Whamcloud - gitweb
fs/lustre-release.git
22 years agoadd vfs_intent_hp_2.4.19.patch
wangdi [Wed, 23 Apr 2003 09:58:35 +0000 (09:58 +0000)]
add vfs_intent_hp_2.4.19.patch

22 years agoWork-in-progress checkin of recovery logging. Not even compiling yet.
adilger [Wed, 23 Apr 2003 09:22:42 +0000 (09:22 +0000)]
Work-in-progress checkin of recovery logging.  Not even compiling yet.

22 years agoWork-in-progress checkin for logging code. Not even compiling yet.
adilger [Wed, 23 Apr 2003 09:20:09 +0000 (09:20 +0000)]
Work-in-progress checkin for logging code.  Not even compiling yet.

22 years agocomment out the warning line in top_current_warn
wangdi [Wed, 23 Apr 2003 07:30:32 +0000 (07:30 +0000)]
comment out the warning line in top_current_warn

22 years agoadd check pc file before add one patch to fix the flaw of poppatch
wangdi [Wed, 23 Apr 2003 06:23:49 +0000 (06:23 +0000)]
add check pc file before add one patch to fix the flaw of poppatch

22 years agoadd the check-pc-match
wangdi [Wed, 23 Apr 2003 06:21:50 +0000 (06:21 +0000)]
add the check-pc-match

22 years ago- add the fixes with correct pc files
braam [Tue, 22 Apr 2003 21:39:33 +0000 (21:39 +0000)]
- add the fixes with correct pc files

22 years ago- forgot a parameter in truncate
braam [Tue, 22 Apr 2003 21:19:08 +0000 (21:19 +0000)]
- forgot a parameter in truncate

22 years ago- small error in intent patch fixed
braam [Tue, 22 Apr 2003 19:58:45 +0000 (19:58 +0000)]
- small error in intent patch fixed
- add a cvs test to sanity
- update the UML config file, it's still wrong

22 years ago- fix a lost fix for exec.c
braam [Tue, 22 Apr 2003 18:25:06 +0000 (18:25 +0000)]
- fix a lost fix for exec.c

22 years agoadd xattr in fs/ext3/Makefile
wangdi [Sun, 20 Apr 2003 09:06:58 +0000 (09:06 +0000)]
add xattr in fs/ext3/Makefile

22 years agoChange obdfilter/fsfilt code so that preprw/commitrw can be called from
adilger [Fri, 18 Apr 2003 21:13:42 +0000 (21:13 +0000)]
Change obdfilter/fsfilt code so that preprw/commitrw can be called from
within a nested journal transaction.  This will allow us to log from the
MDS to a local obdfilter transactionally.

22 years agoInitial versions of Peter's commit logs/daemon code.
adilger [Wed, 16 Apr 2003 19:58:33 +0000 (19:58 +0000)]
Initial versions of Peter's commit logs/daemon code.

22 years agoadd vfs_intent-2.4.20-rh
wangdi [Wed, 16 Apr 2003 13:56:05 +0000 (13:56 +0000)]
add vfs_intent-2.4.20-rh

22 years agoadd patch vfs_intent_2.4.20-rh
wangdi [Wed, 16 Apr 2003 13:54:22 +0000 (13:54 +0000)]
add patch vfs_intent_2.4.20-rh

22 years agoadd the directory of config and spec file
wangdi [Wed, 16 Apr 2003 12:55:37 +0000 (12:55 +0000)]
add the directory of config and spec file

22 years agoadd tmp uml-patch-2.4.20
wangdi [Wed, 16 Apr 2003 12:53:47 +0000 (12:53 +0000)]
add tmp uml-patch-2.4.20

22 years agofor signal panic of 2.4.20 uml
wangdi [Wed, 16 Apr 2003 12:50:43 +0000 (12:50 +0000)]
for signal panic of 2.4.20 uml

22 years agoadd a tmp patch of uml-2.4.20 for panic
wangdi [Wed, 16 Apr 2003 12:48:46 +0000 (12:48 +0000)]
add a tmp patch of uml-2.4.20 for panic

22 years agoAdd an old version of the TCP zero copy patch for zero-copy socknal. Having
adilger [Tue, 15 Apr 2003 18:01:34 +0000 (18:01 +0000)]
Add an old version of the TCP zero copy patch for zero-copy socknal.  Having
it in lustre instead of portals probably isn't idea, but this is where we do
our kernel patch management from.

