Whamcloud - gitweb
Oleg Drokin [Mon, 22 Apr 2019 21:58:41 +0000 (17:58 -0400)]
New RC 2.12.1-RC1
Change-Id: I768486afc4ee30be96ad835e51522c9b769ddb2c
Signed-off-by: Oleg Drokin <green@whamcloud.com>
Oleg Drokin [Mon, 22 Apr 2019 21:57:32 +0000 (17:57 -0400)]
Revert "LU-9193 security: return security context for metadata ops"
Mike noticed this introduces a regression that is tracked under LU-12212.
This reverts commit
7aa5ae2673f70ef851fb903b280a0fc9a47c476b.
James Simmons [Mon, 15 Apr 2019 23:16:27 +0000 (19:16 -0400)]
LU-11986 lnet: properly cleanup lnet debugfs files
The function lnet_router_debugfs_remove() is suppose to cleanup
the lnet specific debugfs files but that is not happening at all.
Change lnet_remove_debugfs() from doing the final debugfs lnet
and libcfs cleanup to doing specific debugfs file removal. We
can make libcfs module unloading to directly finish the entire
libcfs and debugfs tree removal instead. With this change we can
make lnet_router_debugfs_fini() call lnet_remove_debugfs().
Lustre-change: https://review.whamcloud.com/34669/
Lustre-commit:
8cb7ccf54e2d34010bea9a71fe0eff708545ab78
Change-Id: I9e314e7efde806073b621166ff2e1b344e550875
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34692
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Lai Siyao [Mon, 4 Mar 2019 15:56:16 +0000 (23:56 +0800)]
LU-12037 mdt: add option for cross-MDT rename
Add option mdt.mdt_remote_rename, if it's not set (it's set by
default), do cross-MDT rename as cp, this is used for debug or
user want to move inode in rename.
Add sanity test_24z.
Lustre-change: https://review.whamcloud.com/34410
Lustre-commit:
c6f3d533542b9462b5b8df95183d80321d4d9c34
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Ia0d122f1716f17078b375f770a193347a6e50708
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34616
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Qian Yingjin [Thu, 28 Feb 2019 08:05:29 +0000 (16:05 +0800)]
LU-12021 lsom: Add an OBD_CONNECT2_LSOM connect flag
Add an OBD_CONNECT2_LSOM connect flag so that clients do not send
MDS_ATTR_LSIZE and MDS_ATTR_LBLOCKS flags to the old servers that
do not support them.
Lustre-change: https://review.whamcloud.com/34343
Lustre-commit:
fdd2c5d3a6e5f866e5ca887064e9ed37316af234
Change-Id: I266c74e56c2cb1462e204d6fd4f1399f10621416
Signed-off-by: Qian Yingjin <qian@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34663
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Amir Shehata [Thu, 21 Mar 2019 15:53:34 +0000 (11:53 -0400)]
LU-11931 lnd: bring back concurrent_sends
Revert "LU-10291 lnd: remove concurrent_sends tunable"
This reverts commit
8d35d6c9bd85ed3a282aa124b672e50c02322a7d.
Lustre-change: https://review.whamcloud.com/#/c/34646/
Lustre-commit:
83e45ead69babfb2909a3157f054fcd8fdf33360
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: Icb63d7383f0d2a3cab82c1565f66670dca1f698d
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34646
Tested-by: Jenkins
Reviewed-by: Alexey Lyashkov <c17817@cray.com>
Reviewed-by: Chris Horn <hornc@cray.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Bruno Faccini [Wed, 26 Apr 2017 10:35:28 +0000 (12:35 +0200)]
LU-9193 security: return security context for metadata ops
Security layer needs to fetch security context of files/dirs
upon metadata ops like lookup, getattr, open, truncate, and
layout, for its own purpose and control checks.
Retrieving the security context consists in a getxattr operation
at the file system level. The fact that the requested metadata
operation and the getxattr are not atomic can create a window
for a dead-lock situation where, based on some access patterns,
all MDT service threads can become stuck waiting for lookup lock
to be released and thus unable to serve getxattr for security context.
Another problem is that sending an additional getxattr request for
every metadata op hurts performance.
This patch introduces a way to get atomicity by having
the MDT return security context upon granted lock reply,
sparing the client an additional getxattr request.
Lustre-change: https://review.whamcloud.com/26831
Lustre-commit:
fca35f74f9ec5c5ed77e774f3e3209d9df057a01
Signed-off-by: Bruno Faccini <bruno.faccini@intel.com>
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Signed-off-by: Sebastien Piechurski <sebastien.piechurski@atos.net>
Change-Id: Iaaf4d93f8d3bf31b5a2c23e7db36b3cb3feb31ba
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34573
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Mikhail Pershin [Fri, 1 Feb 2019 12:13:38 +0000 (15:13 +0300)]
LU-10496 tgt: move FMD handling from OFD to target
- move ofd/ofd_fmd.c to target/tgt_fmd.c with corresponding
changes
- add FMD calls to the MDT for Data-on-MDT files
- per-target tunable parameters init/fini
- update related tests to be correctly used with DOM
- make sanity.sh test_36 to work again
- remove target_handle_ping() along with o_ping method in
obd operations because it is not used anymore. Ping is
fully handled in tgt_obd_ping()
Lustre-change: https://review.whamcloud.com/34190
Lustre-commit:
52e33c507b84bcaf3af9df010f5de4a282aa3fca
Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I24280a2a9610d05eb9655c73bb067f94ff251980
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34691
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Mikhail Pershin [Thu, 31 Jan 2019 13:15:28 +0000 (16:15 +0300)]
LU-10496 ofd: move FMD to the target code
- make FMD structures common for all targets
- adapt FMD functionality to be isolated from OFD for
further move to the target code.
Lustre-change: https://review.whamcloud.com/34176
Lustre-commit:
6459fa2b458612b5213b3b70839e340efff7aebc
Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I9f67f14e4132205cca67aa778b990bb3b45c30be
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34690
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Wang Shilong [Wed, 3 Apr 2019 09:13:16 +0000 (17:13 +0800)]
LU-12151 osd-ldiskfs: pass owner down rather than transfer it
Currently, for object creation, initially uid/gid set as 0,
and then osd_quota_trasfer() is called to correct space accounting
for non-root users, function call is like:
|->osd_create
|->osd_create_type_f
|->osd_mkreg
|->ldiskfs_create_inode
|->ext4_new_inode() ->owner as NULL, create 0 as uid/gid
|->osd_attr_init
|->osd_quota_transfer ->which will change uid/gid again for above.
This is inefficient since osd_quota_transfer() is a more
heavy operations, we could just pass downer owner(uid,gid),
project quota will inherit from its' parents automatically
when creating inode.
Some distros ext4 still did not support passing @owner down,
that is (rhel6,sles11) we just added extra @owner arg in
ldiskfs_create_inode() to make build system happy, and we
could add similar support to older kernel if that is really needed.
Command:
$ salloc -N 32 --ntasks-per-node=24 mpirun -np 768 mdtest -n 2000
-F -u -d <mnt>
Without Patch:
Users Speed
root 175741.938 ops/sec
non-root 108631.673 ops/sec
Patched:
Users Speed
root 184775.286 ops/sec
non-root 185218.466 ops/sec
Patch improved ~80% for non-root users and we reached
same speed for both root and non-root users.
Lustre-change: https://review.whamcloud.com/34581
Lustre-commit:
697f2d95bfdca13565ccc5d50e106114604c1724
Change-Id: I57b0d2a6913268448c0ed90cfe76bd9f051b0b40
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34685
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Wed, 21 Nov 2018 13:10:22 +0000 (22:10 +0900)]
LU-8955 tests: exercise SELinux policy info
Add new tests 21a and 21b to sanity-selinux.sh. Goal is to test
that SELinux policy info is properly sent by the client, and
checked by the server, in the following cases:
- connection
- create
- open
- unlink
- rename
- getxattr
- setxattr
- setattr
- getattr
- symlink
- hardlink
Lustre-change: https://review.whamcloud.com/33699
Lustre-commit:
1796539799e2798caa80799e957faa03ef6af1a5
Test-Parameters: trivial testlist=sanity-selinux clientselinux
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: Ibd9c5added027e12d8126641c56f21fdbc791941
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34643
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Mon, 4 Mar 2019 07:43:42 +0000 (08:43 +0100)]
LU-12039 tests: fix 'lfs mkdir' in sanity-selinux
sanity-selinux test_2b and test_20c assume that directory created
with 'lfs mkdir' will be on MDT0, but they have to use the '-i 0'
flag to make sure.
Lustre-change: https://review.whamcloud.com/34368
Lustre-commit:
e4166f4e9970bbc7ea713d411219a5710c778d61
Test-Parameters: trivial testlist=sanity-selinux clientselinux
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I4c27a93dd8f411cff154c50bb324574179f1a8c8
Reviewed-on: https://review.whamcloud.com/34373
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Tue, 16 Aug 2016 08:17:40 +0000 (17:17 +0900)]
LU-8955 ptlrpc: manage SELinux policy info for metadata ops
Add SELinux policy info for following metedata operations:
- create
- open
- unlink
- rename
- getxattr
- setxattr
- setattr
- getattr
- symlink
- hardlink
On server side, get SELinux policy info from nodemap and compare
it with the one received from client.
Lustre-change: https://review.whamcloud.com/24424
Lustre-commit:
0a773f04b28860c3748f9f1460818b8461c96ad1
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I16493d7c5713180fb065623b735d7348fc3f9140
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34642
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Tue, 16 Aug 2016 12:53:03 +0000 (21:53 +0900)]
LU-8955 ptlrpc: manage SELinux policy info at connect time
At connect time, compute SELinux policy info on client side, and
send it over the wire.
On server side, get SELinux policy info from nodemap and compare
it with the one received from client.
Lustre-change: https://review.whamcloud.com/24422
Lustre-commit:
dd200e5530fd841999399f6dcafb5ded46ba3cf1
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I9b4a206455f2c0b451f6b3ed7e3a85285592758e
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34641
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Fri, 16 Jun 2017 12:36:23 +0000 (14:36 +0200)]
LU-8955 sec: create new function sptlrpc_get_sepol()
Create new function sptlrpc_get_sepol() in ptlrpc/sec.c to compute
SELinux policy info, by calling new userland command l_getsepol.
