LU-10177 lfs: support DOM-to-OST migration

Migraton of DoM file to an OST file is possible with
'lfs migrate' command in general but would cause space loss
on MDS, because DOM local inode blocks are not deleted.
Patch doesn the following:
- adds truncate for local MDS inode after migration.
- check and prevent migration from non-DOM to DOM file,
  that will be done later with mirroring.
- prohibit 'lfs swap_layouts' command if either file has
  DOM component, 'lfs migrate' should be used instead

Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I1ce7b09eefab5e13f81af30c007475c927bd2874
Reviewed-on: https://review.whamcloud.com/32979
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11128 ptlrpc: new request vs disconnect race

new request can race with disconnect-by-idle process.
disconnect code detect this state and initiate a new connection.

Change-Id: I6acc913c371f2ae63f27151edce457c2a13118c5
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/32980
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11373 libcfs: fix wrong check in libcfs_debug_vmsg2()

Logic here is we skip output if time is before @cdls_next
reach and increase @cdls_count. however we did it in the
opposite way:

1)libcfs_debug_vmsg2() is called for a long time, that means
current check succeed, we skip print messages and return, we
will skip all messages later too..

2)libcfs_debug_vmsg2() is called frequently, current check
fail every time, message will be bumped out always. the
worst case is we never skip any messages.

Also fix test case to cover this later which is from Andreas:

The test_60a() llog test is being run on the MGS, while the
check in test_60b() to confirm that CDEBUG_LIMIT() works properly
is being run on the client.  There has been a breakage in
CDEBUG_LIMIT() that this test failed to catch, now we need to
track it down.

Change test_60b to dump the dmesg logs on the MGS.

Fixes: fdb5d3d50
Test-parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Change-Id: Idb2ecfe5ddadc72d8931e6623b171b9c773ebbe5
Reviewed-on: https://review.whamcloud.com/33154
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-11071 build: create lustre resource package for Ubuntu

The new Ubuntu server support is missing on last package that RHEL
currently supports. Enable Debian/Ubuntu packaging for the resource
agent package.

Test-Parameters: trivial

Change-Id: I872ae6b1b02782155db14c5cc971607ca3e93d56
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/33152
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Nathaniel Clark <nclark@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11268 mdc: use smaller buffers for getxattr

In mdc_intent_getxattr_pack() only the xattr values buffer should be
upsized for older MDTs. This refines the interop fix from change
https://review.whamcloud.com/31990 (LU-10912 mdc: use large xattr
buffers for old servers).

Signed-off-by: John L. Hammond <jhammond@whamcloud.com>
Change-Id: If7c6fe7be96a6a227c746f90757b7aae1874b14e
Reviewed-on: https://review.whamcloud.com/33024
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 llite: remove redundant lookup in dump_pgcache

Both the 'next' and the 'show' functions for the dump_page_cache
seqfile perform a lookup based on the current file index.  This is
needless duplication.

The reason appears to be that the state that needs to be communicated
from "next" to "show" is two pointers, but seq_file only provides for
a single pointer to be returned from next and passed to show.

So make use of the new 'seq_private' structure to store the extra
pointer.
So when 'next' (or 'start') find something, it returns the page and
stores the clob in the private area.
'show' accepts the page as an argument, and finds the clob where it
was stored.

Linux-commit: 85b6542bbade42935386661cb45d90c4e13766b7

Test-Parameters: trivial envdefinitions="ONLY=63b" testlist=sanity
Test-Parameters: trivial envdefinitions="ONLY=118" testlist=sanity
Test-Parameters: trivial envdefinitions="ONLY=20" testlist=sanityn

Change-Id: I6a45430f7ba3007dcd70bdf09c4c7ed5a213533d
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/33010
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11237 build: delete obsolete slapd-lustre.conf

Delete the obsolete slapd-lustre.conf file, as it was only used
for LDAP configuration of clients and servers back before
"zero-conf" (MGS+llog) configuration was available.  Also remove
the use of openldap in Makefile.am.

This has been obsolete since Lustre 1.4 or so.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: If99ca0a62a1753ead1b29d217bc2437bd29e0850
Reviewed-on: https://review.whamcloud.com/32989
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11169 obdclass: fix old return code usage

Commit 49d8a7ccd73 from LU-9855 introduce a fail in the
obd_commitrw function which parent error code
replaced with result of exp_check_ops function.

Cray-bugid: LUS-6195

Test-Parameters: trivial
Change-Id: If8643ba39232f94ba9c523fdb9f10c1411a1838a
Signed-off-by: Alexey Lyashkov <c17817@cray.com>
Reviewed-on: https://review.whamcloud.com/32906
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11020 osd: use right sync

use a sync_fs instead of journal flush only.
ext4 commit with similar change

commit 06a407f13daf9e48f0ef7189c7e54082b53940c7
Author: Dmitry Monakhov <dmonakhov@openvz.org>
Date:   Wed Jun 12 22:25:07 2013 -0400

ext4: fix data integrity for ext4_sync_fs

Inode's data or non journaled quota may be written w/o jounral so we
 _must_ send a barrier at the end of ext4_sync_fs. But it can be
skipped if journal commit will do it for us.

Cray-bug-id: LUS-5993
Signed-off-by: Alexey Lyashkov <c17817@cray.com>
Change-Id: Ie242b48d0b8ad61cf4d38ac0fb173176193716d9
Reviewed-on: https://review.whamcloud.com/32866
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 ofd: migrate from proc to sysfs

Move the ofd module from using proc for most single value files
to sysfs. Leave the more complex proc entries for now. Migrate
the sysfs and most of the proc handling to lproc_ofd.c.

Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Change-Id: Ief21636a0dce3fd4946f9a6971a8b09c2812200e
Reviewed-on: https://review.whamcloud.com/33059
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6864 mdc: move RPC semaphore code to lustre/osp

The "MDC RPC semaphore" is no longer used by MDC code since patch
http://review.whamcloud.com/14374 "LU-5319 mdc: manage number of
modify RPCs in flight" landed.  It is only still used by the OSP
currently.  While there are plans to remove this from the OSP as
well, it makes sense to move all of this code from MDC to OSP so
that it will also be cleaned up when that functionality lands.

Signed-off-by: Andreas Dilger <andreas.dilger@intel.com>
Change-Id: I1c4c9a45f308a29600631ac7fed40e592b3ebbe5
Reviewed-on: https://review.whamcloud.com/32412
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8130 ptlrpc: convert conn_hash to rhashtable

Linux has a resizeable hashtable implementation in lib,
so we should use that instead of having one in libcfs.

