- 04 Jun, 2013 19 commits
-
-
Jan Kara authored
Currently PageWriteback bit gets cleared from put_io_page() called from ext4_end_bio(). This is somewhat inconvenient as extent tree is not fully updated at that time (unwritten extents are not marked as written) so we cannot read the data back yet. This design was dictated by lock ordering as we cannot start a transaction while PageWriteback bit is set (we could easily deadlock with ext4_da_writepages()). But now that we use transaction reservation for extent conversion, locking issues are solved and we can move PageWriteback bit clearing after extent conversion is done. As a result we can remove wait for unwritten extent conversion from ext4_sync_file() because it already implicitely happens through wait_on_page_writeback(). We implement deferring of PageWriteback clearing by queueing completed bios to appropriate io_end and processing all the pages when io_end is going to be freed instead of at the moment ext4_io_end() is called. Reviewed-by:
Zheng Liu <wenqing.lz@taobao.com> Signed-off-by:
Jan Kara <jack@suse.cz> Signed-off-by:
"Theodore Ts'o" <tytso@mit.edu>
-
Jan Kara authored
Now that we have extent conversions with reserved transaction, we have to prevent extent conversions without reserved transaction (from DIO code) to block these (as that would effectively void any transaction reservation we did). So split lists, work items, and work queues to reserved and unreserved parts. Reviewed-by:
-
Jan Kara authored
Later we would like to clear PageWriteback bit only after extent conversion from unwritten to written extents is performed. However it is not possible to start a transaction after PageWriteback is set because that violates lock ordering (and is easy to deadlock). So we have to reserve a transaction before locking pages and sending them for IO and later we use the transaction for extent conversion from ext4_end_io(). Reviewed-by:
-
Jan Kara authored
There isn't any need for setting BH_Uninit on buffers anymore. It was only used to signal we need to mark io_end as needing extent conversion in add_bh_to_extent() but now we can mark the io_end directly when mapping extent. Reviewed-by:
-
Jan Kara authored
There are two issues with current writeback path in ext4. For one we don't necessarily map complete pages when blocksize < pagesize and thus needn't do any writeback in one iteration. We always map some blocks though so we will eventually finish mapping the page. Just if writeback races with other operations on the file, forward progress is not really guaranteed. The second problem is that current code structure makes it hard to associate all the bios to some range of pages with one io_end structure so that unwritten extents can be converted after all the bios are finished. This will be especially difficult later when io_end will be associated with reserved transaction handle. We restructure the writeback path to a relatively simple loop which first prepares extent of pages, then maps one or more extents so that no page is partially mapped, and once page is fully mapped it is submitted for IO. We keep all the mapping and IO submission information in mpage_da_data structure to somewhat reduce stack usage. Resulting code is somewhat shorter than the old one and hopefully also easier to read. Reviewed-by:
-
Jan Kara authored
We limit the number of blocks written in a single loop of ext4_da_writepages() to 64 when inode uses indirect blocks. That is unnecessary as credit estimates for mapping logically continguous run of blocks is rather low even for inode with indirect blocks. So just lift this limitation and properly calculate the number of necessary credits. This better credit estimate will also later allow us to always write at least a single page in one iteration. Reviewed-by:
-
Jan Kara authored
ext4_ind_trans_blocks() wrongly used 'chunk' argument to decide whether blocks mapped are logically contiguous. That is wrong since the argument informs whether the blocks are physically contiguous. As the blocks mapped are always logically contiguous and that's all ext4_ind_trans_blocks() cares about, just remove the 'chunk' argument. Reviewed-by:
-
Jan Kara authored
This attribute is now unused so deprecate it. We still show the old default value to keep some compatibility but we don't allow writing to that attribute anymore. Signed-off-by:
-
Jan Kara authored
Writeback code got better in how it submits IO and now the number of pages requested to be written is usually higher than original 1024. The number is now dynamically computed based on observed throughput and is set to be about 0.5 s worth of writeback. E.g. on ordinary SATA drive this ends up somewhere around 10000 as my testing shows. So remove the unnecessary smarts from ext4_da_writepages(). Reviewed-by:
-
Jan Kara authored
Reviewed-by:
-
Jan Kara authored
In some cases we cannot start a transaction because of locking constraints and passing started transaction into those places is not handy either because we could block transaction commit for too long. Transaction reservation is designed to solve these issues. It reserves a handle with given number of credits in the journal and the handle can be later attached to the running transaction without blocking on commit or checkpointing. Reserved handles do not block transaction commit in any way, they only reduce maximum size of the running transaction (because we have to always be prepared to accomodate request for attaching reserved handle). Signed-off-by:
-
Jan Kara authored