The SELinux policy info syntax is the following:
<mode>:<name>:<version>:<hash>
where:
- <mode> is a digit telling if SELinux is in Permissive mode (0)
or Enforcing mode (1)
- <name> is the name of the SELinux policy
- <version> is the version of the SELinux policy
- <hash> is the computed hash of the binary representation of the
policy, as exported in /etc/selinux/<name>/policy/policy.<version>
Userland command l_getsepol can be called on the command line by a
security administrator to get SELinux status information to store into
'sepol' field of nodemap.
SELinux status information is reported by Lustre client only if
new 'send_sepol' ptlrpc kernel module's parameter is not zero, and
SELinux is enabled on the client.
'send_sepol' accepts various values:
- 0: do not send SELinux policy info;
- -1: send SELinux policy info for every request;
- N > 0: only send SELinux policy info every N seconds. Use max value
2^31-1 (signed int on 32 bits) to make sure SELinux policy info is
only checked at mount time.
Independently from 'send_sepol' value, SELinux policy info has an
associated mtime. l_getsepol checks mtime and recalculates whole
SELinux policy info (including SHA) only if mtime changed.
Lustre-change: https://review.whamcloud.com/24421
Lustre-commit:
c61168239eff571aefc2a695ef12ae355230e611
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Change-Id: I7a4b955f36c5e0f4eca1561beae2b40fec88d570
Reviewed-on: https://review.whamcloud.com/34640
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Thu, 6 Dec 2018 09:40:45 +0000 (10:40 +0100)]
LU-8955 nodemap: add SELinux policy info to nodemap
Give the ability to set SELinux policy information on a nodemap,
in a new nodemap field named 'sepol'.
When set, a client pertaining to this nodemap will be allowed to
connect only if the SELinux policy information it sends matches
the one stored in the nodemap.
Expected 'sepol' string format is:
<1-digit>:<policy name>:<policy version>:<policy hash>
1-digit is 0 for SELinux Permissive mode, 1 for Enforcing mode.
SELinux policy info of nodemap is stored permanently by using
'lctl set_param -P' commands. It means MDS and OSS will be able to
retrieve SELinux policy info of nodemap after a restart (when they
read params llog).
MGS will not see SElinux policy info after restart, but this does
not prevent the feature from working.
Lustre-change: https://review.whamcloud.com/24420
Lustre-commit:
1f6cb3534e74f0c9462008c8088b5734b64ed41c
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: Ia1d178dd34f05ede020b490b1797a71dbae15d7b
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34639
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Thu, 6 Dec 2018 09:35:47 +0000 (10:35 +0100)]
LU-8955 cfg: reserve flags for SELinux status checking
Reserve LCFG_NODEMAP_SET_SEPOL config flag that will be used to
define sepol parameter on nodemap entries.
Reserve OBD_CONNECT2_SELINUX_POLICY connection flag that will be set
(in ocd_connect_flags2) if a client supports sending the SELinux
policy status info.
Add checks for all lcfg_command_type constants, along with lustre_cfg
and cfg_record_type.
Lustre-change: https://review.whamcloud.com/33797
Lustre-commit:
e71a77ba8d47279ed6a2704d5677e601e9cb80bb
Test-Parameters: trivial
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I009eb8f1597b51acce7dc21498a43096e41cd034
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <farr0186@gmail.com>
Reviewed-on: https://review.whamcloud.com/34638
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Nathaniel Clark [Tue, 19 Feb 2019 22:22:41 +0000 (17:22 -0500)]
LU-11394 utils: Adjust HOSTID constant
Use constant defined in spl / post-0.8.0 libspl, for HOSTID file.
Also allows get_system_hostid() to be pulled in from ZFS 0.8.x
Lustre-change: https://review.whamcloud.com/34278
Lustre-commit:
dce29976d14ca5aeba2dc8f0c464931c3826a6de
Test-Parameters: trivial
Signed-off-by: Nathaniel Clark <nclark@whamcloud.com>
Change-Id: Iba70d4f3b7f237260bdc964b28b601deeee81208
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34654
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Nathaniel Clark [Wed, 28 Nov 2018 22:31:40 +0000 (17:31 -0500)]
LU-11394 build: Remove SPL requirements
Because ZFS and SPL are version locked, and ZFS has explicit
requirements for SPL, remove lustre's SPL requirements.
lbuild: Make building spl optional when version is changed.
Lustre-change: https://review.whamcloud.com/33743
Lustre-commit:
d61103d329bad5b92c951c8ad06a4f1b431759aa
Test-Parameters: trivial
Test-Parameters: fstype=zfs ostcount=2
Signed-off-by: Nathaniel Clark <nclark@whamcloud.com>
Change-Id: Iedba8d4047ba1fa852a2f99db2cd1b6caff33326
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34653
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Jian Yu [Mon, 8 Apr 2019 23:58:09 +0000 (16:58 -0700)]
LU-12138 kernel: kernel update SLES12 SP4 [4.12.14-95.13.1]
Update SLES12 SP4 kernel to 4.12.14-95.13.1 for Lustre client.
Test-Parameters: trivial clientdistro=sles12sp4 \
envdefinitions=LNET_SELFTEST_EXCEPT=smoke,SANITY_EXCEPT=103a
Change-Id: I0831e611caa1ad51775e5f73d7989212f1347c2e
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34621
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Jian Yu [Mon, 8 Apr 2019 23:43:32 +0000 (16:43 -0700)]
LU-12172 kernel: kernel update RHEL7.6 [3.10.0-957.10.1.el7]
Update RHEL7.6 kernel to 3.10.0-957.10.1.el7.
Test-Parameters: clientdistro=el7.6 serverdistro=el7.6
Change-Id: I5471cf0f88201fdeac960eeaf6579bc454591d6b
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34620
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alex Zhuravlev [Thu, 4 Apr 2019 10:03:28 +0000 (13:03 +0300)]
LU-12160 osd-ldiskfs: use-after-free in osd_object_delete()
store a local copy of projid to avoid use-after-free.
Fixes:
39f63cf54c62 ("LU-4017 quota: add setting/getting project id function")
Lustre-change: https://review.whamcloud.com/#/c/34596/
Lustre-commit:
6a4cc98cd1692b14f4598335dcd373ec4f5b5fb2
Change-Id: I60e19de3485cae3df1cc2e8aae6eeed4b5de3a11
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34617
Tested-by: Jenkins
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Gu Zheng [Mon, 1 Apr 2019 09:19:21 +0000 (17:19 +0800)]
LU-12141 build: correct the required kernel version for lustre kmod
Use %kversion rather than %kver when creating preamble for lustre kmods
in lustre spec, to avoid *Requires kernel version* mismatch.
Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/#/c/34559/
Lustre-commit:
fa9922e8f0af3ddadce07aed7d27b00e42f4b487
Change-Id: I9929471abd48b214510bcb499e25793ad120e6d1
Signed-off-by: Gu Zheng <gzheng@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34614
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Lai Siyao [Mon, 4 Mar 2019 12:20:14 +0000 (20:20 +0800)]
LU-12037 mdt: call mdt_dom_discard_data() after rename unlock
mdt_reint_rename() should drop all locks including global rename
lock, and then call mdt_dom_discard_data(), otherwise it may
cause deadlock.
Lustre-change: https://review.whamcloud.com/34401
Lustre-commit:
480a221aa7e76f001288c8b1127e14e7922ce497
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I72cad3ee589c98c54f1e1281c39faa8779e562e8
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Stephan Thiell <sthiell@stanford.edu>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34615
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alex Zhuravlev [Mon, 11 Feb 2019 11:27:54 +0000 (14:27 +0300)]
LU-11951 ptlrpc: reset generation for old requests
All requests generated while the import is changing from
FULL to IDLE need to be moved to the new generation.
Lustre-change: https://review.whamcloud.com/34221
Lustre-commit:
42d8cb04637b62d91deb9ef047f1d9ef8473eca6
Change-Id: I59d9b92680c724132dba9c7315c26e9851c5d5d2
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34435
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Sonia Sharma [Mon, 1 Apr 2019 12:40:27 +0000 (05:40 -0700)]
LU-11986 lnet: Avoid lnet debugfs read/write if ctl_table does not exist
Running command "lctl get param -n stats" after lnet
is taken down leads to kernel panic because it
tries to read from the file which doesnt exist
anymore.
In lnet_debugfs_read() and lnet_debugfs_write(),
check if struct ctl_table is valid before trying
to read/write to it.
Change-Id: I2450d2f89c2e8a7db793680a4df581282ee46a16
Signed-off-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34634
Tested-by: Jenkins
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Patrick Farrell [Sun, 23 Dec 2018 21:04:33 +0000 (16:04 -0500)]
LU-11825 llite: Remove ptask framework
With the removal of pio, the ptask framework no longer has
any users.
Lustre-change: https://review.whamcloud.com/33913
Lustre-commit:
2b045f3bc1729d43a8d9613d5609b838ad79ccc7
Signed-off-by: Patrick Farrell <paf@cray.com>
Change-Id: Id3237740c251b01bc176967f8fe5fd12bb82f553
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34462
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Ann Koehler [Fri, 8 Feb 2019 21:41:37 +0000 (15:41 -0600)]
LU-11944 llite: Lock inode on tiny write if setuid/setgid set
During a write, the setuid/setgid bits must be reset if they are
enabled and the user does not have the correct permissions. Setting
any file attributes, including setuid and setgid, requires the inode
to be locked. Writes became lockless with the introduction of
LU-1669. Locking the inode in the setuid/setgid case was added to
vvp_io_write_start() as a special case. The inode locking was not
included when support for tiny writes was added with LU-9409. This
mod adds the necessary inode lock/unlock calls to ll_do_tiny_write().
If the inode is not locked when setuid/setgid are reset, the kernel
will issue a one time warning and Lustre may hang trying to get the
inode lock in ll_setattr_raw().
