LU-8346 obdclass: protect key_set_version

In lu_context_refill, the key_set_version should be protected
before comparing it to version stored in the lu_context.

This patch is a supplement of the previous patch
https://review.whamcloud.com/#/c/28405/, which adds protection
for key_set_version from modification in lu_context_refill
and lu_context_key_degister.

Lustre-change: https://review.whamcloud.com/27448
Lustre-commit: 4538de675cc1ee05408fa912e71c65d9109d7027

Change-Id: I201f56214382a717cfc31ba573e06fec9fbedae4
Signed-off-by: Hongchao Zhang <hongchao.zhang@intel.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/31017
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10463 osd-zfs: use 1MB RPC size by default

Revert back to using 1MB RPC size for ZFS back-end storage, if it
is not otherwise specified, and as long as the ZFS recordsize is
1MB or smaller.  Continue to use the ZFS recordsize if it is larger.

For ldiskfs, continue to use 4MB RPC size, unless the bigalloc
feature is enabled and has a larger chunksize.

Testing has shown that while 4MB RPC size is good for ldiskfs, it
does not improve ZFS performance, and increases IO variability in
some cases.

Lustre-change: https://review.whamcloud.com/30757
Lustre-commit: af34a876d2ebde2b4717c920683c7fc8b5eae1cf

Signed-off-by: Andreas Dilger <andreas.dilger@intel.com>
Change-Id: I4b306843667bfd960ad07ecc3886a696fd3ebbe5
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30969
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10237 mdc: interruptable during RPC retry for EINPROGRESS

Sometimes, some system resource may be inaccessible temporarily,
for example, related OI mapping is crashed and has yet not been
rebuilt. Under such case, the server will reply the client with
"-EINPROGRESS", then client will retry the RPC some time later.

Currently, the client will retry infinitely until related RPC
succeed or get other failure. But we do not know how long it
will be before related resource becoming available. It may be
very long time as to the RPC sponsor - the application or the
user does not want to retry any more, then we need to make the
logic to be interruptable. This patch is for such purpose.

Lustre-change: https://review.whamcloud.com/30166
Lustre-commit: 9c596a4996ee242aa1b954f5f2f19101d3941bf0

Signed-off-by: Fan Yong <fan.yong@intel.com>
Change-Id: I4f939f9a350d3a99ce3d3af37d0dea8ab8030fee
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Mike Pershin <mike.pershin@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30903
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10444 utils: Don't remount debugfs every time

Check if debugfs is mounted at /sys/kernel/debug and only
mount if it is not.

Lustre-change: https://review.whamcloud.com/30675
Lustre-commit: 767f03b161ae44bd9d33dae7e03e71e73852813f

Change-Id: Ib31bd8f7c5c93ab942c6708ed3a4d17a11159e95
Signed-off-by: Oleg Drokin <oleg.drokin@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30900
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-8999 test: ignore unrelated quota id

In test_38 of sanity_quota, the quota id larger than 9999
should be ignored.

Lustre-change: https://review.whamcloud.com/30730
Lustre-commit: 8a0a9190cd0a68a88e42210e9c3dac324319fa6d

Change-Id: I12e7936c0c1abc2dcaad7646a048c98bb37de254
Signed-off-by: Hongchao Zhang <hongchao.zhang@intel.com>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30896
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-6051 utils: allow lfs_migrate to migrate links

When running on a server that supports "lfs migrate", it is possible
to migrate hard links transparently.  This is still not possible for
servers that do not support "lfs migrate" (layout swap) so we still
need to keep the hard-link check if "lfs migrate" fails.

Add test for migrating many hardlinks on supported kernels.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/27553
Lustre-commit: 6086d0d69c84ce57c4daff18595fa7b620ed2b04

Signed-off-by: Andreas Dilger <andreas.dilger@intel.com>
Change-Id: I7fa1c70611aa7dd61f822844d5fe339f730640e5
Reviewed-by: Steve Guminski <stephenx.guminski@intel.com>
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30799
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10357 hsm: open file to be archived before starting

In the archive case of llapi_hsm_action_begin(), open the file to be
archived before calling the LL_IOC_HSM_COPY_START ioctl. Store the
open FD in struct hsm_copyaction_private, return a dup of it
llapi_hsm_action_get_fd(), and close it in
llapi_hsm_action_end(). Calling open() first avoids 3 extra RPCs
(MDS_GETATTR, LDLM_ENQUEUE for layout to get data version,
LDLM_ENQUEUE for fstat()) when archiving.

Lustre-change: https://review.whamcloud.com/30456
Lustre-commit: 77cd1a21e312ca00b37b33689091734a12eec048

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Idea0a7f4cb63bd9d712ff2ce9fcb59a3b278d0f2
Reviewed-by: Quentin Bouget <quentin.bouget@cea.fr>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30721
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10341 hsm: filter kkuc write by client UUID

Add a struct obd_uuid kr_uuid member to struct kkuc_reg to hold the
UUID of the client (super block) that owns the kkuc pipe. Modify
libcfs_kkuc_group_{put,rem,foreach}() to accept a UUID pointer which
filters the kkuc pipes operated on. Modify mdc_hsm_copytool_send() to
pass the UUID of the MDC device when calling
libcfs_kkuc_group_put(). The effect of all this is that HALs received
by a given MDC will only be delivered to copytools registered on the
corresponding mount point.

Remove the cluuid member of struct lmv_obd since it is always the same
as the obd_uuid member of the corresponding struct obd_device. Remove
the kcd_uuid member of struct kkuc_ct_data as it is no longer needed.

Lustre-change: https://review.whamcloud.com/30419
Lustre-commit: c73736545fafac4373569187e064aab9cd435320

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Ibbda253979739a1d56d3e132a51a482a02a0ec27
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: Faccini Bruno <bruno.faccini@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30719
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-9998 libcfs: split single NUMA node into partitions

For machines with single NUMA node change default behavior
and slpit it with cpu_npartitions as it was before 2.8.59.
See LU-5050 libcfs: default CPT matches NUMA topology

Lustre-change: https://review.whamcloud.com/29645
Lustre-commit: c9d14a01263bd0fb7a5fac853b5e2d34ff8cadab

Change-Id: I7f9122931a88fd5770628d7ae21b764efc21c134
Signed-off-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: Sonia Sharma <sonia.sharma@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30690
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10462 lod: Correct lfs --component-add striping

lfs --component-add -E <end> -c -1 would apply the default
stripe count to a file when it should be striping across
all OSTs. This was due to incorrect handling of sentinel
values in various portions of lod_object.

Lustre-change: https://review.whamcloud.com/30790
Lustre-commit: b7285d387c78fbd11579c577230593ba1b0be84e

Signed-off-by: Giuseppe Di Natale <dinatale2@llnl.gov>
Change-Id: I178f13be81ee546f44edcdadcf7086a1a57f7e9a
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/31048
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10437 lod: clear layout header when generating layout

LOD needs to clear layout header otherwise the lcm_flags and
lcm_padding will be random data, which will create issues when
those fields are used by future module.

It already confused FLR because it uses lcm_flags and mirror_count
to do sanity check.

Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Change-Id: If9511e6691144debd51ccab575ef4479d0c9b865
Reviewed-on: https://review.whamcloud.com/30784
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10297 lod: prepare inuse array always

The OST inuse array should be prepared for composite files and for
plain files as well, since creating OST objects in both cases needs
to use it.

Lustre-change: https://review.whamcloud.com/30334
Lustre-commit: 2cca16ba7da4070c319cc6230b7dbb3e7a91e323

Signed-off-by: Bobi Jam <bobijam.xu@intel.com>
Change-Id: Ibb37b680c68f8883650cdee6bebebc1c4d844623
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30486
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10422 lfsck: misc fixes to avoid unexpected repairing

There are several issues that will misguide LFSCK to
trigger unexpected RPC or repairing by wrong, including:

1) object_update_result_insert() should pack the OUT RPC
   result (not the return value) into the reply buffer via
   object_update_result::our_data. But it did that in some
   wrong address.

2) out_xattr_get() used wrong index to obtain the EA buffer
   as to may overwrite former update (such as OUT_XATTR_GET)
   results.

3) osp_declare_xattr_get() does not consider the last '0'
   of the EA name for the length parameter for
   osp_insert_async_request().