I'm not sure which exact kernel this was generated against, nor do I have any
idea on how much this part of the code changes between kernel releases.

22 years agofix a flaw of function do_coredump in fs/exec
wangdi [Mon, 14 Apr 2003 06:56:18 +0000 (06:56 +0000)]
fix a flaw of function do_coredump in fs/exec

22 years ago- initial version of cluster manger service script
rread [Fri, 11 Apr 2003 22:49:58 +0000 (22:49 +0000)]
- initial version of cluster manger service script

22 years agoNot sure how this got into CVS.
adilger [Thu, 10 Apr 2003 11:13:43 +0000 (11:13 +0000)]
Not sure how this got into CVS.

22 years agoFixes to make compile on HP PNNL kernels.
mmex [Thu, 10 Apr 2003 10:14:58 +0000 (10:14 +0000)]
Fixes to make compile on HP PNNL kernels.

22 years agoMerge from b_devel.
adilger [Thu, 10 Apr 2003 09:23:44 +0000 (09:23 +0000)]
Merge from b_devel.

22 years ago- another minor fix to forkpatch
braam [Thu, 10 Apr 2003 07:55:14 +0000 (07:55 +0000)]
- another minor fix to forkpatch
- add missing sum-series to poppatch

22 years ago- fix forkpatch, it had two bugs:
braam [Thu, 10 Apr 2003 07:50:03 +0000 (07:50 +0000)]
- fix forkpatch, it had two bugs:
  - copying over the symlinked series file removed the file
  - basename should have been stripit.

22 years ago- revert some changes Matthew made
braam [Thu, 10 Apr 2003 06:25:20 +0000 (06:25 +0000)]
- revert some changes Matthew made

22 years agoAdd 2.4.20 UML support to ptlrpc/pinger.c.
adilger [Wed, 9 Apr 2003 22:45:53 +0000 (22:45 +0000)]
Add 2.4.20 UML support to ptlrpc/pinger.c.

22 years agoThese update the patch files so that they apply cleanly in the
mmex [Wed, 9 Apr 2003 18:27:55 +0000 (18:27 +0000)]
These update the patch files so that they apply cleanly in the
PNNL world.

22 years agoUpdated complete patch for hp-pnnl kernels.
mmex [Wed, 9 Apr 2003 17:58:55 +0000 (17:58 +0000)]
Updated complete patch for hp-pnnl kernels.

22 years agoAdded a hp-pnnl-2.4.20 series to the kernel patchs and fixed up the patch
mmex [Wed, 9 Apr 2003 17:55:41 +0000 (17:55 +0000)]
Added a hp-pnnl-2.4.20 series to the kernel patchs and fixed up the patch
files to work correctly.

22 years agoFixed patch scripts so they can once again locate the patching tools.
mmex [Wed, 9 Apr 2003 17:46:54 +0000 (17:46 +0000)]
Fixed patch scripts so they can once again locate the patching tools.

22 years agoThis gives a good first shot at fixing the patch management issues:
braam [Wed, 9 Apr 2003 10:25:30 +0000 (10:25 +0000)]
This gives a good first shot at fixing the patch management issues:

 - we followed the instructions that are being posted on the wiki
   and wich were discussed this morning

 - patches are now fairly easy to create and update

22 years agothe last merge b_devel to b_cray
nfshp [Tue, 8 Apr 2003 09:34:56 +0000 (09:34 +0000)]
the last merge b_devel to b_cray

22 years agoAdd in some missing bits to the vfs_intent patch (lib, exec).
adilger [Tue, 8 Apr 2003 08:55:55 +0000 (08:55 +0000)]
Add in some missing bits to the vfs_intent patch (lib, exec).

22 years agoOne final fix for wantedi.
adilger [Tue, 8 Apr 2003 07:54:26 +0000 (07:54 +0000)]
One final fix for wantedi.