Lustre-change: https://review.whamcloud.com/34218
Lustre-commit:
f39a552922ca2db0c6974374fa3a917a34a4a747
Signed-off-by: Ann Koehler <amk@cray.com>
Change-Id: I5e8a98789828de52dbff4226958741320aba92e6
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34461
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Oleg Drokin [Tue, 5 Feb 2019 19:42:07 +0000 (14:42 -0500)]
LU-11930 llite: Restore pio flags
flags could never be removed from the LL_SBI_FLAGS list,
since the order is dependent on actual bits in the
structure.
Lustre-change: https://review.whamcloud.com/34187
Lustre-commit:
045c1a968a0478ee57aaa61deed8ec563bf50002
Change-Id: I601ad0df478b17075658706c830f4a615c418104
Fixes:
2b0a34fe43bf ("LU-11825 clio: Remove pio feature")
Signed-off-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34472
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Andreas Dilger [Wed, 26 Dec 2018 09:18:45 +0000 (02:18 -0700)]
LU-8066 ldlm: match store macro prototype
Use size_t in the LDLM_POOL_SYSFS_WRITER_STORE() function declaration
to match the struct lustre_attr (*store) function prototype.
Test-Paramters: trivial
Fixes:
1196bd199e7 ("LU-8066 ldlm: move /proc/fs/lustre/ldlm to /sys")
Lustre-change: https://review.whamcloud.com/33920
Lustre-commit:
3bbbe70d099466079e4c8c31291bcbe2a90da58c
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I41012a66507a048c63bfe6b6e732cf858ba5a5b1
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-on: https://review.whamcloud.com/34557
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Patrick Farrell [Sun, 23 Dec 2018 21:04:08 +0000 (16:04 -0500)]
LU-11825 clio: Remove pio feature
The pio feature was an interesting concept, but never
achieved real use in production, primarily because it was
actually slower than normal i/o for some common workloads,
so it could not be on by default.
It has had a trivial deadlock in it (with truncate) since
release, and this has never been reported by a customer.
The attemp to rewrite readahead to use ptasks was never
fully successful, and is being superseded by a different
implementation.
Given all this, there is no reason to keep the extra
complexity in the already complicated clio code.
Lustre-change: https://review.whamcloud.com/33912
Lustre-commit:
2b0a34fe43bf4fce5560af61a45e5393c96070a9
Signed-off-by: Patrick Farrell <paf@cray.com>
Change-Id: Ie558db946af94189e35e985e8894706c14ed5f39
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Wang Shilong <wshilong@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34460
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Wed, 26 Dec 2018 09:29:55 +0000 (02:29 -0700)]
LU-11830 lov: avoid signed vs. unsigned comparison
In the expansion of do_div64() GCC complains about pointer comparison
because loff_t is not a u64 variable as it should be. lov_do_div64()
also has signed vs. unsigned comparisons due to a signed loff_t.
Change lov_do_div() to use a 64-bit variable for do_div() instead of
loff_t to avoid these warnings.
Change OST_MAXREQSIZE and friends to be consistently unsigned values
to avoid compiler warnings.
Fix "lfs mirror resync" to avoid comparing signed and unsigned valued.
Lustre-change: https://review.whamcloud.com/33921
Lustre-commit:
632b3591b6ea21e3029299ef875179a4b5ca918f
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I6df31a2c0d75e5777f471fe8cb252715dd85a5b1
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/34558
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Jian Yu [Mon, 11 Feb 2019 23:53:13 +0000 (15:53 -0800)]
LU-11927 kernel: new kernel [SLES12 SP4 4.12.14-95.6.1]
This patch makes changes to support new SLES12 SP4 release
for Lustre client.
Test-Parameters: trivial clientdistro=sles12sp4 \
envdefinitions=LNET_SELFTEST_EXCEPT=smoke,SANITY_EXCEPT=103a
Change-Id: Ibe59ebc30c25f2cab771ac4c2c9b7a9b974732d5
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34569
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Nathaniel Clark [Mon, 11 Mar 2019 17:46:20 +0000 (13:46 -0400)]
LU-12059 build: Update ZFS version to 0.7.13
ZFS
* test-runner: python3 support #8096
* Fix flake 8 style warnings #7925 #7952
* GCC 9.0: Fix ztest "directive argument is not a nul-terminated
string" #8330
* Linux 5.0 compat: Fix bio_set_dev() #8287
* Linux 5.0 compat: Disable vector instructions on 5.0+ kernels
#8259
* Linux 5.0 compat: Fix SUBDIRs #8257
* Linux 5.0 compat: Convert MS_* macros to SB_* #8264
* Linux 5.0 compat: Use totalram_pages() #8263
* Linux 5.0 compat: access_ok() drops 'type' parameter #8261
* deadlock between mm_sem and tx assign in zfs_write() and page
fault #7939
* dkms: Enable debuginfo option to be set with zfs sysconfig file
#8304
* Bump commit subject length to 72 characters #8250
* zfs.8 uses wrong snapshot names in Example 15 #8241
* Add enclosure_symlinks option to vdev_id #8194
* vdev_id: new slot type ses #6956
* vdev_id: extension for new scsi topology #6592
* Rename macro ZFS_MINOR due to Lustre conflict #8195
* Add kernel module auto-loading #7287
* Use autoconf variable for C preprocessor #8180
* OpenZFS 9577 - remove zfs_dbuf_evict_key tsd #7602
* Honor --with-mounthelperdir where applicable #6962
* contrib/initramfs: switch to automake #6761
SPL
* Linux 4.20 compat: Fix current_kernel_time() #8258
* Linux 5.0 compat: Fix timespec_sub() tonyhutter/spl@a333b28
* Linux 5.0 compat: Fix SUBDIRs #8257
* Linux 5.0 compat: Use totalram_pages() #8263
* deadlock between mm_sem and tx assign in zfs_write() and page
fault #7939
* Linux 4.18 compat: Use ktime_get_coarse_real_ts64() #8258
* Use autoconf variable for C preprocessor #8180
Lustre-change: https://review.whamcloud.com/34393
Lustre-commit:
1e3508bb4023ff467227f57b744ccb2668ba00b4
Signed-off-by: Nathaniel Clark <nclark@whamcloud.com>
Change-Id: I73fa5c2a9ddcf19683229d6fb9e61ff0835639ff
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34567
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Minh Diep [Mon, 1 Apr 2019 15:19:56 +0000 (08:19 -0700)]
LU-11723 kernel: kernel update RHEL7.6 [3.10.0-957.1.3.el7]
Update RHEL7.6 kernel to 3.10.0-957.1.3.el7.
Change-Id: I5a43ae8221f76fee8bbffdea0c372e630b8fd0d4
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34564
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Thomas Stibor [Wed, 30 Jan 2019 13:47:46 +0000 (14:47 +0100)]
LU-11902 build: Remove obsolete lustre-utils files and entries
DEB packages can be build for server or client, where naming
convention for server is:
* lustre-server-modules-*
* lustre-server-utils-*
and for client:
* lustre-client-modules-*
* lustre-client-utils-*
Previously the util package was named lustre-utils which
is now obsolete due to the client and server separation
and thus can be removed.
Lustre-change: https://review.whamcloud.com/34137
Lustre-commit:
ee009da38d016a129b975aa3db77c675a17c1c3d
Test-Parameters: trivial
Signed-off-by: Thomas Stibor <t.stibor@gsi.de>
Change-Id: Id0a945d5b76e5c35cf858e3ab224efa342cde28d
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Nathaniel Clark <nclark@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34508
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Minh Diep [Mon, 1 Apr 2019 15:11:15 +0000 (08:11 -0700)]
LU-12015 build: update changelog for ubuntu kernel
Update changelog for Ubuntu client build kernel
Test-Parameters: trivial
Change-Id: If8eb74f95c2c5568f0c082b1d07bd2b4609ea4e2
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34563
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
James Nunez [Thu, 28 Mar 2019 19:35:34 +0000 (13:35 -0600)]
LU-11208 tests: add version check to sanity tests
sanity test 27G was added to Lustre tag 2.11.51. Thus, we
need to check that the server is 2.11.51 or later before
running test 27G (LU-11208).
sanity test 239A, change version check to 2.10.4 (LU-10230).
sanity test 311 was modified in Lustre tag 2.12.51. We need
to check that the server is 2.12.51 or later (LU-11965).
sanity test 317 was added to Lustre tag 2.11.53.
We need to check that the server is 2.11.53 or later before
running test 317 (LU-11778).
Fixes:
37f6357a5c9f ("LU-10629 lod: Clear OST pool with setstripe")
Fixes:
0ba690a526be ("LU-7251 osp: do not assign commit callback to
every thandle")
Fixes:
a531ab5f38a6 ("LU-11605 osp: max_create_count and create_count
changes")
Fixes:
6115eb7fd5 ("LU-10370 ofd: truncate does not update blocks
count on client")
This patch is a back port from
Lustre-commit:
f7155420024e142c86ec4a589ba4ba78679c9c8d
Lustre-change: https://review.whamcloud.com/33420
Test-Parameters: trivial
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: I3be45bd0bde5ec041fefef2559656ec74448dffa
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34535
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Patrick Farrell [Mon, 4 Feb 2019 03:47:10 +0000 (22:47 -0500)]
LU-11919 llite: Initialize cl_dirty_max_pages
cl_dirty_max_pages must be initialized to zero before
calling client_adjust_max_dirty.
Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/34173
Lustre-commit:
2e9c896dec6d5c582c5dd24d3026e8324dfa807c
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: Ie34306ae329e377520a7a4858ab969f901c6154d
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Li Xi <lixi@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34458
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
James Nunez [Wed, 27 Jun 2018 15:52:22 +0000 (09:52 -0600)]
LU-11010 tests: remove return after skip for conf-sanity
The skip() routine now contains a call to exit. All calls
to skip() and skip_env() should be reviewed and calls to
return() that followed skip() should be removed.
This is the fifth patch in a series of patches that
remove calls to return() after skip() in the Lustre test
suites.
A comment is added to skip_env() defining when it should
be used.
