summaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFilesLines
* [S390] Add support for IBM zEnterprise 114Heiko Carstens2011-08-032-4/+5
| | | | | | Just fix up the Kconfig description and the elf platform. Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* [S390] dasd: check if raw track access is supportedStefan Haberland2011-08-031-0/+9
| | | | | | | | | | | To use raw track access some special storage server commands are needed. Older storage hardware may not support these commands. So check if raw track access is possible while setting the DASD online. Signed-off-by: Stefan Haberland <stefan.haberland@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* [S390] Use diagnose 308 for system resetMichael Holzheu2011-08-033-0/+43
| | | | | | | | The diagnose 308 call is the prefered method for clearing all ongoing I/O. Therefore if it is available we use it instead of doing a manual reset. Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* [S390] Export store_status() functionMichael Holzheu2011-08-031-20/+60
| | | | | | | | | For kdump we need a store status function to save the registers for the current CPU. Therefore this patch exports a function "store_status()". In addition to that now also floating point registers are saved correctly. Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* [S390] dasd: use vmalloc for statistics input bufferStefan Weinhuber2011-08-032-6/+7
| | | | | | | | | | The size of the buffer that is used to store DASD statistics input strings depends on the user input. If the input string is to large, the write operation could fail with -ENOMEM. To avoid this, use vmalloc instead of kmalloc. Signed-off-by: Stefan Weinhuber <wein@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* [S390] Add PSW restart shutdown triggerMichael Holzheu2011-08-039-5/+146
| | | | | | | | | | | | | With this patch a new S390 shutdown trigger "restart" is added. If under z/VM "systerm restart" is entered or under the HMC the "PSW restart" button is pressed, the PSW located at 0 (31 bit) or 0x1a0 (64 bit) bit is loaded. Now we execute do_restart() that processes the restart action that is defined under /sys/firmware/shutdown_actions/on_restart. Currently the following actions are possible: reipl (default), stop, vmcmd, dump, and dump_reipl. Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* [S390] missing return in page_table_alloc_pgsteJan Glauber2011-08-031-0/+1
| | | | | | | | | | | Fix the following compile warning for !CONFIG_PGSTE: CC arch/s390/mm/pgtable.o arch/s390/mm/pgtable.c: In function ‘page_table_alloc_pgste’: arch/s390/mm/pgtable.c:531:1: warning: no return statement in function returning non-void [-Wreturn-type] Signed-off-by: Jan Glauber <jang@linux.vnet.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* [S390] qdio: 2nd stage retry on SIGA-W busy conditionsJan Glauber2011-08-032-3/+20
| | | | | | | | | | | | | | | The SIGA-W may return with the busy bit set which means the device was blocked. The busy loop which retries the SIGA-W for 100us may not be long enough when running under a heavily loaded hypervisor. Extend the retry mechanism by adding a longer second stage which retries the SIGA-W for up to 10s. In difference to the first retry loop the second stage is using mdelay to stop the cpu between the retries and thereby avoid additional preassure in on the hypervisor. If the second stage retry is successfull a device reset is avoided. Signed-off-by: Jan Glauber <jang@linux.vnet.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
* Merge branch 'for-linus' of ↵Linus Torvalds2011-08-0219-528/+269
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (31 commits) Btrfs: don't call writepages from within write_full_page Btrfs: Remove unused variable 'last_index' in file.c Btrfs: clean up for find_first_extent_bit() Btrfs: clean up for wait_extent_bit() Btrfs: clean up for insert_state() Btrfs: remove unused members from struct extent_state Btrfs: clean up code for merging extent maps Btrfs: clean up code for extent_map lookup Btrfs: clean up search_extent_mapping() Btrfs: remove redundant code for dir item lookup Btrfs: make acl functions really no-op if acl is not enabled Btrfs: remove remaining ref-cache code Btrfs: remove a BUG_ON() in btrfs_commit_transaction() Btrfs: use wait_event() Btrfs: check the nodatasum flag when writing compressed files Btrfs: copy string correctly in INO_LOOKUP ioctl Btrfs: don't print the leaf if we had an error btrfs: make btrfs_set_root_node void Btrfs: fix oops while writing data to SSD partitions Btrfs: Protect the readonly flag of block group ... Fix up trivial conflicts (due to acl and writeback cleanups) in - fs/btrfs/acl.c - fs/btrfs/ctree.h - fs/btrfs/extent_io.c
| * Btrfs: don't call writepages from within write_full_pageJosef Bacik2011-08-011-10/+0
| | | | | | | | | | | | | | | | | | | | | | When doing a writepage we call writepages to try and write out any other dirty pages in the area. This could cause problems where we commit a transaction and then have somebody else dirtying metadata in the area as we could end up writing out a lot more than we care about, which could cause latency on anybody who is waiting for the transaction to completely finish committing. Thanks, Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: Remove unused variable 'last_index' in file.cMitch Harder2011-08-011-5/+2