22 years agoFix context when not applying ext3-2.4.18-ino_sb_macro.patch
adilger [Tue, 8 Apr 2003 07:37:20 +0000 (07:37 +0000)]
Fix context when not applying ext3-2.4.18-ino_sb_macro.patch

22 years ago- fixup xattr patch slightly
braam [Tue, 8 Apr 2003 07:18:40 +0000 (07:18 +0000)]
- fixup xattr patch slightly
- put old scripts back, the new ones have some problems

22 years agoFix typo in series file.
adilger [Tue, 8 Apr 2003 07:11:25 +0000 (07:11 +0000)]
Fix typo in series file.

22 years agoWe already have patches/extN-wantedi.patch.
adilger [Tue, 8 Apr 2003 06:38:10 +0000 (06:38 +0000)]
We already have patches/extN-wantedi.patch.

22 years agoAdd module.h include for proper EXPORT_SYMBOL() definition.
adilger [Tue, 8 Apr 2003 06:28:03 +0000 (06:28 +0000)]
Add module.h include for proper EXPORT_SYMBOL() definition.

22 years agoAdd exports for xattr functions for fsfilt_ext3 to use.
adilger [Tue, 8 Apr 2003 06:02:30 +0000 (06:02 +0000)]
Add exports for xattr functions for fsfilt_ext3 to use.

22 years agoAdd several ext3 bug-fix patches from extN.
adilger [Mon, 7 Apr 2003 23:41:24 +0000 (23:41 +0000)]
Add several ext3 bug-fix patches from extN.
Add wantedi patch for recovery code.

22 years agoMinor compilation fixes:
adilger [Mon, 7 Apr 2003 23:38:15 +0000 (23:38 +0000)]
Minor compilation fixes:
- add new do_truncate() parameter (called_from_open) to do_coredump()
- add definition of path_lookup_it()

22 years agoDon't add xattr.o to export-objs twice.
adilger [Mon, 7 Apr 2003 23:36:36 +0000 (23:36 +0000)]
Don't add xattr.o to export-objs twice.

22 years agoMinor change to match patch submitted to l-k.
adilger [Mon, 7 Apr 2003 23:36:00 +0000 (23:36 +0000)]
Minor change to match patch submitted to l-k.

22 years agoRemove need for whitespace formerly added by exports_hp.patch.
adilger [Mon, 7 Apr 2003 23:18:35 +0000 (23:18 +0000)]
Remove need for whitespace formerly added by exports_hp.patch.

22 years agoAdd bad blocks allocation fix from extN (only used when on-disk data is bad).
adilger [Mon, 7 Apr 2003 21:13:32 +0000 (21:13 +0000)]
Add bad blocks allocation fix from extN (only used when on-disk data is bad).

22 years agoRemove CVS tags from patch, so we don't get patch conflicts.
adilger [Mon, 7 Apr 2003 19:55:55 +0000 (19:55 +0000)]
Remove CVS tags from patch, so we don't get patch conflicts.

22 years agomerge b_devel into b_cray
nfshp [Mon, 7 Apr 2003 07:21:38 +0000 (07:21 +0000)]
merge b_devel into b_cray

22 years ago- add ext3 patches to the kernel patch instead of extN directory, and
braam [Sat, 5 Apr 2003 11:15:56 +0000 (11:15 +0000)]
- add ext3 patches to the kernel patch instead of extN directory, and
  associated changes.  This branch will require a small amount of
  debugging, cleanup and some testing before landing.

22 years agoanother segfault fix
nfshp [Fri, 4 Apr 2003 14:57:29 +0000 (14:57 +0000)]
another segfault fix

22 years agoadd iop_gone() to avoid segfault
nfshp [Fri, 4 Apr 2003 14:39:51 +0000 (14:39 +0000)]
add iop_gone() to avoid segfault

22 years agore-organize the layout under liblustre
nfshp [Fri, 4 Apr 2003 14:27:33 +0000 (14:27 +0000)]
re-organize the layout under liblustre

22 years agoadd rudiment I/O support
nfshp [Fri, 4 Apr 2003 10:39:49 +0000 (10:39 +0000)]
add rudiment I/O support

22 years agoinitially add open support. Now it didn't involed ldlm, just simply
nfshp [Thu, 3 Apr 2003 16:48:24 +0000 (16:48 +0000)]
initially add open support. Now it didn't involed ldlm, just simply
create object on mds/ost.

