summaryrefslogtreecommitdiffstats
path: root/fs
Commit message (Collapse)AuthorAgeFilesLines
* sysfs: Remove sysfs_get/put_active_twoEric W. Biederman2010-03-074-77/+38
| | | | | | | | | | | | | | | | It turns out that holding an active reference on a directory is pointless. The purpose of the active references are to allows us to block when removing sysfs entries that have custom methods so we don't remove modules while running modular code and to keep those custom methods from accessing data structures after the files have been removed. Further sysfs_remove_dir remove all elements in the directory before removing the directory itself, so there is no chance we will remove a directory with active children. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
* Driver core: Constify struct sysfs_ops in struct kobj_typeEmese Revfy2010-03-076-10/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Constify struct sysfs_ops. This is part of the ops structure constification effort started by Arjan van de Ven et al. Benefits of this constification: * prevents modification of data that is shared (referenced) by many other structure instances at runtime * detects/prevents accidental (but not intentional) modification attempts on archs that enforce read-only kernel data at runtime * potentially better optimized code as the compiler can assume that the const data cannot be changed * the compiler/linker move const data into .rodata and therefore exclude them from false sharing Signed-off-by: Emese Revfy <re.emese@gmail.com> Acked-by: David Teigland <teigland@redhat.com> Acked-by: Matt Domsch <Matt_Domsch@dell.com> Acked-by: Maciej Sosnowski <maciej.sosnowski@intel.com> Acked-by: Hans J. Koch <hjk@linutronix.de> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Jens Axboe <jens.axboe@oracle.com> Acked-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
* kobject: Constify struct kset_uevent_opsEmese Revfy2010-03-071-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | Constify struct kset_uevent_ops. This is part of the ops structure constification effort started by Arjan van de Ven et al. Benefits of this constification: * prevents modification of data that is shared (referenced) by many other structure instances at runtime * detects/prevents accidental (but not intentional) modification attempts on archs that enforce read-only kernel data at runtime * potentially better optimized code as the compiler can assume that the const data cannot be changed * the compiler/linker move const data into .rodata and therefore exclude them from false sharing Signed-off-by: Emese Revfy <re.emese@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
* sysfs: Cache the last sysfs_dirent to improve readdir scalability v2Eric W. Biederman2010-03-071-22/+60
| | | | | | | | | | | | | | | | | | | | | | | | When sysfs_readdir stops short we now cache the next sysfs_dirent to return to user space in filp->private_data. There is no impact on the rest of sysfs by doing this and in the common case it allows us to pick up exactly where we left off with no seeking. Additionally I drop and regrab the sysfs_mutex around filldir to avoid a page fault abritrarily increasing the hold time on the sysfs_mutex. v2: Returned to using INT_MAX as the EOF condition. seekdir is ambiguous unless all directory entries have a unique f_pos value. Fixes http://bugzilla.kernel.org/show_bug.cgi?id=14949 Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
* sysfs: Add sysfs_add/remove_files utility functionsAndi Kleen2010-03-071-0/+20
| | | | | | | | | | | Adding/Removing a whole array of attributes is very common. Add a standard utility function to do this with a simple function call, instead of requiring drivers to open code this. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
* seq_file: fix new kernel-doc warningsRandy Dunlap2010-03-071-2/+2
| | | | | | | | | | Fix kernel-doc notation in new seq-file functions and correct spelling. Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Revert "lib: build list_sort() only if needed"Linus Torvalds2010-03-071-1/+0
| | | | | | | | | | | | | | | | | | | | This reverts commit a069c266ae5fdfbf5b4aecf2c672413aa33b2504. It turns ou that not only was it missing a case (XFS) that needed it, but perhaps more importantly, people sometimes want to enable new modules that they hadn't had enabled before, and if such a module uses list_sort(), it can't easily be inserted any more. So rather than add a "select LIST_SORT" to the XFS case, just leave it compiled in. It's not all _that_ big, after all, and the inconvenience isn't worth it. Requested-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Don Mullis <don.mullis@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/joern/logfsLinus Torvalds2010-03-0617-0/+9004
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/joern/logfs: [LogFS] Change magic number [LogFS] Remove h_version field [LogFS] Check feature flags [LogFS] Only write journal if dirty [LogFS] Fix bdev erases [LogFS] Silence gcc [LogFS] Prevent 64bit divisions in hash_index [LogFS] Plug memory leak on error paths [LogFS] Add MAINTAINERS entry [LogFS] add new flash file system Fixed up trivial conflict in lib/Kconfig, and a semantic conflict in fs/logfs/inode.c introduced by write_inode() being changed to use writeback_control' by commit a9185b41a4f84971b930c519f0c63bd450c4810d ("pass writeback_control to ->write_inode")
| * [LogFS] Change magic numberJoern Engel2010-03-061-1/+1
| | | | | | | | | | | | | | Many changes were made during development that could result in old versions of mklogfs and the kernel code being subtly incompatible. Not being a friend of subtleties, I hereby change the magic number. Any old version of mklogfs is now guaranteed to fail.
