; An array of these values is returned by the GETDEVICELIST operation. They define the set of devices associated with a file system. Welch, et al. Expires December 11, 2005 [Page 28] Internet-Draft pNFS Operations June 2005 6.5 pnfs_layout4 union pnfs_layouttypes4 switch (pnfs_layouttype4 layout_type) { case LAYOUT_NFSV4_FILES: pnfs_nfsv4_layouttype4 file_layout; default: opaque layout_data<>; }; struct pnfs_layout4 { offset4 offset; length4 length; pnfs_layouttypes4 layout; }; The pnfs_layout4 structure defines a layout for a file. The pnfs_layouttypes4 union contains the portion of the layout specific to the layout type. Currently, only the NFSv4 file layout type is defined; see Section 5.1 for its definition. Since layouts are sub- dividable, the offset and length (together with the file's filehandle and the clientid), identifies the layout. 7. pNFS File Attributes 7.1 pnfs_layouttype4<> LAYOUT_TYPES This attribute applies to a file system and indicates what layout types are supported by the file system. We expect this attribute to be queried when a client encounters a new fsid. This attribute is used by the client to determine if it has applicable layout drivers. 7.2 pnfs_layouttype4 LAYOUT_TYPE This attribute indicates the particular layout type used for a file. This is for informational purposes only. The client needs to use the LAYOUTGET operation in order to get enough information (e.g., specific device information) in order to perform I/O. 7.3 pnfs_layouttypes4 LAYOUT_HINT This attribute may be set on newly created files to influence the metadata server's choice for the file's layout. The metadata server may ignore this attribute. This attribute is a sub-set of the layout returned by LAYOUTGET. For example, instead of specifying particular devices, this would be used to suggest the stripe width of a file. It is up to the server implementation to determine which fields within the layout it uses. Welch, et al. Expires December 11, 2005 [Page 29] Internet-Draft pNFS Operations June 2005 8. pNFS Error Definitions NFS4ERR_BADLAYOUT Layout specified is invalid. NFS4ERR_LAYOUTUNAVAILABLE Layouts are not available for the file or its containing file system. NFS4ERR_LAYOUTTRYLATER Layouts are temporarily unavailable for the file, client should retry later. 9. pNFS Operations 9.1 LAYOUTGET - Get Layout Information SYNOPSIS (cfh), clientid, layout_type, iomode, offset, length -> layout ARGUMENT enum layoutget_iomode4 { LAYOUTGET_READ = 1, LAYOUTGET_RW = 2 }; struct LAYOUTGET4args { /* CURRENT_FH: file */ clientid4 clientid; pnfs_layouttype4 layout_type; layoutget_iomode4 iomode; offset4 offset; length4 length; }; RESULT struct LAYOUTGET4resok { pnfs_layout4 layout; }; union LAYOUTGET4res switch (nfsstat4 status) { case NFS4_OK: LAYOUTGET4resok resok4; default: void; }; Welch, et al. Expires December 11, 2005 [Page 30] Internet-Draft pNFS Operations June 2005 DESCRIPTION Requests a layout for reading or writing the file given by the filehandle at the byte range specified by offset and length. Layouts are identified through the clientid, filehandle, and byte range (offset, length pair). The iomode specifies whether the client intends to read or read/write the data pertaining to the layout. The metadata server's use of the iomode may depend on the layout type being used. The storage devices may validate I/O accesses against the iomode (and reject invalid accesses). As well, the metadata server may adjust the range of the returned layout based on striping patterns and usage implied by the iomode. The client must be prepared to get a layout that does not line up exactly with their request; there MUST be at least one byte of overlap between the layout returned by the server and the client's request, or the server SHOULD reject the request. See Section 3.3 for more details. The LAYOUTGET operation returns layout information for the specified byte range. To get a layout from a specific offset through the end- of-file (no matter how long the file actually is) use a length field with all bits set to 1 (one). If the length is zero, or if a length which is not all bits set to one is specified, and length when added to the offset exceeds the maximum 64-bit unsigned integer value, the error NFS4ERR_INVAL will result. The format of the returned layout is specific to the underlying file system. Layout types other than the NFSv4 file layout type should be specified outside of this document. If layouts are not supported for the requested file or its containing file system the server SHOULD return NFS4ERR_LAYOUTUNAVAILABLE. If layout for the file is unavailable due to transient conditions, e.g. file sharing prohibits layouts, the server SHOULD return NFS4ERR_LAYOUTTRYLATER. On success, the current filehandle retains its value. IMPLEMENTATION