This patch converts the ptlrpc conn_hash to use rhashtable.
In the process we gain lockless lookup.

As connections are never deleted until the hash table is destroyed,
there is no need to count the reference in the hash table.  There
is also no need to enable automatic_shrinking.

Linux-commit: ac2370ac2bc5215daf78546cd8d925510065bb7f

Change-Id: I576daf314c3ac31a58df02d731292e1e8bb408c6
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/32036
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-4684 lmv: support accessing migrating directory

Migrating directory contains stripes of both old and new layout, and
its sub files may be located on either one. To avoid race between
access and new creations, there are 4 rules to access migrating
directory:
1. always create new file under new layout.
2. any operation that tries to create new file under old layout will
   be rejected, e.g., 'mv a <migrating_dir>/b', if b exists and is
   under old layout, this rename should fail with -EBUSY.
3. operations that access file by name should try old layout first,
   if file doesn't exist, then it will retry new layout, such
   operations include: lookup, getattr_name, unlink, open-by-name,
   link, rename.
4. according to rule 1, open(O_CREAT | O_EXCL) and create() will
   create new file under new layout, but they should check existing
   file in one transaction, however this can't be done for old
   layout, so check existing file under old layout on client side,
   then issue the open/create request to new layout.

Disable sanity 230d for ZFS backend because it will trigger lots of
sync, which may cause system hung.

Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Icd587eb17f4c6dc2234dcc3c7ba40759bc3e8d31
Reviewed-on: https://review.whamcloud.com/31504
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-5026 obdclass: Add lbug_on_eviction option

Add an lbug_on_eviction sysfs interface.  When it is set to a non-zero
value on a client, it will cause the client to LBUG whenever it is
evicted by the server. Note, an MDS is a client to OSTs, and every
server is a client of MGS. Thus, it is probably desireable to leave
this set to zero on servers.

Change-Id: I2f694e4bc1b1ec9daf52f8a6ac46ad87f40f810f
Cray-bug-id: LUS-2591
Signed-off-by: Ryan Haasken <haasken@cray.com>
Signed-off-by: Chris Horn <hornc@cray.com>
Reviewed-on: https://review.whamcloud.com/10257
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Alexandr Boyko <c17825@cray.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11329 utils: add get_maintainer.pl script

The get_maintainer.pl script can be given a patch file or list of
pathnames and will look at the MAINTAINERS file for different code
subsections and the developers that are maintaining those sections.
If no maintainer is found, it will also check the git commit history
and "git blame" to see which developers were active on the specified
file(s) and use them.

This patch adds a copy of the get_maintainers.pl and MAINTAINERS files
to the Lustre tree to make it easier to find reviewers for the code.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I5f2e717227a7c86c924e7edb889e087c7c3ebbe5
Reviewed-on: https://review.whamcloud.com/33104
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11128 ptlrpc: add debugging for idle connections

Add a "debug" parameter for the idle client disconnection so that
it can log disconnect/reconnect events to the console.

Print the idle time in the "import" file.

Enable the connection debugging for all test runs.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I47a4f73542fb4864e4f35275ecfe8907493ebbe5
Reviewed-on: https://review.whamcloud.com/33168
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Nathaniel Clark <nclark@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11301 target: add lock in sub_trans_stop_cb()

sub_trans st_committed and st_stopped flags take different bit of
the same memory address, so both of them should be set with lock,
but sub_trans_stop_cb() doesn't, which may cause it overriden.

Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Ic3d7d7281b3cf9bd20702be944e14f35200318f1
Reviewed-on: https://review.whamcloud.com/33169
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11372 o2iblnd: add clarifying comment to ko2iblnd.conf

The settings in ko2iblnd.conf are recommended only for
OPA but if other IB cards are present along with
OPA, then these settings are applied across all the
configured IB interfaces.

Change-Id: I6daf1f59a100db4e9c2cd12c255ad33fda274093
Test-Parameters: trivial
Signed-off-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/33163
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Amir Shehata <ashehata@whamcloud.com>
Reviewed-by: Doug Oucharek <dougso@me.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11071 ldiskfs: fix ldiskfs patch for ubuntu18

the original ext4-corrupted-inode-block-bitmaps-handling-patches.patch
missed the changes to ext4_validate_inode_bitmap, add it back

Test-Parameters: trivial
Signed-off-by: Li Dongyang <dongyangli@ddn.com>
Change-Id: I42ff97be5c5680be04d69e0e818b622df6bd400d
Reviewed-on: https://review.whamcloud.com/33144
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10899 obdclass: remove unused ll_import_cachep

The ll_import_cache is not used anywhere, and can be removed.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I3f43c81ffbf1385117f9ba1f8f9881388a3ebbe5
Reviewed-on: https://review.whamcloud.com/33119
Tested-by: Jenkins
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11303 out: clean up osp_update_rpc_pack() macro

The osp_update_rpc_pack() macro was using both an operation "name"
argument as well as an "opcode" argument, but totally ignoring the
"opcode" argument.  This allowed a caller in osp_attr_set() to pass
a non-existent opcode name to the function that was ignored.

The function also concatenated the passed name string to generate
a function name to be called (which supplied its own opcode value).
This name concatenation obscures the code functionality, since the
called functions are not actually referenced directly in the code.

Instead, pass the function name as the argument, and drop the opcode
completely.  This at least makes it possible to see where the function
is being called.  Change the macro to be upper-case, so that it is
more clear that it is a macro rather than a real function.  It would
be better to replace the macro with an actual function, but this is
not very practical due to the use of variable-length argument lists.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I7bf5c1d0f7a9abab1d8de8046cc408961f3ebbe5
Reviewed-on: https://review.whamcloud.com/33107
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 llite: use more private data in dump_pgcache

The dump_page_cache debugfs file allocates and frees an 'env' in each
call to vvp_pgcache_start,next,show.  This is likely to be fast, but
does introduce the need to check for errors.

It is reasonable to allocate a single 'env' when the file is opened,
and use that throughout.

So create 'seq_private' structure which stores the sbi, env, and
refcheck, and attach this to the seqfile.

Then use it throughout instead of allocating 'env' repeatedly.

