CITI ASC status
From Linux NFS
University of Michigan/CITI NFSv4 ASC alliance
Status of October 2006
Task 1. Demonstration of pNFS with multiple back end methods (PVFS and File) including layout recall — LANL will replicate this demonstration at LANL working with CITI remotely.
Development
We updated the Linux pNFS client and server to the 2.6.17 kernel level, and are preparing to rebase again for 2.6.19.
We updated the pNFS code base to draft-ietf-nfsv4-minorversion1-05. Testing identified multiple bugs, which we fixed.
To make a clean separation of the common NFS v2/3/4/4.1 code from code specific to pNFS, we rewrote the Linux pNFS client to use its own set of RPC operations.
Four client layout modules are in development.
- File layout driver (CITI, Network Appliance, and IBM Almaden).
- PVFS2 layout driver (CITI).
- Object layout driver (Panasas).
- Block layout driver (CITI under contract with EMC).
To accommodate the requirements of the multiple layout drivers, we expanded the layout operation policy interfaces between the layout driver and generic pNFS client.
We are designing and coding a pNFS client layout cache to replace the current implementation, which supports only a single layout per inode.
We improved the interface to the underlying file system on the Linux pNFS server. The new interface is being used by the Panasas object layout server and the IBM GPFS server.
We are coding the pNFS layout management service and file system interfaces on the Linux pNFS server to do a better job of bookkeeping so that we can extend the layout recall implementation, which is limited to a single layout.
We've continued to developed the pVFS2 layout and pVFS2 pNFS server.
* Dean, can you throw some text here?
We developed prototype implementations of pNFS operations:
- OP_GETDEVICELIST,
- OP_GETDEVICEINFO,
- OP_LAYOUTGET,
- OP_LAYOUTCOMMIT,
- OP_LAYOUTRETURN and
- OP_CB_LAYOUTRECALL
We continue to test the ability of our prototype to send direct I/O data to data servers.
Milestones
At the September 2006 NFSv4 Bake-a-thon, hosted by CITI, we continued to test the ability of CITI's Linux pNFS client to operate with multiple layouts, and the ability of CITI's Linux pNFS server to export pNFS capable underlying file systems.
We demonstrated the Linux pNFS client support for multiple layouts by copying files between multiple pNFS back ends.
The following pNFS implementations were tested.
File Layout
- Clients: Linux, Solaris
- Servers: Network Appliance, Linux IBM GPFS, DESY dCache, Solaris
Object layout
- Clients: Linux
- Servers: Linux, Panasas
Block layout
- Clients: Linux
- Server: EMC
Activities
Our current Linux pNFS implementation uses a single whole file layout. We are extending the layout cache on the client and layout management on the server to support multiple layouts and small byte ranges.
In cooperation with EMC, we continue to develop a block layout driver module for the generic pNFS client.
We continue to measure I/O performance.
We joined the Ultralight project and are testing pNFS I/O using pNFS clients on 10 GbE against pNFS clusters on 1 GbE. The Linux pNFS client included in the Ultralight kernel and distributed to Ultralight sites, providing opportunities for future long-haul WAN testing.
Task 2. Migration of client from one mount/metadata server to another to be demonstrated. This demonstration may be replicated at LANL depending on success of this work.
When a file system moves, the former server notifies clients with NFS4ERR_MOVED. Clients then reclaim state held on the former server by engaging in reboot recovery with the new server. For cluster file systems, server-to-server state transfer lets clients avoid the reclaim.
We redesigned state bookkeeping to ensure that state created on NFSv4 servers exporting the same cluster file system will not collide. We are rewriting the interface that clients use when saving NFSv4 server state in stable storage to also support the server-server state transfer.
It remains to inform clients that state established with the former server remains valid on the new server. IETF is considering solutions, e.g., augmented FS_LOCATIONS information or a new error code NFS4ERR_MOVED_DATA_AND_STATE.
Task 3. Analysis of caching and lock coherency, demonstration of caching and lock performance with scaling, under various levels of conflict, using byte range locks (looking at lock splitting issues etc.).
We have set up test machines and begun planning for tests. We have some immediate concerns over the memory footprint imposed by server lock structures.
Task 4. Analysis of directory delegations – how well does it work and when, when does it totally not work.
Development
We have implemented directory delegations in the Linux client and server. Our server implementation of directory delegations follows the file delegations architecture. We extended the lease API in the Linux VFS to support read-only leases on directories and NFS-specific lease-breaking semantics.
We implemented a /proc interface for enabling or disabling directory delegation at run time. At startup, the client queries the server for directory delegation support.
Directory delegations promise to extend the usefulness of negative dentry caching on the client. Negative caching is unsafe without cache invalidation (positive caching can be treated as a hint). To give an example, opening a file that does not exist produces an OPEN RPC that fails. Open-to-close semantics and the lack of consistent negative caching requires that subsequent opens of the same non-existent file yield repeated OPEN RPC calls being sent to the server. This example is played out frequently when searching for an executable in PATH or a shared library in LD_LIBRARY_PATH.
Directory delegation enables negative caching by assuring that no entries have been added or modified in a cached directory. This should markedly decrease unnecessary repeated checks for non-existent files. We are testing this use case.
The server has hooks for a policy layer to control the granting of directory delegations. (No policy is implemented yet.) When and whether to acquire delegations is also a client concern.
Testing
We are testing delegation grant and recall in a test rig with one or two clients. Testing consists mostly of comparing NFS operation-counts when directory delegations is enabled or disabled.
Tests range from simple UNIX utilities — ls, find, touch — to hosting a CVS repository or compiling with shared libraries and header files on NFS servers. Tests will become more specific.
We have extended PyNFS to support directory delegations. So far, the support is basic and the tests are trivial. Tests will become more specific.
We are designing mechanisms that allow simulation experiments to compare delegation policies on NFSv4 network traces.
Task 5. How do you specify/measure NFS Server load.
We have no progress to report on this task.