Typically, LAYOUTGET will be called as part of a compound RPC after an OPEN operation and results in the client having location information for the file; a client may also hold a layout across multiple OPENs. The client specifies a layout type that limits what kind of layout the server will return. This prevents servers from issuing layouts that are unusable by the client. Welch, et al. Expires December 11, 2005 [Page 31] Internet-Draft pNFS Operations June 2005 [Comment: The notion of the layout class indicating a sub-set of possible layout types is gone. Now that the class is a flat number space, there is no official way to reference a "class" of layouts (e.g., files, blocks, or objects). This means that the type in the LAYOUTGET may be too restrictive, or that it is up to the server to decide if it can give out a "closely associated" layout that the client may be able to use.] ERRORS NFS4ERR_INVAL NFS4ERR_NOTSUPP NFS4ERR_LAYOUTUNAVAILABLE NFS4ERR_LAYOUTTRYLATER Welch, et al. Expires December 11, 2005 [Page 32] Internet-Draft pNFS Operations June 2005 9.2 LAYOUTCOMMIT - Commit writes made using a layout SYNOPSIS (cfh), layout_stateid, offset, length, neweof, newlayout -> neweof ARGUMENT union neweof4 switch (bool eofchanged) { case TRUE: length4 eof; case FALSE: void; }; union newlayout4 switch (bool layoutchanged) { case TRUE: pnfs_layouttypes4 layout; case FALSE: void; }; struct LAYOUTCOMMIT4args { /* CURRENT_FH: file */ clientid4 clientid; neweof4 neweof; offset4 offset; length4 length; newlayout4 newlayout; }; RESULT struct LAYOUTCOMMIT4resok { neweof4 neweof; }; union LAYOUTCOMMIT4res switch (nfsstat4 status) { case NFS4_OK: LAYOUTCOMMIT4resok resok4; default: void; }; DESCRIPTION Commits changes in the layout portion represented by the current Welch, et al. Expires December 11, 2005 [Page 33] Internet-Draft pNFS Operations June 2005 filehandle, clientid, and byte range. Since layouts are sub- dividable, a smaller portion of a layout, retrieved via LAYOUTGET, may be committed. The region being committed is specified through the byte range (length and offset). Note: the "newlayout" field does not include the length and offset, as they are already specified in the arguments. The LAYOUTCOMMIT operation indicates that the client has completed writes using a layout obtained by a previous LAYOUTGET. The client may have only written a subset of the data range it previously requested. LAYOUTCOMMIT allows it to commit or discard provisionally allocated space and to update the server with a new end of file. The metadata server may use the included new EOF as a hint. If the metadata server changes the EOF of the file, it MUST return the new EOF as part of the results. The layout argument to LAYOUTCOMMIT describes what regions have been used and what regions can be deallocated. NFSv4 file layout type implementations should ignore this field. The resulting layout is still valid after LAYOUTCOMMIT and can be continued to be referenced by the clientid, filehandle, and byte range. The layout information is more verbose for block devices than for objects and files because the latter hide the details of block allocation behind their storage protocols. At the minimum, the client needs to communicate changes to the end of file location back to the server, and its view of the file modify and access times (unless it wants the server to set those times to the time of LAYOUTCOMMIT). For blocks, it needs to specify precisely which blocks have been used. The metadata server should use the time of the LAYOUTCOMMIT operation as the file modify time, unless it is able to determine that the file has not been updated since the last mtime update. The client may use a SETATTR operation in a compound right after LAYOUTCOMMIT in order to override the access and modify times of the file. See Section 3.5 for more details. On success, the current filehandle retains its value. ERRORS NFS4ERR_INVAL NFS4ERR_BADLAYOUT TBD Welch, et al. Expires December 11, 2005 [Page 34] Internet-Draft pNFS Operations June 2005 9.3 LAYOUTRETURN - Release Layout Information SYNOPSIS (cfh), clientid, offset, length -> - ARGUMENT struct LAYOUTRETURN4args { /* CURRENT_FH: file */ clientid4 clientid; offset4 offset; length4 length; }; RESULT struct LAYOUTRETURN4res { nfsstat4 status; }; DESCRIPTION Returns the layout represented by the current filehandle, clientid, and byte range. After this call, the client MUST NOT use the layout and the associated storage protocol to access the file data. The layout being returned may be a subdivision of a layout previously fetched through LAYOUTGET. If the length is all 1s, the layout covers the range from offset to EOF. Layouts may be returned when recalled or voluntarily (i.e., before the server has recalled them). In either case the client must properly