Linux-commit: fc5f499af16c247c5bff68d2625a6d1ca48b3332

Test-Parameters: trivial envdefinitions="ONLY=63b" testlist=sanity
Test-Parameters: trivial envdefinitions="ONLY=118" testlist=sanity
Test-Parameters: trivial envdefinitions="ONLY=20" testlist=sanityn

Change-Id: Id7e7f5ec1729d1e5af041adcb247ca11299ed734
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/33009
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11133 dkms: Add missing ldiskfs module in dkms config

The dkms.conf file generated by the script dkms.mkconf does not
include the ldiskfs kernel module. This results in not being able to
use ldiskfs when using the lustre-ldiskfs-dkms or lustre-all-dkms
packages.
This patch adds the module in the configuration for both of these
packages.

Test-Parameters: trivial
Signed-off-by: Sebastien Piechurski <sebastien.piechurski@atos.net>
Change-Id: Icc98fba208c78c3061fe591e3315af1eb9199f4f
Reviewed-on: https://review.whamcloud.com/32800
Reviewed-by: Nathaniel Clark <nclark@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 llite: move /proc/fs/lustre/llite/statahead_{max, agl} to sysfs

Move statahead_max and statahead_agl files from /proc/fs/lustre/llite/*
to /sys/fs/lustre/llite/*/

This is a modified version of

Linux-commit: 4081a3201ade8b3be715ebb0b7879a2bfe5fcc98

due to the large amount of changes to the OpenSFS/Intel branch.

Change-Id: Ic16d48d0cf1baabb462952de9739544923eba8cd
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/32504
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 llite: move /proc/fs/lustre/llite/stats_track* to
 sysfs

Move stats_track_pid, stats_track_ppid and stats_track_gid files
from /proc/fs/lustre/llite/* to /sys/fs/lustre/llite/*/

This is a modified version of

Linux-commit: 62cf4b1315e86a1f373f77acf32a23d76428ba27

due to the large amount of changes to the OpenSFS/Intel branch.

Test-Parameters: trivial

Change-Id: I29dc2dd269f66e40a7d016ba366353ae2ca7fb51
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/32503
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10124 lnet: Correctly add peer MR value while importing

while adding peer using lnetctl import, the MR value of the
peer is not correctly imported.

Checks for MR value other than True/False in
handle_yaml_config_peer() -
1. No value provided - Use default as True
2. Value other than True/False - Error out

Change-Id: I02a21e35086f1c6f29081b464dd1a63aba692cbc
Test-Parameters: trivial
Signed-off-by: Sonia Sharma <sonia.sharma@intel.com>
Reviewed-on: https://review.whamcloud.com/31138
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Amir Shehata <ashehata@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-4684 migrate: shrink dir layout after migration

Use setxattr(XATTR_NAME_LMV) to shrink dir layout after migration,
this may change dir fid because it may shrink dir to 1-stripe, if so
replace this dir with its stripe.

Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I4fd3e83e188ac0c6c4845183c17701276fae94a8
Reviewed-on: https://review.whamcloud.com/31626
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-4684 migrate: migrate striped directory

Migrate striped directory in below steps:
1. create target object if needed: if source is directory, a
   target object is always created, otherwise if source is
   already located on the target MDT, or source still has
   link on source MDT, then skip creating.
a) if source is directory, detach source stripes and
   attach them to target.
b) migrate source xattrs to target.
c) if source is regular file, update PFID to target
   fid.
d) update fid to target for all links of source
2. update namespace
a) migrate dirent from source parent to target parent.
b) update linkea parent fid to target parent.
c) destroy source object.

This implementation improves following fields:
1. all involved objects are locked to avoid race.
2. directory migration doesn't migrate its dir entries, instead
   it's done in each sub file migration, this avoids timeout in
   migrating dir entries for large directory, and also avoids
   touching dir entries without lock.
3. file/dir is migrated in one transaction, so migrate recovery
   is the same as others.
4. migrating directory can be accessed (modifiable) like normal
   directory.
5. if migration of sub files under a directory fails, user can
   redo migrate to finish migration of this directory.

Disable migrate in racer.sh.

Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I7906e50a0bf55375eafdf2cf5500979dd2d94d48
Reviewed-on: https://review.whamcloud.com/31427
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11016 obdclass: change JobID error into warning

Change the "jobid value too large" message from a console error into a
warning, since it doesn't really indicate incorrect Lustre behaviour.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ibde3b686061fc7b4daa48dae5623e60ad157e5c8
Reviewed-on: https://review.whamcloud.com/33128
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11349 tests: remove insanity test 15

Test 15 of the insanity test suite has not been used
in testing since 2003 and tries to run a script that no
longer exists. Thus, this test needs to be removed.

At the same time, clean up the script in converting
spaces to tabs.

Test-Parameters: trivial testlist=insanity
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: Ie3b2f88dde925d7a1c53f288215b3643d20fd5ff
Reviewed-on: https://review.whamcloud.com/33121
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11281 ptlrpc: race in AT early reply

In ptlrpc_at_check_timed, the refcount of the request could
be already dropped to zero, the ptlrpc_server_drop_request
could continue without the "scp_at_lock" and free the request
by writing 0x5a5a5a5a5a5a5a5a to the memory, but the following
"atomic_inc_not_zero(&rq->rq_refcount)" will return nonzero and
cause freed request to be used in ptlrpc_at_send_early_reply.

Change-Id: I5d884be86de007f49b044e022ad90663b08078d7
Signed-off-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/33071
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11010 tests: remove calls to return after skip()

The skip routine now contains a call to exit. All calls
to skip() and skip_env() should be reviewed and calls to
return() that follow skip() should be removed.

This is the third patch in a series that removes calls
to return() after skip() in the Lustre test suites.

Calls to return after skip() are removed for:
large-lun.sh
large-scale.sh
lfsck-performance.sh
lnet-selftest.sh
lustre-rsync-test.sh
mds-survey.sh
metadata-updates.sh

Test-Parameters: trivial testlist=large-lun,large-scale,lfsck-performance,lnet-selftest,lustre-rsync-test,mds-survey,metadata-updates

Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: Id11dc4bbde5824976a5a4d8f94ea59efd45e46f4
Reviewed-on: https://review.whamcloud.com/32732
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11165 llite: set iflags and catch error from md_setattr() properly

As John Hammond pointed out:
In ll_ioctl_fssetxattr() we may discard errors from md_setattr().
And we only set the local i_flags when lli_clob is not NULL.

This patch tried to address above problems.

