Whamcloud - gitweb
Chris Horn [Tue, 7 Nov 2023 21:14:42 +0000 (14:14 -0700)]
LU-17271 kfilnd: Protect RKEY for bulk Put/Get
The initiator of a bulk Put/Get generates an RKEY based on the the
values of the struct kfilnd_tn::tn_mr_key and
struct kfilnd_peer::kp_local_session_key. kp_local_session_key is
assigned at peer creation, and tn_mr_key is assigned when the
kfilnd_tn is allocated.
A bulk Put/Get can fail in various ways such that the target of the
operation may have a reference to the RKEY, but the originator cannot
know the state of the operation at the target. In these cases, the
initiator must ensure that the RKEY is not re-used. To accomplish
this, we need to delete the target peer from the originator's peer
cache to ensure that subsequent bulk Put/Get operations will use
a new kp_local_session_key, and thus avoid re-using any old RKEY
values.
HPE-bug-id: LUS-11972
Test-Parameters: trivial
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: If270a2df745ee88c35addc8194cdb160cb373c3e
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53028
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Ron Gredvig <ron.gredvig@hpe.com>
Reviewed-by: Ian Ziemba <ian.ziemba@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Chris Horn [Tue, 7 Nov 2023 17:36:29 +0000 (10:36 -0700)]
LU-17270 kfilnd: Check status of TAG_RX_OK in WAIT_COMP
When the target of a bulk Get/Put drops the message it sends
ENODATA back to the initiator via immediate data. This status needs to
be accounted for while the transaction is in the TN_STATE_WAIT_COMP
state, otherwise it can be lost if the TN_EVENT_TAG_RX_OK event
arrives before the TN_EVENT_TX_OK event.
HPE-bug-id: LUS-11971
Test-Parameters: trivial
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: I52d6ea52746cbc14a86478fcccb32b25badd3b0a
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53027
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Ron Gredvig <ron.gredvig@hpe.com>
Reviewed-by: Ian Ziemba <ian.ziemba@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Chris Horn [Tue, 5 Dec 2023 04:25:01 +0000 (22:25 -0600)]
LU-16822 tests: Skip tests lacking large NID support
Test 230 - Needs lctl conn_list but this does not support large NIDs.
Tests 204-207,209-213,216,218,231,302,500 - These test cases use
commands that do not support large NIDs (drop rules, printing recovery
queue, etc.), or do not work properly (lnetctl import/export,
lctl which_nid).
Tests 101,103 - These tests exercise NID ranges, so they do not
work with large NIDs.
Tests 100,102,105-106 - These test cases need to be re-written to
specify valid IPv6 NIDs.
Test 220 - Calls lst which does not support large NIDs.
Test 250 - Uses ksocklnd-config but this does not support IPv6.
Test 208 and 255 use ip2nets and routes parameters that do not support
large NIDs.
Test 214 - If the destination NID to the ping commands is IPv6, then
the fake interface cannot be cleaned up.
Some places where drop or delay rules were added did not check for
success or failure. This has been corrected.
Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: I7f251a82aa2eee304419a765df728a014b9c9e27
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53727
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Shaun Tancheff [Fri, 26 Jan 2024 17:57:35 +0000 (00:57 +0700)]
LU-16967 build: Separate lnet LND deb packaging
Enable separate packaging of lnet lnd kernel modules into
separate packages with build profile multiple-lnds:
lustre-lnet-module-socklnd for socklnd.ko
lustre-lnet-module-gnilnd for kgnilnd.ko, profile gnilnd
lustre-lnet-module-kfilnd for kkfilnd.ko, profile kfilnd
lustre-lnet-module-o2iblnd for o2iblnd.ko, profile ext_o2ib
lustre-lnet-module-in-kernel-o2iblnd for ko2iblnd.ko,
profile int_o2ib
Test-Parameters: trivial
HPE-bug-id: LUS-11711
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: I3a5ca03fa410238f66083289db0899c8b4bfab5c
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52397
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Alexey Lyashkov <alexey.lyashkov@hpe.com>
Reviewed-by: Petros Koutoupis <petros.koutoupis@hpe.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Sebastien Buisson [Thu, 14 Sep 2023 16:00:04 +0000 (18:00 +0200)]
LU-16498 obdclass: change uc_lock to rwlock
Change the upcall cache uc_lock to a read-write lock so that threads
can get the read lock to do concurrent lookups in the upcall cache,
and only grab the write lock in the rare case when a new entry is
added or old entries are expired. That reduces serialization between
server threads during normal operation, and avoids all of the threads
spinning for some time if the requested key (UID or gss context) is
not in the cache at all, before they sleep.
Test-Parameters: kerberos=true testlist=sanity-krb5
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I812400104fd2115d19386fb4a03bb3ce99c49383
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52395
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Shaun Tancheff [Wed, 18 Oct 2023 09:27:10 +0000 (04:27 -0500)]
LU-16314 debug: Enable optional unhashed pointers
This patch takes a page out of the kernel trace debug
playbook to rewrite format strings and change %p -> %px
on-the-fly when:
libcfs_debug_raw_pointers
is enabled.
The module parameter can be viewed and modified by root
via lctl:
lctl get_param debug_raw_pointers
lctl set_param debug_raw_pointers=1
Since nothing uses the return value from libcfs_debug_msg
change it to void.
Use percpu pre-allocated buffers for holding modified
format strings to avoid kmalloc/kfree as well as avoid
bloating stack usage.
HPE-bug-id: LUS-10945
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: I63d90d614ce4435b07f5e84991a12ae7351ac2bb
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51877
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Petros Koutoupis <petros.koutoupis@hpe.com>
Shaun Tancheff [Tue, 6 Jun 2023 04:07:44 +0000 (11:07 +0700)]
LU-16314 lnet: Migrate LASSERTF %p to %px
This change covers libcfs and lnet and converts LASSERTF
statements to explicitly use %px.
Use %px to explicitly report the non-hashed pointer value
messages printed when a kernel panic is imminent. When
analyzing a crash dump the associated kernel address can
be used to determine the system state that lead to the
system crash.
As crash dumps can and are provided by customers from
production systems the use of the kernel command line
parameter:
no_hash_pointers
is not always possible.
Ref: Documentation/core-api/printk-formats.rst
Test-Parameters: trivial
HPE-bug-id: LUS-10945
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: I4d0c956e1b914cea9517b632d46f1714bcd43a85
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51231
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Petros Koutoupis <petros.koutoupis@hpe.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Shaun Tancheff [Tue, 6 Jun 2023 03:44:53 +0000 (10:44 +0700)]
LU-16314 llite: Migrate LASSERTF %p to %px
This change covers lustre/ec through lustre/mgs and
converts LASSERTF statements to explicitly use %px.
Use %px to explicitly report the non-hashed pointer value
messages printed when a kernel panic is imminent. When
analyzing a crash dump the associated kernel address can
be used to determine the system state that lead to the
system crash.
As crash dumps can and are provided by customers from
production systems the use of the kernel command line
parameter:
no_hash_pointers
is not always possible.
Ref: Documentation/core-api/printk-formats.rst
Test-Parameters: trivial
HPE-bug-id: LUS-10945
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: I708d9ef60c63f5b4006c7986599a2f39fc9e5fdf
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51213
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Petros Koutoupis <petros.koutoupis@hpe.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Shaun Tancheff [Thu, 25 May 2023 12:01:32 +0000 (07:01 -0500)]
LU-16314 obdclass: Migrate LASSERTF %p to %px
This change covers lustre/obdclass through lustre/target and
converts LASSERTF statements to explicitly use %px.
Use %px to explicitly report the non-hashed pointer value
messages printed when a kernel panic is imminent. When
analyzing a crash dump the associated kernel address can
be used to determine the system state that lead to the
system crash.
As crash dumps can and are provided by customers from
production systems the use of the kernel command line
parameter:
no_hash_pointers
is not always possible.
Ref: Documentation/core-api/printk-formats.rst
Test-Parameters: trivial
HPE-bug-id: LUS-10945
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ia256dc1f74f976640ec82746a5d761ef662f45ae
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/49405
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Petros Koutoupis <petros.koutoupis@hpe.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Fri, 19 Jan 2024 03:44:33 +0000 (20:44 -0700)]
LU-17426 tests: add crossdir parallel rename test
Add sanityn test_81d to test cross-dir (same-MDT) parallel rename
if the MDT supports this functionality.