Calls to return() after skip() are removed for:
conf-sanity.sh
functions.sh
Lustre-change: https://review.whamcloud.com/32735
Lustre-commit:
915b16cf1278026a9f914f268e8cdfb578d929c4
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: Idbcdffda38aaac07f128ae42a2ffcda8986afc33
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: Quentin Bouget <quentin.bouget@cea.fr>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34565
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Alexey Lyashkov [Wed, 8 Aug 2018 04:47:51 +0000 (07:47 +0300)]
LU-11111 lfsck: skip orphan processing
LFSCK can reconnect a recently-deleted orphan object back
into the normal namespace when it shouldn't. This can
cause access to the deleted data (potential security risk),
and sometimes cause an assertion if orphan is later deleted.
Skip LFSCK on orphan objects. Fix the handling of the
LUSTRE_ORPHAN_FL in both osd-zfs and osd-ldiskfs so that
la_valid |= LA_FLAGS is set when la_flags |= LUSTRE_ORPHAN_FL
is set, otherwise the upper layers cannot properly detect it.
Clean up alignment of flags values and provide hex equivalents
so that they are more easily referenced during debugging.
Lustre-change: https://review.whamcloud.com/32959
Lustre-commit:
077570483e75e0610fd45149b926097547c434b8
Signed-off-by: Alexey Lyashkov <c17817@cray.com>
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I9b2809b95efa4b3c3e3b2c7d0a501624ed743ede
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34528
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Patrick Farrell [Wed, 20 Feb 2019 22:46:20 +0000 (17:46 -0500)]
LU-10143 tests: Add version check for interop
Without the fix for LU-10143, these tests will fail, so add
a version check for interop.
Lustre-change: https://review.whamcloud.com/34285
Lustre-commit:
1e63c2f85da17947d78d4b2fb79cab2bd04b2ca5
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: I65eead5d5252ec6abf5d8de68d73e4f9b690d030
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34562
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Lai Siyao [Tue, 5 Mar 2019 04:30:15 +0000 (12:30 +0800)]
LU-12081 mdt: rename shouldn't PDO lock if parent is remote
In rename parent locking, if target parent is source parent, but
it's remote, rename shouldn't PDO lock on it because PDO lock is
for local lock.
Lustre-change: https://review.whamcloud.com/34440
Lustre-commit:
9f1711f3d7d14cbe70fd058cbb59cda87d69eaa7
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Ib6ee1f70a50ddec3182c04c38a10ebbf2c384ccd
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34568
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alex Zhuravlev [Wed, 2 Jan 2019 18:11:29 +0000 (10:11 -0800)]
LU-11798 grant: prevent overflow of o_undirty
tgt_grant_inflate() returns a u64, and if tgd_blockbits and val are
large enough, can return a value >= 2^32. tgt_grant_incoming()
assigns oa->o_undirty the returned value. Since o_undirty is u32, it
can overflow.
This occurs with Lustre clients < 2.10 and a ZFS backend when the zfs
"recordsize" > 128k (the default).
In tgt_grant_inflate(), check the returned value and prevent o_undirty
from being assigned a value greater than 2^30.
Lustre-change: https://review.whamcloud.com/33948
Lustre-commit:
d6f5219162116778e49865d83724276b17b9ce3a
Change-Id: I75b9065a524238df2d582e640418fdfa2f1e9a72
Signed-off-by: Alexey Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Olaf Faaland <faaland1@llnl.gov>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34561
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Patrick Farrell [Thu, 28 Feb 2019 18:02:13 +0000 (13:02 -0500)]
LU-11943 llog: Reset current log on ENOSPC
The original LU-10527 patch:
"LU-10527 obdclass: don't recycle loghandle upon ENOSPC"
https://review.whamcloud.com/#/c/30897/
Kept the current log on ENOSPC.
This appears to cause llog corruption on failover, and the
other part of the original patch (removing an incorrect
assert) should be sufficient to fix the original issue.
Fixes:
5761b9576d39 ("LU-10527 obdclass: don't recycle loghandle upon ENOSPC")
Lustre-change: https://review.whamcloud.com/34347
Lustre-commit:
7f4a1dd92a900a55cbb980bac3d20c32968334ec
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: Ie5c0ab77940c1be0ec1f166e4d38080b254bed5c
Reviewed-by: Faccini Bruno <bruno.faccini@intel.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34459
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alexander Boyko [Thu, 29 Nov 2018 13:58:30 +0000 (08:58 -0500)]
LU-11591 llog: add synchronization for the last record
The initial problem was a race between llog_process_thread
and llog_osd_write_rec for a last record with lgh_last_idx.
The catalog should be wrapped for the problem. The lgh_last_idx
could be increased with a modification of llog bitmap, and a writing
record happen a bit later. When llog_process_thread processing
lgh_last_idx after modification and before a write it operates
with old record data.
The patch adds synchronization when lgh_last_idx is processed.
The patch changes llog_test 10h to check race between
llog_process_thread and llog_osd_write_rec.
1 Thread with write 2 Thread with read
llog_osd_write_rec() llog_process_thread()
lgh_last_idx++
lock lgh_hdr_mutex
ext2_set_bit()
dt_write_rec (write header) ext2_test_bit()
check lgh_last_idx was changed
dt_read_rec()
reread the record, and here we
got the old value of record
unlock lgh_hdr_mutex
dt_write_rec (write the record)
Lustre-change: https://review.whamcloud.com/33683
Lustre-commit:
ec4194e4e78c959ace97afeacd580d3609658115
This patch also include LU-11975 test: fix for llog test 10h
Lustre-change: https://review.whamcloud.com/#/c/34287/
Lustre-commit:
0670d5aed457196121c843fd24877d3f2670d478
Signed-off-by: Alexander Boyko <c17825@cray.com>
Cray-bug-id: LUS-6683
Change-Id: I642b488655940b9456ca8e2f2174c98a966ba242
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alexander Zarochentsev <c17826@cray.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34507
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
James Nunez [Thu, 28 Mar 2019 18:44:55 +0000 (12:44 -0600)]
LU-11777 tests: add version check sanityn 102
sanityn test 102 was added to Lustre tag 2.11.57. Thus,
we need to check that the server is 2.11.57 or later
before running test 102.
This patch is a back port from
Lustre-commit:
0a567ae4f3b0a4152bb8428244f7c2993584364e
Lustre-change: https://review.whamcloud.com/33953
Test-Parameters: trivial testlist=sanityn
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Change-Id: I5e34280db7bfc884fea784401406abfde57b9c98
Reviewed-on: https://review.whamcloud.com/34534
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Amir Shehata [Wed, 28 Nov 2018 01:54:51 +0000 (17:54 -0800)]
LU-11415 socklnd: improve scheduling algorithm
Modified the scheduling algorithm to use all scheduler threads
available. Previously a connection is assigned a single thread
and can only use that one. With this patch any scheduler thread
available on the assigned CPT can pick up and work on requests
queued on the connection.
Lustre-change: https://review.whamcloud.com/33740
Lustre-commit:
89df5e712ffd40064f1d4ce2f00f9156f68a2262
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I7e8e5220e1914155fd793994485e3a443fe1ba44
Reviewed-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34299
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Wed, 26 Dec 2018 09:03:55 +0000 (02:03 -0700)]
LU-11880 build: allow Debian build on Raspbian
Allow the Debian build to work on Raspbian and other Debian and
Ubuntu variants that use the same build machinery. Add armhf
to the list of allowed CPU architectures.
Lustre-change: https://review.whamcloud.com/34085
Lustre-commit:
7f3977ccd45fce0d150196e515286603135e7f3d
Test-Parameters: trivial clientdistro=ubuntu1804 testlist=sanity
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Iedc90ad32754f81a3d387a66409f07aaa305a5b1
Reviewed-by: Thomas Stibor <t.stibor@gsi.de>
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34456
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Andriy Skulysh [Wed, 22 Aug 2018 19:22:49 +0000 (22:22 +0300)]
LU-7558 ptlrpc: connect vs import invalidate race
Connect can't be sent while import invalidate is
in progress, thus it leaves the import in not
initialized state.
Don't allow reconnect in evicted state.
Lustre-change: https://review.whamcloud.com/33718
Lustre-commit:
b1827ff1da829ae5f320a417217757221eedda5f
Change-Id: I79a1a1eb05fede30e100ba09b6f3f98636a46213
Cray-bug-id: LUS-6322
Signed-off-by: Andriy Skulysh <c17819@cray.com>
Reviewed-by: Alexander Boyko <c17825@cray.com>
Reviewed-by: Andrew Perepechko <c17827@cray.com>
Reviewed-by: Mike Pershin <mpershin@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34293
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Alexander Boyko [Thu, 29 Nov 2018 08:20:00 +0000 (03:20 -0500)]
LU-10913 llog: add startcat for wrapped catalog
The osp_sync_thread loop for a llog_cat_process has a mistake.
When llog_cat_process has reached a bottom of catalog, the processing
restarts with 0. Which means a default processing. In this case a
catalog is wrapped and processing starts from a llh_cat_idx. But
records at the bottom were processed already, and were not cancelled
yet. The next message appears at log.
osp_sync_interpret()) reply req
ffff8800123e3600/1, rc -2, transno 0
llog_cat_process support startcat index for processing catalog.
In this case the processing starts from startcat index. But if
catalog is wrapped startcat index is ignored.
The patch adds supporting of startcat index for wrapped catalog.
Lustre-change: https://review.whamcloud.com/33749
Lustre-commit:
8109c9e1718d7f425a7186c31399ac035157acd6
Signed-off-by: Alexander Boyko <c17825@cray.com>
Change-Id: Ie4e3ecf2532878578ae0463969115664e3589188
Cray-bug-id: LUS-6765
Reviewed-by: Sergey Cheremencev <c17829@cray.com>
Reviewed-by: Alexander Zarochentsev <c17826@cray.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34506
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Jinshan Xiong [Sun, 24 Feb 2019 22:32:41 +0000 (14:32 -0800)]
LU-11999 dne: performance improvement for file creation
This is to remove an obsoleted code where it causes drastic
performance degradation. This code is written before PERM lock
is introduced, and it requests UPDATE lock at path walk for
remote directory, which will be cancelled at later file creation.