Test-Parameters: trivial testlist=sanity-quota
Change-Id: Ib65ec61932b00f71367a8da6be67e3f94ebd5005
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/32860
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-9268 tests: check obj distribution for PFL striping

Add test to sanity-pfl to verfy that new components are
distributed evenly among OSTs for composite files.

Test-Parameters: trivial osscount=3 ostcount=4 testlist=sanity-pfl
Signed-off-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Signed-off-by: James Nunez <james.a.nunez@intel.com>
Change-Id: I0335fd376f6008529885236faad19a29eb01d5ba
Reviewed-on: https://review.whamcloud.com/26863
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10660 mdt: revoke lease lock for truncate

Lustre lease lock is usually used to protect file data
against concurrent access. Open lock used on MDT side
is for this purpose. However, truncate will change
file data but it doesn't revoke lease lock.

This patch fixes the issue by acquiring open sem,
checking lease count and revoking lease if there exists
any pending lease on the file.

Change-Id: Ia55457c6d7e1e76f98b41feef39577822304513b
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/33093
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

New tag 2.11.55

Change-Id: I08a290fd7cd909cf24405daf412fe9a0dd4a8757
Signed-off-by: Oleg Drokin <green@whamcloud.com>

Revert "LU-11057 tests: exercise 'network' client mount option"

This is causing 100% failures in review-dne-zfs-part-2
which are tracked in LU-11363

This reverts commit 76af9f62481b1ac910cd6a0f7237fe32b0657c29.

Change-Id: Ie82f848ce1f170b2c93f106c5886deadf7b4df75
Reviewed-on: https://review.whamcloud.com/33139
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: Oleg Drokin <green@whamcloud.com>

LU-10447 build: fix checkpatch.pl to not mangle case

Fix the checkpatch.pl script to not mangle the case of the lines
in the spelling.txt file, so that the replacement text can be
found, and is shown as intended.

Add checks for "GETSTRIPE" and "SETSTRIPE" to spelling.txt.

Sort the spelling.txt file so that it is easier to see what lines
are present in the file.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Id3a3319bc62898fbdc94573512cd6a665b13cd11
Reviewed-on: https://review.whamcloud.com/32865
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 llite: move /proc/fs/lustre/llite/checksum_pages to sysfs

Move checksum_pages file from /proc/fs/lustre/llite/*
to /sys/fs/lustre/llite/*/

This is a modified version of

Linux-commit: 40cc864a9fcd48d7f3a67421a8e578e8d4cbe308

due to the large amount of changes to the OpenSFS/Intel branch.

Change-Id: Ice48c69503680ac995b60844a8d0d7ae2bddd102
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/32502
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-11012 doc: improve the lfs-setstripe.1 man page

Restructure the lfs-setstripe.1 man page to be more like a standard
man page.  The DESCRIPTION section provides a high-level overview of
the command, and describes the various different ways that it can be
used.  The various options are described in the STRIPE_OPTIONS and
COMPONENT_OPTIONS sections.

Describe how default layouts are inherited for plain and composite
files, and that different pools can be specified for each component.

Add description of the --copy option.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I7ba3f3f4dba6825f283dd6874ae1988914c774fb
Reviewed-on: https://review.whamcloud.com/32463
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Joseph Gmitter <jgmitter@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11309 lnd: Clean up logging

No need to output error in ksocknal_tx_done() as this error is
tracked in lnet.
No need to keep a cookie in the connection. It's always set to
the message. This will allow us to set the msg's health status
properly before calling lnet_finalize()

Test-Parameters: trivial
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I168c8ca32192ba4f8f4480e8e7384d45f0a062a7
Reviewed-on: https://review.whamcloud.com/33096
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Doug Oucharek <dougso@me.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11283 lnet: fix setting health value manually

Changed the health value option letter to 't' instead
of 'h' to avoid conflict with help option.
Don't increment optind unnecessarily.
In the handling code in api-ni.c there was a missing return.

Test-Parameters: trivial
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: Ib56f19d1781e44297158c64c5b26004220a1db21
Reviewed-on: https://review.whamcloud.com/33074
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: Doug Oucharek <dougso@me.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11245 flr: lfs mirror dump command

Adds "lfs mirror dump" command to dump a mirror's content of a
mirrored file.

Usage:

lfs mirror dump <-N|--mirror-id <mirror_id>>
[-o|--outfile <output_file> ] <mirrored_file>

Options:

--mirror-id <mirror_id>
  Specify the mirror by mirror_id to dump its content.
--outfile <output_file>
  Dump the content into file output_file, if not specified, the
  content will be dump to the standard output stream.

Test-Parameters: testlist=sanity-flr
Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: I2846b1c1968d9cc302c07b57a05687af50530d53
Reviewed-on: https://review.whamcloud.com/32997
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11057 tests: exercise 'network' client mount option

Test 'network' client mount option that enables to limit connections
from the client to be on the network NID specified.

This option is currently not compatible with Dynamic Peer Discovery.
test_31 will have to be updated once Dynamic Peer Discovery is
modified so that it does not conflict with 'network' client mount
option.

Test-Parameters: trivial testlist=sanity-sec
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I4631a034137a346d0bb4efed20983e2a8bd7b0ec
Reviewed-on: https://review.whamcloud.com/32590
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Amir Shehata <ashehata@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10961 ldlm: don't cancel DoM locks before replay

Weigh a DOM locks before lock replay like that is done
for OSC EXTENT locks and don't cancel locks with data.

Add DoM replay tests for file creation and write cases.

Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: If706835455c2b25c01cfcde033fccc4f3c67ee24
Reviewed-on: https://review.whamcloud.com/32791
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11270 mdt: better DOM data discard

Discard DOM data when all object are put and unlocked.
So current thread will wait for discard but resources are
not blocked by it. Also cancel discard lock immediately.

Patch also add missing part for lock prolongation for DoM
locks and fix for tgt_blocking_ast() to don't miss a call to
ldlm_server_blocking_ast() in case of lu_env_init() failure.

Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I09aaa08e28d2a280ca1f9939315311c45d0334b5
Reviewed-on: https://review.whamcloud.com/33026
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-9855 include: replace OBD_CHECK_DEV by obd_check_dev

Static inline functions are preferred over macros. Hence, the function
obd_check_dev was introduced. obd_check_dev replaces the macro
OBD_CHECK_DEV. All functions that call obd_check_dev store the return
values and return them if they represent an error code.