22 years agofix according to changes in b_devel merged last time:
nfshp [Thu, 3 Apr 2003 11:01:13 +0000 (11:01 +0000)]
fix according to changes in b_devel merged last time:
 - inter_module_get
 - generate_random_bytes

22 years ago- patches for 2.4.20: vanilla with UML, chaos, redhat 9, and hp-pnnl
braam [Thu, 3 Apr 2003 07:49:18 +0000 (07:49 +0000)]
- patches for 2.4.20: vanilla with UML, chaos, redhat 9, and hp-pnnl
  ia64

22 years agoupdate patches for 2.4.20. The HP kernel might well work if we are lucky.
braam [Wed, 2 Apr 2003 13:12:21 +0000 (13:12 +0000)]
update patches for 2.4.20.  The HP kernel might well work if we are lucky.
the redhat 2.4.20 kernel is next in line

22 years agob=957
pschwan [Wed, 2 Apr 2003 03:56:24 +0000 (03:56 +0000)]
b=957
- Infrastructure for the pinger thread; needs multi-rpc and some refinements
- Add last_request_time to obd_export

- Fixed export leak in lov_brw success case
- test22 rears its head again: tar gets pissy if it can't access $PWD,
  which is common for homedirs at LLNL.  cd to /tmp before running tar.

Merged many of the changes from b_proto:
- multi-rpc infrastructure, but not the key bits
- removed some bitfield flags in favour of individual struct members
- merged obd_brw_write and obd_brw_read into a single obd_brw_internal
- move the Elan-related page wrangling from the IOD into the OSC

22 years agomerge b_devel into b_cray
nfshp [Tue, 1 Apr 2003 16:21:24 +0000 (16:21 +0000)]
merge b_devel into b_cray

22 years agolanding b_recovery on b_devel
pschwan [Mon, 31 Mar 2003 18:31:23 +0000 (18:31 +0000)]
landing b_recovery on b_devel

* bug fixes
 - imports and exports cleanup too early, need refcounts (349, 879, 1045)
 - per-import/export recovery handling (958, 931, 959)
 - multiple last-rcvd slots, for serving multiple FSes (949)
 - connections are again shared between multiple imp/exports (963, 964)
 - "umount -f" would hang if any requests needed to be sent (393, 978)
 - avoid pinning large req buffer by copying for queued messages (989)
 - add "uuid" to "lctl device" command to help upcalls (991)
 - "open" RPCs with transnos would confuse recovery counters (1037)
* major user-visible changes
 - fail out/fail over policy now controlled by the upcall (993)
* protocol changes
 - add OBD_PING to check server availability and failure (954)

22 years agoAdded mkdir and sys_symlink code. Removed problem of intent_release being
amrutjoshi [Mon, 31 Mar 2003 17:30:21 +0000 (17:30 +0000)]
Added mkdir and sys_symlink code. Removed problem of intent_release being
called twice each time.

22 years ago- correct the llu_iop_lookup() with peter's help
nfshp [Mon, 31 Mar 2003 15:05:47 +0000 (15:05 +0000)]
- correct the llu_iop_lookup() with peter's help
- rename the prefix ll -> llu, avoid duplicated function name with llite

22 years agofirst peice of code glue liblustre with libsysio, and initial small testing
nfshp [Sun, 30 Mar 2003 13:49:14 +0000 (13:49 +0000)]
first peice of code glue liblustre with libsysio, and initial small testing
program

22 years agomodification for liblustre compilation in windows
shorthair [Sat, 29 Mar 2003 14:39:16 +0000 (14:39 +0000)]
modification for liblustre compilation in windows

22 years agouse older 4xslt syntax, for compatibility
rread [Sat, 29 Mar 2003 02:50:00 +0000 (02:50 +0000)]
use older 4xslt syntax, for compatibility

22 years agob=1039
rread [Sat, 29 Mar 2003 02:23:18 +0000 (02:23 +0000)]
b=1039
- ost failover is now an lmc option, and no longer a configure option.
  To enable failover  on an ost,  use the --failover flag when
  when the ost is created with with lmc.

    lmc --add ost ... --failover ...

b=1056
- --journal_size=SIZE lmc option is now available for both ost and mds.
  Note, the size is passed directly to the mkfs program, so you need to make
  sure it is the proper units for the file system being used. (mke2fs expects
  megabyets, mkreiserfs expects blocks)

22 years agob=965
rread [Fri, 28 Mar 2003 07:55:40 +0000 (07:55 +0000)]
b=965
- lconf gets a new option, --recover and will do recovery for a connection on the client

- fix bug reported by Morrone where a client would use the elan nid even
  when it wanted to use tcp. (untested)

- And the bulk of this patch is a consolidation of the command line processing
  for the python tools.  Now all options are displayed in the usage string,
  and includes the defaults if any.  It's also trivial to add new options now.