Tests result before and after this patch is applied:
Test case:
rm -rf /mnt/lustre_purple/testdir
lfs mkdir -i 0 /mnt/lustre_purple/testdir
lfs mkdir -i 2 /mnt/lustre_purple/testdir/dir2
./lustre-release/lustre/tests/createmany -o \
/mnt/lustre_purple/testdir/dir2/f 10000
Before the patch is applied:
total: 10000 open/close in 12.82 seconds: 780.22 ops/second
After the patch is applied:
total: 10000 open/close in 4.89 seconds: 2044.75 ops/second
Lustre-change: https://review.whamcloud.com/34291
Lustre-commit:
bfbd062e6b177cf934b75d6be2db695b9fe1648b
Signed-off-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Change-Id: Ib474dc28d6edc7d15801b6821edc0e1d108bb4b6
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Andrew Perepechko <c17827@cray.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34505
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Fri, 1 Feb 2019 20:10:40 +0000 (13:10 -0700)]
LU-11913 utils: allow "mq-deadline" as scheduler
Allow the "mq-deadline" scheduler for multi-queue block devices, in
addition to just "noop" and "deadline". Explicitly add "deadline"
as a valid option, in case the default scheduler is changed.
Lustre-change: https://review.whamcloud.com/34163
Lustre-commit:
4326ab53b7142e474c75b46da2361d148a2f7ce8
Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I2cb0878188aea43f88c503ea70a699be083ebbe5
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/34426
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Nathaniel Clark [Mon, 3 Dec 2018 19:04:37 +0000 (14:04 -0500)]
LU-11720 spec: srpm should be free of kernel requiements
This moves the fix for LU-9731 into spec file and out of lbuild.
This lets "make rpms" benefit from the fix.
This also prevents the srpm from being incorrectly locked to the
kernel present when lbuild was used to create it (via
kmp-lustre.preamble).
Lustre-change: https://review.whamcloud.com/33771
Lustre-commit:
3c280a95736a884bc2f36dad674505f1d5b00982
Test-Parameters: trivial
Signed-off-by: Nathaniel Clark <nclark@whamcloud.com>
Change-Id: I15f61c0e37182c0efbea3566d43b1e89f180d3e5
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34310
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Dmitry Eremin [Fri, 8 Jul 2016 21:15:37 +0000 (00:15 +0300)]
LU-8384 scripts: Add scripts to systemd for EL7
When rebooting a lustre client where Lustre filesystem is still
mounted, the shutdown hangs. This patch create a systemd service
that unmount the Lustre filesystems and unload the Lustre modules
when system is shutdown.
Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/21457
Lustre-commit:
495deddfbb43f247b2fa9dd2da5743abc89cd862
Change-Id: I1cfe84684e23b8861743241dfbc4d6e320ace4a6
Signed-off-by: Dmitry Eremin <dmitry.eremin@intel.com>
Signed-off-by: Gregoire Pichon <gregoire.pichon@atos.net>
Signed-off-by: Nathaniel Clark <nclark@whamcloud.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34503
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Wang Shilong [Thu, 10 Jan 2019 15:32:14 +0000 (23:32 +0800)]
LU-11849 utils: fix to make exclude projid works
We intended to use projid not uid here, fix it.
Also add ! --projid options test to cover this.
Lustre-change: https://review.whamcloud.com/34005
Lustre-commit:
db9965ce33365c2645827b06af21f8f5918ea2bb
Test-Parameters: trivial testlist=sanity-quota
Change-Id: I64c3f1c68885947d0e91626525ee037756e1d7d8
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Li Xi <lixi@ddn.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Reviewed-on: https://review.whamcloud.com/34407
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Mikhail Pershin [Thu, 14 Feb 2019 21:51:00 +0000 (00:51 +0300)]
LU-11964 mdc: prevent glimpse lock count grow
DOM locks matching tries to ignore locks with
LDLM_FL_KMS_IGNORE flag during ldlm_lock_match() but
checks that after ldlm_lock_match() call. Therefore if
there is any lock with such flag in queue then all other
locks after it are ignored and new lock is created causing
big amount of locks on single resource in some access
patterns.
Patch extends lock_matches() function to check flags to
exclude and adds ldlm_lock_match_with_skip()p to use that
when needed.
Corresponding test was added in sanity-dom.sh
Test-Parameters: testlist=sanity-dom
Lustre-change: https://review.whamcloud.com/34261
Lustre-commit:
b915221b6d0f3457fd9dd202a9d14c5f8385bf47
Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: Ic45ca10f0e603e79a3a00e4fde13a5fae15ea5fc
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34504
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Lai Siyao [Tue, 23 Oct 2018 11:17:20 +0000 (19:17 +0800)]
LU-11418 mdd: delete name if orphan doesn't exist
mdd_orphan_destroy() should delete name if orphan object doesn't
exist, otherwise the orphan clean thread will try to destroy this
orphan in dead loop.
add sanity test_811.
Lustre-change: https://review.whamcloud.com/33661
Lustre-commit:
fffef5c29e3bdf0f96168abc3d0488bad06f33bb
Fixes:
5d89450b462f ("LU-11516 mdd: do not assert on missing orphan")
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Id22b2fab0ac87dfb81ca9f01d8ed0338f1b12120
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34326
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Vladimir Saveliev [Sat, 22 Dec 2018 00:31:45 +0000 (03:31 +0300)]
LU-11827 llog: protect cathandle in llog_cat_declare_add_rec
llog_cat_declare_add_rec() calls llog_cat_prep_log() passing
&cathandle->u.chd.chd_current_log and
&cathandle->u.chd.chd_next_log. Then it has to protect cathandle in
order to avoid race with llog_cat_current_log() when it decides to
change cathandle->u.chd.chd_current_log and
cathandle->u.chd.chd_next_log.
Lustre-change: https://review.whamcloud.com/33914
Lustre-commit:
59a62ada2e18174e5611730e8bcf5ba3165ca2b9
Signed-off-by: Vladimir Saveliev <c17830@cray.com>
Cray-bug-id: LUS-6804
Change-Id: I689efb40452af180f137aff35ccabe132a24180a
Reviewed-by: Alexandr Boyko <c17825@cray.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34455
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Patrick Farrell [Mon, 11 Feb 2019 17:47:09 +0000 (12:47 -0500)]
LU-11206 tests: Use import_ready to check IDLE
When checking if a client/OST import is up, we have to
check for IDLE as well as FULL.
wait_osc_import_ready is provided for this, but a few spots
don't use it, so they occasionally fail.
Lustre-change: https://review.whamcloud.com/34225
Lustre-commit:
3ed6b8c2ea27b1a3a9fa073e19d77d7c317ae69f
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: I826659a7f5953dee4e4551c1177479ef742b5589
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34471
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Alex Zhuravlev [Thu, 24 Jan 2019 05:04:09 +0000 (08:04 +0300)]
LU-11330 osd-zfs: hash for ./.. must be 0
do not use current iterator position as hash source for dot and dotdot.
instead just return 0 as hash for these entries.
Lustre-commit:
fb75af7d45d1217c877f75c4296f9df0cc731604
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I5ee439b237e8ed98d295f5672b1d0e8a6b48a55b
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Lustre-change: https://review.whamcloud.com/34098
Reviewed-by: Nathaniel Clark <nclark@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34451
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Alex Zhuravlev [Thu, 7 Feb 2019 09:33:12 +0000 (12:33 +0300)]
LU-9706 dt: remove dt_txn_hook_commit()
it's not used and it's not safe as dt_txn_callback_del()
and dt_txn_callback_add() can race with commit callbacks.
Lustre-change: https://review.whamcloud.com/34212
Lustre-commit:
e763467ebe00913e8d03f855dc4b918b95099931
Change-Id: Ib80b0f69be008b4f895586dde35d1a5833a1a861
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34496
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Wang Shilong [Mon, 10 Dec 2018 05:45:33 +0000 (13:45 +0800)]
LU-11243 lod: fix assertion and hang upon lod_add_device failure
There are two problems:
See following assertion:
lod_add_device() lustre-OSTe42a-osc-MDT0000:
can't set up pool, failed with -12
osp_disconnect() ASSERTION( imp != ((void *)0) ) failed:
osp_disconnect() LBUG
CPU: 1 PID: 10059 Comm: llog_process_th
Problem is obd_disconnect() will cleanup @imp and set NULL.
->osp_obd_disconnect
->class_manual_cleanup
->class_process_config
->class_cleanup
->obd_precleanup
->osp_device_fini
->client_obd_cleanup
While ldo_process_config() will try to access @imp again:
->ldo_process_config
->osp_shutdown
->osp_disconnect
->LASSERT(imp != NULL)
Another problem is if we failed before obd_connect().
we will hang on with mount:
->ldo_process_config
->osp_shutdown
->osp_disconnect
->ptlrpc_disconnect_import
->rc = l_wait_event(imp->imp_recovery_waitq,
!ptlrpc_import_in_recovery(imp), &lwi);
Since connect is not called, imp state will stay LUSTRE_IMP_NEW.
Fix this by check whether we are in recovery properly, only consider
we are in recovery if we are in following states:
LUSTRE_IMP_CONNECTING = 4,
LUSTRE_IMP_REPLAY = 5,
LUSTRE_IMP_REPLAY_LOCKS = 6,
LUSTRE_IMP_REPLAY_WAIT = 7,
LUSTRE_IMP_RECOVER = 8,
Lustre-change: https://review.whamcloud.com/32994
Lustre-commit:
f28353b3d810cfbec018a263556ceac84ab9413e
Change-Id: I2113b95a421bae7117f3057d5f0fdf78db95caa3
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34450
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Nathaniel Clark [Sat, 3 Nov 2018 04:03:43 +0000 (00:03 -0400)]
LU-11555 utils: ZFS check multihost enabled in read_ldd()
For ZFS check that multihost is enabled if failover host is defined.
Print a warning if it's not.