propagate state changed under the context of the layout to storage or to the server before returning the layout. If a client fails to return a layout in a timely manner, then the metadata server should use its management protocol with the storage devices to fence the client from accessing the data referenced by the layout. See Section 3.4 for more details. On success, the current filehandle retains its value. [TODO: We need to work out how clients return error information if they encounter problems with storage (if they should). We could return a single OK bit, or we could return more extensive information from the layout driver that describes the error condition in more detail. We could use an opaque "layout_error" type that is defined by the storage protocol along with its layout types.] Welch, et al. Expires December 11, 2005 [Page 35] Internet-Draft pNFS Operations June 2005 [There is a proposal for communicating extended error information in the "newlayout" argument to LAYOUTCOMMIT. This could provide an additional status code for each device in the layout, for example.] ERRORS NFS4ERR_INVAL NFS4ERR_BADLAYOUT TBD 9.4 GETDEVICEINFO - Get Device Information SYNOPSIS (cfh), device_id -> device_addr ARGUMENT struct GETDEVICEINFO4args { pnfs_deviceid4 device_id; }; RESULT struct GETDEVICEINFO4resok { pnfs_devaddr4 device_addr; }; union GETDEVICEINFO4res switch (nfsstat4 status) { case NFS4_OK: GETDEVICEINFO4resok resok4; default: void; }; DESCRIPTION Returns device type and device address information for a specified device. The returned device_addr includes a type that indicates how to interpret the addressing information for that device. At this time we expect two main kinds of device addresses, either IP address and port numbers, or SCSI volume identifiers. The final protocol specification will detail the allowed values for device_type and the format of their associated location information. Welch, et al. Expires December 11, 2005 [Page 36] Internet-Draft pNFS Operations June 2005 See Section 3.1.1 for more details on device ID assignment. 9.5 GETDEVICELIST - Get List of Devices SYNOPSIS (cfh), max_bytes, cookie, cookie_verf -> device_addr<> ARGUMENT struct GETDEVICELIST4args { /* Current file handle */ uint32_t max_bytes; nfs_cookie4 cookie; verifier4 cookie_verf; }; RESULT struct GETDEVICELIST4resok { pnfs_devlist_item4 device_addr_list<>; }; union GETDEVICEINFO4res switch (nfsstat4 status) { case NFS4_OK: GETDEVICEINFO4resok resok4; default: void; }; DESCRIPTION In some applications, especially SAN environments, it is convenient to find out about all the devices associated with a file system. This lets a client determine if it has access to these devices, e.g., at mount time. This operation returns a list of items that establish the association between the short pnfs_deviceid4 and the addressing information for that device. This operation may not be able to fetch all device information at once, thus it uses a cookie based approach, similar to READDIR, to fetch additional device information. 10. Callback Operations Welch, et al. Expires December 11, 2005 [Page 37] Internet-Draft pNFS Operations June 2005 10.1 CB_LAYOUTRECALL SYNOPSIS fh, offset, length -> - ARGUMENT struct CB_LAYOUTRECALLargs { nfs_fh4 fh; offset4 offset; length4 length; }; RESULT struct CB_LAYOUTRECALLres { nfsstat4 status; }; DESCRIPTION The CB_LAYOUTRECALL operation is used to begin the process of recalling a layout, or a portion thereof, and returning it to the server. The offset and length fields specify the portion of the layout to be returned. A length of all 1s specifies that the layout to EOF MUST be returned. If the handle specified is not one for which the client holds a layout, an NFS4ERR_BADHANDLE error is returned. If the layout byte range specified does not correspond to a valid layout for the file specified by the filehandle, an NFS4ERR_BADLAYOUT is returned. If the byte range overlaps with a layout being held, the portion of the layout represented by the overlap MUST be returned. IMPLEMENTATION The client should reply to the callback immediately. Replying does not complete the recall except when an error was returned. The recall is not complete until the layout is returned using a LAYOUTRETURN. The client should complete any in-flight I/O operations using the recalled layout before returning it via LAYOUTRETURN. If the client has buffered dirty data, it may chose to write it directly to storage before calling LAYOUTRETURN, or to write it later using normal NFSv4 Welch, et al. Expires December 11, 2005 [Page 38] Internet-Draft pNFS Operations June 2005 WRITE operations to the metadata server. ERRORS NFS4ERR_BADHANDLE NFS4ERR_BADLAYOUT 10.2 CB_EOFCHANGED SYNOPSIS fh, eof -> - ARGUMENT struct CB_EOFCHANGEDargs { nfs_fh4 fh; length4 eof; }; RESULT