1 2002-10-01 Phil Schwan <phil@clusterfs.com>
4 - locks would be cancelled without throwing away data pages,
5 resulting in inconsistent data (605627)
6 - inode attributes were not always being refreshed (605627, 612449)
7 - lconf now continues to cleanup after lctl reports an error
8 - MDS now enforces user permissions (602707)
9 - lprocfs cleanup fixed, but not yet enabled (614157)
10 - fixed infinite server hang, should a client not respond to an AST
11 - avoid going into recovery if user calls readlink() with a buffer
12 that's too small (613941)
13 - AST RPCs no longer require replies (614867) -- this may be changed
14 - don't crash server if client sends an IOV that's too big (611336)
15 - fixed lock conversion deadlock (611892)
16 - fixed the following of symlinks (614622)
17 * recovery: the server can remove locks from a client that dies, other
18 clients can make progress
19 * more extN patch fixes
20 * compile-time configurable ptlrpc buffer allocations
22 - collaborative read cache document
23 - Lustre Lite Performance CDR document-in-progress
25 2002-09-20 Andreas Dilger <adilger@clusterfs.com>
28 - fix typo in patch-2.4.18
30 2002-09-20 Andreas Dilger <adilger@clusterfs.com>
33 - clear ptlrpc request each time in handle_incoming_request()
34 - unlink of files now destroys the object on the OST
36 2002-09-19 Peter Braam <braam@clusterfs.com>
38 * add hard link support
39 * change obdfile creation method
40 * kernel patch changed
42 2002-09-19 Peter Braam <braam@clusterfs.com>
45 - stack overflow bug in extN fixed
47 2002-09-18 Andreas Dilger <adilger@clusterfs.com>
49 * documentation updates
50 - add man pages for config tools
51 - update tests/README to describe testing with new config tools
52 - finish metadata API descriptions
53 * bug fixes and cleanups
54 - statfs workaround for 16TB limit
55 - LOV stripe allocation improved, can stripe on subset of OSTs
56 - LOV file size/IO offset was wrong for files > 4GB in size
57 - object EA data was being dropped, caused files to be unreadable
58 - memory overflow with non-LOV OST caused memory corruption
59 - fixed regression tests to work with new config tools, obdfilter
60 - fixed bug when directory size became larger than 1 block
61 - fixed bug (for single client case) when PWD was deleted
62 - invalidate local directory pages when doing intent-based ops
63 - avoid LDLM oops when lock callback contained bad data
65 2002-09-09 Andreas Dilger <adilger@clusterfs.com>
67 * documentation updates
68 * bug fixes and cleanups
72 - 64-bit compile warnings
73 - 64-bit internal statfs data
75 * test_brw on persistent OST devices
79 2002-09-04 Andreas Dilger <adilger@clusterfs.com>
81 * documentation updates
82 * bug fixes and cleanups
85 2002-08-30 Peter J. Braam <braam@clusterfs.com>
88 * many small fixes to 0_5_4
90 * thinkos in MDS operations
92 2002-08-24 Peter J. Braam <braam@clusterfs.com>
95 * crucial basic fixes to 0.5.3
96 * IOR, Iozone work over Elan
99 2002-08-07 Phil Schwan <phil@clusterfs.com>
100 * version 0_5_3, our first alpha
101 * we use the new Portals iovs
102 * documentation updates
103 * bug fixes and cleanups
104 * small changes in the DLM wire protocol
106 2002-07-25 Peter J. Braam <braam@clusterfs.com>
107 * version 0_5_1 with some initial stability,
108 * locking on MD and file I/O.
109 * documentation updates
110 * several bug fixes since 0.5.0
111 * small changes in wire protocol
113 2002-07-18 Phil Schwan <phil@clusterfs.com>
115 * delivered as Lustre Light Alpha
116 * fixed a crash after handling invalid MDS requests
117 * fixed directory pages for architectures with non-4k pages sizes
119 2002-07-11 Andreas Dilger <adilger@clusterfs.com>
120 * release version v0_4_4
121 * Moves TCP acceptor to be on port 2432 (unused Coda port) instead
123 * Fixes a number of interruption problems with OST operations.
124 * Update documentation for portals header changes
125 * Move all wire protocol structs/defines to lustre_idl.h
126 * Fixes symlink length bug.
127 * Add tcpdump to repository.
129 2002-07-05 Andreas Dilger <adilger@clusterfs.com>
130 * release version v0_4_3
131 * Fixes statfs for inodes on extN.
132 * Fixes bug in runtests which would delete /etc/hosts.
133 * Use 64-bit object IDs wherever possible (not into VFS though)
134 Remove ost_get_info, which is unused by lustre, and out of date.
136 2002-07-03 Peter Braam <braam@clusterfs.com>
137 * release version v0_4_2 Fixes a lookup error (type not passed)
138 * move forward to head of Portals
139 * move forward to latest Lustre kernel
141 2002-06-25 Peter Braam <braam@clusterfs.com>
142 * release version v0_4_1. Hopefully stable on single node use.