Test-Parameters: trivial testlist=sanityn
Test-Parameters: testlist=sanityn serverversion=2.15 env=SANITYN_EXCEPT="77q 77r"
Test-Parameters: testlist=sanityn env=ONLY=81d,ONLY_REPEAT=10
Test-Parameters: testlist=sanityn env=ONLY=81d,ONLY_REPEAT=10 mdtcount=2
Test-Parameters: testlist=sanityn env=ONLY=81d,ONLY_REPEAT=10 mdtcount=4
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ic8717e6865a9c6c9698186f4fdf34c1f4f74083f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53738
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Karsten Weiss [Fri, 29 Jun 2018 15:22:09 +0000 (17:22 +0200)]
LU-11112 lnet: improve error msg in lnet_sock_create()
The kernel_bind() call in lnet_sock_create() may fail due to
problems with the local port, or the local IP address. Make sure
to include both items when indicating a fatal error.
Test-Parameters: trivial
Signed-off-by: Karsten Weiss <karsten.weiss@atos.net>
Signed-off-by: Daniel Kobras <d.kobras@science-computing.de>
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: I43c1f089d3b12e61c18c97e532b6872a6c8cf272
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/32758
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 5 Feb 2024 05:23:36 +0000 (10:53 +0530)]
LU-6142 uapi: Fix style issues for lustre_disk.h
This patch fixes issues reported by checkpatch
for file lustre/include/lustre_disk.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I20cc1784602b7e95a5c1541851684d3c2199be1b
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53919
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 5 Feb 2024 05:44:51 +0000 (11:14 +0530)]
LU-6142 ldlm: Fix style issues for lustre_dlm_flags.h
This patch fixes issues reported by checkpatch
for file lustre/include/lustre_dlm_flags.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Icf57d55fe3806e1990d9f88d78787137171f83a3
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53917
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 5 Feb 2024 08:54:46 +0000 (14:24 +0530)]
LU-6142 fid: Fix style issues for lustre_fid.h
This patch fixes issues reported by checkpatch
for file lustre/include/lustre_fid.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I8128bf72826187cc3d941c25e16e42e0736d8e3e
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53915
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 5 Feb 2024 09:14:44 +0000 (14:44 +0530)]
LU-6142 fld: Fix style issues for lustre_fld.h
This patch fixes issues reported by checkpatch
for file lustre/include/lustre_fld.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ic02ff3ec463d9115de5483e4333e935406c0ed93
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53914
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 5 Feb 2024 11:04:33 +0000 (16:34 +0530)]
LU-6142 llog: Fix style issues for lustre_log.h
This patch fixes issues reported by checkpatch
for file lustre/include/lustre_log.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I86650ff994c851a91c109c359251e80dd761b245
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53912
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 5 Feb 2024 04:47:51 +0000 (10:17 +0530)]
LU-6142 build: Fix style issues for lustre_compat.h
This patch fixes issues reported by checkpatch
for file lustre/include/lustre_compat.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I2e91f4faba98d3862d8180f622478518c4b8b0c3
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53907
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Sun, 4 Feb 2024 22:50:06 +0000 (04:20 +0530)]
LU-6142 obdclass: Fix style issues for lprocfs_status.h
This patch fixes issues reported by checkpatch
for file lustre/include/lprocfs_status.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I99d364f698e4319e83d129a2a0c529d6f7ce8dec
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53906
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Sat, 3 Feb 2024 22:56:09 +0000 (04:26 +0530)]
LU-6142 clio: Fix style issues for cl_object.h
This patch fixes issues reported by checkpatch
for file lustre/include/cl_object.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I0332d07569ed3c4ddff1ed6514918b2afdd48179
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53902
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Sat, 3 Feb 2024 21:38:05 +0000 (03:08 +0530)]
LU-6142 utils: Fix style issues for folder lustre/include/lustre
This patch fixes issues reported by checkpatch
for all files under folder lustre/include/lustre/
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I65e87c8343bc0b90b71684827d8ca2bd7efd652e
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53900
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Arshad Hussain [Fri, 2 Feb 2024 13:16:41 +0000 (18:46 +0530)]
LU-6142 fld: Fix style issues for lproc_fld.c
This patch fixes issues reported by checkpatch
for file lustre/fld/lproc_fld.c
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I27e3719cce73f04460fffa5b0583603adb1cd05f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53888
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Fri, 2 Feb 2024 12:19:47 +0000 (17:49 +0530)]
LU-6142 fid: Fix style issues for fid_lib/lproc_fid.c
This patch fixes issues reported by checkpatch
for file lustre/fid/fid_lib.c and lustre/fid/lproc_fid.c
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I829027962170e9494e6ff726804a579dd987dc17
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53887
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Wed, 31 Jan 2024 00:06:36 +0000 (17:06 -0700)]
LU-17489 utils: fix 'lfs getname' ioctl breakage
The removal of the explicit ioctl(OBD_IOC_GETNAME_OLD) fallback
in llapi_file_fget_lov_uuid() caused 'lfs getname' to break when
running against an 2.14 mountpoint missing OBD_IOC_GETDTNAME.
Change this to call llapi_ioctl(OBD_IOC_GETDTNAME) which handles
this compatibility mapping internally.
Also fix the include header ordering to ensure LUSTRE_VERSION_CODE
is defined before including lustre_ioctl_old.h.
Test-Parameters: trivial
Fixes:
0f38a0b9db ("LU-13107 uapi: remove obsolete ioctls")
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I944acd498a42ba4882c8391e27f4156cb63ebbe5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53867
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Chris Horn [Sat, 13 Jan 2024 03:50:00 +0000 (21:50 -0600)]
LU-10003 lnet: Update lctl ping to work with large NIDs
jt_ptl_ping()/lnet_parse_nid() updated to use the large struct
lnet_processid. This allows lctl ping to work with large NIDs. If we
need to fallback to the old_api then the large lnet_processid is
converted to the old struct lnet_process_id.
Test-Parameters: trivial
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: Ie0fb05ed631d0432e6c6caba0f64fc377f785bc2
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53835
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Neil Brown <neilb@suse.de>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Bobi Jam [Wed, 24 Jan 2024 06:15:49 +0000 (14:15 +0800)]
LU-17464 lod: set llc_ostlist to NULL after free
Default LOV striping could free component entry llc_ostlist if needed
e.g. expand component entries, without set it to NULL it could be
double allocated/freed later.
Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: I25824cb61dd47ba284403039259593b88d25fa9d
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53797
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Qian Yingjin <qian@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
James Simmons [Sun, 10 Dec 2023 15:10:53 +0000 (10:10 -0500)]
LU-10391 nrs: use struct lnet_nid for nrs_crrn_hashfn()
In the move to large NIDs nrs_crrn_hashfn() was missed. Update
the hash value generated to use nidhash() since our value
is much larger then 64 bits of lnet_nid_t.
Test-Parameters:trivial testlist=sanityn envdefinitions=ONLY=77b
Fixes:
36a199db2b ("LU-10391 ptlrpc: change cc_nid in nrs to be struct lnet_nid")
Change-Id: I19d7150c773db4755b3b8a18791f1411e13fe2b3
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53399
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Nikitas Angelinas <nikitas.angelinas@hpe.com>
Reviewed-by: Etienne AUJAMES <eaujames@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
James Simmons [Mon, 29 Jan 2024 00:45:40 +0000 (19:45 -0500)]
LU-17479 utils: Update lnet tools to support PyYAML format
The current cYAML implementation can't handle PyYAML indentation
style. The reason is the underlying libyaml library creates
different yaml events / tokens for the PyYAML format. I attempted
to inject the missing yaml tokens from the PyYAML format but that
failed to work. Also the tokens with the PyYAML produced the
wrong scalar strings. I looked at moving to yaml events instead
of tokens but that required a large change. The simplest change
was to capture the YAML config input and place it into a locally
allocated buffer. Then alter the location of '-' which changed
the YAML config from PyYAML to something cYAML can handle. For
this to work I needed to move the YAML config data handling out
of cYAML_build_tree() to jt_import(). The reason was that
lustre_yaml_cb_helper() is called more than once and for stdin
it can only be read once.
Test-Parameters: trivial testlist=sanity-lnet
Change-Id: Ic8529ae264c9cbe6872da9a9e3421db78f8ea371
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53845
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Chris Horn [Tue, 23 Jan 2024 21:54:05 +0000 (14:54 -0700)]
LU-10391 lnet: Fix lnetctl peer set --all
When the --all flag is specified as part of the lnetctl peer set
command, a primary NID argument is not sent to the peer doit command.
The "peer set" case uses NLM_F_REPLACE flag, so in this case the
primary NID argument is optional.
Added test cases to validate behavior of the lnetctl peer set
command.