struct CB_EOFCHANGEDres { nfsstat4 status; }; DESCRIPTION The CB_EOFCHANGED operation is used to notify the client that the EOF pertaining to the filehandle associated with "fh", has changed. The new EOF is specified in the "eof" field. Upon reception of this notification callback, the client should update its internal EOF for the file. If the layout being held for the file is of the NFSv4 file layout type, then the EOF field within that layout should be updated (see Section 5.5.1). For other layout types see Section 3.5.1 for more details. If the handle specified is not one for which the client holds a layout, an NFS4ERR_BADHANDLE error is returned. ERRORS NFS4ERR_BADHANDLE Welch, et al. Expires December 11, 2005 [Page 39] Internet-Draft pNFS Operations June 2005 11. Usage Scenarios This section has a description of common open, close, read, write interactions and how those work with layout delegations. [TODO: this section feels rough and I'm not sure it adds value in its present form.] 11.1 Basic Read Scenario Client does an OPEN to get a file handle. Client does a LAYOUTGET for a range of the file, gets back a layout. Client uses the storage protocol and the layout to access the file. Client returns the layout with LAYOUTRETURN. Client closes stateID and open delegation with CLOSE. This is rather boring as the client is careful to clean up all server state after only a single use of the file. 11.2 Multiple Reads to a File Client does an OPEN to get a file handle. Client does a LAYOUTGET for a range of the file, gets back a layout. Client uses the storage protocol and the layout to access the file. Client closes stateID and with CLOSE. Client does an OPEN to get a file handle. Client finds cached layout associated with file handle. Client uses the storage protocol and the layout to access the file. Client closes stateID and with CLOSE. A bit more interesting as we've saved the LAYOUTGET operation, but we are still doing server round-trips. 11.3 Multiple Reads to a File with Delegations Client does an OPEN to get a file handle and an open delegation. Client does a LAYOUTGET for a range of the file, gets back a layout. Client uses the storage protocol and the layout to access the file. Application does a close(), but client keeps state under the delegation. (time passes) Application does another open(), which client handles under the delegation. Client finds cached layout associated with file handle. Client uses the storage protocol and the layout to access the file. (pattern continues until open delegation and/or layout is recalled) This illustrates the efficiency of combining open delegations and layouts to eliminate interactions with the file server altogether. Of course, we assume the client's operating system is only allowing the local open() to succeed based on the file permissions. The use Welch, et al. Expires December 11, 2005 [Page 40] Internet-Draft pNFS Operations June 2005 of layouts does not change anything about the semantics of open delegations. 11.4 Read with existing writers NOTE: This scenario was under some debate, but we have resolved that the server is able to give out overlapping/conflicting layout information to different clients. In these cases we assume that clients are using an external mechanism such as MPI-IO to synchronize and serialize access to shared data. One can argue that even unsynchronized clients get the same open-to-close consistency semantics as NFS already provides, even when going direct to storage. Client does an OPEN to get an open stateID and open delegation. The file is open for writing elsewhere by different clients and so no open delegation is returned. Client does a LAYOUT get and gets a layout from the server. Client either synchronizes with the writers, or not, and accesses data via the layout and storage protocol. There are no guarantees about when data that is written by the writer is visible to the reader. Once the writer has closed the file and flushed updates to storage, then they are visible to the client. [We should state explicitly that COMMIT and LAYOUTCOMMIT represent explicit points where changes should be visible to other clients.] 11.5 Read with later conflict ClientA does an OPEN to get an open stateID and open delegation. ClientA does a LAYOUTGET for a range of the file, gets back a map and layout stateid. ClientA uses the storage protocol to access the file data. ClientB opens the file for WRITE. File server issues CB_RECALL to ClientA. ClientA issues DELEGRETURN. ClientA continues to use the storage protocol to access file data. If it is accessing data from its cache, it will periodically check that its data is still up-to-date because it has no open delegation. [This is an odd scenario that mixes in open delegations for no real value. Basically this is a "regular writer" being mixed with a pNFS reader. I guess this example shows that no particular semantics are provided during the simultaneous access. If the server so chose, it could also recall the layout with CB_LAYOUTRECALL to force the different clients to serialize at the file server.] 