Whamcloud - gitweb
adilger [Fri, 25 Nov 2005 13:27:45 +0000 (13:27 +0000)]
Branch b_release_1_4_6
Add patches from Bull for 2.6.12 kernel into CVS.
r=pbojanic
brian [Wed, 23 Nov 2005 21:15:05 +0000 (21:15 +0000)]
b_release_1_4_6_rhel3_37 needs it's parents portals/lnet.
Support rhel3 kernel SRPM unpacking/tarball building.
lbuild can use a local SRPM.
Whitespace cleanup.
brian [Wed, 23 Nov 2005 17:39:06 +0000 (17:39 +0000)]
b=9682
r=adilger
Land RHEL3-37 update kernel support.
lsy [Sat, 19 Nov 2005 15:32:38 +0000 (15:32 +0000)]
Land b1_4_merge_ptlrpc onto b_release_1_4_6 (20051119_2035)
brian [Fri, 18 Nov 2005 18:15:48 +0000 (18:15 +0000)]
b=9358
r=adilger
Land RHEL4-22 kernel changes to the 1.4.6 release branch for inclusion in beta2.
- includes enabling firewire support on all platforms to enable use of shared
firewire drives.
nic [Wed, 16 Nov 2005 22:19:13 +0000 (22:19 +0000)]
reformat and cleanup don't mix
brian [Wed, 9 Nov 2005 23:03:10 +0000 (23:03 +0000)]
Update for release 1.4.5.94, a.k.a. 1.4.6 beta1.
ericm [Wed, 9 Nov 2005 19:32:30 +0000 (19:32 +0000)]
branch: b_release_1_4_6
add back acl test scripts which were missing in landing for unknown reason.
yury [Wed, 9 Nov 2005 13:28:01 +0000 (13:28 +0000)]
- removed not used var in pinger.
- make filter_preprw_read() do not complain about not existing OSt object, as it nicely handles that case.
niu [Wed, 9 Nov 2005 09:49:27 +0000 (09:49 +0000)]
fix previous wrong assertion.
b: 6027
yury [Wed, 9 Nov 2005 08:13:37 +0000 (08:13 +0000)]
- fixes in CROW related tests (15*)
niu [Wed, 9 Nov 2005 07:48:29 +0000 (07:48 +0000)]
add more debug message.
b: 6027
niu [Wed, 9 Nov 2005 04:05:57 +0000 (04:05 +0000)]
don't compile quota in 2.4
yury [Tue, 8 Nov 2005 16:35:41 +0000 (16:35 +0000)]
- returned to original schema (using PING_INTERVAL) of checking if some exports need to be evicted on server side.
yury [Tue, 8 Nov 2005 13:31:15 +0000 (13:31 +0000)]
- different fixes from Andreas and me:
- do nothing in ptlrpc_statfs_interpret() if rc != 0
- update obd->obd_osfs_age in ptlrpc_statfs_interpret() to make all obd_statfs() users do not emmit not needed RPCs if statfs ping is just handled out and fresh stat info is in here.
- make ptlrpc_update_next_ping() not inlined function as it makes it easy to debug and it is not needed to be inlined there from perf. POV.
- removed not needed lwi init in loop over all pingable imports in ping thread.
- fixed updating imp->imp_next_ping for non-CROW-able imports. Thus, they are not pinged again.
niu [Tue, 8 Nov 2005 02:39:49 +0000 (02:39 +0000)]
disable quota build for 2.4
yury [Sun, 6 Nov 2005 15:27:19 +0000 (15:27 +0000)]
- fixes, improvemtns, more verbosity.
phil [Sat, 5 Nov 2005 07:32:43 +0000 (07:32 +0000)]
b=9646
update error message to refer to knowledge base
niu [Fri, 4 Nov 2005 06:48:50 +0000 (06:48 +0000)]
improve test8
niu [Fri, 4 Nov 2005 06:35:46 +0000 (06:35 +0000)]
improve cfs_user_write() for quota
niu [Fri, 4 Nov 2005 05:46:41 +0000 (05:46 +0000)]
land b1_4_quota (20051104_1137)
yury [Thu, 3 Nov 2005 11:28:28 +0000 (11:28 +0000)]
- changes about handling CROW flag. URGENT is removed and all create calls are urgent if not CROW is specified.