Some of the changes were carried out manually while others were done
using coccinelle.

Linux-commit: 4ca1b8fbe609b7c52aeaa78a5f4678efcc9b8d73

Test-Parameters: trivial

Signed-off-by: Aya Mahfouz <mahfouz.saif.elyazal@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Change-Id: Iad96cc151a711892d950bd2ccaa93b13d6b23ae5
Reviewed-on: https://review.whamcloud.com/33101
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Ben Evans <bevans@cray.com>

LU-11328 ldlm: fix compile problem with --disable-lru-size

add the missing type change for ldlm_pool_recalc.

Test-Parameters: trivial
Signed-off-by: Li Dongyang <dongyangli@ddn.com>
Change-Id: I5b96dbe79e9b202888cf0f23a947c2d6c0f0d8d8
Reviewed-on: https://review.whamcloud.com/33103
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-10740 tests: disable tests for replay-dne-zfs-part-4

Disable a few tests, by adding them to the ALWAYS_EXCEPT list,
that are constantly failing for replay-single so that
review-dne-zfs-part-4 might normally pass.

A potential fix for replay-ost-single test_6 and test_7 to calculate
the log size for DNE+ZFS systems more accurately for multiple MDTs.

Test-Parameters: trivial testgroup=review-dne-zfs-part-4
Test-Parameters: trivial testgroup=review-dne-zfs-part-3
Test-Parameters: testlist=sanity-sec
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: I2316baeacbb18686d2958265f7128e95033ebbe5
Reviewed-on: https://review.whamcloud.com/33106
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11304 misc: update all url links to whamcloud

Even old links could redirect to whamcloud automatically,
We'd better update to use new whamcloud links to
avoid any further confusions.

Test-parameters: trivial
Change-Id: Ida7161a062d822141bf0c1fdf20b2098a21ea9e7
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/33094
Reviewed-by: Peter Jones <pjones@whamcloud.com>
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-11279 lod: reset ostlist properly in lod_get_default_lov_striping

Ostlist might be allocated previously, and we should
reset them properly, otherwise, it will pollute new
default setting and cause unexpected behavior.

Test-Parameters: trivial testlist=sanity,sanity,sanity,sanity,sanity,sanity,sanity,sanity,sanity
Change-Id: I9b7acb5f05ec4b371da99f68b9647f0b75cd7021
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/33069
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11006 lnet: fix show peer yaml tree with no peer

When no peer exists then the root created for the peer
yaml tree should be deleted. And lnetctl show peer
should not display anything.

Currently lnetctl peer show shows the root string "peer"
even when there is no peer. This create issues when
starting lnet using /etc/lnet.conf derived from the
existing configuration.

Change-Id: Ie310a49e60386b579b48898b032467b1bc112da9
Test-Parameters: trivial
Signed-off-by: Sonia Sharma <sonia.sharma@intel.com>
Reviewed-on: https://review.whamcloud.com/32320
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Amir Shehata <ashehata@whamcloud.com>
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8130 libcfs: prepare rhashtable support

Linux has a resizeable hashtable implementation in lib,
so we should use that instead of having one in libcfs.
In the process we gain lockless lookup which should be
a performance boost. All modern distributions Lustre
support has rhashtable support but a few pieces are
missing for systems running a 4.4 kernel. The other
target platforms have the full implementation we need.

Test-Parameters: trivial

Change-Id: I63d5b7dae9d52eed12dbefed8ca6062af33efd30
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/32102
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

LU-10654 lnet: lnetctl doesn't error out on mistyped options

Running lnetctl command to add/delete peer/net/route should
error out with mistyped options.

This patch add the changes in lnetctl.c to make lnetctl
error out withmistyped options.

Change-Id: Ib8ae54bea919d6ff235b4ca3a23807a809f8962c
Test-Parameters: trivial
Signed-off-by: Sonia Sharma <sonia.sharma@intel.com>
Reviewed-on: https://review.whamcloud.com/31265
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: Amir Shehata <ashehata@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11273 lnet: update logging

Add the retry count when logging message sending/resending.
Make timed out responses visible on net error.
Log cases when a message is not resent

Test-Parameters: trivial
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I0908d495c8ba54754fa77b0fc3b5df59317bb2e8
Reviewed-on: https://review.whamcloud.com/33044
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Doug Oucharek <dougso@me.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11195 lod: Mark comps cached on replay of layout change

Replay of a layout change request on a PFL file leaves the object
in an unexpected state: Some components can have llc_stripe set
but ldo_comp_cached is not set in the object. The next layout
change request on the same object will LBUG when it tries to free
the comp entries.

The fix is to set ldo_comp_cached on replay so subsequent layout
change requests will use the in memory components rather than
fetching them from disk.

Signed-off-by: Ann Koehler <amk@cray.com>
Change-Id: I8eaee5614c7f2f6e6a3f2c51de93a65422a3122b
Reviewed-on: https://review.whamcloud.com/32904
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10818 obdecho: don't set ma_need in echo_attr_get_complex()

echo_attr_get_complex() copies ma_need to a local variable, masks
MA_* values other than MA_INODE if MA_INODE is set in ma_need,
and restores the saved value of ma_need before the function exits.
This does not seem to be useful, and triggers an assertion in
echo_big_lmm_get() when MA_LOV and/or MA_LMV is set in ma_need.

Signed-off-by: Nikitas Angelinas <nangelinas@cray.com>
Cray-bug-id: LUS-6252
Reviewed-by: Patrick Farrell <paf@cray.com>
Reviewed-by: Andrew Perepechko <c17827@cray.com>
Change-Id: I3f5a01b57bdd83937f19fd1fa392b53f7b316455
Reviewed-on: https://review.whamcloud.com/33097
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11057 obd: check '-o network' and peer discovery conflict

"-o network=net" client mount option is not taken into account
when LNet dynamic peer discovery is active.
Check if LNet dynamic peer discovery is active on local node. If it
is, return error if "-o network=net" option is specified.

This patch will have to be reverted when the incompatibility between
"-o network=net" client mount option and LNet dynamic peer discovery
is resolved.

Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I0520e58b22b7adecf797fbd351506c2f8712dc85
Reviewed-on: https://review.whamcloud.com/32562
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Amir Shehata <ashehata@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11272 lnet: router handling

Re-create the md and mdh if the router checker ping times out.
When re-transmitting a message do so even if the peer is marked down
to fulfill the message's retry quota.