Test-Parameters: trivial
Fixes:
8a0fdfa0b2 ("LU-10391 lnet: migrate peer NI control to Netlink")
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: I58de030b061280e837de27611bc701a3affab0f3
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53791
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Wed, 2 Aug 2023 12:18:22 +0000 (17:48 +0530)]
LU-6142 ldlm: Fix style issues for lustre_sec.h
This patch fixes issues reported by checkpatch
for file lustre/include/lustre_sec.h
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ic4a8d3c5188e79dee2347db9b9d951afdee72630
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51853
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 31 Jul 2023 06:39:32 +0000 (12:09 +0530)]
LU-6142 ldlm: Fix style issues for sec_gss.c
This patch fixes issues reported by checkpatch
for file lustre/ptlrpc/gss/sec_gss.c
Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ia56b8f9881aab705e27daaa7539c9c1388f4bb5d
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51810
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Jinshan Xiong [Thu, 12 Oct 2023 22:55:58 +0000 (15:55 -0700)]
LU-17189 o2ib: assign tx_gpu properly
tx_gpu is not assigned or initialized properly.
Test-Parameters: trivial
Fixes:
f792297212 ("LU-16211 o2iblnd: Avoid NULL md deref")
Signed-off-by: Jinshan Xiong <jinshan.xiong@gmail.com>
Change-Id: I5e14d66f41f6194203fec7832493efd432b54c36
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52702
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Andrew Perepechko <andrew.perepechko@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alex Zhuravlev [Mon, 13 Nov 2023 04:48:40 +0000 (07:48 +0300)]
LU-17285 obdclass: remove debug from obd_get_at_*
Removing debugging CDEBUG() from obd_get_at_*() helpers.
Messages like the following:
00010000:
00100000:0.0:
1699657756.854481:0:27978:0:
(ldlm_request.c:181:ldlm_cp_timeout()) NULL obd
Fixes:
0f2bc318d7 ("LU-15246 ptlrpc: per-device adaptive timeout parameters")
Test-Parameters: trivial
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Change-Id: Iaaa964d4e3ca62de5fb273f865d7cd4c3a4f9a29
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53106
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 22 Jan 2024 10:33:02 +0000 (16:03 +0530)]
LU-17000 utils: In mydaemon() check after calling open()
This patch adds check after calling open() in function
mydaemon() instead of directly using the value
Test-Parameters: trivial kerberos=true testlist=sanity-krb5
CoverityID: 397666 ("Argument cannot be negative")
Fixes:
d2d56f38da0 ("make HEAD from b_post_cmd3")
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ic59414977029221e8618c5bb3320e95d39d9cded
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53758
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Fri, 19 Jan 2024 07:44:21 +0000 (13:14 +0530)]
LU-17000 utils: Remove check for errno != 0
In lustre_rename_fsname() after calls to system calls
like open/read/write/lseek there is a check if global
errno is not equal to zero. This is noop and not
required, as these system calls do reset errno to 0
on success.
The side effect of this check was that it appeared
that the errno could be 0 which would leave 'ret' as
negative. This would never happen, but was causing
Coverity to complain.
This patch fixes this coverity issue by removing
the comparison of errno != 0 which is not required.
Test-Parameters: trivial testlist=conf-sanity,sanityn
Fixes:
d0c6e97fa53 ("LU-8900 snapshot: rename filesysetem fsname")
CoverityID: 397153 ("Argument cannot be negative")
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I7257434e6546f56f30841f49a3bde35e80360bb8
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53742
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Alexandre Ioffe [Thu, 4 Jan 2024 03:34:40 +0000 (19:34 -0800)]
LU-17370 utils: simplify lfs-mirror-extend help text
Add list of lfs setstripe command line options
to help text of lfs mirror extend.
Simplify syntax of lfs mirror extend help text.
Update corresponding lfs-mirror-extend man page.
On man pages make left side adjustment and disable hyphenation:
'.nh', '.ad l' to prevent hyphenation of keywords
Signed-off-by: Alexandre Ioffe <aioffe@ddn.com>
Test-Parameters: trivial
Change-Id: I6cffcdb9651062e169f53868827646b876a82cb5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53719
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Etienne AUJAMES [Wed, 17 Jan 2024 10:28:35 +0000 (11:28 +0100)]
LU-17430 tests: fix interop sanity-hsm testing with b2_15
Add a MDS server check for sanity-hsm test 114 and 409a. Those tests
require fixes on MDS server side.
Test-Parameters: trivial testlist=sanity-hsm
Test-Parameters: serverversion=2.15.4 testlist=sanity-hsm
Test-Parameters: clientversion=2.15.4 testlist=sanity-hsm
Fixes:
b13a5b351e ("LU-16188 mdt: fix incompatible HSM request handling")
Signed-off-by: Etienne AUJAMES <eaujames@ddn.com>
Change-Id: I8bb5fb93e38f2428432fd3469317d3d13899a107
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53694
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Deiter
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Arshad Hussain [Wed, 17 Jan 2024 09:34:25 +0000 (15:04 +0530)]
LU-17000 utils: Add check after calling sysconf(_SC_PAGESIZE)
Calling sysconf(_SC_PAGESIZE) could return -1
on error. This patch adds check after calling
sysconf() instead of directly using the value
Test-Parameters: trivial testlist=sanity-flr
CoverityID: 397578 ("Argument cannot be negative")
CoverityID: 397246 ("Argument cannot be negative")
CoverityID: 397320 ("Argument cannot be negative")
CoverityID: 397671 ("Argument cannot be negative")
CoverityID: 397826 ("Argument cannot be negative")
CoverityID: 397898 ("Argument cannot be negative")
CoverityID: 397917 ("Argument cannot be negative")
CoverityID: 399702 ("Argument cannot be negative")
Fixes:
0561c144 (LU-13397 lfs: mirror extend/copy keeps sparseness)
Fixes:
a5905b2a (LU-11245 flr: lfs mirror dump command)
Fixes:
f1daa8fc (LU-10287 flr: lfs mirror verify command)
Fixes:
0e5c12ac (LU-10916 lfs: improve lfs mirror resync)
Fixes:
5d7c4fa6 (LU-9771 flr: mirror read and write)
Fixes:
5999c0b8 (LU-9771 flr: resync support and test tool)
Fixes:
9b44cf70 (LU-13224 utils: expose llapi_param* functions)
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I19d13528f63d4586a17aaa9d15313872f8c40c94
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53693
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Tue, 16 Jan 2024 10:22:54 +0000 (15:52 +0530)]
LU-17000 utils: Fix check after return from fopen()
Return from fopen() for option 't' (trace) was
checked with a different variable. This patch
fixes this.
Test-Parameters: trivial
CoverityID: 397651 ("Copy-paste error")
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I04bd207582d421cc3744e7b0f4298e738502edbe
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53686
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alex Deiter [Sun, 14 Jan 2024 19:40:42 +0000 (23:40 +0400)]
LU-930 doc: update lfs-setstripe.1 man page
Update the lfs-setstripe.1 man page to describe
maximum value for the mirror_count option.
Test-Parameters: trivial
Signed-off-by: Alex Deiter <adeiter@tintri.com>
Change-Id: I1879eabef5c397730e0795858e6c6a103d6a2259
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53672
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Arshad Hussain [Thu, 11 Jan 2024 09:35:02 +0000 (15:05 +0530)]
LU-17414 lnet: Use POSIX error number for libnetconfig
Currently liblnetconfig.c is returning custom define
LUSTRE_CFG_RC_* numbers which can be confusing to users.
This patch redefines LUSTRE_CFG_RC_* to use POSIX
error number to be consistent.
Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I585d1dfd80d07160e5cdeef784920414132bcaf8
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53657
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Timothy Day [Tue, 9 Jan 2024 17:17:10 +0000 (17:17 +0000)]
LU-17242 debug: use dump_stack() where possible
In some cases, libcfs_debug_dumpstack() can fail to output a
stack trace - either because the needed symbols are not exported
or those symbols can't be resolved at runtime. This seems to
occur more often with newer kernels. The messages appears only
as:
Lustre: ldlm_cb01_002: service thread pid 57876 was inactive for
40.494 seconds. The thread might be hung, or it might only be
slow and will resume later. Dumping the stack trace for
debugging purposes:
Pid: 57876, comm: ldlm_cb01_002 6.1.70 #1 SMP PREEMPT_DYNAMIC
Thu Jan 4 18:52:41 UTC 2024
Call Trace TBD:
with no stack trace (seen on CentOS 8.5 with ml 6.1.70).
For reference, the runtime symbol lookup was added and updated in:
b49ce7a ("LU-12400 libcfs: save_stack_trace_tsk if ARCH_STACKWALK")
58ac9d3 ("LU-14099 build: Fix for unconfigured arch_stackwalk")
First, add a message when the symbol can't be resolved correctly.
