00d65ec8e158121638ad8fa049b5f58960ad560c |
|
29-Aug-2014 |
John L. Hammond <john.hammond@intel.com> |
staging/lustre: move lustre_intent.h to .. Move lustre/include/linux/lustre_intent.h to lustre/include. Signed-off-by: John L. Hammond <john.hammond@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
1accaadf2af8b871601d8b1cc8a06dce87b6a435 |
|
12-Jul-2014 |
Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
staging: lustre: fix include relative paths In drivers/staging/lustre/lustre/include there was a bunch of .h files relying on ccflags to be set up right. Make all of them proper relative paths so that ccflags for different subdirs can be now removed. Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: hpdd-discuss <hpdd-discuss@lists.01.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
9fdaf8c0b92ab374f8501eb47855776afc928e45 |
|
12-Jul-2014 |
Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
staging: lustre: remove top level ccflags variable We need to remove the ccflags from the Lustre code as it prevents individual object files from building properly in the kernel build system. It also hids the horrid mess that the Lustre include files are made up of. Start out by removing the toplevel ccflags variable pointing to drivers/staging/lustre/include/ as a valid include path. This requires the absolute include markings of a bunch of .h and .c files, which is also done here. Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: hpdd-discuss <hpdd-discuss@lists.01.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
44779340c6dcb8c858955c02b3aeef7d6b28a684 |
|
27-Apr-2014 |
Brian Behlendorf <behlendorf1@llnl.gov> |
staging/lustre: Limit reply buffer size When allocating a reply buffer for the striping information don't assume the unlikely worst case. Instead, assume the common case and size the buffer based on the observed default ea/cookie size. The default size is initialized to a single stripe and allowed to grow up to an entire page if needed. This means that for smallish filesystems (less than ~21 OSTs) where the worst case striping information can fit in a single page there is effectively no change. Only for larger filesystem will the default be less than the maximum. This has a number of advantages. * By limiting the default reply buffer size we avoid always vmalloc()'ing the buffer because it exceeds four pages in size and instead kmalloc() it. This prevents the client from thrashing on the global vmalloc() spin lock. * A reply buffer of exactly the right size (no larger) is allocated in the overflow case. These larger reply buffers are still unlikely to exceed the 16k limit where a vmalloc() will occur. * Saves memory in the common case. Wide striped files exceeded the default are expected to be the exception. The reason this patch works is because the ptlrpc layer is smart enough to reallocate the reply buffer when an overflow occurs. Therefore the client doesn't have to drop the incoming reply and send a new request with a larger reply buffer. It's also worth mentioning that the reply buffer always contains a significant amount of extra padding because they are rounded up to the nearest power of two. This means that even files striped wider than the default have a good chance of fitting in the allocated reply buffer. Also remove client eadatasize check in mdt xattr packing because as said above client can handle -EOVERFLOW. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Lai Siyao <lai.siyao@intel.com> Reviewed-on: http://review.whamcloud.com/6339 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3338 Reviewed-by: James Simmons <uja.ornl@gmail.com> Reviewed-by: Andreas Dilger <andreas.dilger@intel.com> Reviewed-by: Bob Glossman <bob.glossman@intel.com> Signed-off-by: Oleg Drokin <oleg.drokin@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
38585ccc4627a9da381af9e912b756cfceb615a5 |
|
11-Feb-2014 |
Andreas Dilger <andreas.dilger@intel.com> |