22 years agob=1035
pschwan [Thu, 27 Mar 2003 22:43:47 +0000 (22:43 +0000)]
b=1035
if ll_inode_getattr fails in ll_extent_lock, don't clobber the 'rc',
because it makes its way all the way back to userspace

22 years agoChecked-in by Peng Zhao.
pengzhao [Tue, 25 Mar 2003 09:00:40 +0000 (09:00 +0000)]
Checked-in by Peng Zhao.

openfile is used to enable scripts opening files with arbitrary combination of
flags and modes.

openfile.c and modified sanity.sh together handle bug894.1

bug894.2 is not handled yet. Need further feedback from Peter.

22 years ago- remove unused ptlrpc_uuid2conn
shaver [Mon, 24 Mar 2003 20:49:14 +0000 (20:49 +0000)]
- remove unused ptlrpc_uuid2conn
- lose extra dlm-hook-put CERROR
- don't need to cleanup DLM ns or schedule when forcing disconnect: it's already
  cleaned up, or we don't get unmounted
- export and import extra-put assertion checking
- fix connection switching to work when we don't already have a connection created

22 years agopc file for Zach's truncate_complete_page() export patch
pschwan [Mon, 24 Mar 2003 17:41:36 +0000 (17:41 +0000)]
pc file for Zach's truncate_complete_page() export patch

22 years agoAdd Zach's patch to export truncate_complete_page(); still needs an
pschwan [Mon, 24 Mar 2003 17:41:08 +0000 (17:41 +0000)]
Add Zach's patch to export truncate_complete_page(); still needs an
hp-pnnl and vanilla equivalent

22 years agoFixed the patch for intent_release. After this fix lock refs are in order now.
amrutjoshi [Mon, 24 Mar 2003 15:52:19 +0000 (15:52 +0000)]
Fixed the patch for intent_release. After this fix lock refs are in order now.
Most of the metadata ops are working.

22 years agounlinkmany a-la createmany and statmany
pschwan [Sat, 22 Mar 2003 20:18:29 +0000 (20:18 +0000)]
unlinkmany a-la createmany and statmany

22 years ago- don't need to unregister the recovd, since it's gone
rread [Fri, 21 Mar 2003 22:57:24 +0000 (22:57 +0000)]
- don't need to unregister the recovd, since it's gone
- class_destroy_import() is doing an import_put, so
  I removed an extra put from class_obd_cleanup().

22 years agoRefreshed patche with intent_release calls
amrutjoshi [Fri, 21 Mar 2003 20:41:58 +0000 (20:41 +0000)]
Refreshed patche with intent_release calls

22 years agoFixing IT_GETATTR intents and many small changes.
amrutjoshi [Fri, 21 Mar 2003 13:28:52 +0000 (13:28 +0000)]
Fixing IT_GETATTR intents and many small changes.

22 years ago- MDS/client open code changes, to open directories on the MDS.
braam [Fri, 21 Mar 2003 03:59:05 +0000 (03:59 +0000)]
- MDS/client open code changes, to open directories on the MDS.
- no more slab validation on the MDS

22 years agoThese are the kernel patches for Peter's open directory fixes. Old
braam [Fri, 21 Mar 2003 03:56:20 +0000 (03:56 +0000)]
These are the kernel patches for Peter's open directory fixes.  Old
code can probably work with this (we'll allow it in through a small
change in obd_class.c)

22 years agoI believe that this will fix the remaining threaded unlink issues, although
adilger [Thu, 20 Mar 2003 11:02:16 +0000 (11:02 +0000)]
I believe that this will fix the remaining threaded unlink issues, although
I wasn't able to get a chance to test it...