adilger [Thu, 3 Nov 2005 01:00:33 +0000 (01:00 +0000)]
Branch b_release_1_4_6
Update build version to 1.4.5.93 to avoid re-using this version for
the b_release_4_6 branch.
yury [Wed, 2 Nov 2005 13:14:18 +0000 (13:14 +0000)]
- fixes, comments and cleanups:
- fixed test 34c from sanity.sh. It has two sub-bugs:
(1) when reg file is created by mknod and did not open as reg file, it has no lsm and has no OST object. I nthis case truncate path should set i_size into inode on MDS. This ws done correctly, but i_size was not returned corectly to client after that as mds_reint_setattr() had bug with setting body->valid |= SIZE for that case (comment added).
(2) later, in the same test, when file was opened and lsm created, MDS sent setattr RPC to OST to pass its inode attrs. As there was o_flags set to CROW, filter_setattr_internal() was confused and called fsfilt_iocontrol() instead of fsfilt_setattr(). Thus inode size was not set correctly and 0 was returned to client whereas MDS inode size should have been returned instead.
- in filter_preprw_read() more fixes about handling unexisting object. No -ENOENT should be returned and everythign should be done like object exists, but its size is 0 (thanks to Niu for catching this out).
nkj [Tue, 1 Nov 2005 17:41:45 +0000 (17:41 +0000)]
fixing terminology inconsistency.
nkj [Tue, 1 Nov 2005 16:22:56 +0000 (16:22 +0000)]
I've updated the lfs.1 manpage to reflect the updated documentation in the lfs.lyx file. This includes 'lfs check' and 'lfs osts'.
commit to b_release_1_4_6
yury [Tue, 1 Nov 2005 12:55:24 +0000 (12:55 +0000)]
- fixes in filter_preprw_read() for case when OST object is not yet allocated.
yury [Tue, 1 Nov 2005 09:16:21 +0000 (09:16 +0000)]
- fixed parent locking in filter_create_object(). Parent should be unlocked after child's inode fid EA is stored and transaction committed. Otherwise concurrent thread might access child object which is not realy ready (no fid EA)
yury [Tue, 1 Nov 2005 08:31:17 +0000 (08:31 +0000)]
- removed incorrect check in filter_lvbo_init().
yury [Mon, 31 Oct 2005 16:38:06 +0000 (16:38 +0000)]
- changes about obd_statfs ->os_state and ->os_spare* fields
yury [Sun, 30 Oct 2005 11:17:58 +0000 (11:17 +0000)]
- landing CROW stuff.
b=8888
r=adilger
r=nikita
r=bzzz
r=niu
ericm [Fri, 28 Oct 2005 23:18:05 +0000 (23:18 +0000)]
land b1_4_acl on b_release_1_4_6: add Posix ACL support.
green [Fri, 28 Oct 2005 20:23:09 +0000 (20:23 +0000)]
Landing Inodebits to b_release_1_4_6.
nic [Fri, 28 Oct 2005 03:55:07 +0000 (03:55 +0000)]
get a tagged lnet for releases after 1_4_6
cvs2svn [Thu, 27 Oct 2005 23:26:12 +0000 (23:26 +0000)]
This commit was manufactured by cvs2svn to create branch 'b_release_1_4_6'.
nathan [Thu, 27 Oct 2005 23:26:10 +0000 (23:26 +0000)]
b=9501
r=adilger
automatically create /dev/lnet, /dev/obd when needed.
nathan [Thu, 27 Oct 2005 23:24:45 +0000 (23:24 +0000)]
b=9501
r=adilger
automatically create /dev/lnet, /dev/obd when needed.
