- 21 Aug, 2016 22 commits
-
-
wang di authored
1. Clear the client dentry cache before migrating file/directory to the remote MDT. 2. Do not return stripe information to client, if it did not get the layout lock. Signed-off-by:
wang di <di.wang@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4682 Reviewed-on: http://review.whamcloud.com/9522Reviewed-by:
Andreas Dilger <andreas.dilger@intel.com> Reviewed-by:
John L. Hammond <john.hammond@intel.com> Signed-off-by:
James Simmons <jsimmons@infradead.org> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Jinshan Xiong authored
Sometimes the rq_commit_cb of BRW RPC can be called twice if that RPC has already committed at reply time. This will cause inaccuracy of unstable pages accounting and then assertion. Signed-off-by:
Jinshan Xiong <jinshan.xiong@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3274 Reviewed-on: http://review.whamcloud.com/8215Reviewed-by:
Prakash Surya <surya1@llnl.gov> Reviewed-by:
Oleg Drokin <oleg.drokin@intel.com> Signed-off-by:
-
Fan Yong authored
This enables the client to inject an error by altering the parent FID in order to test if the server side file system checker behaves properly. Signed-off-by:
Fan Yong <fan.yong@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3951 Reviewed-on: http://review.whamcloud.com/7667Reviewed-by:
Alex Zhuravlev <alexey.zhuravlev@intel.com> Signed-off-by:
-
Ryan Haasken authored
Since the log file name contains the current time in seconds, dumping the logs more than once per second causes EEXIST errors to be emitted. Add a static variable to libcfs_debug_dumplog_internal that records the time of the last Lustre log dump. If the current time in seconds is equal to the last time, do not dump logs again. Note that this is not thread-safe. However, in the rare case that two threads try to access last_dump_time simultaneously, the worst thing that could happen is that one of the threads will get an EEXIST error when trying to write the log file. This is no worse than the current situation, and it is not likely to happen. Signed-off-by:
Ryan Haasken <haasken@cray.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4129 Reviewed-on: http://review.whamcloud.com/8964Reviewed-by:
Bob Glossman <bob.glossman@intel.com> Signed-off-by:
-
Dmitry Eremin authored
'plock.cookie' might be used uninitialized in this function. sscanf format specification '%d' expects type 'int *' for 'd', but parameter 3 has a different type '__u32*' Signed-off-by:
Dmitry Eremin <dmitry.eremin@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4629 Reviewed-on: http://review.whamcloud.com/9390Reviewed-by:
James Simmons <uja.ornl@gmail.com> Reviewed-by:
-
wang di authored
Add client support to migrate the individual inodes from one MDT to another MDT, and this functionality will only migrate inode layout on MDT but not touch data object on OST. The directory will be migrated from top to the bottom, i.e. migrating parent first, then migrating the child. Signed-off-by:
-
Fan Yong authored
There was no protection when inc/dec lu_device_type::ldt_device_nr, which may caused the ldt_device_nr to be wrong and trigger assert. This patch redefine lu_device_type::ldt_device_nr as atomic type. There was no protection when add/del lu_device_type::ldt_linkage into/from the global lu_device_types list, which may caused bad address accessing. This patch uses the existing obd_types_lock to protect related operations. We do NOT need lu_types_stop() any longer. Such function scans the global lu_device_types list, and for each type item on it which has zerod lu_device_type::ldt_device_nr, call its stop() method. In fact, the lu_device_type::ldt_device_nr only will be zero when the last lu_device_fini() is called, and at that time, inside the lu_device_fini(), its stop() method will be called. So it is unnecessary to call the stop() again via lu_types_stop(). Signed-off-by:
Jian Yu <jian.yu@intel.com> Reviewed-by:
-
Jian Yu authored
This patch handles the upgrade situation that old mountdata already contains comma-separated NIDs. The correct way to fix the original issue is to parse comma-separated NIDs in lmd_parse(). Signed-off-by:
Niu Yawei <yawei.niu@intel.com> Reviewed-by:
Bobi Jam <bobijam@gmail.com> Reviewed-by:
Sebastien Buisson <sebastien.buisson@bull.net> Reviewed-by:
-
wang di authored
Add delete striped directory, it includes 1. enable sync log between MDTs, so slave objects will be delete by unlink log, which is similar as deleting ost object. 2. retrieve layout information of striped directory on MDT, then lock all of the slave objects before unlink. Signed-off-by:
-
wang di authored
Fix "lfs getdirstripe", so it can show layout information of striped directory [root@testnode tests]# ../utils/lfs getdirstripe /mnt/lustre/test1 /mnt/lustre/test1 lmv_stripe_count: 2 lmv_stripe_offset: 0 mdtidx FID[seq:oid:ver] 0 [0x280000400:0x1:0x0] 1 [0x2c0000400:0x1:0x0] Signed-off-by: -
wang di authored
1. client send create request to the master MDT, which will allocate FIDs and create slaves. for all of slaves. 2. Client needs to revalidate slaves during intent getattr and open request. 3. lmv_stripe_md will include attributes(size, nlink etc) from all of stripe, which will be protected by UPDATE lock. client needs to merge these attributes when update inode. 4. send create request to the MDT where the file is located, which can help creating master stripe of striped directory. Signed-off-by:
-
wang di authored
Use lmv_free_memmd for proper cleanup instead of the generic obd_free_memmd. Signed-off-by:
-
wang di authored
Completely replace lmv_get_easize with lmv_mds_md_size. With this change we can delete lmv_get_easize. Signed-off-by:
-
wang di authored