This makes it much easier to understand why the stack trace is
missing.
Second, replace libcfs_debug_dumpstack(NULL) with dump_stack().
When the task_struct is NULL, libcfs uses the current
task_struct. This replicates the functionality of dump_stack().
Using dump_stack() is more reliable, more in line with kernel
style, and not likely to be un-exported in the future.
Finally, in lustre/osc/osc_object.c the stack isn't dumped since
there is already an LBUG().
There only remains one user of libcfs_debug_dumpstack() which
uses a task_struct other than current. This can be cleaned up
in a future patch.
Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I196c1da7e39b1a694c0cb67ecfaab58ab3e4662c
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53625
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Josh Samuelson [Mon, 8 Jan 2024 19:03:52 +0000 (13:03 -0600)]
LU-17400 uapi: Fix incorrect snamelen return value
The sname char array is limited by the struct
changelog_rec.cr_namelen value and has no '\0' character allocated
to it, so strlen() will overrun the char array till it finds the next
'\0' char.
This issue can be seen on the client side when "lfs changelog"
is run and 08RENME record types are present.
Pointer arithmetic was used between sname and name to avoid the
GCC 11 warnings mentioned in
6331eadbd6.
Added Andreas's safety/range check code to changelog_rec_sname.
Fixes:
6331eadbd6 ("LU-15420 uapi: avoid gcc-11 -Werror=stringop-overread")
Signed-off-by: Josh Samuelson <josh@1up.unl.edu>
Change-Id: Ie0817dfdd1d02e06b9399e66f1affaadb9e156c4
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53624
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: xinliang <xinliang.liu@linaro.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Mon, 8 Jan 2024 09:02:24 +0000 (14:32 +0530)]
LU-17000 lnet: don't assign unused return codes
In lnet_peer_discovery() return from lnet_peer_ping_failed()
and lnet_peer_push_failed() is unused and return value of
former get quashed without getting used.
Remove rc assignment and cast function to void to make it
clear the return code can be ignored.
Test-Parameters: trivial
CoverityID: 412758 ("Unused Value")
CoverityID: 412759 ("Unused Value")
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I02d5e883fc02814d5dbe307b78f028703023db52
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53608
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Lai Siyao [Tue, 19 Dec 2023 08:24:07 +0000 (03:24 -0500)]
LU-9457 test: improve sanity 253
Improve sanity test_253: set high watermark to 50M, and fill OST with
fallocate.
Test-Parameters: trivial
Test-Parameters: testlist=sanity,sanity,sanity,sanity,sanity,sanity,sanity env=EXCEPT=77c
Test-Parameters: testlist=sanity,sanity,sanity,sanity,sanity,sanity,sanity env=EXCEPT=77c
Test-Parameters: testlist=sanity,sanity,sanity,sanity,sanity,sanity,sanity env=EXCEPT=77c
Test-Parameters: testlist=sanity,sanity,sanity,sanity,sanity,sanity,sanity env=EXCEPT=77c
Test-Parameters: testlist=sanity,sanity,sanity,sanity,sanity,sanity,sanity env=EXCEPT=77c
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I85139d7fc0697d08c21bdb19432b40c8dab82ee9
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53548
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Wed, 13 Dec 2023 09:20:47 +0000 (14:50 +0530)]
LU-16796 lnet: Change sfw_session to use refcount_t
This patch changes struct sfw_session to use
refcount_t instead of atomic_t
This patch also address checkpatch errors.
Test-Parameters: trivial testlist=lnet-selftest
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ifa77b8d9280756ce52c8f59d1d193a866f0ba8a7
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53438
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Tue, 12 Dec 2023 07:16:19 +0000 (12:46 +0530)]
LU-16796 ldlm: Change struct ldlm_resource to use refcount_t
This patch changes struct ldlm_resource and
struct nrs_tbf_client to use refcount_t instead of atomic_t
This patch also only changes spaces to tabs which were close
to lines of code being changed.
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ic15f27bc6281725f00bddc465668f81291aad6ec
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53416
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alex Zhuravlev [Mon, 11 Dec 2023 15:15:40 +0000 (18:15 +0300)]
LU-17354 osp: don't reset sequence client
do not reset sequence client if sequence allocation returned an
error, instead try to to get sequence later upon reconnection.
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Change-Id: Ie23b688e4f93651c4615d77a9686c44a150d3961
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53406
Reviewed-by: Sergey Cheremencev <scherementsev@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Timothy Day [Sun, 10 Dec 2023 22:58:09 +0000 (22:58 +0000)]
LU-17000 contrib: script to prepare coverity builds
Add script 'coverity-run' to semi-automate running
and submitting Coverity builds for Lustre. This
should make it much easier to reproducibly submit
builds to Coverity - and serve as an example of
how the Coverity build process works. It should
also provide more transparency in how builds are
being prepared for Coverity.
Add a Vagrantfile for the Vagrant VM used during
the build process.
Update in-tree Documentation.
Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I050b10d9df0e4e4c1b8bcc91a3c296c11f27ffef
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53400
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Etienne AUJAMES [Tue, 28 Nov 2023 13:26:15 +0000 (14:26 +0100)]
LU-17229 tests: rely on IR for replay-dual 33
test 33 seems to fail with a combined MDT0000 and MGT.
This patch failover MDT0001 instead of MDT0000 to keep the IR working
on the MGS.
Test-Parameters: testlist=replay-dual env=ONLY="33",ONLY_REPEAT=50
Test-Parameters: testlist=replay-dual
Test-Parameters: testlist=replay-dual
Signed-off-by: Etienne AUJAMES <eaujames@ddn.com>
Change-Id: Ibf317283b005c103c5f28b7343a808fd25f992a1
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53267
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Deiter
Reviewed-by: Sarah Liu <sarah@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Etienne AUJAMES [Tue, 21 Nov 2023 19:01:43 +0000 (20:01 +0100)]
LU-17308 mgs: move pool_cmd check to the kernel
Several checks for pool_cmd need to be done before touching the MGS
configuration.
e.g: the following case should be denied before adding a destroy
record in the MGS configurations:
- The pool does not exist
- The pool is not empty (OSTs still in the pool)
This work is done in userspace (check_pool_cmd) by checking the client
lov parameters for pools. But nothing guarantees those parameters to
be in sync. So, only the MGS configuration should be trusted for that.
This patch move those checks in the kernel. There are several reasons
for this:
- It guarantees the pool configurations consistency even if an
external tool is used.
- For standalone MGS, it limits the overhead of reading the
configuration several times.
This patch add a "-n|--nowait" option for pool_cmd to skip waiting
for pool updates on the clients. This is useful when doing a lot of
pool_cmd in a raw. And this avoids cancelling clients CONFIG lock
each times (because of mgc_requeue_timeout_min).
e.g:
lctl pool_destroy -n lustre.old
lctl pool_new -n lustre.test
lctl pool_add -n lustre.test OST0001
...
lctl pool_add lustre.test OST0010
check_pool_cmd_result() is modified to compute the client wait delay
with mgc_requeue_timeout_min.
Add a regression test "ost-pools 2f".
Test-Parameters: testlist=ost-pools
Test-Parameters: testlist=ost-pools
Test-Parameters: testlist=ost-pools env=ONLY=2f,ONLY_REPEAT=50
Test-Parameters: testlist=ost-pools env=ONLY=2f,ONLY_REPEAT=50
Signed-off-by: Etienne AUJAMES <eaujames@ddn.com>
Change-Id: Ifbc49b5667bf17253716052a7480114936c65149
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53202
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Guillaume Courrier <guillaume.courrier@cea.fr>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Sebastien Buisson [Mon, 13 Nov 2023 10:03:38 +0000 (11:03 +0100)]
LU-17173 tests: fix security related tests
Several cleanups required in security related tests.
In sanity-krb5, in order to get proper access to keyrings, use su -
instead of runas to initialize process more completely.
Also fix use of 'lfs flushctx', as some tests do not call it properly.
And in test_8, avoid waiting arbitrarily and change fail_loc to just
sleep once.
In sanity-krb5 and sanity-sec, fix parameters passed to
start_gss_daemons().
Test-Parameters: trivial
Test-Parameters: kerberos=true testlist=sanity-krb5
Test-Parameters: testgroup=review-dne-selinux-ssk-part-2
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I4598ae5a7d28afbc39d7cc2d0afd1096d877d03b
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53012
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Etienne AUJAMES [Thu, 26 Oct 2023 19:28:55 +0000 (21:28 +0200)]
LU-16566 sptlrpc: remove rq_sepol from ptlrpc_request
This patch remove rq_sepol from ptlrpc_request to reduce the memory
consumption on the servers.
rq_sepol field is 327 bytes long allocated for each request and this
is rarely used (it needs SELinux activated with the send_sepol
feature).
