- 19 Sep, 2016 40 commits
-
-
Bobi Jam authored
An OSC object could be destroyed with AGL locks waiting for granted, so we'd get rid of the osc_object_ast_clear() assertion that its dlm locks all getting granted. Signed-off-by:
Bobi Jam <bobijam.xu@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6042 Reviewed-on: http://review.whamcloud.com/13163Reviewed-by:
Jinshan Xiong <jinshan.xiong@intel.com> Reviewed-by:
Niu Yawei <yawei.niu@intel.com> Reviewed-by:
Oleg Drokin <oleg.drokin@intel.com> Signed-off-by:
James Simmons <jsimmons@infradead.org> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Alexander Boyko authored
mgc_apply_recover_logs use only first nid from entry, this could be the problem for a cluster with several network address for a one node. Signed-off-by:
Alexander Boyko <alexander.boyko@seagate.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5950 Xyratex-bug-id: MRP-2255 Reviewed-on: http://review.whamcloud.com/12829Reviewed-by:
Andreas Dilger <andreas.dilger@intel.com> Reviewed-by:
Mike Pershin <mike.pershin@intel.com> Reviewed-by:
Ann Koehler <amk@cray.com> Signed-off-by:
-
Alexander Boyko authored
Buggy code at ptlrpc_connect_interpret() finish: rc = ptlrpc_import_recovery_state_machine(imp); ... Set import connection flags When import has FULL state ptlrpc_import_recovery_state_machine() wakeup all waiters on import and all delayed request, which was resented. And it could happened that request was send without updated flags and AT is disabled. If such request is in progress on the server, server drop the new instance, and could do early reply for it. But this early reply confuse client, cause it wait real reply(no AT for this request). Client try to touch buffer outside reply and got EPROTO error. The same bug existed for initital connect too. Import became FULL before import connection flags was set. Signed-off-by:Alexander Boyko <alexander_boyko@xyratex.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5528 Xyratex-bug-id: MRP-2034 Reviewed-on: http://review.whamcloud.com/11723Reviewed-by:
Li Wei <wei.g.li@intel.com> Reviewed-by:
Liang Zhen <liang.zhen@intel.com> Reviewed-by:
-
John L. Hammond authored
Flatten out the lsm_wire struct from the middle of struct lov_stripe_md and remove the member name macros. Signed-off-by:
John L. Hammond <john.hammond@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5814 Reviewed-on: http://review.whamcloud.com/12581Reviewed-by:
Bobi Jam <bobijam@gmail.com> Reviewed-by:
-
Jinshan Xiong authored
lustre_idl.h only includes wire data; lustre_dlm.h is the right place for LDLM_GID_ANY. Signed-off-by:
James Simmons <uja.ornl@gmail.com> Reviewed-by:
-
Dmitry Eremin authored
Change return type and size argiments of lustre_msg_hdr_size(), lustre_msg_buf{len,count}() and req_capsule_*_size() to __u32. Change type of req_format->rf_idx and req_format->rf_fields.nr to size_t. Also return zero for incorrect message magic instead of -EINVAL. This will be more robust because of few of them after LASSERTF(0, "...") and will not be returned. In the rest places it return zero size instead of huge number after implicit unsigned conversion. Signed-off-by:Dmitry Eremin <dmitry.eremin@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5577 Reviewed-on: http://review.whamcloud.com/12475Reviewed-by:
Fan Yong <fan.yong@intel.com> Reviewed-by:
-
Bobi Jam authored
Use cl_object_operations::coo_getstripe() to handle LL_IOC_LOV_GETSTRIPE ops. Signed-off-by:
-
Dmitry Eremin authored
Change the type accordant usage. Signed-off-by:
-
Dmitry Eremin authored
Pages count is unsigned. So, change the type accordant usage. Signed-off-by:
-
Nathaniel Clark authored
Instead of rechecking a static value, recalculate to see if pool stats need to be updated. Add newline so message will print instead of warning about missing newline. Signed-off-by:
Nathaniel Clark <nathaniel.l.clark@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4536 Reviewed-on: http://review.whamcloud.com/12547Reviewed-by:
Lai Siyao <lai.siyao@intel.com> Reviewed-by:
Jian Yu <jian.yu@intel.com> Signed-off-by:
-
Amir Shehata authored
There is a race condition on client reconnect when the import is being destroyed. Some outstanding client bound requests are being processed when the imp_sec has alread been freed. Ensure to suppress the error message in import_sec_validate_get() in that case Signed-off-by:
Amir Shehata <amir.shehata@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3353 Reviewed-on: http://review.whamcloud.com/10200Reviewed-by:
-
Bob Glossman authored
Always return an ERR_PTR() on errors, never return a NULL, in lu_object_find_slice(). Also clean up callers who no longer need special case handling of NULL returns. Signed-off-by:
Bob Glossman <bob.glossman@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5858 Reviewed-on: http://review.whamcloud.com/12554Reviewed-by:
-
Dmitry Eremin authored
Cleanup warnings about comparison between signed and unsigned. Signed-off-by:
-
Bobi Jam authored
When we've collected enough extents as user requested, we'd check one further to decide whether we've reached the last extent of the file. Signed-off-by:
-
Alexey Lyashkov authored
To test proper behavior of clients returning errors on ASTs we can induce a failure with setting OBD_FAIL_LDLM_BL_CALLBACK_NET. Handle the new additonal case of cfs_fail_err being set as well so that the cfs_fail_err can be sent back in a reply. Signed-off-by:
Alexey Lyashkov <alexey_lyashkov@xyratex.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5581 Xyratex-bug-id: MRP-2041 Reviewed-on: http://review.whamcloud.com/11752Reviewed-by:
-
Yoshifumi Uemura authored
In mdc_setattr_pack() access the members of struct lov_user_md by little endian byte order. Signed-off-by:
Yoshifumi Uemura <kogexe@gmail.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5889 Reviewed-on: http://review.whamcloud.com/12683Reviewed-by:
Yang Sheng <yang.sheng@intel.com> Reviewed-by:
-
Dmitry Eremin authored
Change the type accordant usage. Signed-off-by:
-
Bob Glossman authored
The name 'xattr' is used for two different ll_flags bits. Change the names to be distinct and different, reflecting the names of the bits used in LL_SBI_xbitnamex #defines. Signed-off-by:
Minh Diep <minh.diep@intel.com> Reviewed-by:
-
frank zago authored
llog_process_thread() can be called from llog_cat_process_cb with an index already out of bound, leading to the following crash: LustreError: 3773:0:(llog.c:310:llog_process_thread()) ASSERTION(index <= last_index + 1 ) failed: LustreError: 3773:0:(llog.c:310:llog_process_thread()) LBUG #0 [ffff8801144bf900] machine_kexec at ffffffff81038f3b #1 [ffff8801144bf960] crash_kexec at ffffffff810c5d82 #2 [ffff8801144bfa30] panic at ffffffff8152798a #3 [ffff8801144bfab0] lbug_with_loc at ffffffffa02f8eeb [libcfs] #4 [ffff8801144bfad0] llog_process_thread at ffffffffa0413fff [obdclass] #5 [ffff8801144bfb80] llog_process_or_fork at ffffffffa041585f [obdclass] #6 [ffff8801144bfbd0] llog_cat_process_cb at ffffffffa0418612 [obdclass] #7 [ffff8801144bfc30] llog_process_thread at ffffffffa0413c22 [obdclass] #8 [ffff8801144bfce0] llog_process_or_fork at ffffffffa041585f [obdclass] #9 [ffff8801144bfd30] llog_cat_process_or_fork at ffffffffa0416b9d [obdclass] If index is too big, simply return success. Signed-off-by:
frank zago <fzago@cray.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5635 Reviewed-on: http://review.whamcloud.com/12161Reviewed-by:
Patrick Farrell <paf@cray.com> Reviewed-by:
-