Lustre-change: https://review.whamcloud.com/33491
Lustre-commit:
5e62552e7fc6e9da4068bb29f62eb2cf7a42970e
Test-Parameters: trivial mdtfilesystemtype=zfs ostfilesystemtype=zfs
Signed-off-by: Nathaniel Clark <nclark@whamcloud.com>
Change-Id: Iddb5871afc6fb6808a25921c8d3e8516d675f15c
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Olaf Faaland-LLNL <faaland1@llnl.gov>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34300
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Mikhail Pershin [Thu, 13 Dec 2018 10:11:05 +0000 (13:11 +0300)]
LU-11752 osc: pass client page size during reconnect too
Client page size is reported to the server in ocd_grant_blkbits
and server returns back device blocksize. During reconnect that
ocd_grant_blkbits contains server device blocksize which is used
by server as client page size wrongly.
Patch sets ocd_grant_blkbits to the client page size again during
reconnect so server will get expected information.
Lustre-change: https://review.whamcloud.com/33847
Lustre-commit:
5bec8f95cc1028d207e55e659a27d80081864a83
Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I14bba1d025e4e9fb99fd4bae4002463439ac265c
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34485
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Alex Zhuravlev [Tue, 26 Feb 2019 07:31:53 +0000 (10:31 +0300)]
LU-12018 quota: do not start a thread under memory pressure
this leads to a deadlock as kthreadd creating new threads
can get stuck waiting for memory as well:
PID: 2 TASK:
ffff88015d1e0fb0 CPU: 3 COMMAND: "kthreadd"
Lustre-change: https://review.whamcloud.com/34328
Lustre-commit:
94b11d5a7c55f4f6aff918c3b565b74cb18d04fb
Change-Id: I88f14da24ea64dcc02a9fd1f4a9c03f5771f8fda
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34464
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Patrick Farrell [Thu, 13 Dec 2018 20:21:31 +0000 (14:21 -0600)]
LU-11773 utils: add PFL flags support to YAML API
The setstripe YAML interface currently ignores the
lcme_flags field. This means it doesn't work correctly with
some FLR layouts.
Fixing this is a trivial matter of making the YAML layout
generator read & use the lcme_flags field.
Lustre-change: https://review.whamcloud.com/33852
Lustre-commit:
b71766311daa0faf3560a2435778f7b2de1e3ad6
Signed-off-by: Patrick Farrell <paf@cray.com>
Change-Id: If15999aa58ac3e31da677bd5d1ef8b063b46b1e5
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34454
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Arshad Hussain [Fri, 16 Nov 2018 23:48:41 +0000 (05:18 +0530)]
LU-6142 lod: Fix style issues for lod_dev.c
This patch fixes issues reported by checkpatch for file
lustre/lod/lod_dev.c
Lustre-change: https://review.whamcloud.com/33594
Lustre-commit:
263401f804eb108da2b09ba95bbd441857281c95
Change-Id: I72eaa79a12769e61889e567e5f28fdf3e8045c94
Signed-off-by: Arshad Hussain <arshad.super@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34452
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Li Xi [Tue, 19 Feb 2019 02:33:20 +0000 (10:33 +0800)]
LU-11974 llapi: improve llapi_layout_get_by_xattr(3) API
llapi_layout_get_by_xattr() assumes that the lum has already
been properly swapped by llapi_layout_swab_lov_user_md().
However, llapi_layout_swab_lov_user_md() function is not
exported, so external tool won't be able to use it.
Instead of exporting a lot of APIs, this patch include the
swab functions into llapi_layout_get_by_xattr() and add an
argument flags to the API.
Lustre-change: https://review.whamcloud.com/34276
Lustre-commit:
89e43812da871bb560f3c50a0c36713ea7788e0a
Change-Id: I9fbf0f0ba66660d2f382fb20b03f069c1a7afad5
Signed-off-by: Li Xi <lixi@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34463
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Sebastien Buisson [Mon, 28 Jan 2019 15:16:42 +0000 (00:16 +0900)]
LU-11894 lnet: check for asymmetrical route messages
Asymmetrical routes can be an issue when debugging network,
and allowing them also opens the door to attacks where hostile
clients inject data to the servers.
In order to prevent asymmetrical routes, add a new lnet kernel
module option named 'lnet_drop_asym_route'. When set to non-zero,
lnet_parse() will check if the message received from a remote peer
is coming through a router that would normally be used by this node
to reach the remote peer. If it is not the case, then it means we
are dealing with an asymmetrical route message, and the message will
be dropped.
The check for asymmetrical route can also be switched on/off with
the command 'lnetctl set drop_asym_route 0|1'. And this parameter is
exported/imported in Yaml.
Lustre-change: https://review.whamcloud.com/34119
Lustre-commit:
4932febc121349d855ac9934c538ce688c140afa
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I06fb23d9e46984d79c14fa9b53b2fa04ce3c50c5
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Chris Horn <hornc@cray.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34457
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Wang Shilong [Tue, 26 Feb 2019 14:38:29 +0000 (22:38 +0800)]
LU-12020 llite: make sure name pack atomic
We are trying to access dentry name directly and pass it
down without holding @d_lock, this is racy and possibly
make us trigger assertions:
(mdc_lib.c:137:mdc_pack_name()) ASSERTION( lu_name_is_valid_2(buf, cpy_len) ) failed:
Fix the problem by allocting memory and copy name with @d_lock
held.
Lustre-change: https://review.whamcloud.com/34330
Lustre-commit:
f575b6551b2b8690894baeab95d6fe35e57e9418
Change-Id: Iae0066661f42e8fca9358cbedd9cb21828779bbb
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34465
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Yang Sheng [Tue, 13 Nov 2018 20:17:09 +0000 (04:17 +0800)]
LU-11658 lov: cl_cache could miss initialize
The cl_cache may be missed initialize when we mount
a client with deactivate osc and then active it.
Lustre-change: https://review.whamcloud.com/33650
Lustre-commit:
42e83c44eb5a22cbacf1ed4c6d4d6b588e07faa9
And followup patch:
Lustre-change: https://review.whamcloud.com/33983
Lustre-commit:
c69e34ce0ed5759fbef20f5aae7f47ead5598094
Signed-off-by: Yang Sheng <ys@whamcloud.com>
Change-Id: I92cd44375d70624fb55ef7a0218e7178211a8687
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34306
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Wang Shilong [Thu, 22 Nov 2018 01:23:36 +0000 (09:23 +0800)]
LU-11689 lfs: make sure project proceed all dirs
Leftover fix since LU-10986 lfs: make lfs project tolerant errors
We should proceed other dirs if we hit errors, otherwise,
some dirtree like following will fail if aaaa not exists.
testdir/
├── subdir
│  └── 1
├── bbbb -> aaaa
└── cccc
Also remove extra error output since we have output failing
messages inside every action function.
Lustre-change: https://review.whamcloud.com/33707
Lustre-commit:
e022922fb4a2429d0c2488a13ad8127c068aa2b8
Fixes:
d189024bd306 ("LU-10986 lfs: make lfs project tolerant errors")
Test-Parameters: trivial testlist=sanity-quota,sanity-quota
Change-Id: I0062dbc3f4d1925c9e9e1a509ee35ac569bd9b74
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34307
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
James Nunez [Tue, 15 Jan 2019 00:48:17 +0000 (17:48 -0700)]
LU-11401 tests: add version check sanity-flr tests
sanity-flr test 48 and 203 was added to Lustre tag 2.11.55.
Thus, we need to check that the server version is 2.11.55 or
later before running test 48 and 203.
sanity-flr test 0h checks for a file inheriting the directory
layout. sanity-flr test 37 added ‘lfs mirror write’ functionality.
Inheritance was fixed and ‘lfs mirror write’ was added in Lustre
tag 2.11.57. Thus, we need to check that the server version is
2.11.57 or later before running test 0h and 37.
Lustre-change: https://review.whamcloud.com/33955
Lustre-commit:
fa3b858d5c5b9124591e05a5dcdd98a3ee3619c6
Test-Parameters: trivial testlist=sanity-flr
Test-Parameters: serverjob=lustre-b2_11 serverdistro=el7 serverbuildno=2 testlist=sanity-flr
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: I94c68e900d60e2b97d7f74c6629ee54bcb3a5480
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34298
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
James Nunez [Wed, 2 Jan 2019 22:38:58 +0000 (15:38 -0700)]
LU-11402 tests: add version check sanity-quota 60
sanity-quota test 60 was added to Lustre tag 2.11.53. Thus,
we need to check that the server is 2.11.53 or later before
running test 60.
This patch is back-port from:
Lustre-commit:
d187a78afc960849c3eb86a1a0559c9ba00e8cdf
Lustre-change: https://review.whamcloud.com/33418
Test-Parameters: trivial serverjob=lustre-b2_10 serverbuildno=152 testlist=sanity-quota
Test-Parameters: testlist=sanity-quota
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: I5db738f0776b5615165977df1708f197f215b994
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34094
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
James Nunez [Fri, 28 Dec 2018 16:23:32 +0000 (09:23 -0700)]
LU-11607 tests: create routine to get Lustre env
The Lustre tests in the test suites make repeated calls
to a small number functions that relate to the Lustre
environment. Some examples are the version of the Lustre
server or client and the file system type of the server.
Collect these calls into a routine called get_lustre_env()
in the test-framework.sh library and replace calls in
sanity with the global variables.
Lustre-change: https://review.whamcloud.com/33938
Lustre-commit:
4eb4479b0ea050d99033a9bac9994d2f1509200c
This patch corrected a bracket issue with sanity test 156,
but made the test fail for ZFS testing. Thus, we are
backporting a second patch into this one so this patch
passes testing.