| * [LogFS] Remove h_version fieldJoern Engel2010-03-062-6/+5
| | | | | | | | Incompatible change: h_compr is moved up so the padding is all in one chunk.
| * [LogFS] Check feature flagsJoern Engel2010-03-052-2/+12
| |
| * [LogFS] Only write journal if dirtyJoern Engel2010-03-046-13/+19
| | | | | | | | | | This prevents unnecessary journal writes. More importantly it prevents an oops due to a journal write on failed mount.
| * [LogFS] Fix bdev erasesJoern Engel2010-03-046-20/+97
| | | | | | | | | | | | | | | | | | | | | | | | Erases for block devices were always just emulated by writing 0xff. Some time back the write was removed and only the page cache was changed to 0xff. Superficialy a good idea with two problems: 1. Touching the page cache isn't necessary either. 2. However, writing out 0xff _is_ necessary for the journal. As the journal is scanned linearly, an old non-overwritten commit entry can be used on next mount and cause havoc. This should fix both aspects.
| * [LogFS] Silence gccJoern Engel2009-12-071-1/+1
| | | | | | | | | | | | | | | | Andrew Morton sayeth: fs/logfs/journal.c: In function 'logfs_init_journal': fs/logfs/journal.c:266: warning: 'last_len' may be used uninitialized in this function Can this be squished please?
| * [LogFS] Prevent 64bit divisions in hash_indexJoern Engel2009-11-281-5/+10
| | | | | | | | | | | | | | Randy Dunlap caught this built error on i386: fs/built-in.o: In function `hash_index': dir.c:(.text+0x6c1f2): undefined reference to `__umoddi3'
| * [LogFS] Plug memory leak on error pathsJoern Engel2009-11-231-2/+6
| | | | | | | | Spotted by Dan Carpenter.
| * [LogFS] add new flash file systemJoern Engel2009-11-2017-0/+8903
| | | | | | | | | | | | | | This is a new flash file system. See Documentation/filesystems/logfs.txt Signed-off-by: Joern Engel <joern@logfs.org>
* | Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfsLinus Torvalds2010-03-0626-1484/+1344
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-linus' of git://oss.sgi.com/xfs/xfs: (21 commits) xfs: return inode fork offset in bulkstat for fsr xfs: Increase the default size of the reserved blocks pool xfs: truncate delalloc extents when IO fails in writeback xfs: check for more work before sleeping in xfssyncd xfs: Fix a build warning in xfs_aops.c xfs: fix locking for inode cache radix tree tag updates xfs: remove xfs_ipin/xfs_iunpin xfs: cleanup xfs_iunpin_wait/xfs_iunpin_nowait xfs: kill xfs_lrw.h xfs: factor common xfs_trans_bjoin code xfs: stop passing opaque handles to xfs_log.c routines xfs: split xfs_bmap_btalloc xfs: fix xfs_fsblock_t tracing xfs: fix inode pincount check in fsync xfs: Non-blocking inode locking in IO completion xfs: implement optimized fdatasync xfs: remove wrapper for the fsync file operation xfs: remove wrappers for read/write file operations xfs: merge xfs_lrw.c into xfs_file.c xfs: fix dquota trace format ...