| | | | | | | | | | | | | | | | | | | | | | The variable 'last_index' is calculated in the __btrfs_buffered_write function and passed as a parameter to the prepare_pages function, but is not used anywhere in the prepare_pages function. Remove instances of 'last_index' in these functions. Signed-off-by: Mitch Harder <mitch.harder@sabayonlinux.org> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: clean up for find_first_extent_bit()Xiao Guangrong2011-08-011-40/+24
| | | | | | | | | | | | | | | | | | find_first_extent_bit() and find_first_extent_bit_state() share most of the code, and we can just make the former call the latter. Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: clean up for wait_extent_bit()Xiao Guangrong2011-08-011-5/+1
| | | | | | | | | | | | | | | | We can just use cond_resched_lock(). Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: clean up for insert_state()Xiao Guangrong2011-08-011-5/+5
| | | | | | | | | | | | | | | | Don't duplicate set_state_bits(). Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: remove unused members from struct extent_stateXiao Guangrong2011-08-011-2/+0
| | | | | | | | | | | | | | | | These members are not used at all. Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: clean up code for merging extent mapsLi Zefan2011-08-011-38/+21
| | | | | | | | | | | | | | | | unpin_extent_cache() and add_extent_mapping() shares the same code that merges extent maps. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: clean up code for extent_map lookupLi Zefan2011-08-011-56/+29
| | | | | | | | | | | | | | lookup_extent_map() and search_extent_map() can share most of code. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: clean up search_extent_mapping()Li Zefan2011-08-011-14/+3
| | | | | | | | | | | | | | | | rb_node returned by __tree_search() can be a valid pointer or NULL, but won't be some errno. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: remove redundant code for dir item lookupLi Zefan2011-08-011-28/+2
| | | | | | | | | | | | | | | | | | When we search a dir item with a specific hash code, we can just return NULL without further checking if btrfs_search_slot() returns 1. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: make acl functions really no-op if acl is not enabledLi Zefan2011-08-013-21/+15
| | | | | | | | | | | | | | So there's no overhead for something we don't use. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: remove remaining ref-cache codeLi Zefan2011-08-012-120/+0
| | | | | | | | | | | | | | | | | | Since commit f2a97a9dbd86eb1ef956bdf20e05c507b32beb96 ("btrfs: remove all unused functions"), there's no extern functions at all in ref-cache.c, so just remove the remaining dead code. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: remove a BUG_ON() in btrfs_commit_transaction()Li Zefan2011-08-011-4/+2
| | | | | | | | | | | | | | wait_for_commit() always returns 0. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: use wait_event()Li Zefan2011-08-011-52/+7
| | | | | | | | | | | | | | Use wait_event() when possible to avoid code duplication. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: check the nodatasum flag when writing compressed filesLi Zefan2011-08-011-4/+10
| | | | | | | | | | | | | | | | | | If mounting with nodatasum option, we won't csum file data for general write or direct-io write, and this rule should also be applied when writing compressed files. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: copy string correctly in INO_LOOKUP ioctlLi Zefan2011-08-011-2/+1
| | | | | | | | | | | | | | | | Memory areas [ptr, ptr+total_len] and [name, name+total_len] may overlap, so it's wrong to use memcpy(). Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: don't print the leaf if we had an errorJosef Bacik2011-08-011-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | In __btrfs_free_extent we will print the leaf if we fail to find the extent we wanted, but the problem is if we get an error we won't have a leaf so often this leads to a NULL pointer dereference and we lose the error that actually occurred. So only print the leaf if ret > 0, which means we didn't find the item we were looking for but we didn't error either. This way the error is preserved. Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * btrfs: make btrfs_set_root_node voidMark Fasheh2011-08-012-5/+4
| | | | | | | | | | | | | | | | | | | | | | This is fairly trivial - btrfs_set_root_node() - always returns zero so we can just make it void. All callers ignore the return code now anyway. I also made sure to check that none of the functions that btrfs_set_root_node() calls returns an error that we might have needed to catch and pass back. Signed-off-by: Mark Fasheh <mfasheh@suse.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: fix oops while writing data to SSD partitionsliubo2011-08-011-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Here I have a two SSD-partitions btrfs, and they are defaultly set to "data=raid0, metadata=raid1", then I try to fill my btrfs partition till "No space left on device", via "dd if=/dev/zero of=/mnt/btrfs/tmp". I get an oops panic from kernel BUG at fs/btrfs/extent-tree.c:5199!, which refers to find_free_extent's BUG_ON(index != get_block_group_index(block_group)); In SSD mode, in order to find enough space to alloc, we may check the block_group cache which has been checked sometime before, but the index is not updated, where it hits the BUG_ON. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Acked-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: Protect the readonly flag of block groupWuBo2011-08-011-3/+7