11.6 Basic Write Case Client does an OPEN to get a file handle. Client does a LAYOUTGET for a range of the file, gets back a layout and layout stateid. Client writes to the file using the storage protocol. Client uses Welch, et al. Expires December 11, 2005 [Page 41] Internet-Draft pNFS Operations June 2005 LAYOUTCOMMIT to communicate new EOF position. Client does SETATTR to update timestamps. Client does a LAYOUTRETURN. Client does a CLOSE. Again, the boring case where the client cleans up all of its server state by returning the layout. 11.7 Large Write Case Client does an OPEN to get a file handle. (loop.) Client does a LAYOUTGET for a range of the file, gets back a layout and layout stateid. Client writes to the file using the storage protocol. Client fills up the range covered by the layout. Client updates the server with LAYOUTCOMMIT, communicating about new EOF position. Client does SETATTR to update timestamps. Client releases the layout with LAYOUTRELEASE. (end loop.) Client does a CLOSE. 11.8 Create with special layout Client does an OPEN and a SETATTR that specifies a particular layout type using the LAYOUT_HINT attribute. Client gets back an open stateID and file handle. (etc) 12. Layouts and Aggregation This section describes several layout formats in a semi-formal way to provide context for the layout delegations. These definitions will be formalized in other protocols. However, the set of understood types is part of this protocol in order to provide for basic interoperability. The layout descriptions include (deviceID, objectID) tuples that identify some storage object on some storage device. The addressing formation associated with the deviceID is obtained with GETDEVICEINFO. The interpretation of the objectID depends on the storage protocol. The objectID could be a filehandle for an NFSv4 storage device. It could be a OSD object ID for an object server. The layout for a block device generally includes additional block map information to enumerate blocks or extents that are part of the layout. 12.1 Simple Map The data is located on a single storage device. In this case the file server can act as the front end for several storage devices and distribute files among them. Each file is limited in its size and performance characteristics by a single storage device. The simple map consists of (deviceID, objectID). Welch, et al. Expires December 11, 2005 [Page 42] Internet-Draft pNFS Operations June 2005 12.2 Block Map The data is located on a LUN in the SAN. The layout consists of an array of (deviceID, blockID, blocksize) tuples. Alternatively, the blocksize could be specified once to apply to all entries in the layout. 12.3 Striped Map (RAID 0) The data is striped across storage devices. The parameters of the stripe include the number of storage devices (N) and the size of each stripe unit (U). A full stripe of data is N * U bytes. The stripe map consists of an ordered list of (deviceID, objectID) tuples and the parameter value for U. The first stripe unit (the first U bytes) are stored on the first (deviceID, objectID), the second stripe unit on the second (deviceID, objectID) and so forth until the first complete stripe. The data layout then wraps around so that byte (N*U) of the file is stored on the first (deviceID, objectID) in the list, but starting at offset U within that object. The striped layout allows a client to read or write to the component objects in parallel to achieve high bandwidth. The striped map for a block device would be slightly different. The map is an ordered list of (deviceID, blockID, blocksize), where the deviceID is rotated among a set of devices to achieve striping. 12.4 Replicated Map The file data is replicated on N storage devices. The map consists of N (deviceID, objectID) tuples. When data is written using this map, it should be written to N objects in parallel. When data is read, any component object can be used. This map type is controversial because it highlights the issues with error recovery. Those issues get interesting with any scheme that employs redundancy. The handling of errors (e.g., only a subset of replicas get updated) is outside the scope of this protocol extension. Instead, it is a function of the storage protocol and the metadata management protocol. 