Basically, uncomment extN-delete_thread.diff in extN/Makefile.am and give
it a whirl under dbench and/or runtests or whatever, and if it passes we
are golden.

22 years ago- move the xml/ldap handling class from lconf into an external module
rread [Wed, 19 Mar 2003 20:51:37 +0000 (20:51 +0000)]
- move the xml/ldap handling class from lconf into an external module
- load_ldap.sh - loads a lustre xml config into ldap
- lactive - updates failover targets with new active devices

22 years agoPatches for 2.5.63. This wont work until lustre is patched for 2.5.
amrutjoshi [Sat, 15 Mar 2003 16:20:08 +0000 (16:20 +0000)]
Patches for 2.5.63. This wont work until lustre is patched for 2.5.

22 years agoBugzilla 895
thantry [Sat, 15 Mar 2003 02:36:06 +0000 (02:36 +0000)]
Bugzilla 895

22 years agoDelete thread patch. First, tried to "fake out" the VFS by twiddling bits in
adilger [Sat, 15 Mar 2003 01:32:50 +0000 (01:32 +0000)]
Delete thread patch.  First, tried to "fake out" the VFS by twiddling bits in
the inode to keep it around after it should have been destroyed, but no dice.

Then, I tried to allocate a "mock inode" and copy over the existing inode to
that and use it only for the unlink code.  Sadly, copying list_head,
semaphore, etc does not work, so you have to end up re-initializing the whole
thing anyways, and it would just break on 2.5 anyways.

Finally, I did the "right" thing - read the same inode into a new struct
inode with iget(), and then flag that inode for "real" destruction and
have the delete thread just do an iput.  Very simple, very easy.[*]

I also split the orphan list handling out of the superblock lock into
its own lock, so that we don't get stuck behind the delete thread (which
holds it for long periods doing truncates) when we are trying to add new
inodes to the truncate list.

This code passes basic acceptance testing under UML, but I'm not checking
in the Makefile.am changes that activate it until I give it a shot with
dbench 20 or "rm -r directory_full_of_large_files" so on DEV.  Other
people testing it is of course welcome (just add extN-delete_thread.diff
and ext3-orphan_lock.diff to the end of EXTNP).

[*] It reminds me about a story I heard once, where an engineer who had
    retired, but was on retainer for his old company in case they needed
    him for consulting.  Sure enough, the company's complex oil refinery
    was not working properly, and after the company engineers couldn't
    figure out what was wrong they called the retiree for assistance.

    The retiree walked around the refinery, asking questions, looking at
    valves and guages, etc., until finally he asked for a hammer, gave a
    pipe a swift blow, and told them to fire up the plant again.  Sure
    enough, all was working properly again, and the company was happy.

    Until they got the invoice - $25,000.  In an outrage, they called the
    retiree up and asked how he could charge $25,000 for just hitting a
    pipe with a hammer.  In reply, the engineer said "Hitting the pipe
    with the hammer was only $10, the other $24,990 was for knowing where
    to hit it."

22 years agoBackport of bugfix from 2.5/2.4.21-pre5 which calculates the correct value
adilger [Fri, 14 Mar 2003 21:12:07 +0000 (21:12 +0000)]
Backport of bugfix from 2.5/2.4.21-pre5 which calculates the correct value
for the number of blocks to reserve for a truncate.  We were asking for 8x
as many blocks as we needed, although for large files this was capped at
EXT3_MAX_TRANS_BLOCKS anyways, so not much harm done.

Conditionally applied so when it appears in our upstream kernels we will
not die (when I commit corresponding changes to Makefile.am).

22 years ago- b=959: add connection-switching to import recovery. (Not yet tested: one of
shaver [Wed, 12 Mar 2003 12:51:15 +0000 (12:51 +0000)]
- b=959: add connection-switching to import recovery. (Not yet tested: one of
  my MDS nodes isn't coming up right now.)

22 years agoScript to grab asm output and look for heavy stack (ab)users.
adilger [Wed, 12 Mar 2003 00:58:12 +0000 (00:58 +0000)]
Script to grab asm output and look for heavy stack (ab)users.
Could be improved a bit by having it take a list of files as args and
running objdump and then preceding each line with the filename, so we can
run it on modules more easily than having a shell script call a perl script...