4) osp_xattr_get_interpterer() missed to handle the positive
   value for the given parameter @rc. That will cause the PFID
   EA to be double read when the target OST-object has it.

Back port from master:
Lustre-commit: bf0448c16e6d311b4773a80ec02ed9c48e8c11f4
Lustre-change: http://review.whamcloud.com/30612

Signed-off-by: Fan Yong <fan.yong@intel.com>
Change-Id: Ibf0e095ae2735c60b9b88e4b0992389c906728f9
Reviewed-on: https://review.whamcloud.com/30628
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10321 lfsck: not start lfsck during umount

There is race condition bewtween lfsck_start and umount:
the LFSCK may be triggered just after the LFSCK stopped
during umount the target, then nobody will stop the new
started LFSCK, as to the umount may be blocked.

This patch sets flag on the lfsck instance when umount
that will prevent subsequent lfsck_start.

This is a port to b2_10 of
Lustre-change: https://review.whamcloud.com/#/c/30513/
Lustre-commit: 6263064b369dd4fddbb0dfa9ab49013a0d791629

Signed-off-by: Fan Yong <fan.yong@intel.com>
Change-Id: I779f862d4195d4289bb9dd96575cd7746ac4b35b
Reviewed-on: https://review.whamcloud.com/30514
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10321 lfsck: allow to stop the in-starting lfsck

The LFSCK start logic will hold li_mutex on the lfsck instance
during LFSCK start processing. The LFSCK stop logic also needs
to take the li_mutex on the lfsck instance when stop the LFSCK.
If someone triggers lfsck_stop (such as when umount the target)
before the lfsck_start return, then lfsck_stop will be blocked
on the li_mutex. And if the li_mutex holder is blocked by other
things, for example, it may be waiting for the LFSCK RPC to be
handled by remote server (MDT/OST) but the connection or remote
server is not ready yet, then the lfsck_stop will be blocked.

To avoid such cascade block trouble, the patch makes lfsck_stop
can go ahead without taking li_mutex, then it can directly tell
related LFSCK engines the stop event even if former lfsck_start
does not complete yet.

This is a port to b2_10 of
Lustre-change: https://review.whamcloud.com/#/c/30420/
Lustre-commit: 7817928a62c8a212f5c2b040587042c193bd5c1a

Signed-off-by: Fan Yong <fan.yong@intel.com>
Change-Id: I6e168d955db33d74778142235a8ed2802d3577d9
Reviewed-on: https://review.whamcloud.com/30422
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10564 kernel: kernel update RHEL6.9 [2.6.32-696.20.1.el6]

Update RHEL6.9 kernel to 2.6.32-696.20.1.el6

Test-Parameters: clientdistro=el6.9 mdsdistro=el6.9 \
  ossdistro=el6.9 mdtfilesystemtype=ldiskfs \
  ostfilesystemtype=ldiskfs testgroup=review-ldiskfs

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: I5d72a5416e091b2690f56764eb4d195b8137d405
Reviewed-on: https://review.whamcloud.com/31066
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Reviewed-by: Yang Sheng <yang.sheng@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10563 kernel: kernel update RHEL7.4 [3.10.0-693.17.1.el7]

update RHEL 7.4 kernel to 3.10.0-693.17.1.el7

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: I1302c2de6d8eebb33ca741dd357b65579ce71d7d
Reviewed-on: https://review.whamcloud.com/31035
Reviewed-by: Yang Sheng <yang.sheng@intel.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9892 test: fix SuSe nfsserver setup

Checking for SuSE-release and use nfsserver
Add export info to a /etc/exports

Test-Parameters: trivial testlist=parallel-scale-nfsv4 clientdistro=sles12sp3

Lustre-change: https://review.whamcloud.com/#/c/30476/
Lustre-commit: 9f07081fd9f57bd6bd52a8c26d28a477a0c20cfb

Change-Id: Id12370ae35d878e51bdf6f71a77b1b82b5e82c33
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30809
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10327 test: use nogroup instead of nobody

In Ubuntu, there isn't any nobody group

Lustre-change: https://review.whamcloud.com/#/c/30559/
Lustre-commit: 6229a5ff318471fda18daceec79143007c4b204f

Change-Id: I2d4607b3d1384d2d619dd9640363533f92397356
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30772
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10161 lbuild: fix the problem of determine default_iface

The script of determining the default interface is broken.
Remove complexity and replace with hostname

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/29776
Lustre-commit: bac71754b9dbb83b3ccf10ae99c027cc6b2f9829

Signed-off-by: Li Xi <lixi@ddn.com>
Change-Id: I0d662e9e24bed17078e31b6b5ca305cff2c0548e
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Gu Zheng <gzheng@ddn.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30273
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9899 tests: mount client on MGS for tests with pools

When a Lustre file system has the MGS and MDS on separate
nodes, the file system must be mounted on the MGS to allow
OST pools to work properly.

There are several tests that deal with creating, adding
to and deleting OST pools. Create functions to mount and
unmount the file system on the MGS in test-framework and call
these functions when necessary for the Lustre test suites
conf-sanity test 82b, 103
sanity tests 27D, 200, 220, 406 and
replay-single test 85b.

This is a port from master to b2_10 of
Lustre change: https://review.whamcloud.com/28806
Lustre commit: 75d6d35bcc48eefe490e8b4efd673c58b3373507

Test-Parameters: combinedmdsmgs=false testlist=sanity,replay-single,conf-sanity
Signed-off-by: James Nunez <james.a.nunez@intel.com>
Change-Id: I4b3e331b8d1ea6c3f8c9ea8a571e26f66f4535f8
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Reviewed-on: https://review.whamcloud.com/30217
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9946 nodemap: have fileset on default nodemap.

When a directory is defined as fileset on the default nodemap entry,
all clients that fall into default will be imposed subdirectory
mount on this directory.

Lustre-change: https://review.whamcloud.com/28858
Lustre-commit: 8ed31f48b3492909739a35ae6a0fbde111f7f028

Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I3491bce4f8c2011629e56494bf1a0de57f19829d
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Emoly Liu <emoly.liu@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29943
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-9052 lod: accept lfs mkdir from old client

MDS should also accept create striped directory request
from old client, but it will only honour stripe index in
this case, since the old client can only create remote
directory.

And also move the magic check from LOD to MDD to validate
LMV as early as possible.

Directory creation for echo client should go with lmv_user_md,
otherwise validation on user md will fail.

For striped directory, echo client should first choose stripe
before MD operation.

And also remove some unecessary lmv audit.

Re-enable 225b tests for DNE to test echo operations on
striped directory.

In mds-survey, if the current environment has more than one MDS,
let's skip the test. Because echo test will attach echo_client
individually on each MDSs(all of MDDs on the MDS), so each echo
client will not be able to access all of MDTs. But the test will
create a striped dir by MAX MDS count internally in mds_survey,
so echo client can not resolve the directory path in this case.

Lustre-change: https://review.whamcloud.com/25091
Lustre-commit: 069f593572509d6ee285ba6ea8950101ccb62d72

Signed-off-by: Di Wang <di.wang@intel.com>
Change-Id: I74a3712edfa36fd178f92965f8e35f5ff77ad422
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-on: https://review.whamcloud.com/30542
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-8653 lod: use stripe_count instead of stripe_nr

Replace the use of stripenr and stripecnt in the code with
stripe_count to be consistent the rest of the code.

Introduce LOV_PATTERN_NONE instead of using "0" around the
code to indicate no layout has been specified.

Introduce LOV_PATTERN_DEFAULT to indicate the entire layout
is unset, instead of using "0xffffffff" in the code.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/26681
Lustre-commit: 53d3890f16e4c6e5717c4d020ef213897a36c2b7

Signed-off-by: Andreas Dilger <andreas.dilger@intel.com>
Change-Id: I6056aebc1a381b09c1a436fb4a7986a51f3ebbe5
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: Steve Guminski <stephenx.guminski@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29142
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

New release 2.10.3.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Ieb54fe23c9417dc77cbf1e1933bfd9921444bd75

New tag 2.10.3-RC1.

First release candidate for 2.10.3 release.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Ifa0083fadb85c46fa5daca028a3bbd96456845c9

LU-10399 test: use /dev/urandom in sanity-hsm test_1b()

In sanity-hsm test_1b() use /dev/urandom instead of /dev/random so we
won't have to wait for the second law of thermodynamics to become
true.