The patch store the SELinux policy status string in a separate object.
The pointer is stored in ptlrpc_sec->ps_sepol and protected by RCU
(mostly read-only, the SELinux policy should rarely change).
When the policy status needs to be packed in a request, we take a
reference to the current ps_sepol object and release it after the
packing. If the policy has changed in the meantime, the object used
will be free after.
A read operation is added to srpc_sepol parameter to return the
SELinux policy string cached in Lustre.
Test-Parameters: testlist=sanity-selinux env=ONLY=21,ONLY_REPEAT=50
Test-Parameters: testlist=sanity-selinux env=ONLY=21,ONLY_REPEAT=50
Signed-off-by: Etienne AUJAMES <eaujames@ddn.com>
Change-Id: I80fb76c97885c4b2987eb7f91a9bfe6e0e6e6c70
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52845
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Sebastien Buisson [Mon, 13 Nov 2023 10:02:24 +0000 (11:02 +0100)]
LU-17173 utils: cleanup lfs flushctx
When lfs flushctx is called without mount points, build the list of
all mounts first, and then call the ioctl to flush associated
contexts. Otherwise fetching the mount points unfortunately refreshes
the contexts being flushed, because the mount points are being
accessed.
Test-Parameters: trivial
Test-Parameters: kerberos=true testlist=sanity-krb5
Test-Parameters: testgroup=review-dne-selinux-ssk-part-2
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I75b9efe4c65ce66f5f692f9e49a28fde705d0140
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52604
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Sebastien Buisson [Fri, 20 Oct 2023 08:27:14 +0000 (10:27 +0200)]
LU-17173 gss: user keys go to user keyring
Keys for root, that are used for Lustre internal processing, are
stored in the session keyring. That way they can be found by all
Lustre processes in userspace and in the kernel.
For end user keys, it is better to store them in the user keyring.
This simplifies key management, makes them shared accross all user
sessions, and avoids unfortunate key leak if lfs flushctx is not
called at user logout.
Test-Parameters: kerberos=true testlist=sanity-krb5
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: Ibb3d326e89dcacc89e77eca76cdb773861d3a8a7
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52771
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Patrick Farrell [Thu, 31 Aug 2023 00:07:03 +0000 (20:07 -0400)]
LU-17078 ldlm: do not spin up thread for local cancels
When doing lockless IO on the client, the server is
responsible for taking LDLM locks for each IO.
Currently, the server sends these locks to a separate
thread for cancellation. This behavior is necessary on the
client where a lock may protect a large number of cached
pages, so cancelling it in a user thread may introduce
unacceptable delays. But the server doesn't have cached
pages, so it makes more sense for the server to do the
cancellation in the same thread.
We do this by not spinning up an ldlm_bl thread for
cancellations of local (server side only) locks.
This improves 4K DIO random read performance by about 9%.
Without patch, maximum server IOPs on 4K reads:
2864k IOPS
With patch:
3118k IOPS
This is the maximum performance achieved with many clients
and client threads doing 4K random AIO reads from different
files.
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: Ia996732780d278c5d0bc290c5484e3bc325a347a
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52192
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Xinliang Liu [Mon, 7 Aug 2023 10:18:49 +0000 (10:18 +0000)]
LU-17029 lustre.spec.in: match rpm macro openEuler for openEuler Linux
So that it can handle openEuler derived OSes, because different
derived OS has different vendor name, like KylinOS's vendor name
is Kylin.
Change-Id: I12ceda5bf9d1f17a75d4adddbad292fd1ae9967b
Test-Parameters: trivial
Signed-off-by: Xinliang Liu <xinliang.liu@linaro.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51954
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Fri, 4 Aug 2023 05:01:42 +0000 (23:01 -0600)]
LU-17016 mdd: no EXDEV for parent dir projid mismatch
Don't return EXDEV if the parent directory projid of a renamed
directory does not match the projid of the target dir. Only the
projid of the source directory itself and the target matter.
Rename variables in mdd_rename_sanity_check() and mdd_rename()
so the object and attribute variable names are consistent.
Improve console error messages to contain more useful information.
Replace spaces with tabs in affected functions.
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I7aa53f6d168926719ad9fd5df3c760e6c73ebbe5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51868
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Shaun Tancheff [Thu, 18 Jan 2024 04:30:34 +0000 (11:30 +0700)]
LU-17131 ldiskfs: Add Ubuntu 20.04.5 release 5.15 kernel
Add support for Ubuntu 20.04.5 5.15 kernel similar to el9.2
with updated patches:
ext4-corrupted-inode-block-bitmaps-handling-patches.patch
ext4-data-in-dirent.patch
ext4-dont-check-before-replay.patch
ext4-inode-version.patch
ext4-mballoc-extra-checks.patch
ext4-prealloc.patch
ext4-filename-encode.patch
Tested with tag Ubuntu-hwe-5.15-5.15.0-91.101_20.04.1
Test-Parameters: trivial
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ic1b4b0f25a9ac984186cf4f37b5a73d93af93ebd
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52414
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Artem Blagodarenko <ablagodarenko@ddn.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Shaun Tancheff [Sun, 14 Jan 2024 00:50:37 +0000 (17:50 -0700)]
LU-17131 ldiskfs: Refresh ubuntu 5.11 server
Refresh ext4-pdirop and ext4-delayed-iput,
Add
ext4-filename-encode support
ext4-add-periodic-superblock-update
Test-Parameters: trivial
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Icd066a4f507842312924f7c7818208d8f07c8c70
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52413
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Qian Yingjin [Fri, 22 Dec 2023 09:16:07 +0000 (04:16 -0500)]
LU-17383 statahead: quit statahead with a long time wait
If the thread is not doing stat for more than a time threshold
(@sbi->ll_sa_timeout, 30 seconds by default) then it probably does
not care too much about performance, or is no longer using this
directory.
Quit the statahead thread with a long time wait in this case.
This patch also fixes defects reported by Coverity Scan for
Lustre.
Fixes:
e10bf68d7c3 ("LU-14361 statahead: regularized fname statahead pattern")
Test-Parameters: testlist=parallel-scale-nfsv4
Test-Parameters: testlist=parallel-scale-nfsv4
Test-Parameters: testlist=parallel-scale-nfsv4
Test-Parameters: testlist=parallel-scale-nfsv4
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: Ia7c478268fe12eeefa6dfae1b3c94451f010d1d5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53535
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Lai Siyao [Tue, 16 Jan 2024 01:33:22 +0000 (20:33 -0500)]
LU-17426 mdt: relax same MDT file rename lock
Allow cross-directory rename of regular files (strictly, any
non-directory) on the same MDT without holding the BigFilesystemLock
(BFL), as file renames cannot change the directory hierarchy.
This should improve the performance for these rename operations, and
reduce contention between local MDT file renames in different parts of
the directory tree.
Add "mdt.*.enable_parallel_rename_crossdir" parameter to disable
cross-directory file renames if there is an issue with this change.
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I511b392e46c46140cac6aa3ede02bfe793729f7f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53726
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Shaun Tancheff [Fri, 6 Oct 2023 08:03:09 +0000 (03:03 -0500)]
LU-13906 build: Conditionally require kmod-zfs-devel
Server with zfs support requires either kmod-zfs-devel
or a configure that points to the required headers and
library files via configure.
Here we check the configure arguments for '--with-zfs-obj='
if the zfs path is specified for configure the package
requirement is not needed.
Otherwise require the kmod-zfs-devel package and require
one of libzfs-devel, libzfs4-devel or libzfs5-devel
HPE-bug-id: LUS-9743, LUS-10363
Test-Parameters: trivial
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ia12239ac7e3912ff50ec7c8e2ceb888862afbc34
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/46356
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Olaf Faaland <faaland1@llnl.gov>
Alexander Zarochentsev [Thu, 4 Jan 2024 19:07:18 +0000 (19:07 +0000)]
LU-17385 tests: sanity-lfsck 23d fix and enable
lfsck "-t layout -o" requests lfsck runs on all MTDs,
the test needs to wait them all before the next
test starts.
Test-Parameters: trivial testlist=sanity-lfsck mdscount=2 mdtcount=4
Test-Parameters: trivial testlist=sanity-lfsck mdscount=2 mdtcount=4
Test-Parameters: trivial testlist=sanity-lfsck mdscount=2 mdtcount=4
Test-Parameters: trivial testlist=sanity-lfsck mdscount=2 mdtcount=4
Signed-off-by: Alexander Zarochentsev <alexander.zarochentsev@hpe.com>
Change-Id: Ida0bf876b60a73258a5a9bf392f96383c88adcb9
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53591
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Alex Deiter
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Dominique Martinet [Thu, 18 Jan 2024 20:46:10 +0000 (05:46 +0900)]
LU-17444 utils: fix fd leak after conversion to llapi_root_path_open
Conversions to llapi_root_path_open missed a few close() calls, leading
to fd leaks.