Test-Parameters: trivial
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I7b2a1ec6602dac9a112f4d318b0512f68f923969
Reviewed-on: https://review.whamcloud.com/33043
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11271 lnd: conditionally set health status

For specific error scenarios a more accurate health status is set
per transmit. These shouldn't be overwritten in
kiblnd_txlist_done()

Test-Parameters: trivial
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I6c3ad6660aa654d32e823b29ebe3aedb9fc5508e
Reviewed-on: https://review.whamcloud.com/33042
Tested-by: Jenkins
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11275 llite: check truncate race for DOM pages

In ll_dom_finish_open() check vmpage mapping still
exists after locking and exit otherwise. This can
happen if page has been truncated concurrently.

Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: Ib6ef551673a40ad99baaa9bd620225c65ce34454
Reviewed-on: https://review.whamcloud.com/33087
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

LU-11282 osd-zfs: drop cache immediately

if this is requested via:
  lctl set_param osd-zfs.*.readcache_max_filesize=<bytes>

dropping cache at read is almost free, but may take few
cycles at write as we have to find corresponding dbufs.

Change-Id: I107fc1bf5a8d7655da4054048ff07d3dffa9d4d8
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/33072
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-9855 obdclass: simplify md_stats code

The md_stats code is layered in many levels of macros that make
the code difficult to read as well as introduce undetected
errors. This peels away the macro wrappers by replacing it with
the function lprocfs_exp_count_increment() which doesn't care
about the order of the function pointers in struct md_ops. The
other change is macros used for initializing the counters. This
is done by replacing lprocfs_init_mps_stats() with very simple
handling in lprocfs_alloc_md_stats().

Change-Id: I036ce4518ffb08d53e2d27bcdea564a4c799181d
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/32822
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11110 ofd: remove obdfilter.*.* symlinks in few releases

Add a #if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 14, 53, 0) check
around the obdfilter.*.* symlinks creation code to keep them in
place for another few releases, so that old test scripts that use
them will not break, then remove them.

Change-Id: I703c7ec3af8434b0de8b7cbed19c2c32611f6b18
Signed-off-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/32752
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11075 ldlm: correct logic in ldlm_prepare_lru_list()

In ldlm_prepare_lru_list() fix an (x != a || x != b) type error and
correct a use after free.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: I4e34e531260295805c4461e7d8d98675400f1148
Reviewed-on: https://review.whamcloud.com/32660
Tested-by: Jenkins
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10365 tests: set proper paths headers for sanity test 400a

For the case when /usr/include/lustre doesn't exist sanity test
400a attempts to use the lustre user land headers located in the
source tree. Some of the lustre user land headers are wrappers
around the UAPI headers so we need to include those paths as well.

A test move was done in the linux kernel that moved the UAPI headers
to their proper place. Errors were reported mainly due to
linux/types.h being missing. This could be the reason Ubuntu18 fails
the sanity 400a test.

Test-Parameters: trivial clientdistro=ubuntu1604 testlist=sanity envdefinitions=ONLY=400a

Change-Id: If17da7d9fc4cedb3b9c18feaafbee47d1f94d49b
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/31737
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 obdclass: Fix style issues for lu_ref.c

This patch fixes issues reported by checkpatch
for file lustre/obdclass/lu_ref.c

Change-Id: I8733fcac454685704b327219ba4afb096d3943c3
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.super@gmail.com>
Reviewed-on: https://review.whamcloud.com/33081
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-6142 obdclass: Fix style issues for lustre_handles.c

This patch fixes issues reported by checkpatch
for file lustre/obdclass/lustre_handles.c

Change-Id: I6e6ad8c56e225dcdd3707bf5f3b233eda3f90320
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.super@gmail.com>
Reviewed-on: https://review.whamcloud.com/33080
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-6142 obdclass: Fix style issues for lustre_peer.c

This patch fixes issues reported by checkpatch
for file lustre/obdclass/lustre_peer.c

Change-Id: I6cf95dfdd709974cae62626ac50a3507588f425d
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.super@gmail.com>
Reviewed-on: https://review.whamcloud.com/33079
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-11255 kernel: kernel update [SLES12 SP3 4.4.143-94.47]

Update SLES12 SP3 kernel to 4.4.143-94.47.

Test-Parameters: mdtfilesystemtype=ldiskfs ostfilesystemtype=ldiskfs \
clientdistro=sles12sp3 ossdistro=sles12sp3 mdsdistro=sles12sp3 \
testgroup=review-ldiskfs

Change-Id: I8b2c99c9a65149f1b149fa91351970034d6f7a47
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/33065
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11125 ofd: decrease message level

The "destroys_in_progress already cleared" message
in ofd_create_hdl() may be result of high load on OST
server prior failover. It is not an error, so decrease
its level to D_HA from D_ERROR.

Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: Id5142672a61244a6362be3778d0769baafc87b86
Reviewed-on: https://review.whamcloud.com/32985
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>

LU-10509 mdd: don't set size attr for DOM file

When client does truncate it calls ll_md_setattr() followed by
ll_setattr_ost() to set size on OSTs. With DOM file that causes
setattr on MDT first including size then PUNCH RPC on the same
object. That was considered as non-optimized situation and
LU-11033 is intended to improve it, but with ZFS there is
check in OSD which does no truncate if size is the same already.
Therefore real file blocks are not truncated actually so sparse
write beyond the end of file will get old data in hole instead of
zeroes.

Quick patch checks if mdd_attr_set() is going to set SIZE attr for
DOM file and clear LA_SIZE bit, assuming there will be truncate.

Complete solution for this will be implemented under LU-11033

Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I47873dccf4270e5f0338f7b6696aa5969cfb9444
Reviewed-on: https://review.whamcloud.com/33008
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10018 protocol: MDT as a statfs proxy

MDT can act as a proxy for statfs data. this should
make df faster (RTT vs RTT*(#MDTs+1)) and enable
idling connections so that clients don't connect to
each OST just to report statfs data. the protocol
has been changing slightly to let MDT differentiate
self and aggregated statfs.

also, obd_statfs has got a new field "granted" where
OST reports how much space has been granted to the
requesting MDT so that space can be added to available
space.

client's NID is used to distribute MDS_STATFS among
MDTS.