Test-Parameters: trivial testlist=sanity-hsm
Lustre-change: https://review.whamcloud.com/30556
Lustre-commit: 54cf0962e286b8f1bcfca490cf828fd126f1fa60

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Ib64691fd6ee1a172c631ffa55956e1d69f24d349
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: Quentin Bouget <quentin.bouget@cea.fr>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30722
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10371 ptlrpc: check for posix_acl a_entries

Since commit 2211d5ba5c6c4e972ba6dbc912b2897425ea6621
posix_acl_xattr_entry a_entries[0] was removed.
Make sure the LASSERTF test works with Kernels
after this commit.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/30495
Lustre-commit: 429ad0e18eccd7261011ee2c7c193b822747e732

Signed-off-by: Thomas Stibor <t.stibor@gsi.de>
Change-Id: If2404c89775a5f9077c7d9379d73c8187b796a3a
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30691
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-618 llite: IO accounting of page read

When CONFIG_TASK_IO_ACCOUNTING is used with Lustre, writes are
accounted for but not read.

The accounting is normally done in the kernel for page writeback
and readahead functionlity, Therefore, as Lustre implements its
own readahead, it must also maintain its own accounting on read
(but not for write)

Lustre-change: https://review.whamcloud.com/1636
Lustre-commit: 48de9b195d71cb57ee50636d75c59d78ee068cee

Change-Id: I19f330be65324a8da002f9d61cb9262345ecb012
Signed-off-by: Hongchao Zhang <hongchao.zhang@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-on: https://review.whamcloud.com/30570
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10377 build: Update ZFS Version to 0.7.5

Update SPL and ZFS version that is built against.

https://github.com/zfsonlinux/zfs/releases/tag/zfs-0.7.5

Signed-off-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Change-Id: If010d3a7e78b66a2acbd70242fe517218a438c02
Reviewed-on: https://review.whamcloud.com/30523
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10464 kernel: kernel update [SLES12 SP2 4.4.103-92.56]

Update target and kernel_config files for new version

Test-Parameters: clientdistro=sles12sp2 testgroup=review-ldiskfs \
  mdsdistro=sles12sp2 ossdistro=sles12sp2 \
  mdtfilesystemtype=ldiskfs ostfilesystemtype=ldiskfs

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: I0eb5dc783bcbcd4ee8643431345daefb9cb89eb1
Reviewed-on: https://review.whamcloud.com/30750
Tested-by: Jenkins
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10458 kernel: kernel update [SLES12 SP3 4.4.103-6.38]

Update target and kernel_config files for new version

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

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: Ib7a308dbce58d94c5f5775cd54f33563cf067e75
Reviewed-on: https://review.whamcloud.com/30743
Tested-by: Jenkins
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10456 kernel: kernel update RHEL6.9 [2.6.32-696.18.7.el6]

Update RHEL6.9 kernel to 2.6.32-696.18.7.el6

Test-Parameters: clientdistro=el6.9 mdsdistro=el6.9 \
  ossdistro=el6.9 mdtfilesystemtype=ldiskfs \
  ostfilesystemtype=ldiskfs testgroup=review-ldiskfs

Change-Id: Ib0b7d5ff7f50f96c8bbc064541ae5c8bf2a4367f
Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-on: https://review.whamcloud.com/30737
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Tested-by: Jenkins
Reviewed-by: Minh Diep <minh.diep@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10455 kernel: kernel update RHEL7.4 [3.10.0-693.11.6.el7]

update RHEL 7.4 kernel to 3.10.0-693.11.6.el7

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: Id3428aa00e4b1501b642587db7911b6adafd51ef
Reviewed-on: https://review.whamcloud.com/30735
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10427 kernel: kernel update [SLES12 SP2 4.4.103-92.53]

Update target and kernel_config files for new version

Test-Parameters: clientdistro=sles12sp2 testgroup=review-ldiskfs \
  mdsdistro=sles12sp2 ossdistro=sles12sp2 \
  mdtfilesystemtype=ldiskfs ostfilesystemtype=ldiskfs

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: I065ab670ad58fda19610e14440e1c304d0eae74f
Reviewed-on: https://review.whamcloud.com/30652
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Yang Sheng <yang.sheng@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10425 kernel: kernel update [SLES12 SP3 4.4.103-6.33]

Update target and kernel_config files for new version

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

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: Ibdaf6edeb34388d3d9bf39dc7f84639d5fb9992f
Reviewed-on: https://review.whamcloud.com/30648
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Yang Sheng <yang.sheng@intel.com>
Reviewed-by: Cliff White <cliff.white@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-8999 test: check chown result

For test_38 in sanity-quota, the chown operation should be
checked whether it succeeds or not. the patch also collects
the output of quota users if the test failed.

Lustre-change: https://review.whamcloud.com/30243
Lustre-commit: 817b367707d0d4f5c406b4f18cffceea2aae8406

Change-Id: I6c04f9519f3f097af7126064380faf1bdc4fff6a
Signed-off-by: Hongchao Zhang <hongchao.zhang@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30631
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10232 lov: call cl_object_attr_get under cl_attr lock

cl_object_attr_get() must be called under cl_object_attr_lock
get. There is place in lov_getstripe where it is called
without that lock.

Lustre-change: https://review.whamcloud.com/30052
Lustre-commit: 80515fa15ee76fb0174fd3be80c4a113a8d3c875

Signed-off-by: Mikhail Pershin <mike.pershin@intel.com>
Change-Id: Ia0a2322ba4ff0ff4affb081375cb108fbf2988c4
Reviewed-by: Fan Yong <fan.yong@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30586
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10346 utils: use the correct lib path in mount_utils.c

The backfs_load_module() function of mount_utils.c used an outdated
to link itself against the osd library. This patch fixes it.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/30431
Lustre-commit: 74eb79b0fe4815daa0bebd3293c71f052c5b19d4

Signed-off-by: Quentin Bouget <quentin.bouget@cea.fr>
Change-Id: I90a523b45b5772c05f7520e810eec7eac14b75be
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30584
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9535 tests: check server version in sanityn 77j

The QoS feature in the TBF policy was added to Lustre with
tag 2.9.53 and a patch with commit hash d2c403363f6. Thus,
sanityn test 77j should only be run for servers with version
2.9.53 and later.

Test-Parameters: trivial mdsjob=lustre-b2_9 ossjob=lustre-b2_9 serverbuildno=2 testlist=sanityn

Lustre-change: https://review.whamcloud.com/30385
Lustre-commit: 8552476c5495a94d22501d002a35830181b5ea7d

Signed-off-by: James Nunez <james.a.nunez@intel.com>
Change-Id: Ia2a04b5ae688809d4a84a2dc8459598f02932119
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: Saurabh Tandan <saurabh.tandan@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30583
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10267 llog: fix EOF handling in llog_client_next_block()

In llog_client_next_block() update *cur_idx and *cur_offset in the
special case that the handler has returned -EIO after reaching the end
of the log without finding the desired record. This fixes client side
EOF detection in llog_process_thread().

Lustre-change: https://review.whamcloud.com/30313
Lustre-commit: a485c51379a0218aaf01f7c0baf8e4cc993d8824

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: If30ebec065ddd38fb7b06c3e16f96bb3cd76fa1b
Reviewed-by: Mike Pershin <mike.pershin@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30582
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10268 lfsck: postpone lfsck start until initialized

Sometimes, the LFSCK start request may comes (from remote server)
before local target initialized. If we start the LFSCK right away
on current server, the LFSCK engine may access NULL pointer, such
as lookup FID with NULL 'ss_server_fld'.

To avoid such trouble, start LFSCK logic will return -EINPROGRESS
to the request sponsor. It is the sponsor duty to retry the start
request some time later.