Andreas Dilger authored
It may be that a client or MDS is trying to connect to a target (OST or peer MDT) before that target is finished setup. Rather than spamming the console logs during initial connection, only print a console error message if there are repeated failures trying to connect to the target, which may indicate an error on that node. Signed-off-by:
-
Jinshan Xiong authored
The changes for LRU lock policy was introduced by commit bfae5a4e, where I was trying to revise the policy to pick locks for canceling. However, this caused two problems as mentioned in LU-5727. The first problem is that the lock can only be picked for canceling only if the number of LRU locks is over preset LRU number AND it's aged; the second problem is that mdc_cancel_weight() tends to not cancel OPEN locks, therefore open locks can be kept forever and finally exhausts memory on the MDT side. The commit 7b2d26b0 ("revert changes to ldlm_cancel_aged_policy") fixed the first problem. This patch will revert the rest of changes related to LRU policy revise. Signed-off-by:
-
Niu Yawei authored
To avoid scanning the replay open list every time in the ptlrpc_free_committed(), the fix of LU-2613 (4322e0f9) changed the ptlrpc_free_committed() to skip the open list unless the import generation is changed. That introduced a race which could make a closed open being replayed: 1. Application calls ll_close_inode_openhandle()-> mdc_close(), to close file, rq_replay is cleared, but the open request is still on the imp_committed_list; 2. Before the md_clear_open_replay_data() is called for close, client start replay, and that closed open will be replayed mistakenly; 3. Open replay interpret callback (mdc_replay_open) could race with the mdc_clear_open_replay_data() at the end; This patch fix the ptlrpc_free_committed() to make sure the open list is scanned on recovery to prevent the closed open request from being replayed. Signed-off-by:
-
Henri Doreau authored
Fixed changelog_remap_rec() to correctly remap records emitted with jobid_var=disabled, i.e. delivered by new servers but with no jobid field. Signed-off-by:
Henri Doreau <henri.doreau@cea.fr> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5862 Reviewed-on: http://review.whamcloud.com/12574Reviewed-by:
Robert Read <robert.read@intel.com> Signed-off-by:
-
John L. Hammond authored
Remove ll_objects_destroy(). This function is not needed for interoperability with servers of version 2.4 or higher. Remove the then unused function lov_destroy() and its supporting functions. Remove the lsm_destroy method of struct lsm_operations. Remove the unused struct lov_stripe_md, MD export, and capa parameters from obd_destroy() and its implementations. Signed-off-by:
-
John L. Hammond authored
In echo_client replace uses of struct lov_stripe_md with struct lov_oinfo (since the instances of the former really only contained a single instance of the latter). Remove the then unneccessary functions echo_alloc_memmd(), echo_free_memmd(), osc_unpackmd(), and obd_alloc_memmd(). Remove the struct lov_stripe_md * parameter from obd_create(). Signed-off-by:
-
John L. Hammond authored
Remove no longer used osc_packmd() and osc_getstripe(). Several ioctls cases that are no longer used are removed. Remove no longer used adjust_kms() infrastructure. Signed-off-by:
-
Lai Siyao authored
small fixes: * when 'unplug' is set for ll_statahead(), sa_put() shouldn't kill the entry found, because its inflight RPC may not finish yet. * remove 'sai_generation', add 'lli_sa_generation' because the former one is not safe to access without lock. * revalidate_statahead_dentry() may fail to wait for statahead entry to become ready, in this case it should not release this entry, because it may be used by inflight statahead RPC. cleanups: * rename ll_statahead_enter() to ll_statahead(). * move dentry 'lld_sa_generation' update to ll_statahead() to simplify code and logic. * other small cleanups. Signed-off-by:
Bobi Jam <bobijam@hotmail.com> Reviewed-by:
-
John L. Hammond authored
Restore the trailing newline in the definition of OSC_DUMP_GRANT(). Remove an unnecessary CDEBUG() from ldlm_pool_recalc(). Signed-off-by:
James Nunez <james.a.nunez@intel.com> Reviewed-by:
-
John L. Hammond authored
In LOV and OSC remove handlers for the obsolete get and set info keys: KEY_CAPA_KEY, KEY_CONNECT_FLAG, KEY_EVICT_BY_NID, KEY_LAST_ID, KEY_LOCK_TO_STRIPE, KEY_MDS_CONN, KEY_NEXT_ID. Signed-off-by:
-
Dmitry Eremin authored
Change type of changelog_*{namelen,size}() to size_t. Fixed string specifier for unsigned types. Signed-off-by: -
John L. Hammond authored
Remove the obsolete ioctls LL_IOC_RECREATE_FID and LL_IOC_RECREATE_OBJ along with their handlers in llite. Remove the then unused OBD method lov_create(). Remove OBD_FL_RECREATE_OBJS handling from osc_create(). Signed-off-by:
-
Dmitry Eremin authored
Change the type accordant usage. Signed-off-by:
-
Dmitry Eremin authored
Change the type accordant usage. Signed-off-by:
-
Dmitry Eremin authored
Function ldlm_pools_count() return unsigned long but counter is int. Use ldlm_pool_granted() everywhere. Signed-off-by:
-
Jian Yu authored
On some customer's systems, kernel was compiled with HZ defined to 100, instead of 1000. This improves performance for HPC applications. However, to use these systems with Lustre, customers have to re-build Lustre for the kernel because Lustre directly uses the defined constant HZ. Since kernel 2.6.21, some non-HZ dependent timing APIs become non- inline functions, which can be used in Lustre codes to replace the direct HZ access. These kernel APIs include: jiffies_to_msecs() jiffies_to_usecs() jiffies_to_timespec() msecs_to_jiffies() usecs_to_jiffies() timespec_to_jiffies() And here are some samples of the replacement: HZ -> msecs_to_jiffies(MSEC_PER_SEC) n * HZ -> msecs_to_jiffies(n * MSEC_PER_SEC) HZ / n -> msecs_to_jiffies(MSEC_PER_SEC / n) n / HZ -> jiffies_to_msecs(n) / MSEC_PER_SEC n / HZ * 1000 -> jiffies_to_msecs(n) This patch replaces the direct HZ access in lustre modules. Signed-off-by:
-
John L. Hammond authored
Make the following changes in or around struct md_op_data: * rename enum op_cli_flags to enum md_cli_flags. * Change to type of the op_flags member from __u32 to enum md_op_flags. * Remove the used but never set member op_npages. * Remove the set but never used member op_stripe_offset (an alias for op_ioepoch). * Remove the op_max_pages alias for op_valid and add a op_max_pages member. Signed-off-by:
-
Dmitry Eremin authored
Change type of client_obd->*_mds_*size from int to __u32 and argumanets of related create/rename/setattr functions. Change type of op_data->op_namelen to size_t. Change type of argument size for all mdc_*_pack() to size_t. Signed-off-by:
-
Alexander Boyko authored
Once connected, the previously gathered AT statistics is not valid anymore because may reflect other routing, etc. The connect by itself could take a long time due to different reasons (e.g. server was not ready) and net latency got very high (see import_select_connection()) what does not reflect the current situation. Take into account only the current (re-)CONNECT rpc latency. Signed-off-by:
Vitaly Fertman <vitaly_fertman@xyratex.com> Signed-off-by:
-
Lai Siyao authored
When starting statahead thread, it should check whether current lli_opendir_key was deauthorized in the mean time by another process. Signed-off-by:
-
Lai Siyao authored
ll_intent_drop_lock() may sleep, which should not be called inside spinlock. Signed-off-by:
-