12.5 Concatenated Map The map consists of an ordered set of N (deviceID, objectID, size) tuples. Each successive tuple describes the next segment of the file. Welch, et al. Expires December 11, 2005 [Page 43] Internet-Draft pNFS Operations June 2005 12.6 Nested Map The nested map is used to compose more complex maps out of simpler ones. The map format is an ordered set of M sub-maps, each submap applies to a byte range within the file and has its own type such as the ones introduced above. Any level of nesting is allowed in order to build up complex aggregation schemes. 13. Issues 13.1 Storage Protocol Negotiation Clients may want to negotiate with the metadata server about their preferred storage protocol, and to find out what storage protocols the server offers. Client can do this by querying the LAYOUT_TYPES file system attribute. They respond by specifying a particular layout type in their LAYOUTGET operation. 13.2 Crash recovery We use the existing client crash recovery and server state recovery mechanisms in NFSv4. The main new issue introduced by pNFS is that the client may have to do a lot of I/O in response to a layout recall. The client may need to remember to send RENEW ops to the server during this period if it were to risk not doing anything within the lease time. Of course, the client should only reply with its LAYOUTRETURN after it knows its I/O has completed. 13.3 Storage Errors As noted under LAYOUTRETURN, there may be a need for the client to communicate about errors it has when accessing storage directly. 14. Normative References [1] Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", March 1997. [2] Shepler, S., Callaghan, B., Robinson, D., Thurlow, R., Beame, C., Eisler, M., and D. Noveck, "Network File System (NFS) version 4 Protocol", RFC 3530, April 2003. [3] Weber, R., "Object-Based Storage Device Commands (OSD)", INCITS 400-2004, July 2004, . [4] Gibson, G., "pNFS Problem Statement", July 2004, . Authors' Addresses Brent Welch Panasas, Inc. 6520 Kaiser Drive Fremont, CA 95444 USA Phone: +1-650-608-7770 Email: welch@panasas.com URI: http://www.panasas.com/ Benny Halevy Panasas, Inc. 1501 Reedsdale St., #400 Pittsburgh, PA 15233 USA Phone: +1-412-323-3500 Email: bhalevy@panasas.com URI: http://www.panasas.com/ Garth Goodson Network Appliance 495 E. Java Dr Sunnyvale, CA 94089 USA Phone: +1-408-822-6847 Email: goodson@netapp.com David L. Black EMC Corporation 176 South Street Hopkinton, MA 01748 USA Phone: +1-508-293-7953 Email: black_david@emc.com Welch, et al. Expires December 11, 2005 [Page 45] Internet-Draft pNFS Operations June 2005 Andy Adamson CITI University of Michigan 519 W. William Ann Arbor, MI 48103-4943 USA Phone: +1-734-764-9465 Email: andros@umich.edu Appendix A. Acknowledgments Many members of the pNFS informal working group have helped considerably. The authors would like to thank Gary Grider, Peter Corbett, Dave Noveck, and Peter Honeyman. This work is inspired by the NASD and OSD work done by Garth Gibson. Gary Grider of the national labs (LANL) has been a champion of high-performance parallel I/O. Welch, et al. Expires December 11, 2005 [Page 46] Internet-Draft pNFS Operations June 2005 Intellectual Property Statement The IETF takes no position regarding the validity or scope of any Intellectual Property Rights or other rights that might be claimed to pertain to the implementation or use of the technology described in this document or the extent to which any license under such rights might or might not be available; nor does it represent that it has made any independent effort to identify any such rights. Information on the procedures with respect to rights in RFC documents can be found in BCP 78 and BCP 79. Copies of IPR disclosures made to the IETF Secretariat and any assurances of licenses to be made available, or the result of an attempt made to obtain a general license or permission for the use of such proprietary rights by implementers or users of this specification can be obtained from the IETF on-line IPR repository at http://www.ietf.org/ipr. The IETF invites any interested party to bring to its attention any copyrights, patents or patent applications, or other proprietary rights that may cover technology that may be required to implement this standard. Please address the information to the IETF at ietf-ipr@ietf.org. Disclaimer of Validity This document and the information contained herein are provided on an "AS IS" basis and THE CONTRIBUTOR, THE ORGANIZATION HE/SHE REPRESENTS OR IS SPONSORED BY (IF ANY), THE INTERNET SOCIETY AND THE INTERNET ENGINEERING TASK FORCE DISCLAIM ALL WARRANTIES, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Copyright Statement Copyright (C) The Internet Society (2005). This document is subject to the rights, licenses and restrictions contained in BCP 78, and except as set forth therein, the authors retain all their rights. Acknowledgment Funding for the RFC Editor function is currently provided by the Internet Society. Welch, et al. Expires December 11, 2005 [Page 47]