This is a port to b2_10 of
Lustre-change: https://review.whamcloud.com/#/c/30259/
Lustre-commit: 6ec4b7d3fb7351f699569e1a8f5ad2cfa7c78df9

Signed-off-by: Fan Yong <fan.yong@intel.com>
Change-Id: If7bc44e025b5f3c4f977b3a35e3784ada548a2df
Reviewed-on: https://review.whamcloud.com/30421
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10134 lfsck: not add requests if engine out of work

There is race condition between LFSCK assistant engine and
LFSCK request generators: before the LFSCK assistant engine
exit, it will mark itself as 'stopping', then cleanup the
in-queue requests, and then mark itself as 'stopped'. It is
expected that the 'stopping' status will prevent generators
adding more LFSCK requests. But current implementation only
checks 'stopped' or not. So if the LFSCK engine thread exit
before the whole system scanned that may because of some
failures or on demand, more LFSCK requests may be added in
the queue after the cleanup.

The patch fixes the wrong logic by checking 'running' or not,
and stop adding more LFSCK requests if not 'running'.

This is a port to b2_10 of
Lustre-change: https://review.whamcloud.com/#/c/30165/
Lustre-commit: 159bde49676b9a49eb3e4cb57c8c3a58a49ba0af

Signed-off-by: Fan Yong <fan.yong@intel.com>
Change-Id: Ic2b5ca3f5e80b5be5a5c60aa24f0b54682b717d9
Reviewed-on: https://review.whamcloud.com/30375
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-5020 llite: don't reconnect MGC if connecting

1. In mgc_set_info_async(KEY=KEY_INIT_RECOV_BACKUP "init_recov_bk"),
   the MGC import should be reconnected only if its state is
   LUSTRE_IMP_DISCON

2. in mgc_target_register, if the target will regenerate the config,
   we should use some longer delay limit to wait the MGC to connect
   to MGS for the target (server) will fail to exit if the request
   expired due to delay limit.

3. In case of parallel mount, the async cleanup of OSS will affects
   the following mount for the OSS can't be setup again, then there
   should be some barrier to sync with the OSS cleanup.

Lustre-change: https://review.whamcloud.com/10229
Lustre-commit: 1a7ff02c1fbb8e85ac2e8fa458ba3fb810a76ea4

Change-Id: I805b84cf12100ec2cc68f95bb65a9c396e0fbc1b
Signed-off-by: Hongchao Zhang <hongchao.zhang@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30581
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-4134 obdclass: fix double free in failure path

We should just decref for obd if register is failed.
Since class_export_put will invoke class_free_dev,
then we may face a double free.

Lustre-change: https://review.whamcloud.com/29967
Lustre-commit: 77d2e604b6bc3c319adefca069b5182c325a43b0

Signed-off-by: Yang Sheng <yang.sheng@intel.com>
Change-Id: Ia8d1e487c69c4de1c7c247158cc8615aa6b6093a
Reviewed-by: Alexey Lyashkov <c17817@cray.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30487
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-4134 obdclass: obd_device improvement

The patch removes self exports from obd's reference counting which
allows to avoid freeing of self exports by zombie thread.
A pair of functions class_register_device()/class_unregister_device()
is to make sure that an obd can not be referenced again once its
refcount reached 0. For target_handle_connect() take a reference for
obd_device during finding it by name.

Fix grant mismatch message
"tot_granted 4194304 != fo_tot_granted".

Lustre-change: https://review.whamcloud.com/8045
Lustre-commit: 45900a7777ac02130d8bf65724c4b6cffca9d546

Signed-off-by: Vladimir Saveliev <vladimir.saveliev@seagate.com>
Signed-off-by: Alexey Lyashkov <alexey.lyashkov@seagate.com>
Signed-off-by: Alexander Boyko <alexander.boyko@seagate.com>
Seagate-bug-id: MRP-2139 MRP-3267
Change-Id: I9cc6860431c6bb7db6983e0d15a5d3d2b564265e
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Alexey Lyashkov <c17817@cray.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29740
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10301 kernel: kernel update RHEL7.4 [3.10.0-693.11.1.el7]

update RHEL 7.4 kernel to 3.10.0-693.11.1.el7

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: Iea7a4604c333c26fdc1b2439e6a00f27472d2410
Reviewed-on: https://review.whamcloud.com/30441
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Reviewed-by: Yang Sheng <yang.sheng@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9558 llite: port lustre to unified handling of bdi

For the linux 4.12 kernel the bdi handling was unified for all
file systems. This was done by allocating struct backing_dev_info
separately instead of embedding it inside superblock. For older
kernels we move all the bdi handling lustre does to the function
super_setup_bdi_name() which is what exist in the latest kernels.

Linux-commit: 9594caf216dc0fe3e318b34af0127276db661241

Lustre-change: https://review.whamcloud.com/28511
Lustre-commit: 1defa62a19e71c021ec2cf9fc9e0481e9ab962e0

Change-Id: I5af60ea3661e3d3a97973fd99a79c28dcd1ce1cc
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Reviewed-on: https://review.whamcloud.com/30575
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-7340 mdd: changelogs garbage collection

When changelogs are almost full (few number of
free entries in catalog), try to recover some space
by unregistering users that are idle since too long,
based on new Changelog User record field (in fact,
using previous cur_padding unused field) to keep
track of last user's changelog cancel request time,
or based on gap between user index and current
ChangeLog record, for older registered user.
sanity/test_160[f,g] have been added to verify feature.

Lustre-change: https://review.whamcloud.com/27103
Lustre-commit: 3442db6faf685fbdbd092bdfdc8d273e4990a141

Signed-off-by: Bruno Faccini <bruno.faccini@intel.com>
Change-Id: I2100b101772e6d027675e5efa5606d4be24342a0
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Stephan Thiell <sthiell@stanford.edu>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30573
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9558 kernel: replace CURRENT_TIME macro

CURRENT_TIME macro is not y2038 safe on 32 bit systems.

The patch replaces all the uses of CURRENT_TIME by current_time() for
filesystem times, and ktime_get_* functions for others.

struct timespec is also not y2038 safe.  Retain timespec for timestamp
representation here as lustre uses it internally everywhere.  These
references will be changed to use struct timespec64 in a separate patch.

This is also in preparation for the patch that transitions vfs
timestamps to use 64 bit time and hence make them y2038 safe.
current_time() is also planned to be transitioned to y2038 safe behavior
along with this change.

CURRENT_TIME macro will be deleted before merging the aforementioned
change.

Linux-commit: 47f38c539e9a42344ff5a664942075bd4df93876

Lustre-change: https://review.whamcloud.com/28305
Lustre-commit: 213db47f6497c0ea49ffef19de0d4673c932eefd

Change-Id: Iec67df8f48066801c227aba2bc9221d444dada65
Link: http://lkml.kernel.org/r/1491613030-11599-10-git-send-email-deepa.kernel@gmail.com
Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30572
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-7991 quota: project quota against ZFS backend

This patch enables the project quota feature against ZFS
backend. The project quota patch for ZFS itself will be
landed via https://github.com/zfsonlinux/zfs/pull/6290.
Such patch may be released via zfs-0.7.x (x >= 5).

This patch also cleanup the quota logic for ZFS backend
and sanity-quota.sh

Lustre-change: https://review.whamcloud.com/27093
Lustre-commit: a046e879fcadd601c9a19fd906f82ecbd2d4efd5

Signed-off-by: Fan Yong <fan.yong@intel.com>
Change-Id: Ic488efe19a6e34a3615811f79fb9ea7954ad9263
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/30540
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-7988 hsm: wake up cdt when requests are empty

The coordinator only runs once per second, we need a mechanism
to send more work when everything is done (cdt_request_count
goes to zero)

Without this, there is a hard limit of max_requests per sec
requests that can be processed, causing performance issues
with small files.

Lustre-change: https://review.whamcloud.com/29742
Lustre-commit: 7251fea8dc3c4d29e30c5a3f763c4c33d35f90a7

Signed-off-by: Ben Evans <bevans@cray.com>
Change-Id: I563666a1a3e53f0ec5908de593de71ff4d925467
Reviewed-by: Frank Zago <fzago@cray.com>
Reviewed-by: Sergey Cheremencev <cherementsev@gmail.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30538
Tested-by: Jenkins
Reviewed-by: Sergey Cheremencev <c17829@cray.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10256 hsm: enable setting archive_id in hsm_set

Setting HSM flags in lfs_hsm_change_flags(...,LFS_HSM_SET)
does not allow to specify the archive_id, that is,
in llapi_hsm_state_set(path, mask, 0, 0 /* archive_id */)
archive_id = 0 is always set, which means no identifier change.
For having full flexibility (e.g. for debugging), introduce
the additional option --archive-id in hsm_set. If the option
is not provided, the default behavior (archive_id = 0) is used
and no archive identifier change is done. In addition a
test case is provided to check the functionality and shell
function get_hsm_archive_id() is modified in favor of more
robust grep for contents after pattern approach.