Lustre-change: https://review.whamcloud.com/34114
Lustre-commit:
42c4dab3c817f9f03efe457fd33e946ed68fab14
Test-Parameters: trivial
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: I01dd00dd50cca39c964c5fd8abc3f51ab3c8e6b8
Reviewed-on: https://review.whamcloud.com/33938
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
(cherry picked from commit
4eb4479b0ea050d99033a9bac9994d2f1509200c)
Reviewed-on: https://review.whamcloud.com/34319
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Amir Shehata [Wed, 20 Mar 2019 18:10:34 +0000 (11:10 -0700)]
LU-12065 lnd: increase CQ entries
Several sites have reported RDMA timeouts. Most of the timeouts
are occurring for transmits on the active_tx queue. Transmits are
placed on the active_tx queue until a completion is received. If
there isn't enough CQ entries available, it's possible for a
completions events to be delayed, causing these timeouts.
Lustre-change: https://review.whamcloud.com/34473
Lustre-commit:
bf3fc7f1a7bf82c02181c64810bc3f93b3303703
Test-Parameters: trivial
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I9edad734b5860ce20af4977b4c1cdc07f25f078e
Reviewed-by: Sonia Sharma <sharmaso@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-on: https://review.whamcloud.com/34474
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <hornc@cray.com>
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Patrick Farrell [Tue, 4 Dec 2018 21:16:50 +0000 (15:16 -0600)]
LU-10070 tests: Fix replay-single test_85b
test_85b of replay single sets a default striping on $DIR
and does not remove it. This makes it impossible to
correctly test self-extending layouts, so fix this first.
This patch is back-port from:
Lustre-commit:
0b9fb772e68db7cbf0c8a755092c1d8b5de6b83d
Lustre-change: https://review.whamcloud.com/33777
Cray-bug-id: LUS-2528
Signed-off-by: Patrick Farrell <paf@cray.com>
Change-Id: I0057c8403e3dae2437cf0c8810af8086e2971c35
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Vitaly Fertman <c17818@cray.com>
Reviewed-on: https://review.whamcloud.com/34406
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34470
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Andreas Dilger [Wed, 26 Dec 2018 09:05:37 +0000 (02:05 -0700)]
LU-11770 osc: allow build without blk_integrity or crc-t10pi
Allow the client to build if blk_integrity or crc-t10pi is not
enabled in the kernel.
Lustre-change: https://review.whamcloud.com/33923
Lustre-commit:
e0fb3133372e5bff434ac7a467304d9ba954bac6
Fixes:
ccf3674c9ca ("LU-10472 osd-ldiskfs: T10PI between RPC and BIO")
Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I97c4e75ad084e99927bcb41cf0df8a680525a5b1
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34156
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Li Dongyang [Wed, 19 Dec 2018 03:03:14 +0000 (14:03 +1100)]
LU-11790 ldiskfs: add terminating u32 when expanding inodes
In ext4_expand_extra_isize_ea(), we calculate the total size of the
xattr header, plus the xattr entries so we know how much of the
beginning part of the xattrs to move when expanding the inode extra
size. We need to include the terminating u32 at the end of the xattr
entries, or else if there is uninitialized, non-zero bytes after the
xattr entries and before the xattr values, the list of xattr entries
won't be properly terminated.
Lustre-change: https://review.whamcloud.com/33893
Lustre-commit:
7c800e460661972925a7acab51f023d0b38161b5
Signed-off-by: Li Dongyang <dongyangli@ddn.com>
Change-Id: I247b935b3cf315481dc4658133a7eee02b6350e9
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34314
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Hongchao Zhang [Thu, 15 Nov 2018 16:21:15 +0000 (11:21 -0500)]
LU-11647 ptlrpc: always unregister bulk
In ptlrpc_check_set, the bulk should be unregistered before
ptl_send_rpc in any case.
Lustre-change: https://review.whamcloud.com/22378
Lustre-commit:
21c53b18a1bc0e36d2ecd1fb731f0dc6403902ee
Change-Id: Icf963002f934b43ccbb9d6ef02ba7f9d11f297f8
Signed-off-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34305
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Fri, 14 Dec 2018 22:43:41 +0000 (15:43 -0700)]
LU-8130 libcfs: don't include rhashtable if unavailable
Don't include <linux/rhashtable.h> if it is not available.
Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I80b2ee63fb2a438399359f8052a5063429dd6506
Reviewed-on: https://review.whamcloud.com/34020
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Nathaniel Clark [Fri, 8 Feb 2019 18:02:28 +0000 (13:02 -0500)]
LU-11947 scripts: handle ZFS targets in Lustre RA
Fixes a regression introduced in LU-11461
This handles the case of realpath of target being an empty string.
Fixes:
c36d70272541 ("LU-11461 scripts: Support symlink target")
Lustre-change: https://review.whamcloud.com/34217
Lustre-commit:
aabcfb0af701d641bbe18336b22c7288c96c7115
Test-Parameters: trivial
Signed-off-by: Nathaniel Clark <nclark@whamcloud.com>
Change-Id: I1bcb85908019e968ac0d69e437db217594a6565e
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34316
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Mon, 29 Oct 2018 06:42:46 +0000 (00:42 -0600)]
LU-11579 llite: remove cl_file_inode_init() LASSERT
If there is some corruption or other reason that the file layout
cannot be used, the first call to cl_file_inode_init() will fail.
If it is called a second time on the same file then it will hit
an LASSERT() since I_NEW is no longer set on the inode.
It would be good to handle the error in lov_init_raid0() better,
but we still want to avoid this LASSERT() if there is an error.
Convert the LASSERT() in cl_file_inode_init() into a CERROR() and
error return. This is being triggered due to corruption on the
server, but that shouldn't cause the client to assert.
lov_dump_lmm_common() oid 0xdf4e:311367, magic 0x0bd10bd0
lov_dump_lmm_common() stripe_size 1048576, stripe_count 4
lov_dump_lmm_objects() stripe 0 idx 10 subobj 0x0:
151194471
lov_dump_lmm_objects() stripe 1 idx 12 subobj 0x0:
152477530
lov_dump_lmm_objects() stripe 2 idx 25 subobj 0x0:
151589797
lov_dump_lmm_objects() stripe 3 idx 2 subobj 0x0:
150332564
lov_init_raid0() fsname-clilov: OST0019 is not initialized
cl_file_inode_init() Failure to initialize cl object
[0x20004c047:0xdf4e:0x0]: -5
cl_file_inode_init() ASSERTION(inode->i_state & (1 << 3) ) failed
cl_file_inode_init() LBUG
Pid: 37233, comm: ll_sa_4709 3.10.0-862.14.4.el7.x86_64 #1 SMP
Call Trace:
libcfs_call_trace+0x8c/0xc0 [libcfs]
lbug_with_loc+0x4c/0xa0 [libcfs]
cl_file_inode_init+0x2ac/0x300 [lustre]
ll_update_inode+0x315/0x600 [lustre]
ll_iget+0x163/0x350 [lustre]
ll_prep_inode+0x232/0xc80 [lustre]
sa_handle_callback+0x3a4/0xf70 [lustre]
ll_statahead_thread+0x40e/0x2080 [lustre]
Instead, return an IO error instead of killing the client.
Lustre-change: https://review.whamcloud.com/33505
Lustre-commit:
0baa3eb1a4abe6e1e882cf03b0edfabda20142b7
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: If8a6eb24df09e7e158b61f02e2517132893ebbe5
Reviewed-by: Patrick Farrell <paf@cray.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34302
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Andreas Dilger [Thu, 6 Dec 2018 00:15:05 +0000 (17:15 -0700)]
LU-11736 utils: don't set max_sectors_kb on MDT/MGT
The max_sectors_kb tunable should not be applied to MDT and MGT
devices. This tuning is needed for efficiency of large IOs for
spinning disks, but is not needed for SSDs or regular IO. It can
cause problems with DM Multipath configurations for minimal
benefits, so should be limited to OST devices.
This only applies to ldiskfs backend filesystems, no such tuning
is currently done for any ZFS devices.
Lustre-change: https://review.whamcloud.com/33796
Lustre-commit:
2f8d7b4679de3fa467040aa61733f262714e39c9
Test-Parameters: trivial testlist=conf-sanity
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I496603da13aae042f63cc37c0dea221a393ebbe5
Reviewed-by: Nathaniel Clark <nclark@whamcloud.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34311
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
James Nunez [Tue, 20 Nov 2018 15:38:26 +0000 (08:38 -0700)]
LU-7631 tests: add debug info to conf-sanity 82a
In the routine check_stripe_count, the different error
messages need to be modified so when an error occurs,
a user can tell what error was hit. Also, print precreated
object information at the beginning of the test and on
error.
Test-Parameters: trivial mdscount=2 mdtcount=4 testlist=conf-sanity envdefinitions=ONLY=82a
Test-Parameters: mdscount=1 mdtcount=1 testlist=conf-sanity envdefinitions=ONLY=82a
Lustre-change: https://review.whamcloud.com/33689
Lustre-commit:
e76683a5bd540cacd2271a969aa9acd9bf790ccf
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: Ifc75d52d38d9cb401118ef7baa4014bddf6298f2
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34294
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Andriy Skulysh [Mon, 3 Dec 2018 14:45:18 +0000 (16:45 +0200)]
LU-11757 lod: use calculated stripe count
lod_prep_md_striped_create() tries to allocat big
chunk of memory because
lum->lum_stripe_count == -1 and is converted to __u32.
ldo_dir_stripe_count was calculated already in lod_ah_init()
Lustre-change: https://review.whamcloud.com/33829
Lustre-commit:
622a94d5e27ed3e596918863c08b304a6be9a646
Change-Id: Id99d9e024638dfb1b34262840d2e543c808a9cdc
Cray-bug-id: LUS-6694
Signed-off-by: Andriy Skulysh <c17819@cray.com>
Reviewed-by: Alexander Boyko <c17825@cray.com>
Tested-by: Elena Gryaznova <c17455@cray.com>
Reviewed-by: Vladimir Saveliev <c17830@cray.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34313
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Alex Zhuravlev [Tue, 11 Dec 2018 11:26:13 +0000 (14:26 +0300)]
LU-11737 lfsck: do not ignore dryrun
lfsck_layout_recreate_lovea() shouldn't ignore dryrun.
