Documentation/filesystems/orangefs.rst

12 Walt Ligon and Eric Blumer as a parallel file system for Parallel
13 Virtual Machine (PVM) as part of a NASA grant to study the I/O patterns
44 Running ORANGEFS On a Single Server
48 clients, but a complete filesystem can be run on a single machine for
59 To generate a filesystem to run xfstests against, see below.
61 There is an example client configuration file in /etc/pvfs2tab.  It is a
96 Building ORANGEFS on a Single Server
115 specifying a target config file. Pvfs2-genconfig will prompt you
139 Now the server should be running. Pvfs2-ls is a simple
157 It is useful to use a scratch filesystem with xfstests.  This can be
160 Make a second copy of the FileSystem section in the server configuration
163 section (2 is usually a good choice).
208 If you want the debug (GOSSIP) statements in a particular
225 Get a list of all debugging keywords::
233 Orangefs is a user space filesystem and an associated kernel module.
242 The kernel module implements a pseudo device that userspace
253 a pointer to each buffer is added to its own PVFS_dev_map_desc structure
257 A pointer to the IO buffer's PVFS_dev_map_desc structure is sent to a
264     - a reference counter
273   * page_array - a pointer to ``page_count * (sizeof(struct page*))`` bytes
275     to each of the pages in the IO buffer through a call to get_user_pages.
276   * desc_array - a pointer to ``desc_count * (sizeof(struct orangefs_bufmap_desc))``
300   * buffer_index_array - a desc_count sized array of ints, used to
302   * buffer_index_lock - a spinlock to protect buffer_index_array during update.
303   * readdir_index_array - a five (ORANGEFS_READDIR_DEFAULT_DESC_COUNT) element
306   * readdir_index_lock - a spinlock to protect readdir_index_array during
317 The slab allocator is used to keep a cache of op structures handy.
319 At init time the kernel module defines and initializes a request list
334 	    - op has to start a timer since client-core
339 When some arbitrary userspace program needs to perform a
341 an op structure is initialized and tagged with a distinguishing ID
347 function through a wait queue. Userspace is polling the pseudo-device
358 and the op is hashed on its tag and put onto the end of a list in the
363 the pseudo device in a series of io_vecs. This triggers the Orangefs
374 userspace. The client-core is a daemon. The client-core has an
377 the client-core is restarted "right away", there is a period of
380 Ops that pass through service_operation during a "dead spell" can timeout
393     The kernel module obtains an index to a free partition before launching
394     a readdir op. Userspace deposits the results into the indexed partition
400     index to a free partition before launching an io op. The kernel module
407 structs. Besides a few other members, pvfs2_downcall_t contains a
408 union of structs, each of which is associated with a particular
426     fill a pvfs2_io_response_t
429     fill a PVFS_object_kref
432     fill a PVFS_object_kref
435     fill a PVFS_object_kref
438     fill in a PVFS_sys_attr_s (tons of stuff the kernel doesn't need)
439     fill in a string with the link target when the object is a symlink.
442     fill a PVFS_object_kref
445     fill a pvfs2_statfs_response_t with useless info <g>. It is hard for
446     us to know, in a timely fashion, these statistics about our
450     fill a pvfs2_fs_mount_response_t which is just like a PVFS_object_kref
451     except its members are in a different order and "__pad1" is replaced
455     fill a pvfs2_getxattr_response_t
458     fill a pvfs2_listxattr_response_t
461     fill a pvfs2_param_response_t
464     fill a pvfs2_perf_count_response_t
467     file a pvfs2_fs_key_response_t
470     jamb everything needed to represent a pvfs2_readdir_response_t into
478   - a pointer to the prepared response to the request from the
480   - and also, in the case of a readdir request, a pointer to a
487 PINT_dev_write_list has a local iovec array: struct iovec io_array[10];
518 Orangefs keeps private data in an object's inode that includes a short
526 Creation of a new object (file, dir, sym-link) includes the evaluation of
527 its pathname, resulting in a negative directory entry for the object.
529 a negative dentry into a "productive full member of society". Orangefs
534 The evaluation of a pathname for an object resolves to its corresponding
536 the dcache. Whenever a dentry is modified or verified Orangefs stores a
538 for that amount of time. Orangefs is a network filesystem, and objects
540 instance, so trusting a dentry is risky. The alternative to trusting
542 least a trip to the client-core, maybe to the servers. Obtaining information
543 from a dentry is cheap, obtaining it from userspace is relatively expensive,
552     difference in a way that takes into account the possibility that the