| | | | | | | | | | | | | | | | The access for ro in btrfs_block_group_cache should be protected because of the racy lock in relocation. Signed-off-by: Wu Bo <wu.bo@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * btrfs: Make extent-io callbacks that never fail return voidJeff Mahoney2011-08-013-62/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The set/clear bit and the extent split/merge hooks only ever return 0. Changing them to return void simplifies the error handling cases later. This patch changes the hook prototypes, the single implementation of each, and the functions that call them to return void instead. Since all four of these hooks execute under a spinlock, they're necessarily simple. Signed-off-by: Jeff Mahoney <jeffm@suse.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: fix readahead in file defragLi Zefan2011-08-012-16/+8
| | | | | | | | | | | | | | | | We passed the wrong value to btrfs_force_ra(). Fix this by changing the argument of btrfs_force_ra() from last_index to nr_page. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs: return error to caller when btrfs_unlink() failesTsutomu Itoh2011-08-012-4/+9
| | | | | | | | | | | | | | | | | | When btrfs_unlink_inode() and btrfs_orphan_add() in btrfs_unlink() are error, the error code is returned to the caller instead of BUG_ON(). Signed-off-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Btrfs:don't check the return value of __btrfs_add_inode_defragWanlong Gao2011-08-011-6/+5
| | | | | | | | | | | | | | | | Don't need to check the return value of __btrfs_add_inode_defrag(), since it will always return 0. Signed-off-by: Wanlong Gao <gaowanlong@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * Merge branch 'alloc_path' of ↵Chris Mason2011-08-016-29/+78
| |\ | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/btrfs-error-handling into for-linus
| | * btrfs: don't BUG_ON allocation errors in btrfs_drop_snapshotMark Fasheh2011-07-251-2/+6
| | | | | | | | | | | | | | | | | | | | | In addition to properly handling allocation failure from btrfs_alloc_path, I also fixed up the kzalloc error handling code immediately below it. Signed-off-by: Mark Fasheh <mfasheh@suse.com>
| | * btrfs: Don't BUG_ON alloc_path errors in find_next_chunkMark Fasheh2011-07-252-2/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I also removed the BUG_ON from error return of find_next_chunk in init_first_rw_device(). It turns out that the only caller of init_first_rw_device() also BUGS on any nonzero return so no actual behavior change has occurred here. do_chunk_alloc() also needed an update since it calls btrfs_alloc_chunk() which can now return -ENOMEM. Instead of setting space_info->full on any error from btrfs_alloc_chunk() I catch and return every error value _except_ -ENOSPC. Thanks goes to Tsutomu Itoh for pointing that issue out. Signed-off-by: Mark Fasheh <mfasheh@suse.com>
| | * btrfs: Don't BUG_ON alloc_path errors in btrfs_balance()Mark Fasheh2011-07-141-2/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | Dealing with this seems trivial - the only caller of btrfs_balance() is btrfs_ioctl() which passes the error code directly back to userspace. There also isn't much state to unwind (if I'm wrong about this point, we can always safely move the allocation to the top of btrfs_balance() anyway). Signed-off-by: Mark Fasheh <mfasheh@suse.com>
| | * btrfs: Don't BUG_ON alloc_path errors in btrfs_read_locked_inodeMark Fasheh2011-07-141-5/+17
| | | | | | | | | | | | | | | | | | | | | btrfs_iget() also needed an update so that errors from btrfs_locked_inode() are caught and bubbled back up. Signed-off-by: Mark Fasheh <mfasheh@suse.com>
| | * btrfs: Don't BUG_ON alloc_path errors in btrfs_truncate_inode_itemsMark Fasheh2011-07-141-4/+5
| | | | | | | | | | | | | | | | | | | | | | | | I moved the path allocation up a few lines to the top of the function so that we couldn't get into the state where we've dropped delayed items and the extent cache but fail due to -ENOMEM. Signed-off-by: Mark Fasheh <mfasheh@suse.com>
| | * btrfs: Don't BUG_ON alloc_path errors in replay_one_buffer()Mark Fasheh2011-07-141-3/+9
| | | | | | | | | | | | | | | | | | | | | The two ->process_func call sites in tree-log.c which were ignoring a return code have also been updated to gracefully exit as well. Signed-off-by: Mark Fasheh <mfasheh@suse.com>