Change-Id: I59e03cb5abf809ae8820f874ec51dd2b74e1806c
Signed-off-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-on: https://review.whamcloud.com/29136
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8708 osc: enable/disable OSC grant shrink

Add an OSC proc interface to enable/disable client's grant shrink
feature.

lctl get_param osc.*.grant_shrink
lctl set_param osc.*.grant_shrink={0,1}

Change-Id: I7974b3bf1c4f9c294dd0d4871d09b1a2e45a8d78
Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/23203
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11212 lod: preserve mirror ID on mirror extension

When merging/expanding existing mirrors of a FLR file, we need keep
its existing mirror's mirror ID.

Signed-off-by: Bobi Jam <bobijam.xu@intel.com>
Change-Id: If139076c37c33bb1a330e1a5e997f8f56015fd9a
Reviewed-on: https://review.whamcloud.com/32938
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11238 lod: refine obj avoid collect for FLR

When a FLR file is being created, the MDS tries to allocate objects
for the first components of all mirrors, and in this decalre phase,
the objects for their component has been allocated, but the
component's ID and init flag has not been set until the exec phase,
lod_create()->lod_striped_create(), so lod_collect_avoidance() should
take heed of this scenario.

This patch also addes some debug messages.

Test-Parameters: testlist=sanity-flr,sanity-flr,sanity-flr,sanity-flr,sanity-flr
Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: I16ef2da44f6db06a8e0bc67ae2646cdc3ff3bb63
Reviewed-on: https://review.whamcloud.com/32995
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11259 test: correct fail_loc names in replay-{single,dual}

Some comments in replay-single and replay-dual confusingly referred to
OBD_FAIL_OUT_UPDATE_NET_REP as OBD_FAIL_OBJ_UPDATE_NET_REP or
OBD_FAIL_UPDATE_OBJ_NET_REP. Correct these.

Test-Parameters: trivial
Signed-off-by: John L. Hammond <jhammond@whamcloud.com>
Change-Id: Ib724e8151ba0ea34a5dacf2f148673a52dc37824
Reviewed-on: https://review.whamcloud.com/33015
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>

LU-8066 tests: don't access /proc/sys/lnet/debug directly

In replay-single test_70e use "lctl set_param" to set the debug mask
rather than writing into the /proc/sys/lnet/debug file directly, since
this tunable moved to sysfs in commit v2_10_51_0-12-g7092309f32.

Clean up the test code style in test_70e as well.

Test-Parameters: trivial testlist=replay-single
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I65c2bd9643fc6fc54a5de7b6404d316c0ff12537
Reviewed-on: https://review.whamcloud.com/33005
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Doug Oucharek <dougso@me.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11240 gnilnd: Replace KGNILND_BUILD_REV

The current format of the gnilnd version string causes a compilation
error. Since gnilnd doesn't really need its own version string we just
replace it with LUSTRE_VERSION_STRING.

Cray-bug-id: LUS-6072
Test-Parameters: trivial
Signed-off-by: Chris Horn <hornc@cray.com>
Change-Id: I6f45df2566853a6f4c2078cf72c7eac7a52f3fad
Reviewed-on: https://review.whamcloud.com/32990
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Chuck Fossen <chuckf@cray.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11135 mdt: LASSERT(lu_object_exists(o)) fails

mdt_object_find() can return a vaild nonexisting object.
It's return value needs to be checked additionaly if exists.

Change-Id: Ib1f5bd5289a69e29437db520706591929bf55830
Cray-bug-id: LUS-6192
Signed-off-by: Andriy Skulysh <c17819@cray.com>
Reviewed-on: https://review.whamcloud.com/32803
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Alexandr Boyko <c17825@cray.com>
Reviewed-by: Andrew Perepechko <c17827@cray.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11056 lwp: fix lwp reconnection issue

After the OST or MDT was restarted, the lwp reconnection can be
failed for -EALREADY because the connect count in the connecttion
request is less then the value saved in the corresponding export
at MDT0000, which could cause the system hang.

The patch also changes lustre_lwp_connect to use OBD_CONNECT_MDS_MDS
flag only when the connection is between MDTs.

Change-Id: I9ae7b4faadc65fdaa78458a06315b1739d144feb
Signed-off-by: Hongchao Zhang <hongchao.zhang@intel.com>
Reviewed-on: https://review.whamcloud.com/32536
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10855 llog: use llog_common_cat_ops

Remove changelog_orig_logops, hsm_actions_logops, and
osp_mds_ost_orig_logops, replacing each with llog_common_cat_ops.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Ia19337350452f9793b3ea9a56343ef3a065c1f83
Reviewed-on: https://review.whamcloud.com/31812
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10824 llite: don't use ll_mnt to get fstype name

Originally lustre would report using the fstype proc file either
'lustre' or 'llite'. This required us to query struct super_block
but its been a very long time since that is the case. This also
removes a direct use of ll_mnt. The fix is simply report 'lustre'.

Test-Parameters: trivial

Change-Id: Ia766c8e0a027e58a48de8fa6e2756238e20312b2
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/33025
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 obdclass: Fix style issues for statfs_pack.c

This patch fixes issues reported by checkpatch
for file lustre/obdclass/statfs_pack.c

Change-Id: I7a34dd87875ab049c3339022f3153fb07937021e
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.super@gmail.com>
Reviewed-on: https://review.whamcloud.com/32981
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-6142 osd-ldiskfs: Fix style issues for osd_handler.c

This patch fixes issues reported by checkpatch
for file lustre/osd-ldiskfs/osd_handler.c

Change-Id: Ifd6468acc75b59a4324385c68af1175a74a3c312
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.super@gmail.com>
Reviewed-on: https://review.whamcloud.com/32818
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-11266 build: update changelog for Ubuntu

Record the version that we are building

Test-Parameters: trivial

Change-Id: Ib1c2e74774d8a6caa6c3f70814affb53cf8cd22e
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/33020
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11009 test: add version check to test_102

Skip test_102 if server is equal or less than 2.9.53

Test-Parameters:trivial testlist=conf-sanity envdefinitions=ONLY=102 serverjob=lustre-b2_9 serverbuildno=22
Signed-off-by: Wei Liu <sarah@whamcloud.com>
Change-Id: I1964a7a5df8b910652b2fe774703d7b62f953e95
Reviewed-on: https://review.whamcloud.com/32340
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11040 utils: improve mount usage/man page

Improve the description of the mount.lustre.8 man page and usage:
- provide separate SYNOPSYS for client and server mount commands
- move "acl" option out of general options into server-only options,
  since client option was removed and ACLs are only controlled by MDS
- correct "CLIENT OPTIONS" section to be named "SERVER OPTIONS"
- add checksum, lruresize, lazystatfs, 32bitapi, user_fid2path usage
- mark the default values of the options in the usage message

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I28fe0f13d363e0a26ffcbc1ba9923e4fd35804f0
Reviewed-on: https://review.whamcloud.com/32481
Tested-by: Jenkins
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11096 osd: wrap new blk integrity stuff

to be able to build Lustre against kernels with no blk integrity.