| * \ Merge branch 'for-2.6.34-rc1-batch2' into for-linusAlex Elder2010-03-0526-1484/+1344
| |\ \
| | * | xfs: return inode fork offset in bulkstat for fsrDave Chinner2010-03-052-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | So that fsr can attempt to get the fork offset of the temporary inode it uses the same as the inode it is defragmenting, pass the fork offset out in the bulkstat information. The bulkstat structure has padding that has always been zeroed, so userspace can tell if this field is set or not by use of the xattr present flag and a non-zero value for the fork offset. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: Increase the default size of the reserved blocks poolDave Chinner2010-03-051-20/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current default size of the reserved blocks pool is easy to deplete with certain workloads, in particular workloads that do lots of concurrent delayed allocation extent conversions. If enough transactions are running in parallel and the entire pool is consumed then subsequent calls to xfs_trans_reserve() will fail with ENOSPC. Also add a rate limited warning so we know if this starts happening again. This is an updated version of an old patch from Lachlan McIlroy. Signed-off-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: truncate delalloc extents when IO fails in writebackDave Chinner2010-03-051-10/+114
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We currently use block_invalidatepage() to clean up pages where I/O fails in ->writepage(). Unfortunately, if the page has delalloc regions on it, we fail to remove the delalloc regions when we invalidate the page. This can result in tripping a BUG() in xfs_get_blocks() later on if a direct IO read is done on that same region - the delalloc extent is returned when none is supposed to be there. Fix this by truncating away the delalloc regions on the page before invalidating it. Because they are delalloc, we can do this without needing a transaction. Indeed - if we get ENOSPC errors, we have to be able to do this truncation without a transaction as there is no space left for block reservation (typically why we see a ENOSPC in writeback). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: check for more work before sleeping in xfssyncdDave Chinner2010-03-051-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | xfssyncd processes a queue of work by detaching the queue and then iterating over all the work items. It then sleeps for a time period or until new work comes in. If new work is queued while xfssyncd is actively processing the detached work queue, it will not process that new work until after a sleep timeout or the next work event queued wakes it. Fix this by checking the work queue again before going to sleep. Signed-off-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: Fix a build warning in xfs_aops.cDave Chinner2010-03-051-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix a build warning that slipped through. Dave Chinner had posted an updated version of his patch but the previous version--without this fix--was what got committed. Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: fix locking for inode cache radix tree tag updatesChristoph Hellwig2010-03-012-8/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The radix-tree code requires it's users to serialize tag updates against other updates to the tree. While XFS protects tag updates against each other it does not serialize them against updates of the tree contents, which can lead to tag corruption. Fix the inode cache to always take pag_ici_lock in exclusive mode when updating radix tree tags. Signed-off-by: Christoph Hellwig <hch@lst.de> Reported-by: Patrick Schreurs <patrick@news-service.com> Tested-by: Patrick Schreurs <patrick@news-service.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: remove xfs_ipin/xfs_iunpinChristoph Hellwig2010-03-013-37/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Inodes are only pinned/unpinned via the inode item methods, and lots of code relies on that fact. So remove the separate xfs_ipin/xfs_iunpin helpers and merge them into their only callers. This also fixes up various duplicate and/or incorrect comments. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: cleanup xfs_iunpin_wait/xfs_iunpin_nowaitChristoph Hellwig2010-03-011-28/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Remove the inode item pointer and ili_last_lsn checks in __xfs_iunpin_wait as any pinned inode is guaranteed to have them valid. After this the xfs_iunpin_nowait case is nothing more than a xfs_log_force_lsn, as we know that the caller has already checked the pincount. Make xfs_iunpin_nowait the new low-level routine just doing the log force and rewrite xfs_iunpin_wait around it. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: kill xfs_lrw.hChristoph Hellwig2010-03-014-30/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Move the two declarations to better fitting headers now that xfs_lrw.c is gone. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: factor common xfs_trans_bjoin codeChristoph Hellwig2010-03-011-150/+66
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Most of xfs_trans_bjoin is duplicated in xfs_trans_get_buf, xfs_trans_getsb and xfs_trans_read_buf. Add a new _xfs_trans_bjoin which can be called by all four functions. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: stop passing opaque handles to xfs_log.c routinesChristoph Hellwig2010-03-014-64/+62
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currenly we pass opaque xfs_log_ticket_t handles instead of struct xlog_ticket pointers, and void pointers instead of struct xlog_in_core pointers to various log manager functions. Instead pass properly typed pointers after adding forward declarations for them to xfs_log.h, and adjust the touched function prototypes to the standard XFS style while at it. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: split xfs_bmap_btallocChristoph Hellwig2010-03-011-101/+119