The lmv_[un]pack_md function are used to calculate the size of the data used to represent the LMV striping data. The original code was straight forward in its calculate with lmv_get_easize since only one type of data format could exist. We want to be able to support different version of this data in the future so this patch moves to generating the size of the data using the stripe count and which LMV_MAGIC_* version. Signed-off-by:
-
wang di authored
The MAX_HASH_* macros already exist in obd.h. Remove the duplicated defines in lustre_idl.h. Signed-off-by:
-
wang di authored
The function lmv_get_mea() is not used so remove it. Signed-off-by:
-
wang di authored
If the operation is IT_READDIR don't need to handle the mdc RPC lock. Signed-off-by:
-
wang di authored
Change the 3rd parameter remove to a bool for ll_release_page function. Signed-off-by:
-
wang di authored
Add a inode parameter to ll_release_page. This will be used in the future. Signed-off-by:
-
wang di authored
Group function prototypes together related to dir.c. Move ll_release_page to be with function declarations. Signed-off-by:
-
wang di authored
Remove comment about fixing swabbing that is not needed. Signed-off-by:
-
wang di authored
Pass in struct md_op_data for ll_get_dir_page function. Signed-off-by:
-
- 18 Aug, 2016 5 commits
-
-
Christian Gromm authored
The networking AIM does not use the *_irqsave and *_irqrestore flavored spinlock functions. The rx_completion callback, however, can be called from an interrupt context. This patch is needed to fix this problem. Signed-off-by:
Andrey Shvetsov <andrey.shvetsov@k2l.de> Signed-off-by:
Christian Gromm <christian.gromm@microchip.com> Signed-off-by:
-
Ben LeMasurier authored
This fixes the checkpatch.pl "Alignment should match open parenthesis" issues in ion_test.c. Signed-off-by:
Ben LeMasurier <ben@crypt.ly> Signed-off-by:
-
Ben LeMasurier authored
This fixes the checkpatch.pl "Alignment should match open parenthesis" issues in ion_heap.c. Signed-off-by:
-
Christian Gromm authored
This patch removes duplicated code by putting it into the new function dim2_transfer_madr. Signed-off-by:
-
Christian Gromm authored
In the time after a synchronous DIM2 channel is enabled and before the first buffer travels this channel, the DIM2 macro is babbling random random data to the network. This patch initializes the internal DBR memory of the DIM2 that is used to transfer the synchronous data. Signed-off-by:
-
- 15 Aug, 2016 13 commits
-
-
Tim Sell authored
Since lock_visor_dev is a binary semaphore it makes more sense to use a mutex lock. Signed-off-by:
Tim Sell <Timothy.Sell@unisys.com> Signed-off-by:
David Kershner <david.kershner@unisys.com> Acked-By:
Neil Horman <nhorman@tuxdriver.com> Reviewed-by:
Thomas Gleixner <tglx@linutronix.de> Signed-off-by:
-
Tim Sell authored
Ensure we properly lock between visorinput_channel_interrupt(), visorinput_open(), and devdata_create(). We now guarantee that: * interrupts will be disabled and remain disabled during device creation, by setting 'paused = true' across device creation * we canNOT get into visorinput_open() until the device structure is totally initialized, by delaying the input_register_device() until the end of device initialization We also now ensure that lock_visor_dev is held across updates of devdata state, to ensure state consistency. Signed-off-by:
-
David Kershner authored
Only visorbus needs this header file so move it to visorbus directory. Signed-off-by:
-
Tim Sell authored
This patch ONLY touches comment lines, i.e., NO executable code is affected. Comments were fixed in visorbus_private.h: * Minor typos were corrected. * Useless comments were removed. Signed-off-by:
-
David Binder authored
Renames visorchipset_device_pause_response to device_pause_response, thereby following the convention that other responder functions follow. Signed-off-by:
David Binder <david.binder@unisys.com> Signed-off-by:
-
David Binder authored
When this functionality was first implemented, visorchipset and visorbus were separate drivers, which necessitated a registration mechanism for them to communicate. More-recently, visorchipset and visorbus were combined into a single driver, and now exist as separate source files within the same driver, known as 'visorbus'. This eliminated the need for a registration mechanism, but it has remained nevertheless until now. For the sake of simplification, this registration mechanism is now being removed. Signed-off-by:
-
David Binder authored
Fixes the kerneldoc comment for struct visor_device - the struct members were not listed with the appropriate @ prefix. Signed-off-by:
-
David Binder authored
Moves function prototypes that are unique to visorbus from include/visorbus.h to visorbus/visorbus_private.h. Signed-off-by:
-
David Binder authored
Adds kerneldoc formatting to appropriate functions. Other multi-line comments now use proper formatting. Signed-off-by:
-
David Binder authored
This patch ONLY touches comment lines, i.e., NO executable code is affected. Comments were fixed in visorchannel.c: * All functions worthy of documenting now use standard kerneldoc formatting. * Multi-line comments were tweaked so as to use appropriate conventions. * Minor typos were corrected. * Useless comments were removed. Signed-off-by:
-
David Binder authored
This patch ONLY touches comment lines, i.e., NO executable code is affected. * All functions worthy of documenting now use standard kerneldoc formatting. * Improper uses of kerneldoc formatting were converted to standard multi-line comments. * Multi-line comments were tweaked so as to use appropriate conventions. Signed-off-by:
-
David Binder authored
This patch ONLY touches comment lines, i.e., NO executable code is affected. * All functions worthy of documenting now use standard kerneldoc formatting. * Multi-line comments were tweaked so as to use appropriate conventions. * Minor typos were corrected. Signed-off-by:
-
Tim Sell authored
The off parameter to visorchannel_create_guts() was never used, so it was removed. Signed-off-by:
-