nathan [Thu, 27 Oct 2005 22:54:42 +0000 (22:54 +0000)]
Branch b_hd_newconfig
b=9501
fix 'lctl net down' twice assert
pjkirner [Thu, 27 Oct 2005 21:34:51 +0000 (21:34 +0000)]
* Key for peer db is ptl_process_id_t rather than just NID
(+ Assocated log msg chanages)
Necesary to support catamount processes that come up one right
after another using the same NID but diffrent PIDs
* Fix to bug in peer_time() code with incorrect return code
pjkirner [Thu, 27 Oct 2005 21:05:15 +0000 (21:05 +0000)]
* Fixed handling of NOOP message
* Fixed dssstamp check to handle multple routers & incoming connections
* Cleanup a few log messages + qkcc compiler warnings
lincent [Thu, 27 Oct 2005 08:20:27 +0000 (08:20 +0000)]
modify llog_reader to show args of lov_modify_tgts.
eeb [Thu, 27 Oct 2005 02:26:09 +0000 (02:26 +0000)]
* iiblnd: drain disconnecting sockets
* lnet: explicit configure/teardown for routers ("lctl network up" as well as
"lctl network down"). config_on_load=0 is the new default (setting it
effectively does "lctl network up" at module load time).
Added "net" as an alias for "network" to lctl so you don't have to type
"work" when you run "lctl net up" from the shell.
Also fixed a couple of bugs which required lnet to be unloaded before it
could be brought up again.
* lnet routing: restored automatic route disabling when comms to a router
fails (currently kernel elan and tcp only).
eeb [Thu, 27 Oct 2005 02:26:07 +0000 (02:26 +0000)]
* iiblnd: drain disconnecting sockets
* lnet: explicit configure/teardown for routers ("lctl network up" as well as
"lctl network down"). config_on_load=0 is the new default (setting it
effectively does "lctl network up" at module load time).
Added "net" as an alias for "network" to lctl so you don't have to type
"work" when you run "lctl net up" from the shell.
Also fixed a couple of bugs which required lnet to be unloaded before it
could be brought up again.
* lnet routing: restored automatic route disabling when comms to a router
fails (currently kernel elan and tcp only).
brian [Wed, 26 Oct 2005 23:15:01 +0000 (23:15 +0000)]
r=nic
Allow lbuild to build a kernel from a downloaded RHEL4 SRPM. It should only
need to do this once as it caches the .tar.bz2 it builds.
This technique can/should be ported to other vendor kernels we deal with.
Just more "hands off" automation of the build process.
adilger [Wed, 26 Oct 2005 18:35:46 +0000 (18:35 +0000)]
Branch b1_4
Don't compare .xml mtimes, they will always be different.
Split "long UUID" and "consistent .xml" into separate subtests.
nathan [Wed, 26 Oct 2005 16:46:51 +0000 (16:46 +0000)]
Branch b1_4
(lin)print lov_setup info
adilger [Wed, 26 Oct 2005 09:29:33 +0000 (09:29 +0000)]
Branch b1_4
Description: When migrating a subset of services from a node (e.g. failback
from a failover service node) the remaining services would
time out and evict clients.
Details : lconf --force (implied by --failover) sets the global obd_timeout
to 5 seconds in order to quickly disconnect, but this caused
other RPCs to time out too quickly. Do not change the global
obd_timeout for force cleanup, only set it for DISCONNECT RPCs.
b=6395, b=9514
adilger [Wed, 26 Oct 2005 00:30:10 +0000 (00:30 +0000)]
Branch b1_4
Use "if (likely(!ext3_mb_agressive))" since it is likely that this is not set
(it defaults to off). Also, check this first since it is the likely case.
nic [Tue, 25 Oct 2005 22:54:10 +0000 (22:54 +0000)]
p=alex
- fix for write performance slowdown on 2.6 kernels. Return early when not in
'aggressive' mode and default aggressive mode to off
adilger [Tue, 25 Oct 2005 19:57:43 +0000 (19:57 +0000)]
Branch b1_4
Don't get ll_inode_size_lock() in ll_update_inode() as this can be called
with inode_lock (spinlock) held and deadlock. This was protecting the
setting of lli_smd to prevent ll_inode_size_unlock() from inconsistently
calling lov_stripe_unlock() when it was never locked because lli_smd changed
since ll_inode_size_lock() was called.