These should be obvious enough to regroup in a single commit.
Fixes:
7154244354e3 ("LU-16786 utils: Replace open call to WANT_FD")
Change-Id: I3af25ef2981367bfaea7f5280972f84bee09a5c2
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53736
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Stephane Thiell <sthiell@stanford.edu>
Reviewed-by: Etienne AUJAMES <eaujames@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Alexey Lyashkov [Mon, 25 Dec 2023 11:52:35 +0000 (14:52 +0300)]
LU-17364 llite: don't use stale page.
using stale page for write might confuse a read path,
which expect any IO page have PG_uptodate flag set,
and it caused an panic with removing from IO.
Test-Parameters: testlist=sanityn env=SLOW=yes,ONLY=16k,ONLY_REPEAT=10
Test-Parameters: testlist=sanityn env=SLOW=yes,ONLY=16k,ONLY_REPEAT=10
Test-Parameters: testlist=sanityn env=SLOW=yes,ONLY=16k,ONLY_REPEAT=10
Test-Parameters: testlist=sanityn env=SLOW=yes,ONLY=16k,ONLY_REPEAT=10
Test-Parameters: testlist=sanityn env=SLOW=yes,ONLY=16k,ONLY_REPEAT=10
Test-Parameters: testlist=sanityn env=SLOW=yes,ONLY=16k,ONLY_REPEAT=10
Signed-off-by: Alexey Lyashkov <alexey.lyashkov@hpe.com>
Change-Id: Ia01129ceaecf53d8d9f301c26cd2d65122f6a267
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53550
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Alexander Zarochentsev <alexander.zarochentsev@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Qian Yingjin [Wed, 10 Jan 2024 09:25:21 +0000 (04:25 -0500)]
LU-14361 statahead: increase the initial statahead count
In this patch, we increase the initial stat-ahead count from the
default 8 to 64 during the fname statahead pattern test sanity/
test_123i. The origial starting statahead count is too small, may
result in that the statahead thread quits wrongly. This will fail
sanity/test_123i fairly often.
We also imporve aheadmany and use it to generate the fname stat()
workload to verify that fname statahead pattern works correctly.
Test-Parameters: mdtcount=4 mdscount=2 testlist=sanity env=ONLY=123i,ONLY_REPEAT=100
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I7d13120a9480ea5b2e53963789074429c414ff90
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53634
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Alex Zhuravlev [Sat, 11 Nov 2023 12:21:48 +0000 (15:21 +0300)]
LU-17284 mdt: revalidate object for migration
if the source object is remote, then we should revlidate it
once the object's ldlm lock is granted. otherwise we can't
use the object's attributes:
lu_object_attr())
ASSERTION( ((o)->lo_header->loh_attr & LOHA_EXISTS) != 0
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Change-Id: I9896cdd011f858091ac68b50b74e2f1f027f7331
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53087
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Andrew Perepechko [Tue, 26 Dec 2023 17:02:12 +0000 (20:02 +0300)]
LU-16637 llite: tolerate fresh page cache pages after truncate
Truncate called by ll_layout_refesh() can race with a fast read
or tiny write, which can add an uninitialized non-uptodate page
into the page cache.
We want to avoid expensive locking for this rare case so if there
is any leftover in the cache after truncate, just check that
the pages are not uptodate, not dirty and do not have any
filesystem-specific information attached to them.
Change-Id: I8cadc022a3d1822a585f32e1a765e59ad0ff434d
Signed-off-by: Andrew Perepechko <andrew.perepechko@hpe.com>
HPE-bug-id: LUS-11937
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53554
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Zhenyu Xu <bobijam@hotmail.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
James Simmons [Sun, 7 Jan 2024 15:13:38 +0000 (08:13 -0700)]
LU-13307 nodemap: have nodemap_add_member support large NIDs
Currently when mounting lustre using IPv6 address fails with
Lustre: 27361:0:(nodemap_handler.c:395:nodemap_add_member())
lustre-MDT0000: error adding to nodemap, no valid NIDs found
LustreError: 11-0: lustre-MDT0000-osp-MDT0003:
operation mds_connect to node 0@lo failed: rc = -22
This was due to no nodemap being set so the ptlrpc layer was not
seeing any new peers. Adding minimal support to nodemap allows
mounting.
Change-Id: If9cfe88ec92afc3f14788f3f3ded8387a1b5d8c7
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53135
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Arshad Hussain [Tue, 9 Jan 2024 06:12:57 +0000 (11:42 +0530)]
LU-16861 obdfilter: Exclude quotes when getting NIDs
In get_targets(), when getting NIDs the quotes were also included.
Exclude quotes when generating NIDs as they are not required.
Use $LCTL instead of $lctl, and make it also work in Janitor testing.
Test-Parameters: trivial testlist=obdfilter-survey
Fixes:
9ef9906d7 ("LU-6863 tests: change obdfilter-survey.sh for CLIENTONLY mode")
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I8642539fc6b396f1339e20e4fef8bc78cda2d969
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53620
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Deiter <alex.deiter@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Thu, 4 Jan 2024 21:32:13 +0000 (14:32 -0700)]
LU-17054 lnet: use GFP_KERNEL for alloc w/o spinlock
Do not use genradix_ptr_alloc(GFP_ATOMIC) when not allocating
under a spinlock in lnet_cpt_of_nid_show_start(), since this
puts unnecessary strain on the atomic memory pools. This
function grabs mutex_lock(&the_lnet.ln_api_mutex) so the caller
cannot be holding a spinlock at the time.
Fix minor code style issues in this function.
Fixes:
466e25a6a3 ("LU-17054 lnet: Change cpt-of-nid to get result from kernel")
Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I091959940bffadc380bff9329bb83e8b099ed63f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53596
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Thu, 4 Jan 2024 05:20:35 +0000 (22:20 -0700)]
LU-17394 libcfs: print cfs_fail_val when fail_loc hit
Add some more information to the console message when fail_loc is hit.
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I99fe4524f3764b068c96965c0b86bd4d7b341707
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53585
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Alexander Boyko <alexander.boyko@hpe.com>
John L. Hammond [Thu, 4 Nov 2021 16:12:57 +0000 (11:12 -0500)]
LU-17172 lov: include FID in some lov asserts
Include the file FID in the assertions in lov_entry() and
lov_mirror_entry(). Use these two functions more consistently in the
lov layer.
Signed-off-by: John L. Hammond <jhammond@whamcloud.com>
Change-Id: I65978fe409842289c158021fb1b8042916d90e23
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52602
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Brian Atkinson [Tue, 26 Sep 2023 18:35:43 +0000 (12:35 -0600)]
LU-16791 utils: ZFS 2.2 const prop args
ZFS 2.2 now expects const char * from certain interfaces in
sys/nvpair.h. I updated the build system to detect if this is the case
and if so update the paramters passed to certain functions in
libmount_utils_zfs.c to account for these changes.
Without this patch, Lustre master would not build with ZFS master and
the 2.2 release candidates.
Signed-off-by: Brian Atkinson <batkinson@lanl.gov>
Change-Id: I0469eeff6dafa6c276fc616381530b6b679d9da1
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52519
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Akash B <akash-b@hpe.com>
Reviewed-by: Thomas Bertschinger <bertschinger@lanl.gov>
Reviewed-by: Olaf Faaland <faaland1@llnl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Shaun Tancheff [Thu, 4 Jan 2024 23:34:37 +0000 (15:34 -0800)]
LU-17351 ldiskfs: RHEL 9.3 ldiskfs server
Updated patch series for el9.3 needs an updated
ext4-data-in-dirent
Test-Parameters: trivial env=SANITY_EXCEPT="906" \
mdtcount=4 mdscount=2 \
clientdistro=el9.3 serverdistro=el9.2 testlist=sanity
Test-Parameters: trivial mdtcount=4 mdscount=2 \
clientdistro=el9.2 serverdistro=el9.3 testlist=sanity
Test-Parameters: optional clientdistro=el9.3 serverdistro=el9.3 \
testgroup=full-part-1
Test-Parameters: optional clientdistro=el9.3 serverdistro=el9.3 \
testgroup=full-part-2
Test-Parameters: optional clientdistro=el9.3 serverdistro=el9.3 \
testgroup=full-part-3
HPE-bug-id: LUS-12050
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Change-Id: Iac9731570422c57ef494602b1a40ac0b3d87d991
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53394
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: xinliang <xinliang.liu@linaro.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Thu, 4 Jan 2024 21:07:43 +0000 (14:07 -0700)]
LU-10391 lnet: use GFP_ATOMIC for alloc under spinlock
Use genradix_ptr_alloc(GFP_ATOMIC) when allocating under a spinlock
(in this case lnet_net_lock_current() is acquiring the per-CPT lock)
to avoid "BUG: sleeping function called from invalid context" in
lnet_discover() and lnet_scan_route() when memory debugging enabled.