Lustre-change: https://review.whamcloud.com/30150
Lustre-commit: d1855f8e22a929066a69470c7e3d082c70478575

Test-Parameters: trivial testlist=sanity-hsm

Signed-off-by: Thomas Stibor <t.stibor@gsi.de>
Change-Id: I2145a18ecf32479527bb045140e5e881e58dd115
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Stephan Thiell <sthiell@stanford.edu>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30500
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-6210 utils: Use C99 struct initializers in lfs_hsm_state()

This patch makes no functional changes.  Struct initializers that
use C89 or GCC-only syntax are updated to C99 syntax.

C89 positional initializers require values to be placed in the
correct order. This will cause errors if the fields of the struct
definition are reordered or fields are added or removed. C99 named
initializers avoid this problem, and also automatically clear any
values that are not explicitly set.

This patch updates lfs_hsm_state() to use the C99 syntax.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/27525
Lustre-commit: 73c2c103f4f43f9bb37119a2e90d6c0fc1870711

Signed-off-by: Steve Guminski <stephenx.guminski@intel.com>
Change-Id: I32f427396e99f1b86d329eb8457883a9aaaed181
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30499
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-9611 lov: allow lov.*.stripe{size,count}=-1 param

Since LU-7344 patch http://review.whamcloud.com/16930 was landed,
lov_stripeoffset_seq_write() and lov_stripecount_seq_write() have
incorrectly checked that lov.*.stripecount and lov.*.stripeoffset
are not negative.  In fact they can both be "-1" to indicate that
the filesystem-wide default value should be used. These parameters
can also be set internally if using "lfs setstripe -c -1 $MOUNT"
or "lfs setstripe -i -1 $MOUNT" to set the system wide default,
generating console errors on the MDS from class_process_proc_param():

    lov.: error writing proc entry 'stripecount': rc = -34
    lov.: error writing proc entry 'stripeoffset': rc = -34

Fix these functions to allow "-1" as a valid value.

Lustre-change: https://review.whamcloud.com/27946
Lustre-commit: f93276d9a5b5df475c9f6007265692632d8e7222

Signed-off-by: Andreas Dilger <andreas.dilger@intel.com>
Change-Id: I295d2591d535b039634689524a29725e963ebbe5
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30407
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-9474 tests: add the stack_trap() utility function

This patch implements the stack_trap() function and uses it in
test_24d of sanity-hsm (where the need for it first arose).

The stack_trap() function is meant to be used to register multiple
cleanup actions on a single sigspec (most likely EXIT). Over time,
any call to bash's trap builtin in tests should be replaced by a call
to stack_trap().

Note that cleanup functions do not need to start with "trap - EXIT".
Each test is run in a subshell of its own (in run_one_logged()) and
therefore traps do not leak from one test to another. This is true
with or without this patch.

This is a port to b2_10 of
Lustre change: https://review.whamcloud.com/#/c/29653/
Lustre commit: 1dfda720c080e39890e5a659a30c8988ca498a7c

Test-Parameters: trivial testlist=sanity-hsm,sanity-hsm
Change-Id: I47f92a963f094d3d7055592a748e81ce357bff75
Signed-off-by: Quentin Bouget <quentin.bouget@cea.fr>
Reviewed-on: https://review.whamcloud.com/29653
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Dominique Martinet <dominique.martinet@cea.fr>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
(cherry picked from commit 1dfda720c080e39890e5a659a30c8988ca498a7c)
Reviewed-on: https://review.whamcloud.com/30371
Reviewed-by: Saurabh Tandan <saurabh.tandan@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10330 tests: fix version check in sanity.sh test_101g

The 16MB RPC patch is available in 2.7.x, so one more version
check needs to be added to 2.7.17 or later to avoid interop
failure.

Test-Parameters: trivial

Change-Id: I6eeefbf74017aaeeb8998accd6da04d8de75606c
Signed-off-by: Emoly Liu <emoly.liu@intel.com>
Reviewed-on: https://review.whamcloud.com/30365
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9872 tests: modify check space requirements for NFS test

In parallel-scale-nfs testing, the Lustre clients NFS mounts
the Lustre file system. In some cases, the file system looks
like it has enough space (du) to run NFS testing, but one or
more OSTs is full or is almost full. Since the default striping
for Lustre is a single stripe, some NFS tests will fail because
the file it is writing gets written to that almost full OST.

Increase the default stripe to all OSTs for all
parallel-scale-nfs tests.

Lustre-change: https://review.whamcloud.com/29786
Lustre-commit: 0b8e9558e88930814857c97dfe2394f8c8e24a9a

Test-Parameters: trivial testlist=parallel-scale,parallel-scale-nfsv3,parallel-scale-nfsv4
Signed-off-by: James Nunez <james.a.nunez@intel.com>
Change-Id: Iff187dc6c158d9063cd36ced0801b88cdc8814ae
Reviewed-by: James Casper <jamesx.casper@intel.com>
Reviewed-by: Saurabh Tandan <saurabh.tandan@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30353
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9509 tests: fix compilebench timeout

With ext4 and lustre found compilebench always takes more time in
create dir operation whenever previous same test aborted without
deleting directory. As per test board result, found compilebench
test ran from suite parallel-scale-nfs.sh timedout before running
from suite parallel-scale.sh, so 1st timedout compilebench not
clear data, rerunning compilebench again causes timeout.

Fix is creating different directory on each run of compilebench.

Lustre-change: https://review.whamcloud.com/27131
Lustre-commit: d15fe1fbb261107b021cd6ebe8b8c435d2148e0f

Seagate-bug-id: MRP-3753
Signed-off-by: Jadhav Vikram <jadhav.vikram@seagate.com>
Reviewed-by: Alexander Lezhoev <alexander.lezhoev@seagate.com>
Reviewed-by: Ashish Purkar <ashish.purkar@seagate.com>
Change-Id: I9b47e28fe5c638f4167c05fb68e46ec5e90de09e
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30352
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9997 ldlm: check lock cancellation in ldlm_cli_cancel()

In that case, the assert for 'list_empty(&lock->l_bl_ast)' will fail
because the lock is already in a cancel list.

This patch checks if the lock is already being canceled in prior.

Lustre-change: https://review.whamcloud.com/29080
Lustre-commit: f4ea4017b4d6a420146b2959f9feb11866858b4a

Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Change-Id: I04b9df789cf3b3b5e6dd61a647376307f9975f4a
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30339
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9894 lfsck: Print correct lfsck start info

When printing which scan type was started, lfsck iterates
through an array of types and compares the given type to
the types in the array.  Type numbers are a bit mask.

However, LFSCK_TYPES_SUPPORTED and LFSCK_TYPES_DEF are the
full mask, and they are the first in the array.  This means
we always match LFSCK_TYPES_SUPPORTED, which results in
always printing "all" as the type of scan.

Reorder the struct to increasing bit order to fix this.

Test-Parameters: trivial testlist=sanity-scrub,sanity-lfsck
Lustre-change: https://review.whamcloud.com/28604
Lustre-commit: 0c6805b2a0d575331dff0c22a657da91f61a1809

Signed-off-by: Patrick Farrell <paf@cray.com>
Change-Id: Ibc82369ff6531b56ceda4b1c0a833720dc61f3f4
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30265
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-6210 utils: Use C99 initializer for lfsck_types_names

This patch makes no functional changes.  The lfsck_types_names
struct initializer in lustre_lfsck.c is updated to C99 syntax.

C89 positional initializers require values to be placed in the
correct order. This will cause errors if the fields of the struct
definition are reordered or fields are added or removed. C99 named
initializers avoid this problem, and also automatically clear any
values that are not explicitly set.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/27791
Lustre-commit: a1d62378ed98e2663c1f95f955433e2a5b13d68c

Signed-off-by: Steve Guminski <stephenx.guminski@intel.com>
Change-Id: I8a3b44b56263b00a926550e4122193300c0c399f
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30264
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9860 tests: Add conf-sanity tests to ALWAYS_EXCEPT list

The following tests fail when run with a separate MDS and MGS:
conf-sanity tests 33a, 43b, 53b, 54b, 70e, 80, 84, 87, 100,
102, 103, 104, 105 and 107.
We need to add these tests to the ALWAYS_EXCEPT list
when running with a separate MDS and MGS.

