Reporting of Errors via LAYOUTRETURN in NFSv4.2

Introduction In the Network File System version4 (NFSv4) with a Parallel NFS (pNFS) Flexible File Layout () server, during recovery after a restart, there is no mechanism for the client to inform the metadata server about an error which occurred during a WRITE (see Section 18.32 of ) operation to the data servers in the period of the outage. Using the process detailed in , the revisions in this document become an extension of NFSv4.2 . They are built on top of the external data representation (XDR) generated from .

Definitions See Section 1.1 of for a more complete set of definitions.

(file) data:: that part of the file system object that contains the data to be read or written. It is the contents of the object rather than the attributes of the object.
data server (DS):: a pNFS server that provides the file's data when the file system object is accessed over a file-based protocol.
(file) metadata:: the part of the file system object that contains various descriptive data relevant to the file object, as opposed to the file data itself. This could include the time of last modification, access time, EOF position, etc.
metadata server (MDS):: the pNFS server that provides metadata information for a file system object.

Requirements Language The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 when, and only when, they appear in all capitals, as shown here.

Layout State Recovery When a metadata server restarts, clients are provided a grace period where they are allowed to recover any state that they had established. With open files, the client can send an OPEN (see Section 18.16 of ) operation with a claim type of CLAIM_PREVIOUS (see Section 9.11 of ). The client uses the RECLAIM_COMPLETE (see Section 18.51 of ) operation to notify the metadata server that it is done reclaiming state. The NFSv4 Flexible File Layout Type allows for the client to mirror files (see Section 8 of ). With client side mirroring, it is important for the client to inform the metadata server of any I/O errors encountered with one of the mirrors. This is the only way for the metadata server to determine one or more of the mirrors is corrupt and then repair the mirrors via resilvering. The client can use LAYOUTRETURN (see Section 18.44 of ) and the ff_ioerr4 (see Section 9.1.1 of ) structure to inform the metadata server of I/O errors. A problem is that if the metadata server restarts and the client has errors it needs to report, it can not do so. The LAYOUTRETURN needs a layout stateid to proceed and there is no way for the client to recover layout state. As such, clients have no choice but to not recover files with I/O errors. In turn, the metadata server MUST assume that the mirrors are inconsistent and pick one for resilvering. It is a MUST because even if the metadata server can determine that the client did modify data during the outage, it MUST NOT assume those modifications were consistent. If the server were to allow the client to use the anonymous stateid of all zeros (see Section 8.2.3 of ) for lrf_stateid in LAYOUTRETURN (see Section 18.44.1 of ), then the client could inform the metadata server of errors encountered. That in turn would allow the metadata server to accurately resilver the file by picking the correct mirror(s). There are two error scenarios that can occur:

During the grace period:: If the client were to send any lrf_stateid in the LAYOUTRETURN other than the anonymous stateid of all zeros, then the metadata server would respond with an error of NFS4ERR_GRACE (see Section of 15.1.9.2 ).
After the grace period:: If the client were to send any lrf_stateid in the LAYOUTRETURN with the anonymous stateid of all zeros, then the metadata server would respond with an error of NFS4ERR_NO_GRACE (see Section 15.1.9.3 of ).

Also, when the metadata server builds the reply to the LAYOUTRETURN, it MUST NOT bump the seqid of the lorr_stateid. The metadata server MUST NOT resilver a file if there are clients with outstanding layouts with iomode of LAYOUTIOMODE4_RW. Whether the metadata server prevents all I/O to the file until the resilvering is done or forces all I/O to go through the metadata server or allows a proxy server to update the new data file as it is being reslivered is all an implementation choice. The constraint is that the metadata server is responsible for the reconstruction of the data file and for the consistency of the mirrors. The metadata server MUST NOT have been resilvering the file such that it has a different layout (set of mirror instances) than the client before the restart of the metadata server. Further, the metadata server MUST NOT start a new resilvering of the file during the grace period unless there are no outstanding layouts with iomode of LAYOUTIOMODE4_RW. If the metadata server detects that the layout being returned in the LAYOUTRETURN does not match the current mirror instances found for the file, then it should ignore the LAYOUTRETURN and resilver the file in question. Finally, the metadata server MUST determine that any files which are neither explicitly recovered with a CLAIM_PREVIOUS nor have a reported error via a LAYOUTRETURN, have to be resilvered. The client has most likely restarted and lost any state.