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Split out the nullfb case into a separate function to reduce the stack footprint and make the code more readable. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: fix xfs_fsblock_t tracingChristoph Hellwig2010-03-012-22/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Using a static buffer in xfs_fmtfsblock means we can corrupt traces if multiple CPUs hit this code path at the same. Just remove xfs_fmtfsblock for now and print the block number purely numerical. If we want the NULLFSBLOCK and NULLSTARTBLOCK formatting back the best way would be a decoding plugin in the trace-cmd userspace command. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: fix inode pincount check in fsyncChristoph Hellwig2010-03-011-9/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We need to hold the ilock to check the inode pincount safely. While we're at it also remove the check for ip->i_itemp->ili_last_lsn, a pinned inode always has it set. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: Non-blocking inode locking in IO completionDave Chinner2010-03-011-37/+56
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The introduction of barriers to loop devices has created a new IO order completion dependency that XFS does not handle. The loop device implements barriers using fsync and so turns a log IO in the XFS filesystem on the loop device into a data IO in the backing filesystem. That is, the completion of log IOs in the loop filesystem are now dependent on completion of data IO in the backing filesystem. This can cause deadlocks when a flush daemon issues a log force with an inode locked because the IO completion of IO on the inode is blocked by the inode lock. This in turn prevents further data IO completion from occuring on all XFS filesystems on that CPU (due to the shared nature of the completion queues). This then prevents the log IO from completing because the log is waiting for data IO completion as well. The fix for this new completion order dependency issue is to make the IO completion inode locking non-blocking. If the inode lock can't be grabbed, simply requeue the IO completion back to the work queue so that it can be processed later. This prevents the completion queue from being blocked and allows data IO completion on other inodes to proceed, hence avoiding completion order dependent deadlocks. Signed-off-by: Dave Chinner <david@fromorbit.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: implement optimized fdatasyncChristoph Hellwig2010-03-014-13/+25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Allow us to track the difference between timestamp and size updates by using mark_inode_dirty from the I/O completion code, and checking the VFS inode flags in xfs_file_fsync. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: remove wrapper for the fsync file operationChristoph Hellwig2010-03-013-131/+117
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently the fsync file operation is divided into a low-level routine doing all the work and one that implements the Linux file operation and does minimal argument wrapping. This is a leftover from the days of the vnode operations layer and can be removed to simplify the code a bit, as well as preparing for the implementation of an optimized fdatasync which needs to look at the Linux inode state. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: remove wrappers for read/write file operationsChristoph Hellwig2010-03-011-171/+114
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently the aio_read, aio_write, splice_read and splice_write file operations are divided into a low-level routine doing all the work and one that implements the Linux file operations and does minimal argument wrapping. This is a leftover from the days of the vnode operations layer and can be removed to simplify the code a lot. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: merge xfs_lrw.c into xfs_file.cChristoph Hellwig2010-03-015-809/+743
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently the code to implement the file operations is split over two small files. Merge the content of xfs_lrw.c into xfs_file.c to have it in one place. Note that I haven't done various cleanups that are possible after this yet, they will follow in the next patch. Also the function xfs_dev_is_read_only which was in xfs_lrw.c before really doesn't fit in here at all and was moved to xfs_mount.c. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: fix dquota trace formatChristoph Hellwig2010-03-011-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The be32_to_cpu in the TP_printk output breaks automatic parsing of the trace format by the trace-cmd tools, so we have to move it into the TP_assign block. While we're at it also fix the format for the quota limits to more regular and easier parseable. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Alex Elder <aelder@sgi.com>
| | * | xfs: increase readdir buffer sizeEric Sandeen2010-03-011-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While doing some testing of readdir perf a while back, I noticed that the buffer size we're using internally is smaller than what glibc gives us by default. Upping this size helped a bit, and seems safe. glibc's __alloc_dir() does: const size_t default_allocation = (4 * BUFSIZ < sizeof (struct dirent64) ? sizeof (struct dirent64) : 4 * BUFSIZ); const size_t small_allocation = (BUFSIZ < sizeof (struct dirent64) ? sizeof (struct dirent64) : BUFSIZ); size_t allocation = default_allocation; #ifdef _STATBUF_ST_BLKSIZE if (statp != NULL && default_allocation < statp->st_blksize) allocation = statp->st_blksize; #endif and #define _G_BUFSIZ 8192 #define _IO_BUFSIZ _G_BUFSIZ # define BUFSIZ _IO_BUFSIZ so the default buffer is 4 * 8192 = 32768 (except in the unlikely case of blocks > 32k....) Signed-off-by: Eric Sandeen <sandeen@sandeen.net> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
* | | | Merge branch 'for-2.6.34' of git://linux-nfs.org/~bfields/linuxLinus Torvalds2010-03-0611-106/+124
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-2.6.34' of git://linux-nfs.org/~bfields/linux: (22 commits) nfsd4: fix minor memory leak svcrpc: treat uid's as unsigned nfsd: ensure sockets are closed on error Revert "sunrpc: move the close processing after do recvfrom method" Revert "sunrpc: fix peername failed on closed listener" sunrpc: remove unnecessary svc_xprt_put NFSD: NFSv4 callback client should use RPC_TASK_SOFTCONN xfs_export_operations.commit_metadata commit_metadata export operation replacing nfsd_sync_dir lockd: don't clear sm_monitored on nsm_reboot_lookup lockd: release reference to nsm_handle in nlm_host_rebooted nfsd: Use vfs_fsync_range() in nfsd_commit NFSD: Create PF_INET6 listener in write_ports SUNRPC: NFS kernel APIs shouldn't return ENOENT for "transport not found" SUNRPC: Bury "#ifdef IPV6" in svc_create_xprt() NFSD: Support AF_INET6 in svc_addsock() function SUNRPC: Use rpc_pton() in ip_map_parse() nfsd: 4.1 has an rfc number nfsd41: Create the recovery entry for the NFSv4.1 client nfsd: use vfs_fsync for non-directories ...