Test-Parameters: trivial combinedmdsmgs=false testlist=conf-sanity envdefinitions=SLOW=yes
Signed-off-by: James Nunez <james.a.nunez@intel.com>
Change-Id: I1b17714216e14ad04eb9a492cb5f1aa4ed82bd1a
Reviewed-on: https://review.whamcloud.com/28497
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Wei Liu <wei3.liu@intel.com>
Reviewed-by: Dilip Krishnagiri <dilipx.krishnagiri@intel.com>
Reviewed-by: Saurabh Tandan <saurabh.tandan@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
(cherry picked from commit 5297bfa671bd2cbb18fb3188c4d9e3b8edf3284a)
Reviewed-on: https://review.whamcloud.com/30216
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9899 tests: mount client on MGS for ost-pools

When a Lustre configuration has the MGS and MDS on separate
nodes, the file system must be mounted on the MGS to allow
OST pools to work properly.

Add the ability to mount the file system on the MGS when
necessary for the Lustre test suite ost-pools.sh.

Test-Parameters: trivial testlist=ost-pools
Signed-off-by: James Nunez <james.a.nunez@intel.com>
Change-Id: Iff0663a38b92bb8e71c313897b12fca98fdae932
Reviewed-on: https://review.whamcloud.com/28638
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Arshad Hussain <arshad.hussain@seagate.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
(cherry picked from commit bb4c3bc38eeeeec111c14c024669465addb30c70)
Reviewed-on: https://review.whamcloud.com/30215
Reviewed-by: Arshad Hussain <arshad.super@gmail.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10255 tests: Fix wrong comparison operator in sanity 129

Currently sanity 129 uses numerica (-eq) operator to check whether
the has_warning variable is true or false depending on whether
expected warnings have been detected. This is wrong since bash
doesn't really have bolean types and true/false are not evaluated to
1/0. This results in the following bash error when the test is run:

    ./sanity.sh: line 9244: [: true: integer expression expected

Fix it by using the correct string operator '=' to check for
correct value.

Test-Paramters: clientdistro=sles12sp2 testlist=sanity
Test-Paramters: clientdistro=sles12sp3 testlist=sanity

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Change-Id: I071dcb3001ea9b2e5806d346dcd48bfcaf3297e9
Reviewed-on: https://review.whamcloud.com/30151
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Tested-by: Jenkins
Reviewed-by: Saurabh Tandan <saurabh.tandan@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10217 test: Make sanity 248 work with newer dds

This patch fixes 2 problems when working with value from dd.

Firstly, extraction of the readings from dd rely on them always
being in field number 6. However, that's not true for newer dd
versions where the output has changed and the time reading is now in
field number 10. So to make the code more generic and work with both
old and new outputs switch to using an egrep regular expression to
extract the correct field.

Secondly, dd can output its time in scientific notation, with
decimal and floating point portion being separated by a comma rather
than a dot:
   4096 bytes (4,1 kB, 4,0 KiB) copied, 9,1229e-05 s, 44,9 MB/s

Unforuntately this is not understood by bc so it needs to be
processed by substituting the comma for a dot and also expanding
the scientific notation to multiplication of 10 to the correct power.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Change-Id: I83ec659874ffe702c68f94f828827ff93325db72
Reviewed-on: https://review.whamcloud.com/30144
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9660 ptlrpc: do not wakeup every second

Even if there are no RPC requests on the set, there is no need to
wake up every second. The thread is woken up when a request is added
to the set or when the STOP bit is set, so it is sufficient to only
wake up when there are requests on the set to worry about.

Lustre-change: https://review.whamcloud.com/28776
Lustre-commit: e81847bd06519dd9847c31244abe6da978bcd016
Change-Id: Iac01d8c46e8645ecb6303ce72e0f6c59f16dcd5d
Signed-off-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29969
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10011 utils: suppress annoying messages for project quota

See following output:

[wsl@w003 ~]$ lfs quota /lustre1
Disk quotas for usr wsl (uid 14434):
      Filesystem  kbytes   quota   limit   grace   files   quota limit
grace
        /lustre1       0       0       0       -       0 0       0       -
Disk quotas for grp se (gid 1000):
      Filesystem  kbytes   quota   limit   grace   files   quota limit
grace
        /lustre1   44028       0       0       -      40 0       0       -
Unexpected quotactl error: Operation not supported
Disk quotas for prj <unknown> (pid 0):
      Filesystem  kbytes   quota   limit   grace   files   quota limit
grace
        /lustre1     [0]     [0]     [0]       -     [0]     [0] [0]       -
Some errors happened when getting quota info. Some devices may be not
working or deactivated. The data in "[]" is inaccurate.

Since project quota is disabled in default, unsupported project
quota messages will be annoying here.

Even Project quota is enabled, project id 0 will be outputed here,
it dose not make much sense either, instead, lfs quota <mnt> will only
output current user/group quota information in default

Lustre-change: https://review.whamcloud.com/29107
Lustre-commit: 0ba70b538768871f8504aca1ed6a24472f46a87d

Change-Id: Ie76ba14c4c4486a9246aafed0e8538eaae85ee98
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Li Xi <lixi@ddn.com>
Reviewed-by: Emoly Liu <emoly.liu@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29600
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10098 scripts: Fix mounted check in Lustre RA

The "Lustre" resource agent for pacemaker can mis-identify a resource
as being mounted if it's mountpoint is a substring match for anything
else in /proc/mounts.  Change the lustre_is_mounted() function to
check to make sure it's a lustre fs mounted at mountpoint and the
"source" (i.e. device) is the target we expect.

Lustre-change: https://review.whamcloud.com/29351
Lustre-commit: df96fab178534adb34067b20490a2d0629aabe2f

Signed-off-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Change-Id: Ib877b0dc3d3ce0d93fd4663aa2418ac21d670428
Reviewed-by: Malcolm Cowe <malcolm.j.cowe@intel.com>
Reviewed-by: Olaf Faaland-LLNL <faaland1@llnl.gov>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29352
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

New release 2.10.2.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: I495068f728dfe75e82f2498a3fbdf9e15f06c58c

New tag 2.10.2-RC2.

Second release candidate for 2.10.2 release.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: I0ced71f744d66a8abc3ce7e51a61fbc45dc6c6e7

LU-10220 mdd: fix buf alloc in mdd_changelog_data_store_by_fid

Fix allocation of mti_big_buf by call to lu_buf_check_and_alloc()
in mdd_changelog_data_store_by_fid().
reclen must take the header size of struct llog_changelog_rec into
account.

Maybe no memory corruptions were seen before because the buffer size
allocated in a previous call to mdd_declare_changelog_store() was
covering the need. But audit will add more information in changelog
records, provoking memory corruptions without this fix.

Lustre-change: https://review.whamcloud.com/30014
Lustre-commit: f173f93032c62bd1f95330f331d3d93ce5a31598

Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: Id0a06c412b54c0ae12c15d53f3e166e3e5d9ed68
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Henri Doreau <henri.doreau@cea.fr>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Faccini Bruno <bruno.faccini@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30356
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-8497 osp: handle remote -ENOMEM from osp_send_update_req()

In osp_send_update_req() detect an unsent request by checking
rq_queued_time == 0 rather than rq_set == NULL, which is always true
after returning from ptlrpc_queue_wait().

Lustre-change: https://review.whamcloud.com/30083
Lustre-commit: cef8983c8b5bf51b58df23a779769cc4b8ca8db5

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Ief959b71600157a9c3521775cc06994326e50c51
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30354
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-9941 lov: lsm_is_composite isn't right

LOVEA magic containing LOV_MAGIC_MAGIC will also be regarded as
a composite magic.

Signed-off-by: Bobi Jam <bobijam.xu@intel.com>
Change-Id: I3ef37ee80364b2a8f27831e3c53fb88b464f2039
Reviewed-on: https://review.whamcloud.com/28845
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
(cherry picked from commit 385518f67eb917335de0c1d727941094f4ab5874)
Reviewed-on: https://review.whamcloud.com/30342
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>

New tag 2.10.2-RC1.