staging/lustre/llite: fix O_TMPFILE/O_LOV_DELAY_CREATE conflict In kernel 3.11 O_TMPFILE was introduced, but the open flag value conflicts with the O_LOV_DELAY_CREATE flag 020000000 previously used by Lustre-aware applications. O_LOV_DELAY_CREATE allows applications to defer file layout and object creation from open time (the default) until it can instead be specified by the application using an ioctl. Instead of trying to find a non-conflicting O_LOV_DELAY_CREATE flag or define a Lustre-specific flag that isn't of use to most/any other filesystems, use (O_NOCTTY|FASYNC) as the new value. These flags are not meaningful for newly-created regular files and should be OK since O_LOV_DELAY_CREATE is only meaningful for new files. I looked into using O_ACCMODE/FMODE_WRITE_IOCTL, which allows calling ioctl() on the minimally-opened fd and is close to what is needed, but that doesn't allow specifying the actual read or write mode for the file, and fcntl(F_SETFL) doesn't allow O_RDONLY/O_WRONLY/O_RDWR to be set after the file is opened. Lustre-change: http://review.whamcloud.com/8312 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4209 Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Oleg Drokin <oleg.drokin@intel.com> Signed-off-by: Peng Tao <bergwolf@gmail.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
04eb2b7f3ff19685531945a484e78ab7b9376ccc |
|
03-Dec-2013 |
Peng Tao <bergwolf@gmail.com> |
staging/lustre: fix build error when CONFIG_FS_POSIX_ACL is off We need to include <linux/posix_acl_xattr.h> regardless of CONFIG_FS_POSIX_ACL is set or not. Otherwise build fails as reported by kbuild robot: >> drivers/staging/lustre/lustre/llite/file.c:2965:2: error: implicit declaration of function 'posix_acl_dup' [-Werror=implicit-function-declaration] acl = posix_acl_dup(lli->lli_posix_acl); <many similar errors omitted> Reported-by: Fengguang Wu <fengguang.wu@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Peng Tao <bergwolf@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
23f14e79ace301c1e46b52344ce02e72254c57b6 |
|
03-Aug-2013 |
Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
staging: lustre: remove EXIT macro We have a kernel-wide function tracing system, so use that instead of rolling a custom one just for one filesystem. Cc: Peng Tao <tao.peng@emc.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
29aaf4962a3bce337d37176858ef1025b9f29cc4 |
|
02-Aug-2013 |
Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
staging: lustre: remove ENTRY macro We have a kernel-wide function tracing system, so use that instead of rolling a custom one just for one filesystem. Cc: Peng Tao <tao.peng@emc.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
bdf43213f9e7faf980025f44ec82b80caf453e8d |
|
22-Jul-2013 |
jcl <jacques-charles.lafoucriere@cea.fr> |
staging/lustre/mdc: layout lock rpc must not take rpc_lock When a client issue an RPC to get a layout lock, it must not hold rpc_lock because in case of a restore the rpc can be blocking for a long time Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3200 Lustre-change: http://review.whamcloud.com/6115 Signed-off-by: JC Lafoucriere <jacques-charles.lafoucriere@cea.fr> Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com> Reviewed-by: Johann Lombardi <johann.lombardi@intel.com> Signed-off-by: Peng Tao <tao.peng@emc.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
d7e09d0397e84eefbabfd9cb353221f3c6448d83 |
|
02-May-2013 |
Peng Tao <bergwolf@gmail.com> |
staging: add Lustre file system client support Lustre is the most deployed distributed file system in the HPC (High Performance Computing) world. The patch adds its client side support. The code is not very clean and needs to live in drivers/staging for some time for continuing cleanup work. See drivers/staging/lustre/TODO for details. The code is based on Lustre master commit faefbfc04 commit faefbfc0460bc00f2ee4c1c1c86aa1e39b9eea49 Author: Alex Zhuravlev <alexey.zhuravlev@intel.com> Date: Tue Apr 30 23:05:21 2013 +0400 LU-3244 utils: tunefs.lustre should preserve virgin label Plus a few under-review patches on Whamcloud gerrit: 3.8 kernel support: http://review.whamcloud.com/#change,5973 http://review.whamcloud.com/#change,5974 http://review.whamcloud.com/#change,5768 http://review.whamcloud.com/#change,5781 http://review.whamcloud.com/#change,5763 http://review.whamcloud.com/#change,5613 http://review.whamcloud.com/#change,5655 3.9 kernel support: http://review.whamcloud.com/#change,5898 http://review.whamcloud.com/#change,5899 Kconfig/Kbuild: http://review.whamcloud.com/#change,4646 http://review.whamcloud.com/#change,4644 libcfs cleanup: http://review.whamcloud.com/#change,2831 http://review.whamcloud.com/#change,4775 http://review.whamcloud.com/#change,4776 http://review.whamcloud.com/#change,4777 http://review.whamcloud.com/#change,4778 http://review.whamcloud.com/#change,4779 http://review.whamcloud.com/#change,4780 All starting/trailing whitespaces are removed, to match kernel coding style. Also ran scripts/cleanfile on all lustre source files. [maked the Kconfig depend on BROKEN as the recent procfs changes causes this to fail - gregkh] Signed-off-by: Peng Tao <tao.peng@emc.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|