We now avoid this race by only ever calling ll_inode_size_lock() with
lli_smd already set, or with "lock_lsm = 0" so we don't care if it changes
between lock and unlock. This makes sense in any case, because if there is
no lli_smd we shouldn't be doing glimpse/enqueue on the OSTs anyways.
b=9547
r=nikita
nathan [Tue, 25 Oct 2005 19:37:04 +0000 (19:37 +0000)]
Branch b1_4
b=9477
r=adilger
- robustify mtime check
- forgot to add back in part of --service= checks
nathan [Tue, 25 Oct 2005 18:22:05 +0000 (18:22 +0000)]
Branch b1_4
b=8080
r=adilger
Change magic for new lmd
pjkirner [Tue, 25 Oct 2005 15:55:30 +0000 (15:55 +0000)]
* Fix for redundant routing on Catamount
* Cleanup of some logging build warnings
* Some additional logging
nathan [Tue, 25 Oct 2005 15:20:15 +0000 (15:20 +0000)]
b=8080
create /dev/lnet
lsy [Tue, 25 Oct 2005 11:36:40 +0000 (11:36 +0000)]
fixes for nikita's inspection.
adilger [Tue, 25 Oct 2005 06:39:23 +0000 (06:39 +0000)]
Branch b1_4
Fix bug 9482 regression for fix to 2.6 llap_shrink_cache() page cleanup.
b=6450, b=9482
r=green
eeb [Tue, 25 Oct 2005 00:07:44 +0000 (00:07 +0000)]
* socklnd: fixed my stupid blunder that could cause the assertion
failure...
LustreError: 20480:0:(socklnd_cb.c:788:ksocknal_launch_packet())
ASSERTION(peer->ksnp_accepting > 0 ||
ksocknal_find_connecting_route_locked(peer) != NULL) failed
* iiblnd: fixed connection race and tested on boston, but didn't manage
to exercise the race resolution code.
ericm [Mon, 24 Oct 2005 17:09:22 +0000 (17:09 +0000)]
branch: b1_4
lconf recognize option --user_xattr (fake) to make ltest happy.
eeb [Mon, 24 Oct 2005 16:27:40 +0000 (16:27 +0000)]
* openiblnd: dropped unused 'rc' from kibnal_peer_connect_failed() to bring
it into line with iib,vib.
* iiblnd: coded connection race resolution
brian [Mon, 24 Oct 2005 16:27:30 +0000 (16:27 +0000)]
Make release 1.4.5.92 on current b1_4 head.
eeb [Sun, 23 Oct 2005 17:12:54 +0000 (17:12 +0000)]
* 9561: completed connection race fix for socklnd
eeb [Sun, 23 Oct 2005 14:08:15 +0000 (14:08 +0000)]
* socklnd:
fixed connection race that can occur with multiple routers
changed 'typed_conns' module parameter to RO
* nidstrings:
allow 0xnnnn parsing of numerical NIDs
libcfs_num_addr2str -> libcfs_decnum_addr2str (LO, QSW, PTL)
libcfs_hexnum_addr2str (GM)
* gmlnd:
change from decimal to hex representation of GM addresses (they're the
lowest 4 bytes of the NIC's MAC address).
* router:
compare routers first on # uncompleted bytes, then credits
for better load balance.
* llmount:
fixed error message (it's a NID, not a host)
fixed bug in checking mdx & profile string lengths
eeb [Sun, 23 Oct 2005 14:08:10 +0000 (14:08 +0000)]
* socklnd:
fixed connection race that can occur with multiple routers
changed 'typed_conns' module parameter to RO
* nidstrings:
allow 0xnnnn parsing of numerical NIDs
libcfs_num_addr2str -> libcfs_decnum_addr2str (LO, QSW, PTL)
libcfs_hexnum_addr2str (GM)
* gmlnd:
change from decimal to hex representation of GM addresses (they're the
lowest 4 bytes of the NIC's MAC address).