Lustre-change: https://review.whamcloud.com/33826
Lustre-commit:
875f3fc03aa15049892fe19d6a4fc1132848fced
Change-Id: Ia8bafc13f148b03573dee5db26b6aff9386b5b5f
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34312
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Wed, 7 Nov 2018 02:40:18 +0000 (19:40 -0700)]
LU-11625 ofd: handle upgraded filter_fid properly
Since there have been several iterations of struct filter_fid stored
on disk, the current code wasn't checking for all of the possible
cases when trying to decide what action to take when accessing and
upgrading the xattr for new capabilities.
Properly check for the various different struct filter_fid sizes and
handle them appropriately. Add a more verbose description of the
various cases so that this is more clear to others in the future.
Add decoding of filter_fid fields added for FLR in 2.11.
We should already be testing for upgrading the filter_fid xattr
from different OST versions in conf-sanity test_32d.
Lustre-change: https://review.whamcloud.com/33627
Lustre-commit:
381a8cdd527ce4deccfc3f7eb461892f6f2f3fff
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ifef2292296236cb06ff7e8cd50caff4b133ebbe5
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34304
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Lai Siyao [Sat, 20 Oct 2018 20:50:49 +0000 (04:50 +0800)]
LU-11620 lfsck: change llsd_rb_lock to rwsemaphore
llsd_rb_lock is taken in ->init, and released in ->fini, but during
this period it may getxattr which can sleep. Change it to rwsemaphore.
Lustre-change: https://review.whamcloud.com/33603
Lustre-commit:
925ce153979d6ac793a65e193181ec14a8281640
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Idc68eb886e60dc45ccfb7ac9bf5bf06db42d690d
Reviewed-by: Alexandr Boyko <c17825@cray.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34303
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Chris Horn [Wed, 28 Nov 2018 21:00:25 +0000 (15:00 -0600)]
LU-11712 osd-ldiskfs: Wrap blk integrity with config check
Build is currently broken for kernels without
CONFIG_BLK_DEV_INTEGRITY. Build failure introduced by LU-11096
commit
c8505c2e70d03ba20edf9fcbf431888e87a21147
https://review.whamcloud.com/#/c/32725/
Use of blk integrity should be wrapped in the config check for
HAVE_BLK_INTEGRITY_ENABLED
Lustre-change: https://review.whamcloud.com/33745
Lustre-commit:
fd193758bb95e3fbb4cd04e88f0d964f9cb510cf
Signed-off-by: Chris Horn <hornc@cray.com>
Change-Id: Iac9e4a2572024c026132c87c11042cf353b14d48
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34309
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Tue, 22 Jan 2019 07:53:44 +0000 (00:53 -0700)]
LU-11878 tests: don't fork-bomb sanity test_103b
Running sanity test_103b may start up to 512 parallel threads for
running the test, each of which starts two bash processes and lfs
or rm processes.
For the VMs running in our testbed (esp. ARM with 64KB PAGE_SIZE)
this can trigger the OOM killer and cause the test to fail if bash
is killed. Limit the number of started bash processes to avoid this.
Lustre-commit:
42c5c9c2ca3e44cb1c3e8ecb144bdd20fb35cddb
Lustre-change: https://review.whamcloud.com/34082
Fixes:
543f1fbe260 ("LU-10830 utils: fix create mode for lfs")
Test-Parameters: trivial clientarch=aarch64
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I82c322013da91d717924e2c664fa57ad4e3ebbe5
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Elena Gryaznova <c17455@cray.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34202
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Andreas Dilger [Wed, 2 Jan 2019 22:12:11 +0000 (15:12 -0700)]
LU-11834 llite: fix temporary instance buffer size
The formatting of the cfg_instance variable was changed in LU-11809
to always use a fixed "%016llu" format, but the temporary buffer
allocations for the instance string were not changed to match the
printed value.
This results in string truncation in some situations. Change the temp
buffer size to always have 16 bytes for the instance instead of using
sizeof(cfg_instance).
Fixes:
cd294a1255 ("LU-11809 llite: don't use %p for cfg_instance")
Lustre-change: https://review.whamcloud.com/33951
Lustre-commit:
1db90b29ad676c2cf1888ef5a7c623161ff23bf9
Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I5eca99afa2787cc57e739489b252b12af68cab07
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34315
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Alex Zhuravlev [Sun, 20 Jan 2019 05:38:26 +0000 (08:38 +0300)]
LU-10143 osd-zfs: allocate sequence in advance
on the controller, so that we have it ready before any potential
read-only makeup. this is what osd-ldiskfs is doing already.
Lustre-change: https://review.whamcloud.com/34069
Lustre-commit:
51c449b73994f2bba98ee27ac77f90c9aa846e88
Change-Id: I3d27f112b0d013ac923c5d250b296b5528b8112d
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34295
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Andreas Dilger [Fri, 1 Feb 2019 21:07:01 +0000 (14:07 -0700)]
LU-11721 tests: wait for statfs to update on DNE
Wait for the statfs to update properly when there are multiple
MDTs so that the test doesn't gratuitously fail.
Fixes:
757403191c3 ("LU-11721 utils: print used inodes ratio ...")
LU-11721 tests: wait for statfs to update on DNE
Lustre-commit:
263e80f4572b49044407b09f8a3e393677eafb5d
Lustre-change: https://review.whamcloud.com/34164
Test-Parameters: trivial testlist=sanity mdscount=2 mdtcount=4 ostcount=7
Test-Parameters: testlist=sanity fstype=zfs mdscount=2 mdtcount=4
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ia75f7bd4d3027c91f10ce990730b2bd7123ebbe5
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34321
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Nikitas Angelinas [Thu, 29 Nov 2018 23:23:05 +0000 (15:23 -0800)]
LU-11721 utils: print used inodes ratio when using "lfs df -i"
"lfs df -i" prints the used blocks percentage, instead of the used
inodes percentage. Fix this by allowing obd_statfs_ratio() to
distinguish when "-i" is used.
Round up the ratio returned from obd_statfs_ratio() in a ceiling
manner, to match the output of df(1). Add a sanity test to check
that the outputs from df(1) and lfs df match.
Lustre-commit:
757403191c37db75ed35b02c971846dced5d5119
Lustre-change: https://review.whamcloud.com/33758
Signed-off-by: Nikitas Angelinas <nangelinas@cray.com>
Cray-bug-id: LUS-6748
Test-Parameters: trivial
Change-Id: I0b31ecb7371875c93bc07dda1f1c89e04d5b4576
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34136
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Qian Yingjin [Mon, 26 Nov 2018 02:11:06 +0000 (10:11 +0800)]
LU-11696 utils: "lfs getsom" returns "24" to userspace
The "lfs getsom" command always returns "24" to userspace because
"rc = 24" (sizeof(struct lustre_som_attrs)) after fetching the
xattr from the kernel.
In this patch, rc is set to 0 if the lfs_getsom()->lgetxattr()
call returns a positive value.
Lustre-change: https://review.whamcloud.com/33714
Lustre-commit:
9209e0e9428b6671c6bab9f901e04fdf5b29abc5
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: Ie3151f67b5ce2b5b2bc35a4b6528ba9a20a5db9f
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Nunez <jnunez@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34308
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Artem Blagodarenko [Mon, 18 Dec 2017 17:09:15 +0000 (20:09 +0300)]
LU-10384 mgs: replace_nids large string and failover support
Replace_nids uses nids list as new UUID. UUID string
length is limited by 38 symbols. So new nids list need
to be less then 38 symbols.
With this patch first nid in list string representation
is used for UUID as this done for failover nids.
Replace nids finds records for given device and regenerates
lines that contain old nids. add_uuid and add_conn lines for
failover used to be deleted during replace_nids which breaks
failover configuration.
This patch adds failover support to replace_nids command.
For example:
lctl replace_nids lustre-MDT0000 nid1,nid2:nid3,nid4:nid5,nid6
nid3,nid4 - nids from first failover node
nid5,nid6 - nids from second failover node
Lustre-change: https://review.whamcloud.com/30624
Lustre-commit:
09da1564d3794ca7b82e1c1791da253bee6178d4
Signed-off-by: Artem Blagodarenko <c17828@cray.com>
Cray-bug-id: MRP-4505
Change-Id: I4e9a35e8fa8781909ecbaa74785700f4ca04cf92
Reviewed-by: Vladimir Saveliev <c17830@cray.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34296
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Jian Yu [Thu, 21 Feb 2019 20:15:12 +0000 (12:15 -0800)]
LU-11739 lod: don't inherit default layout from root directory
There is no need to inherit the default directory layout from
the root directory when subdirectories are created therein.
This consumes xattr space on the subdirectories, and makes it
more complex to change the filesystem default layout in the future.
This patch fixes the above issue in lod_ah_init() to check if
the parent directory is the root directory and not copy
the default layout xattr to the new subdirectory.
Lustre-change: https://review.whamcloud.com/33956
Lustre-commit:
0a988cae95f99fee1a9c0d489ce00d0954d2a68e
Lustre-change: https://review.whamcloud.com/34175
Lustre-commit:
ad1a74527f0ec59510bfa124b8280617a2b93840
Change-Id: Ie0d286785bdbcd73e2ae60b429e66d5d54b44eef
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34135
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
James Nunez [Mon, 7 Jan 2019 18:06:36 +0000 (11:06 -0700)]
LU-11161 tests: start running sanity 160g again
sanity test 160g was failing when run in a DNE configuration
and we stopped running this test meaning added to the
ALWAYS_EXCEPT list. The problem is that the test did not
write enough files to exceed changelog idle index threshold
for deregistering users.
Start running sanity test 160g with DNE testing again.
Lustre-change: https://review.whamcloud.com/33994
Lustre-commit:
22676740969314b1b08a31c24e5ebc4c403e08f2
Test-Parameters: trivial
Test-Parameters: ostfilesystemtype=ldiskfs mdtfilesystemtype=ldiskfs clientcount=2 mdscount=2 mdtcount=4 osscount=1 ostcount=8 testlist=sanity
Signed-off-by: James Nunez <jnunez@whamcloud.com>
Change-Id: I286ef8eb7c4638ff8f357db54c4926d5a2f20ac4
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/34297
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
git://git.whamcloud.com / fs / lustre-release.git / log