| | * btrfs: don't BUG_ON btrfs_alloc_path() errorsMark Fasheh2011-07-144-11/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes many callers of btrfs_alloc_path() which BUG_ON allocation failure. All the sites that are fixed in this patch were checked by me to be fairly trivial to fix because of at least one of two criteria: - Callers of the function catch errors from it already so bubbling the error up will be handled. - Callers of the function might BUG_ON any nonzero return code in which case there is no behavior changed (but we still got to remove a BUG_ON) The following functions were updated: btrfs_lookup_extent, alloc_reserved_tree_block, btrfs_remove_block_group, btrfs_lookup_csums_range, btrfs_csum_file_blocks, btrfs_mark_extent_written, btrfs_inode_by_name, btrfs_new_inode, btrfs_symlink, insert_reserved_file_extent, and run_delalloc_nocow Signed-off-by: Mark Fasheh <mfasheh@suse.com>
* | | Merge branch 'devicetree/next' of git://git.secretlab.ca/git/linux-2.6Linus Torvalds2011-08-025-11/+16
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'devicetree/next' of git://git.secretlab.ca/git/linux-2.6: MAINTAINERS: Add keyword match for of_match_table to device tree section of: constify property name parameters for helper functions input: xilinx_ps2: Add missing of_address.h header of: address: use resource_size helper
| * | | MAINTAINERS: Add keyword match for of_match_table to device tree sectionMark Brown2011-08-021-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a patch is working with an of_match_table it's probably adding an OF binding to a driver in which case the binding ought to be reviewed by the device tree folks to make sure that things like the device matches are set up correctly. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
| * | | of: constify property name parameters for helper functionsJamie Iles2011-08-022-9/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The helper functions for reading u32 integers, u32 arrays and strings should have the property name as a const pointer. Cc: Grant Likely <grant.likely@secretlab.ca> Signed-off-by: Jamie Iles <jamie@jamieiles.com> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
| * | | input: xilinx_ps2: Add missing of_address.h headerMichal Simek2011-08-011-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add missing header. Error log: CC drivers/input/serio/xilinx_ps2.o drivers/input/serio/xilinx_ps2.c: In function 'xps2_of_probe': drivers/input/serio/xilinx_ps2.c:249: error: implicit declaration of function 'of_address_to_resource' Signed-off-by: Michal Simek <monstr@monstr.eu> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
| * | | of: address: use resource_size helperFelipe Balbi2011-08-011-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | that should be the approved way of calculating the size of resources. No functional changes. Cc: Grant Likely <grant.likely@secretlab.ca> Signed-off-by: Felipe Balbi <balbi@ti.com> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
* | | | Merge branch 'spi/next' of git://git.secretlab.ca/git/linux-2.6Linus Torvalds2011-08-021-8/+3
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | * 'spi/next' of git://git.secretlab.ca/git/linux-2.6: spi/pl022: remove function cannot exit
| * | | | spi/pl022: remove function cannot exitLinus Walleij2011-08-021-8/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The remove function in the PL022 driver cannot abort the remove function any way, so restructure the code so as not to make that assumption. Remove will now proceed no matter whether it can stop the transfer queue or not. Reported-by: Russell King <linux@arm.linux.org.uk> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
* | | | | Merge git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dmLinus Torvalds2011-08-0221-404/+1561
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm: (34 commits) dm table: set flush capability based on underlying devices dm crypt: optionally support discard requests dm raid: add md raid1 support dm raid: support metadata devices dm raid: add write_mostly parameter dm raid: add region_size parameter dm raid: improve table parameters documentation dm ioctl: forbid multiple device specifiers dm ioctl: introduce __get_dev_cell dm ioctl: fill in device parameters in more ioctls dm flakey: add corrupt_bio_byte feature dm flakey: add drop_writes dm flakey: support feature args dm flakey: use dm_target_offset and support discards dm table: share target argument parsing functions dm snapshot: skip reading origin when overwriting complete chunk dm: ignore merge_bvec for snapshots when safe dm table: clean dm_get_device and move exports dm raid: tidy includes dm ioctl: prevent empty message ...
| * | | | | dm table: set flush capability based on underlying devicesMike Snitzer2011-08-022-1/+43
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | DM has always advertised both REQ_FLUSH and REQ_FUA flush capabilities regardless of whether or not a given DM device's underlying devices also advertised a need for them. Block's flush-merge changes from 2.6.39 have proven to be more costly for DM devices. Performance regressions have been reported even when DM's underlying devices do not advertise that they have a write cache. Fix the performance regressions by configuring a DM device's flushing capabilities based on those of the underlying devices' capabilities. Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
View Lorry Controller Status