First release candidate for 2.10.2 release.

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: I207f36c4e6815dfb06ba7b9622e939ade167eb89

LU-10234 tests: use wait correctly in sanity-hsm test_3[4-6]

Test 34, 35 and 36 did not properly check the return code of wait
and potentially missed regressions.

Test-Parameters: trivial testlist=sanity-hsm
Signed-off-by: Quentin Bouget <quentin.bouget@cea.fr>
Change-Id: I21e8b16b55b946a8e5837549c3a3698379132e48
Reviewed-on: https://review.whamcloud.com/30102
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Dominique Martinet <dominique.martinet@cea.fr>
Reviewed-by: Henri Doreau <henri.doreau@cea.fr>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
(cherry picked from commit eec4b8985f5eaacd13f0e0db7328dcdd610655bc)
Reviewed-on: https://review.whamcloud.com/30208
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10086 libcfs: use dynamic minors for /dev/{lnet,obd}

Request dynamic minor allocation when registering /dev/lnet and
/dev/obd. Remove the obsolete create-device-if-not-found code from
register_ioc_dev().

Lustre-change: https://review.whamcloud.com/29741
Lustre-commit: e446c1667dc9136e3a1cb3603c3851975b68e0ac

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: I59c70912b4729f58a76dc6107b3e1d7379c6d7a3
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Jian Yu <jian.yu@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29945
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10241 kernel: kernel update RHEL6.9 [2.6.32-696.16.1.el6]

Update RHEL6.9 kernel to 2.6.32-696.16.1.el6

Test-Parameters: clientdistro=el6.9 mdsdistro=el6.9 \
  ossdistro=el6.9 mdtfilesystemtype=ldiskfs \
  ostfilesystemtype=ldiskfs testgroup=review-ldiskfs

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: Ib2215b56e647fb8e19bc8b7e344a94564c7a8c7f
Reviewed-on: https://review.whamcloud.com/30131
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: Yang Sheng <yang.sheng@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10166 mdc: invalid free in changelog reader

Use kthread_stop() to instruct the producer thread to exit
when the device is closed, and only then: release the CRS
structure.

The previous implementation left small time windows open,
during which the producer threads could free a structure
before the consumer thread was completely done with it.

Change-Id: Id2038aa9b7fcfd2c3347f628e749f9d2c265ac6e
Signed-off-by: Henri Doreau <henri.doreau@cea.fr>
Reviewed-on: https://review.whamcloud.com/29818
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Quentin Bouget <quentin.bouget@cea.fr>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
(cherry picked from commit 89e52326b5bd3d2716ce6ec5d9f9d787947d91a1)
Reviewed-on: https://review.whamcloud.com/30207

LU-10040 nodemap: add nodemap idmap correctly

There are 3 situations when adding an idmap {id_client:id_fs} to
a nodemap tree:
 - both id_client and id_fs are matched, that means this idmap
   already exists, so return -EEXIT;
 - neither id_client nor id_fs is matched, that means this is a
   new idmap, so insert it;
 - only "id_client" or "id_fs" is matched, since idmap uses
   "id_client" as index key, we need to delete that old idmap and
   its index by its id_client, and then insert it again. In the
   original implementation, idmap_insert() calls rb_replace_node()
   to replace the old idmap without re-sorting its both id_client
   and id_fs, so that this new added idmap can't be found by
   idmap_search() due to its wrong left and right nodes, and can't
   be deleted either.

Also, this patch improves the following code:
 - nm_idmap_lock: use type rw_semaphore instead of rwlock, because
   nodemap_idx_idmap_del() may sleep on FS operations while this
   lock is being held.
 - Add "update_idmaps" to sanity-sec.sh test_15 to verify this fix,
   and improve other part of this test case as well to make it run
   correctly.

Test-Parameters: testlist=sanity-sec
Signed-off-by: Stephan Thiell <sthiell@stanford.edu>
Signed-off-by: Emoly Liu <emoly.liu@intel.com>
Change-Id: Icf777f14c2e1dd56fa5cd0eb56666240e206d199
Reviewed-on: https://review.whamcloud.com/29364
Tested-by: Jenkins
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
(cherry picked from commit 253ccbd55ffe7fcdc405c9fcc4f72a47578920fe)
Reviewed-on: https://review.whamcloud.com/30206

LU-10041 tests: sanity/51 to cleanup properly

sanity/51 should cleanup properly in case of failure

Test-Parameters: trivial testlist=sanity ostfilesystemtype=zfs mdtfilesystemtype=zfs
Test-Parameters: trivial testlist=sanity mdscount=2 mdtcount=4

Lustre-change: https://review.whamcloud.com/29246
Lustre-commit: 0d5ceb891e904cc9bab3a6b5ce0944b8bab06975

Change-Id: Ib1c0e1a116a6802f2bf25d665be5c076ae07c8b8
Signed-off-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: Wei Liu <wei3.liu@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/30023
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10204 tests: Fix line continuation

There is a simple  missing in one of the error paths in
ladvise_willread_performance which results in an unknown command
error. Fix it by adding the missing backslash.

Test-Parameters: trivial
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Change-Id: Ifff854c6cf5c1add71fd1571cb4de01d56204fde
Reviewed-on: https://review.whamcloud.com/29982
Tested-by: Jenkins
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10007 pacemaker: Use lctl and load lustre

When scripts are started, load lustre module.
Use lctl instead of directly accessing health_check file.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/29144
Lustre-commit: 6e299c2a3bd7566a322cf9bc9494f6850d2c1b7e

Signed-off-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Change-Id: I4a81248939464e498006dc2c4072d44685add018
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29946
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10015 o2iblnd: fix race at kiblnd_connect_peer

cmid will be destroyed at OFED if kiblnd_cm_callback return error.
if error happen before the end of kiblnd_connect_peer, it will touch
destroyed cmid and fail as
(o2iblnd_cb.c:1315:kiblnd_connect_peer())
            ASSERTION( cmid->device != ((void *)0) ) failed:

Lustre-change: https://review.whamcloud.com/29134
Lustre-commit: 576551cb97c6a5efb27d8afc59ad60550dde51ce

Seagate-bug-id: MRP-4592
Signed-off-by: Alexander Boyko <alexander.boyko@seagate.com>
Change-Id: I83eb5bceeb567acef0316498b936d25d6c6ccd95
Reviewed-by: Alexey Lyashkov <c17817@cray.com>
Reviewed-by: Doug Oucharek <dougso@me.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29881
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9951 lustre_compat: add wrapper function for posix_acl_update_mode

posix_acl_update_mode is introduced in kernel 4.9, add the precheck
of it, if not exists, use inline wrapper function instead.

Lustre-change: https://review.whamcloud.com/28871
Lutre-commit: ec6bdd55bb2128dcf9779017ef9623461afe05f8

Change-Id: I8a1476d611c387a88efef5d5b8707edf5feacca8
Signed-off-by: Gu Zheng <gzheng@ddn.com>
Reviewed-by: Wang Shilong <wshilong@ddn.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29880
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10047 tests: stop skipping test_102 subtests

Remove obsolete version check on tar.
All tar versions in supported distros are now capable of --xattrs.
But not all tar version have --xattrs-include, so must test for and
adapt for that.

Lustre-commit: 036641a1e1f6d5d010873267b669528890f19fe4
Lustre-change: https://review.whamcloud.com/29288

Test-Parameters: trivial envdefinitions=ONLY=102 testlist=sanity
Test-Parameters: trivial clientdistro=el6.9 envdefinitions=ONLY=102 testlist=sanity
Test-Parameters: trivial clientdistro=sles12sp2 envdefinitions=ONLY=102 testlist=sanity

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: I5e76bd1a762c4e01cf8a3a33789ca3a30c15abb0
Reviewed-by: James Nunez <james.a.nunez@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-on: https://review.whamcloud.com/29823
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-9663 tests: replace “ls -s” with “stat -c '%s'” to get file size

This patch improves acl/2561{,_zfs}.test to use “stat -c '%s'” to
get file size instead of using “ls -s”, which prints the allocated
size of the file in blocks.