Change-Id: I050020e94524f4519fdf46a22f0d847979754291
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/32725
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Chris Horn <hornc@cray.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 lov: fix lov.*.stripeoffset printing

The move of lov.*.stripeoffset from /proc to /sys in commit 3c900918
reverted the printing of stripeoffset from a signed value to an
unsigned value, which is broken for the common value of "-1".  This
was previously fixed in LU-9611 commit f93276d9.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ib61305ddbf902dd74ac0e16c0c2fe6920052ddf4
Reviewed-on: https://review.whamcloud.com/33019
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11215 tests: replace "large_xattr" with "ea_inode"

Change the test scripts over to using the "ea_inode" name, since
this is what the upstream e2fsprogs is using.  The "large_xattr"
feature name was only ever used in the Lustre-patched e2fsprogs.

Don't try to turn off "ea_inode" feature on the targets anymore,
it's not supported by upstream e2fsprogs.

e2fsprogs commit: 5b72578279fe2470e682692a15d70a43d9289e0f

Test-Parameters: trivial testlist=conf-sanity
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Li Dongyang <dongyangli@ddn.com>
Change-Id: I83bd303827fa28050d1d6d2416b2d630dc94ec12
Reviewed-on: https://review.whamcloud.com/33012
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>

LU-4256 test: add lustre-rsync-test 2b to ALWAYS_EXCEPT

This test continues to fail at a low rate so disable it.

Test-Parameters: trivial testlist=lustre-rsync-test
Signed-off-by: John L. Hammond <jhammond@whamcloud.com>
Change-Id: I8fe4d039e8edd0552e56ee9451cc05f08cb34c8d
Reviewed-on: https://review.whamcloud.com/33006
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11244 build: apply IB_OPTIONS to debian rules

IB_OPTIONS should be honored when making debian package.

Signed-off-by: Jinshan Xiong <jinshan.xiong@uber.com>
Change-Id: Ibc16a5428d47f072499c39a62ea457c922ae7352
Reviewed-on: https://review.whamcloud.com/32996
Tested-by: Jenkins
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Tested-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Thomas Stibor <t.stibor@gsi.de>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Martin Schroeder <martin.h.schroeder@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11227 lod: lod_sync: don't attempt sync to inactive targets

chgrp on a client triggers lod_sync() which in turn loops over OST/MDT
targets with dt_sync(). dt_sync() fails with -ENOTCONN when targets
have been deactivated (ie. set to active=0). The client retries
infinitely causing the client process to hang and considerably MDS
network traffic, load, and disk i/o.

the fix is to not attempt dt_sync() to ost/mdt targets that have been
deactivated and also (because of possible races) to ignore connection
errors.

tested with Lustre 2.10.4.

Signed-off-by: Robin Humble <plaguedbypenguins@gmail.com>
Change-Id: I617509cf7944541489f4fd9762c233b771132165
Reviewed-on: https://review.whamcloud.com/32964
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: John L. Hammond <jhammond@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11226 flr: mirror resync regression

There is a glitch in the lfs mirror resync tool in commit
0e5c12ac29a9622e8ca05d5e39cd5e2a721ace93, resync write needs to
restricted to the component's extent.

Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: Ifbd3f16b2f621407b31c7fe37ce9745de48fcc99
Reviewed-on: https://review.whamcloud.com/32968
Tested-by: Jenkins
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11146 lustre: fix setstripe for specific osts upon dir

LOV_USER_MAGIC_SPECIFIC function is broken and it
was not available for setting directory.

1)llite doesn't handle LOV_USER_MAGIC_SPECIFIC case
properly for dir {set,get}_stripe, and ioctl
LL_IOC_LOV_SETSTRIPE did not alloc enough buf,
copy ost lists from userspace.

2)lod_get_default_lov_striping() did not handle
LOV_USER_MAGIC_SPECIFIC type that newly created
files/dir won't inherit parent setting well.

3)there is not any case to cover lfs setstripe
'-o' interface which make it hard to figure out
when this function was broken.

Change-Id: Icc2ee60a474e5e565db12b35a9a38fde65b05bbd
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/32814
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-8066 llite: move /proc/fs/lustre/llite/uuid to sysfs

Move uuid file from /proc/fs/lustre/llite/*
to /sys/fs/lustre/llite/*/

This is a modified version of

Linux-commit: ec55a6299990efa969dfc00d95c72444ff1e3461

due to the large amount of changes to the OpenSFS/Intel branch.

Change-Id: I2dc13c248879f554f9f7ed6dc62a6772a59f6f35
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/32501
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-8215 tests: sanity-benchmark/iozone should wait for space recovery

otherwise it may fail due to a transient state where the space confsumed
by the previous run hasn't recovered yet. this happens to tiny filesystems
used in local setups.

Change-Id: I04b3ce096621583629277c1e52c64a1551bc8ace
Signed-off-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-on: https://review.whamcloud.com/20499
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11201 lfsck: check linkea entry validity

Invalid linkea data may lead to dead loop in linkea iteration, check
linkea entry validity on unpack, and if entry is not unpacked, check
entry length validity.

Test-Parameters: trivial mdscount=2 mdtcount=4 testlist=sanity-lfsck
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I8e1890ed64fab38b85149ebbfecce04caaf41e17
Reviewed-on: https://review.whamcloud.com/32958
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11154 llite: use proper flags for FS_IOC_{FSSET,FSGET}XATTR

Two problems addressed by this patch:

1)struct fsxattr fsx_xflags has its own flags definition
like FS_XFLAG_XXX, we should use proper convert macro for
it, here we used wrong constant flag for project inherit flag.

2)FS_XFLAG_PROJINHERIT is not a valid vfs inode flag, looking
at current linux codes, local filesystem set project inherit
flag on its private flags, we should do similar thing to Lustre

Test-Parameters: trivial testlist=sanity-quota,sanity-quota,sanity-quota
Change-Id: I453db8ed074e8008f0ec145c726d7577121422e6
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/32828
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>