| * \ \ \ Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs into for-2.6.34-incomingJ. Bruce Fields2010-03-04201-2415/+3128
| |\ \ \ \ | | | |/ / | | |/| | | | | | | Resolve merge conflict in fs/xfs/linux-2.6/xfs_export.c.
| * | | | nfsd4: fix minor memory leakJ. Bruce Fields2010-03-031-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There's no need to allocate this cred more than once. Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
| * | | | NFSD: NFSv4 callback client should use RPC_TASK_SOFTCONNChuck Lever2010-02-241-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The server's callback client should stop trying to connect to the client's callback server as soon as it gets ECONNREFUSED. The NFS server's callback client does not call rpc_ping(), but appears to have it's own "ping" procedure, so it wasn't covered by commit caabea8a. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
| * | | | xfs_export_operations.commit_metadataBen Myers2010-02-201-0/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is the commit_metadata export operation for XFS. - Takes one inode to be committed. - Forces the log up to the lsn of the inode. - Doesn't force the log if the inode doesn't have a pincount. Signed-off-by: Ben Myers <bpm@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <david@fromorbit.com> [bfields@citi.umich.edu: trivial whitespace fix] Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
| * | | | commit_metadata export operation replacing nfsd_sync_dirBen Myers2010-02-202-57/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - Add commit_metadata export_operation to allow the underlying filesystem to decide how to commit an inode most efficiently. - Usage of nfsd_sync_dir and write_inode_now has been replaced with the commit_metadata function that takes a svc_fh. - The commit_metadata function calls the commit_metadata export_op if it's there, or else falls back to sync_inode instead of fsync and write_inode_now because only metadata need be synced here. - nfsd4_sync_rec_dir now uses vfs_fsync so that commit_metadata can be static Signed-off-by: Ben Myers <bpm@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
| * | | | lockd: don't clear sm_monitored on nsm_reboot_lookupJeff Layton2010-02-081-9/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When lockd gets a notify downcall from statd, it'll search its hosts cache and then clear the sm_monitored bit on the host it finds. The idea is apparently to make lockd redo a SM_MON on the next lock request. This is unnecessary and causes the kernel's NSM cache to go out of sync with statd. statd doesn't stop monitoring a host when it gets a SM_NOTIFY and there's no guarantee that another lock will occur after the reclaim and before the unmount. In that event, no SM_UNMON will occur. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
| * | | | lockd: release reference to nsm_handle in nlm_host_rebootedJeff Layton2010-02-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | nsm_reboot_lookup takes a reference to the nsm_handle that it returns, but nlm_host_rebooted never releases that reference. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
| * | | | nfsd: Use vfs_fsync_range() in nfsd_commitTrond Myklebust2010-01-291-10/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The NFS COMMIT operation allows the client to specify the exact byte range that it wishes to sync to disk in order to optimise server performance. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
| * | | | NFSD: Create PF_INET6 listener in write_portsChuck Lever2010-01-271-1/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Try to create a PF_INET6 listener for NFSD, if IPv6 is enabled in the kernel. Make sure nfsd_serv's reference count is decreased if __write_ports_addxprt() failed to create a listener. See __write_ports_addfd(). Our current plan is to rely on rpc.nfsd to create appropriate IPv6 listeners when server-side NFS/IPv6 support is desired. Legacy behavior, via the write_threads or write_svc kernel APIs, will remain the same -- only IPv4 listeners are created. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> [bfields@citi.umich.edu: Move error-handling code to end] Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
OpenPOWER on IntegriCloud