22 years agoadd a extra param to mmap unless it always return error.
nfshp [Tue, 11 Mar 2003 14:45:06 +0000 (14:45 +0000)]
add a extra param to mmap unless it always return error.

22 years agoBug 828 is fixed by Peng Zhao, arrpoved by Andreas.
pengzhao [Tue, 11 Mar 2003 07:17:08 +0000 (07:17 +0000)]
Bug 828 is fixed by Peng Zhao, arrpoved by Andreas.
runas.c allows the root to "runas" another user to do things.

22 years agoRemove liblustre-build-breaking l_wait_event define, and get rid of wait_event
shaver [Mon, 10 Mar 2003 07:22:15 +0000 (07:22 +0000)]
Remove liblustre-build-breaking l_wait_event define, and get rid of wait_event
while I'm at it.

22 years ago- b=977: C-z (and other non-fatal signals) send us into an infinite loop if
shaver [Sun, 9 Mar 2003 21:01:41 +0000 (21:01 +0000)]
- b=977: C-z (and other non-fatal signals) send us into an infinite loop if
         we wait for recovery.  We now use signal blocking to prevent signal
         delivery until we're interested in some or all signals.

- b=988: umount -f hangs when MDS is dead

- b=722: Lustre kernel threads cause load average to skyrocket. (Still get
         a little boost from the socknal threads, but it's much better.)

22 years agooops, fix my last checkin.
nfshp [Sun, 9 Mar 2003 07:56:20 +0000 (07:56 +0000)]
oops, fix my last checkin.

22 years agofix IS_ERR macro: return 0/NULL is sign of success.
nfshp [Sun, 9 Mar 2003 07:53:03 +0000 (07:53 +0000)]
fix IS_ERR macro: return 0/NULL is sign of success.

22 years agoCompletely untested (but compiled) port of noread-creates patch to
adilger [Sat, 8 Mar 2003 15:59:30 +0000 (15:59 +0000)]
Completely untested (but compiled) port of noread-creates patch to
2.5.current.  I suspect it is OK, since the ext3 code hasn't changed much,
but needs testing.

22 years ago- Remove the now-unnecessary connection chaining bits from imports and exports.
shaver [Sat, 8 Mar 2003 02:09:49 +0000 (02:09 +0000)]
- Remove the now-unnecessary connection chaining bits from imports and exports.

- In related news, always drop the exports' and imports' connection refs when
  they're destroyed.

- class_connect was leaking its "caller" (compare: "handle lifetime") ref to
  the new export.  We're going to try without the leak for a while, see how
  it goes.

- Bulk descs now have import and export pointers, so that they can play nicely
  with recovery.

- Clean, informative console diagnostics for recovery cases.  (Hi, Terry!)

- Do the ldlm-hook i_m_g/i_m_p based on emptiness of the conn_list, since it's
  far too late by the time the __exit routines run.

- Put an ugly-but-serviceable UUID in the server's connection's remote_uuid.

- Remember that we can already have an export in req->rq_export upon entry to
  target_handle_connect, if the client and server are the same node, and
  therefore share a handle table.

- Get rid of class_signal_connection_failure, which was vestigial at best.

- Welcome back to the world of connection-sharing.

- Call the upcall like:
  /path/to/upcall $FAILED_IMPORT_UUID $FAILED_OBD_UUID $CONN_UUID

22 years ago- b=958: recovery per export/import, not per connection
shaver [Fri, 7 Mar 2003 20:16:05 +0000 (20:16 +0000)]
- b=958: recovery per export/import, not per connection
  - no more recovd thread:
    - import failure and upcall-execution is done by the failing thread
    - export failure and client eviction is done by the thread that's going
      to be waiting for it to complete anyway
    - import reconnection runs synchronously in the context of the lctl
      invocation, which means that we can now return errors to the upcall
  - no more fancy recovery state machine
  - no more RPCDEV service

- b=954: zero-impact OBD_PING opcode for MDS and OST

- Grand Unified Theory of Client Recovery
  - mdc_recover/osc_recovery unified in ptlrpc_recover_import

22 years agomoved procbridge.h to include/portals
rread [Tue, 4 Mar 2003 21:42:30 +0000 (21:42 +0000)]
moved procbridge.h to include/portals