* router:
compare routers first on # uncompleted bytes, then credits
for better load balance.
* llmount:
fixed error message (it's a NID, not a host)
fixed bug in checking mdx & profile string lengths
adilger [Sat, 22 Oct 2005 07:36:18 +0000 (07:36 +0000)]
Branch b1_4
Save "options" from the wrath of strtok() so we can save them into /etc/mtab.
This is needed for buffalo testing of new features, among other things.
brian [Fri, 21 Oct 2005 22:33:34 +0000 (22:33 +0000)]
Array element access in bash MUST be enclosed with {}.
eeb [Fri, 21 Oct 2005 16:15:45 +0000 (16:15 +0000)]
* Changed iiblnd to use Infinicon iba_xxx() API.
* Changed iiblnd to post multiple work items in 1 go.
eeb [Fri, 21 Oct 2005 15:22:28 +0000 (15:22 +0000)]
* iiblnd fixes (mid-way through changing Infinicon API)
* viblnd fix (tx_waiting not cleared on RDMA ops initiated on a new
connection that fails triggers an assertion failure).
* some prep for userspace ip2nets
* router selection round robins if other selection criterea are equal
* local_nid_dist_zero LNET module param for single-node LND testing.
* reformat LNET /proc buffer displays
* rename userspace tcplnd env params TCPNAL_xxx -> TCPLND_xxx
pjkirner [Fri, 21 Oct 2005 13:48:57 +0000 (13:48 +0000)]
* Make echo_test a proper liblustre test, now that it works even on Catamount!
nikita [Fri, 21 Oct 2005 10:34:56 +0000 (10:34 +0000)]
fix unnecessary line-wrap
nikita [Fri, 21 Oct 2005 10:13:09 +0000 (10:13 +0000)]
ENTRY has to be matched by RETURN()
niu [Fri, 21 Oct 2005 08:33:59 +0000 (08:33 +0000)]
Disable compile userspace quota stuff for b1_4. This is short-term solution
for the <linux/quota.h> problem before b1_4_quota lands.
-b 9542
-r adilger
lsy [Fri, 21 Oct 2005 03:28:06 +0000 (03:28 +0000)]
remove unused LC_CONFIG_QUOTA in lustre-build.m4.
remove check for if_dqblk/dqinfo.
change parameters type from int to __u32, since it's used
in ioctl. and make it align. (according to Andreas' advice)
nathan [Thu, 20 Oct 2005 19:45:29 +0000 (19:45 +0000)]
add configure warning if building without CONFIG_KMOD
nathan [Thu, 20 Oct 2005 19:17:37 +0000 (19:17 +0000)]
Branch b1_4
allow auto-loading of lustre/LNET modules
nathan [Thu, 20 Oct 2005 18:23:35 +0000 (18:23 +0000)]
Branch b1_4
b=none
fix 'make dist' err with llog_reader
niu [Thu, 20 Oct 2005 09:45:15 +0000 (09:45 +0000)]
all children of b1_4 should use same lnet
niu [Thu, 20 Oct 2005 08:16:59 +0000 (08:16 +0000)]
define PORTAL_SYMBOL_GET/PUT for userspace
pjkirner [Thu, 20 Oct 2005 02:13:54 +0000 (02:13 +0000)]
* Added command line support for liblustre echo_test
* Added "hack" to allow echo_test to build on Catamount
nathan [Wed, 19 Oct 2005 21:50:44 +0000 (21:50 +0000)]
b=8080
better errors for 2.4 module autoloading
nathan [Wed, 19 Oct 2005 21:49:51 +0000 (21:49 +0000)]
b=8080
better errors for 2.4 module autoloading
green [Wed, 19 Oct 2005 18:58:42 +0000 (18:58 +0000)]
b=9482
r=adilger
Check that there is no page_mapped() before trying to define it for 2.4 kernels.