Test-Parameters: trivial \
envdefinitions=ONLY=103 \
mdtfilesystemtype=zfs ostfilesystemtype=zfs \
testlist=sanity

Lustre-change: https://review.whamcloud.com/27961
Lustre-commit: 45b8c6cf6916cf012ad0512f9cf249c152b45236

Change-Id: I8bfea5197102baeece244e20731c90172c5cc2f1
Signed-off-by: Jian Yu <jian.yu@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29816
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9752 man: Reference zgenhostid instead of genhostid

In ZFS 0.7.0, they added zgenhostid(8) to be used in place of
Redhat's genhostid, so that there would be a platform agnostic
way to generate /etc/hostid.

Test-Parameters: trivial
Lustre-change: https://review.whamcloud.com/29327
Lustre-commit: a1eb6de081473545fbd5c1fe33e209fe391bf708

Signed-off-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Change-Id: I691266d04f91d5fa7c50b72948c801afa69d647d
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29805
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9578 llite: use security context if it's enabled in the kernel

if it's disabled, then Lustre stop to work properly (can not create
files, etc)

Lustre-change: https://review.whamcloud.com/27364
Lustre-commmit: 61f26ea47f96632a90702f2b404e845a01498612

Change-Id: I1e431ec95a2b0613b43893567eb6d1a64ec832de
Signed-off-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Chris Horn <hornc@cray.com>
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29737
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10141 llapi: integer overflow in llapi_changelog_start

Use the appropriate type to store and check the return value from lseek.
This prevents from misinterpreting high offsets as errors.

Lustre-change: https://review.whamcloud.com/29674
Lustre-commit: aaa808e7a40198581956a1d648f413cc30e830ed

Change-Id: I15e92be3454af20ee6611c2a7ddfc1b597d639c2
Signed-off-by: Henri Doreau <henri.doreau@cea.fr>
Reviewed-by: Thomas LEIBOVICI <thomas.leibovici@cea.fr>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Stephan Thiell <sthiell@stanford.edu>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29735
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>

LU-10150 build: Build with ZFS 0.7.3

Update ZFS and SPL version to 0.7.3
Also Fixup ChangeLog

Changelog: https://github.com/zfsonlinux/zfs/releases/tag/zfs-0.7.3

Signed-off-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Change-Id: I88f0f2601262c0c535431d256a159d9e9d6ebd75
Reviewed-on: https://review.whamcloud.com/29713
Tested-by: Jenkins
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9840 lod: add ldo_dir_stripe_loaded

Add ldo_dir_stripe_loaded flag to avoid loading
stripes mulitple times especcially for non-stripe
directory.

Lustre-change: https://review.whamcloud.com/28962
Lustre-commit: 744fe412fa101609a38f7ccc77efc4f1c540e008

Change-Id: Ia9360aac9e24706e401184c75fae4ec7f8ec46d9
Signed-off-by: Di Wang <di.wang@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-on: https://review.whamcloud.com/29143
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10168 kernel: kernel update [SLES12 SP2 4.4.90-92.45]

Update target and kernel_config files for new version

Test-Parameters: clientdistro=sles12sp2 testgroup=review-ldiskfs \
  mdsdistro=sles12sp2 ossdistro=sles12sp2 \
  mdtfilesystemtype=ldiskfs ostfilesystemtype=ldiskfs

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: If24eddeeadc825b1b3073439304c0958c0ae1b74
Reviewed-on: https://review.whamcloud.com/29840
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Minh Diep <minh.diep@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10132 llite: handle xattr cache refill race

In ll_xattr_cache_refill() if the xattr cache was invalid (and no
request was sent) then return -EAGAIN so that ll_getxattr_common()
caller will fetch the xattr from the MDT.

Lustre-change: https://review.whamcloud.com/#/c/29654/
Lustre-commit: 9cc8c3a20c547ec75325dde3dd17f4b1dcc66348

Signed-off-by: John L. Hammond <john.hammond@intel.com>
Change-Id: Ia9ec7424e8786d92bdecf4897fafcf71d5061fb1
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29795
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>

LU-10164 kernel: kernel update [SLES12 SP3 4.4.92-6.18]

Update target and kernel_config files for new version

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

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: I4b046f0ac64b75545cd0e2a3a44e9117f4d79ef4
Reviewed-on: https://review.whamcloud.com/29825
Tested-by: Jenkins
Reviewed-by: Minh Diep <minh.diep@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10142 kernel: kernel update RHEL7.4 [3.10.0-693.5.2.el7]

update RHEL 7.4 kernel to 3.10.0-693.5.2.el7

Signed-off-by: Bob Glossman <bob.glossman@intel.com>
Change-Id: I6f22d9d96b86d7bd860a400cd803fad26a6b5d1a
Reviewed-on: https://review.whamcloud.com/29728
Tested-by: Jenkins
Reviewed-by: Yang Sheng <yang.sheng@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10131 llite: Update i_nlink on unlink

Currently, the client inode link count is not updated on
last unlink.  This is fine because the dentries are all
gone and the inode is eligible for reclaim, but it's still
incorrect.  This causes two problems:

1. Inode is not immediately reclaimed
2. i_nlink count is > 0 for a fully unlinked file, which
confuses wrapfs

On last unlink, the MDT sends back attributes.  Use the
nlink count from these to update the client inode.

Remove null check inherited from ll_get_child_fid, because
the inode should never be null on an unlink.

Re-enabled test 76, which passes with this patch.
Removed slab allocator tuning from test_76, because slab is
no longer the default Linux allocator.

Lustre-change: https://review.whamcloud.com/29651
Lustre-commit: 947b22b08d3725852a811a9e330562dd986d7336

Signed-off-by: Patrick Farrell <paf@cray.com>
Change-Id: Ib253b5cf3d35188554cf8fc33a8a3d4b8bb237e8
Reviewed-by: Ben Evans <bevans@cray.com>
Reviewed-by: Alexey Lyashkov <c17817@cray.com>
Reviewed-by: Andrew Perepechko <c17827@cray.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29785
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-10041 osd: osd-zfs to choose dnode size

depending on dnodesize property it can be:
legacy (512 bytes), auto (512 bytes to 16K) or absolute
size (512, 1024, 2048, 4096, 8192, 16384).

Lustre-change: https://review.whamcloud.com/29242
Lustre-commit: d993de7b40cd9625b48e5361ae29f77bfceb207a

Change-Id: Iea35d8ae850523440272467320410850821f484c
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Nathaniel Clark <nathaniel.l.clark@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29770
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-9782 osd-ldiskfs: avoid extra search

Extent tree grow greatly durin random IO test with small block size.
osd_is_mapped responsible to large cpu consumption in this case.

|          |
|          |--94.49%-- ldiskfs_es_find_delayed_extent_range
|          |          ldiskfs_fiemap
|          |          osd_is_mapped
|          |          osd_declare_write_commit
|          |
|          |--5.49%-- ldiskfs_fiemap
|          |          osd_is_mapped
|          |          osd_declare_write_commit
|
|--21.80%-- ldiskfs_es_find_delayed_extent_range
|          |
|          |--100.00%-- ldiskfs_fiemap
|          |          osd_is_mapped

let's cache a osd_is_mapped result to avoid extra search in extent
tree,

Lustre-change: https://review.whamcloud.com/28145
Lustre-commit: 1eb0573fdeb7ef8ed667974fd30d4d110b8166c9

Seagate-bug-id: MRP-4474
Signed-off-by: Alexey Lyashkov <alexey.lyashkov@seagate.com>
Change-Id: I63d480bfc7c6b7599b80ceeec9447b227a1610c8
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Andrew Perepechko <andrew.perepechko@seagate.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29739
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andrew Perepechko <c17827@cray.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>

LU-7990 llite: increase whole-file readahead to RPC size

Increase the default whole-file readahead limit to match the current
RPC size.  That ensures that files smaller than the RPC size will be
read in a single round-trip instead of sending multiple smaller RPCs.

Lustre-change: https://review.whamcloud.com/26955
Lustre-commit: 627d0133d9d7bef908544537a8a2b2093719fc72

Signed-off-by: Andreas Dilger <andreas.dilger@intel.com>
Change-Id: I3bdb1c7f92c546d58951a9e6b783af23c83ebbe5
Reviewed-by: Patrick Farrell <paf@cray.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Signed-off-by: Minh Diep <minh.diep@intel.com>
Reviewed-on: https://review.whamcloud.com/29738
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>