BUG: sleeping function called from invalid context at page_alloc.c:3423
in_atomic(): 1, irqs_disabled(): 0, pid: 22268, name: lnetctl
CPU: 3 PID: 22268 Comm: lnetctl 3.10.0-7.9-debug #1
Call Trace:
dump_stack+0x19/0x1b
__might_sleep+0xd9/0x100
__alloc_pages_nodemask+0x313/0xca0
alloc_pages_current+0x98/0x110
__get_free_pages+0xe/0x50
__genradix_ptr_alloc+0xa2/0x1a0 [libcfs]
lnet_discover+0x16e/0x220 [lnet]
lnet_ping_cmd+0x6ab/0x1160 [lnet]
genl_family_rcv_msg+0x1fa/0x420
genl_rcv_msg+0x5b/0xc0
netlink_rcv_skb+0xa9/0xc0
genl_rcv+0x28/0x40
netlink_unicast+0x16a/0x210
netlink_sendmsg+0x308/0x420
sock_sendmsg+0xb0/0xf0
___sys_sendmsg+0x401/0x410
__sys_sendmsg+0x51/0x90
SyS_sendmsg+0x12/0x20
Fixes:
68254c484a ("LU-10391 lnet: handle discovery with Netlink")
Fixes:
4ccac8297d ("LU-9680 lnet: collect data about routes using Netlink")
Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I96f1fd6f6273a7720d661526e58a94210f3ebbe5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53597
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Shaun Tancheff [Tue, 9 Jan 2024 05:49:13 +0000 (12:49 +0700)]
LU-17398 build: detect mlnx-ofa_kernel-devel contents
Parse the configure_args for --with-o2ib and allow the
user specified path to override the mofed defaults.
Further when mlnx-ofa_kernel-devel contents are available silence
the BuildRequires: to allow for an mlnx source installation to
satisfy the lustre build requirements.
In addition move the mlnx specfic requirements to the mofed lnd
when '--with multiple_lnds' is enabled.
Fixes:
67cd54d05d ("LU-16967 build: Separate lnet LND rpm packaging")
Test-Parameters: trivial
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: I30c6b3a196021634c621f6f6c556bf32f28faeed
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53613
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Shaun Tancheff [Sat, 6 Jan 2024 15:13:27 +0000 (22:13 +0700)]
LU-17398 build: quash rpmbuild false warning
Rewrite comment so %() is escaped and does not generate
a false and misleaning warning during build:
sh: -c: line 0: syntax error near unexpected token `)'
sh: -c: line 0: `)'
warning: Macro expanded in comment on line 261: %()
Test-Parameters: trivial
Fixes:
67cd54d05d ("LU-16967 build: Separate lnet LND rpm packaging")
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: I94fa0da88a5c7f64461cd8fc3cea343a7a087413
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53604
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Alexandre Ioffe [Fri, 29 Dec 2023 05:42:41 +0000 (21:42 -0800)]
LU-17370 utils: simplify lfs help text
Simplify help text for lfs getstripe and lfs setstripe.
Update corresponding man pages lfs-getstripe and lfs-setstripe.
On man pages make left side adjustment and disable hyphenation:
'.nh', '.ad l' to prevent hyphenation of keywords
Signed-off-by: Alexandre Ioffe <aioffe@ddn.com>
Test-Parameters: trivial
Change-Id: Iae9d3534230ee7d325fbeffd78b5c12632a4a161
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53564
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Yang Sheng [Wed, 27 Dec 2023 18:26:41 +0000 (02:26 +0800)]
LU-17276 tests: performance test case for flock
Add some test cases for flock performance.
Test-Parameters: trivial testlist=performance-sanity env=ONLY=6,ONLY_REPEAT=50
Signed-off-by: Yang Sheng <ys@whamcloud.com>
Change-Id: Id76d38e14bec6a095fe26e22d08569731d4669c9
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53558
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Deiter <alex.deiter@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Timothy Day [Fri, 15 Dec 2023 21:17:18 +0000 (21:17 +0000)]
LU-16502 lutf: add headers to lutf C code
Add SPDX text and documentation to lutf C code.
This will make it easier for developers to
find where different functionality lives.
Test-Parameters: @lnet
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I67d8acc6b5968e76667130f38018ddcf0fcfd3b0
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53480
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Qian Yingjin [Thu, 7 Dec 2023 09:45:01 +0000 (04:45 -0500)]
LU-17289 test: disable sanity/test_906 temporarily
On the rhel9.3, the fio io_uring engine testing failed with error
"Operation not permitted" on both local file systems (Ext4 and
xfs) and Lustre:
"fio: pid=4551, err=1/file:engines/io_uring.c:1047,
func=io_queue_init, error=Operation not permitted"
This is a generic failure in rhel9.3.
Thus we disable sanity/test_906 temporarily until the bug is fixed
in rhel9.3.
Test-Parameters: trivial testlist=sanity clientdistro=el9.3
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I3805b475c5f3d0b62dc6c57c4cd93f2bc1b67b76
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53362
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Shaun Tancheff [Sat, 11 Nov 2023 01:40:22 +0000 (19:40 -0600)]
LU-17160 build: Use PyConfig_InitPythonConfig 3.11 and later
Python PEP https://peps.python.org/pep-0587 changed the python
initialization scheme and deprecated Py_SetProgramName() among
other functions.
As of python 3.11 the new init scheme is available.
Test-Parameters: trivial
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ia7bdb63a74295ab8cf0313f16bfd03d78cf8fcf7
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52558
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
James Simmons [Tue, 2 Jan 2024 00:11:35 +0000 (19:11 -0500)]
LU-10391 mgs: handle strscpy return value properly
The function strscpy() returns either an error code or the length
of the string copied. We need on success of strscpy in the
function mgs_steal_client_llog_handler() reset rc to zero to avoid
the return value been seen as an error. While we could use large
NIDs some functionality like nodemap was failing due to this
mishandling of the return code.
Fixes:
c0cb747ebe9 ("LU-13306 mgs: use large NIDS in the nid table on the MGS")
Test-Parameters: trivial
Change-Id: I013d34e0d0223367efea97f71dd4baa1052e2e1b
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53571
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
James Simmons [Sat, 23 Dec 2023 18:43:20 +0000 (13:43 -0500)]
LU-10003 lnet: implement Netlink version of lnet distance API.
Userland can query the distance of a peer using an ioctl. Move
this over to Netlink so we can support large NIDs for IPv6
handling.
Test-Parameters: trivial testlist=sanity-lnet
Change-Id: I090538e4cc55fd26bd61888de659b99bba85a111
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53556
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Andreas Dilger [Sat, 23 Dec 2023 01:24:18 +0000 (18:24 -0700)]
LU-6142 build: ignore deleted lines for comment context
checkpatch should skip removed lines when checking comments context.
Otherwise, false "WARNING: memory barrier without comment" and other
messages can be reported when a comment exists on the previous line
but is hidden by the removed line.
For example, a change like below was previously incorrectly flagged:
/* matched by smp_store_release() in some_function() */
- if (smp_load_acquire(&list->tail) == head))
+ if (smp_load_acquire(&list->tail) == head) && flags == 0)
Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ib0cd11e66a5b6a3c4505222eb89ff6479246023a
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53543
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Mikhail Pershin [Wed, 13 Dec 2023 12:43:53 +0000 (15:43 +0300)]
LU-17365 lod: handle llog errors gracefuly
Distinguish remote llog errors by their source and type
in LOD lod_sub_prep_llog() and uniform errors reported
by llog_osd_read_header() and llog_init_handle.
- Partial llog header or 0-size llog is to be
reinitialized, new header is created
- in llog_read_header() dt_attr_get() and read_header()
thier errors are printed and returned as -EIO to caller
- llog with invalid llog header data is skipped and new
one is created to be used instead. To indicate that
the llog_init_handle() returns -EINVAL error code instead
of -EIO. Therefore network errors are to be handled by
lod_sub_recovery_thread() retry logic while bad llog
content will lead to immediate llog re-creation.