nathan [Wed, 19 Oct 2005 18:23:21 +0000 (18:23 +0000)]
Branch b_hd_newconfig
b=8080
add symlink from /proc/sys/portals to /proc/sys/lnet for old failover
scripts
pjkirner [Wed, 19 Oct 2005 18:21:09 +0000 (18:21 +0000)]
* Fixed a few problems in ptllnd_set_txiov relating to iovec mapping
* Remove a "parania" LASSERT that was not valid for Cray Portals
pjkirner [Wed, 19 Oct 2005 04:39:03 +0000 (04:39 +0000)]
* Fix case of PTLLND not being included because of incorrect #if value
nathan [Wed, 19 Oct 2005 00:41:25 +0000 (00:41 +0000)]
Branch b1_4
b=9477
These lines should not have been removed in the 9477 patch. They prevent
--select from limiting services in linux 2.4
ericm [Tue, 18 Oct 2005 21:37:30 +0000 (21:37 +0000)]
b1_4_acl has updated from b1_4, use same portals/lnet as b1_4
nikita [Tue, 18 Oct 2005 19:27:26 +0000 (19:27 +0000)]
Forgotten chunks of 7133 patch.
nathan [Tue, 18 Oct 2005 19:14:35 +0000 (19:14 +0000)]
Branch b1_4
b=9477
exempt bad/incomplete nids from network ping test
nathan [Tue, 18 Oct 2005 18:26:37 +0000 (18:26 +0000)]
b=8080
- modules aren't as automatic as they should be for linux 2.4
- for some reason python in linux 2.4 didn't understand this lmc construct
nathan [Tue, 18 Oct 2005 18:23:08 +0000 (18:23 +0000)]
b=8080
- modules aren't as automatic as they should be for linux 2.4
- for some reason python in linux 2.4 didn't understand this lmc construct
nathan [Tue, 18 Oct 2005 16:38:26 +0000 (16:38 +0000)]
b=8080
Landing LNET (b1_4_newconfig)
nathan [Tue, 18 Oct 2005 16:12:39 +0000 (16:12 +0000)]
b=8080
Landing LNET (b1_4_newconfig)
green [Mon, 17 Oct 2005 21:26:53 +0000 (21:26 +0000)]
Branch: b1_4
b=9482
r=adilger
Try to unmap pages before discarding them in llap_shrink_cache.
gord [Mon, 17 Oct 2005 19:25:47 +0000 (19:25 +0000)]
Commented out LC_CONFIG_QUOTA line, which had no definition.
pjkirner [Mon, 17 Oct 2005 19:13:03 +0000 (19:13 +0000)]
* Fix XT3 build issues
eeb [Sat, 15 Oct 2005 18:33:25 +0000 (18:33 +0000)]
* Changed linking of userspace ptllnd to depend on HAVE_CRAY_XT3 rather than
!HAVE_LIBPTHREAD.
nikita [Sat, 15 Oct 2005 17:26:04 +0000 (17:26 +0000)]
An optimization proposed by Andreas: do not grow (as part of ldlm lock policy)
extent locks acquired on server (e.g., OST-side locks introduced by previous
7311 fixes): server-side locks are not cached and would only conflict with
other threads.
b=7311
r=adilger
eeb [Sat, 15 Oct 2005 16:46:21 +0000 (16:46 +0000)]
* First cut iiblnd (compiles but untested)
* Removed #if LNET_SINGLE_THREADED and replaced with #if !HAVE_LIBPTHREAD
* Fixed LND module descriptions to say LND (not NAL)
* viblnd cleanups (removed unused struct members, fixed some formatting etc)
* minor cleanup in text buffer allocations (lnet/lnet/config.c)
* format string fix in klnd/ptllnd.c
* fixed lustre/utils/obd.c to work without libpthread/fork (disables --threads)
green [Fri, 14 Oct 2005 20:07:42 +0000 (20:07 +0000)]
b=7293
r=adilger
Add possibility (config option) to show minimal available OST free space
pjkirner [Fri, 14 Oct 2005 19:36:09 +0000 (19:36 +0000)]
* Rename max_immd_size -> max_msg_size to reduce further confusion, and align with Catamoun PTLLND