- lod_sub_init_llogs() tries to init all targets even
if some failed
- always recreate llogs after recovery abort no matter
if ctxt->loc_handle exists or not
Patch tries to cover known issues and types of error during
update log recovery and provides also better debug for
similar cases in future
Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I2705e0dc245ed4365123ce47137193a9ed769673
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53510
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Emoly Liu <emoly@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
James Simmons [Thu, 4 Jan 2024 20:02:08 +0000 (15:02 -0500)]
LU-10391 tests: except sanity-lnet/253+254 due to failures
Moving to Netlink for ping support has exposed a timing issues
with some of the sanity-lnet test. Skip those tests temporarily
until the issue can be fixed.
Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: James Simmons <jsimmons@infradead.org>
Change-Id: Ia30fcbf8eca7baaf6f896e6e51229c69cea82804
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53593
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Oleg Drokin [Wed, 3 Jan 2024 18:17:29 +0000 (13:17 -0500)]
New tag 2.15.60
Change-Id: Iebcf2a80949d8d5d14a2e6aeb6582884b11d343f
Signed-off-by: Oleg Drokin <green@whamcloud.com>
Alex Zhuravlev [Fri, 20 Oct 2023 11:23:26 +0000 (14:23 +0300)]
LU-17215 tests: sanity/398q to use $tfile
tfile seems to be a typo
Fixes:
43c3a804fe2 ("LU-13805 tests: Add racing tests of BIO, DIO")
Test-Parameters: trivial
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Change-Id: I85b0afce577b708ef9e69747774bd248484bd9dd
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52772
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Mikhail Pershin <mpershin@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Sebastien Buisson [Mon, 18 Dec 2023 13:59:30 +0000 (14:59 +0100)]
LU-17374 gss: get rid of rsi cache entries after req handle
RPCSEC init requests are kept in the rsi cache. While this is useful
during request processing involving upcall/downcall with userspace,
rsi entries are never used again once RPCSEC init requests have been
handled completely.
And keeping entries in the rsi cache has some impact on authentication
speed. When a new RPCSEC init request is received, the first step is
to check if there is a valid matching entry in the cache. It is never
the case, except if an authentication request is replayed, but GSS
rejects that anyway.
So we spend time browsing a cache from which we expect no match. Even
if the upcall cache mechanism takes this lookup opportunity to remove
invalid or expired entries, it is even better to remove cache entries
as soon as we know they are done.
Test-Parameters: kerberos=true testlist=sanity-krb5
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: Ia9946578c3d3149e6235d832df28214ae8984f1e
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53488
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Jian Yu [Thu, 14 Dec 2023 18:35:00 +0000 (10:35 -0800)]
LU-17366 kernel: update SLES15 SP5 [5.14.21-150500.55.39.1]
Update SLES15 SP5 kernel to 5.14.21-150500.55.39.1 for Lustre client.
Test-Parameters: trivial mdtcount=4 mdscount=2 \
clientdistro=sles15sp5 testlist=sanity
Change-Id: Id9476e8726728b00d4079cdaf31b081f89190eb1
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53467
Reviewed-by: Colin Faber <cfaber@ddn.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Timothy Day [Thu, 14 Dec 2023 16:27:40 +0000 (16:27 +0000)]
LU-8802 obd: str2dev is missing obd_device_unlock()
class_str2dev() was missing an obd_device_unlock(). I haven't
seen any bugs related to this missing unlock. I suspect
the mount state machine avoids this. Add the unlock just
to be safe.
Fixes:
c5e5060d950 ("LU-8802 obd: remove MAX_OBD_DEVICES")
Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I7a813f9d4931a7a9979223bfde5efea07f1e5228
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53466
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
James Simmons [Sun, 10 Dec 2023 14:50:43 +0000 (09:50 -0500)]
LU-16823 lustre: test if large nid is support
Update all LNetGetId() calls to use large NIDs if the connect
flags report large NID support. For the case of lmv_setup()
we update setting qos_rr_index, to avoid the thundering herd,
using nidhash().
Change-Id: I80fda9454f154e27fbc75abb1899c0ccca03097b
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53398
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Lei Feng [Sun, 10 Dec 2023 08:45:38 +0000 (16:45 +0800)]
LU-17352 utils: lljobstat can read dumped stats files
Improve lljobstat command to read dumped stats file.
Usually the file is generated by command:
lctl get_param *.*.job_stats > all_job_stats.txt
Multiple files can be specified with multiple --statsfile
options. For example:
lljobstat --statsfile=1.txt --statsfile=2.txt
Stats data from multiple files will be added up and
sorted. Then the top jobs will be listed.
Try to use CLoader to accelerate the YAML parsing.
Handle SIGINT and exit silently if lljobstat is in the loop
of reading system job_stats files periodically.
Fix a bug when the job_id is a pure number.
Signed-off-by: Lei Feng <flei@whamcloud.com>
Test-Parameters: trivial
Change-Id: Iee1ce69d2befb9d021e34effd4fc65a47297c1fb
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53397
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Timothy Day [Sat, 9 Dec 2023 21:54:41 +0000 (21:54 +0000)]
LU-16751 build: remove symlinks and add SPDX
Remove commit-msg and prepare-commit-msg links
in the build/ directory. Add proper headers and
SPDX to the remaining files in build/.
Test-Parameters: trivial
Fixes:
25c93758d6 ("LU-1199 build: Clean out the build directory")
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I649ed60f5541be2832555efa2e0cf64cd1a5c67c
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53396
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Andreas Dilger [Wed, 20 Dec 2023 18:45:50 +0000 (11:45 -0700)]
LU-13791 mdt: parameter to tune capabilities
Add mdt.*.enable_cap_mask to allow specific capabilities to
be enabled and disabled individually.
Fixes:
f05edf8e2b ("LU-13791 sec: enable FS capabilities")
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I6fc0130a90693d673d8c2158e7e31c2de951553d
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53538
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Alexander Zarochentsev <alexander.zarochentsev@hpe.com>
Reviewed-by: Andrew Perepechko <andrew.perepechko@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Sebastien Buisson [Thu, 7 Dec 2023 17:07:09 +0000 (18:07 +0100)]
LU-17317 gss: do not continue using expired reverse context
In case a server uses an expired gss context to send a callback
request to a client, it might be that the associated context on
the client has already expired, and been purged from the cache.
This results in a GSS_S_NO_CONTEXT reply.
In this specific scenario, the server must mark its reverse context
as dead. This will lead to destruction of the expired context, and
creation of a new context suitable for further callback requests.
Test-Parameters: kerberos=true testlist=sanity-krb5
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I4af90cd70a3815851ec555ea85b49714c8da4202
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53375
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Thomas Bertschinger [Tue, 31 Oct 2023 19:59:18 +0000 (13:59 -0600)]
LU-17245 utils: fix lfs error messages with multiple paths
When using some lfs utilities (find, getstripe) with multiple paths,
if a subset of the paths has an error, for example due to a typo, the
error message produced can be misleading. For "getstripe" it refers to
the last file on the command line regardless of which file had the
error, and for "find" it prints out the right filename but uses
the error code from the last file on the command line.
This cleans up these error messages for "lfs find" and
"lfs getstripe".
This also adjusts "lfs setdirstripe" to continue for subsequent files
if it encounters an error for earlier files on the command line.
Signed-off-by: Thomas Bertschinger <bertschinger@lanl.gov>
Fixes:
bc500536b6dd ("LU-930 utils: fix 'lfs find' error message")
Fixes:
4affa48f676b ("LU-5170 utils: Continue on error when multiple files requested")
Fixes:
a24f61532927 ("LU-11213 dne: add new dir hash type "space"")
Change-Id: I9cdd007912ffb4f6ebc31e422851977e49186ae7
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52942
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Stephane Thiell [Fri, 3 Nov 2023 04:24:26 +0000 (21:24 -0700)]
LU-16771 llite: add statfs_project tunable
Add a client tunable and mount option to turn off project-enabled
statfs() if needed, for example to speed up statfs() execution by
avoiding project quota check.
This new llite tunable statfs_project is set to 1 by default (feature
enabled). To turn statfs_project off:
lctl set_param llite.*.statfs_project=0
Additionally, statfs_project can be disabled at mount time with:
mount -t lustre -o nostatfs_project ...
Signed-off-by: Stephane Thiell <sthiell@stanford.edu>
Change-Id: I1c3eb27e66b1d05a1c713732dfe0a4d8f7af769f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52872
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alexander Boyko <alexander.boyko@hpe.com>
Reviewed-by: Alexander Zarochentsev <alexander.zarochentsev@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
git://git.whamcloud.com / fs / lustre-release.git / log