j_wait_logspace and j_wait_checkpoint are unused. Remove them. Reviewed-by:
-
Jan Kara authored
jbd2_journal_extend() first checked whether transaction can accept extending handle with more credits and then added credits to t_outstanding_credits. This can race with start_this_handle() adding another handle to a transaction and thus overbooking a transaction. Make jbd2_journal_extend() use atomic_add_return() to close the race. Reviewed-by:
-
Jan Kara authored
__jbd2_log_space_left() and jbd_space_needed() were kind of odd. jbd_space_needed() accounted also credits needed for currently committing transaction while it didn't account for credits needed for control blocks. __jbd2_log_space_left() then accounted for control blocks as a fraction of free space. Since results of these two functions are always only compared against each other, this works correct but is somewhat strange. Move the estimates so that jbd_space_needed() returns number of blocks needed for a transaction including control blocks and __jbd2_log_space_left() returns free space in the journal (with the committing transaction already subtracted). Rename functions to jbd2_log_space_left() and jbd2_space_needed() while we are changing them. Reviewed-by:
-
Jan Kara authored
The comment about credit estimates isn't true anymore. We do what the comment describes now. Reviewed-by:
-
Jan Kara authored
Currently when we add a buffer to a transaction, we wait until the buffer is removed from BJ_Shadow list (so that we prevent any changes to the buffer that is just written to the journal). This can take unnecessarily long as a lot happens between the time the buffer is submitted to the journal and the time when we remove the buffer from BJ_Shadow list. (e.g. We wait for all data buffers in the transaction, we issue a cache flush, etc.) Also this creates a dependency of do_get_write_access() on transaction commit (namely waiting for data IO to complete) which we want to avoid when implementing transaction reservation. So we modify commit code to set new BH_Shadow flag when temporary shadowing buffer is created and we clear that flag once IO on that buffer is complete. This allows do_get_write_access() to wait only for BH_Shadow bit and thus removes the dependency on data IO completion. Reviewed-by:
-
Jan Kara authored
Similarly as for metadata buffers, also log descriptor buffers don't really need the journal head. So strip it and remove BJ_LogCtl list. Reviewed-by:
-
Jan Kara authored
When writing metadata to the journal, we create temporary buffer heads for that task. We also attach journal heads to these buffer heads but the only purpose of the journal heads is to keep buffers linked in transaction's BJ_IO list. We remove the need for journal heads by reusing buffer_head's b_assoc_buffers list for that purpose. Also since BJ_IO list is just a temporary list for transaction commit, we use a private list in jbd2_journal_commit_transaction() for that thus removing BJ_IO list from transaction completely. Reviewed-by:
-
Jan Kara authored
Change writeback path to create just one io_end structure for the extent to which we submit IO and share it among bios writing that extent. This prevents needless splitting and joining of unwritten extents when they cannot be submitted as a single bio. Bugs in ENOMEM handling found by Linux File System Verification project (linuxtesting.org) and fixed by Alexey Khoroshilov <khoroshilov@ispras.ru>. CC: Alexey Khoroshilov <khoroshilov@ispras.ru> Signed-off-by:
-
- 31 May, 2013 4 commits
-
-
Jan Kara authored
The arithmetics adding delalloc blocks to the number of used blocks in ext4_getattr() can easily overflow on 32-bit archs as we first multiply number of blocks by blocksize and then divide back by 512. Make the arithmetics more clever and also use proper type (unsigned long long instead of unsigned long). Signed-off-by:
-
Jan Kara authored
On 32-bit architectures with 32-bit sector_t computation of data offset in ext4_xattr_fiemap() can overflow resulting in reporting bogus data location. Fix the problem by typing block number to proper type before shifting. Signed-off-by:
-
Jan Kara authored
ext4_lblk_t is just u32 so multiplying it by blocksize can easily overflow for files larger than 4 GB. Fix that by properly typing the block offsets before shifting. Signed-off-by:
-
Jan Kara authored
On 32-bit archs when sector_t is defined as 32-bit the logic computing data offset in ext4_inline_data_fiemap(). Fix that by properly typing the shifted value. Signed-off-by:
-
- 28 May, 2013 13 commits
-
-
Paul Taysom authored
Suppress the messages releating to processing the ext4 orphan list ("truncating inode" and "deleting unreferenced inode") unless the debug option is on, since otherwise they end up taking up space in the log that could be used for more useful information. Tested by opening several files, unlinking them, then crashing the system, rebooting the system and examining /var/log/messages. Addresses the problem described in http://crbug.com/220976Signed-off-by:Paul Taysom <taysom@chromium.org> Signed-off-by:
-
Darrick J. Wong authored
Al Viro complained of a ton of bogosity with regards to the jbd2 block tag header checksum. This one checksum is 16 bits, so cut off the upper 16 bits and treat it as a 16-bit value and don't mess around with be32* conversions. Fortunately metadata checksumming is still "experimental" and not in a shipping e2fsprogs, so there should be few users affected by this. Reported-by:
Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by:
Darrick J. Wong <darrick.wong@oracle.com>
-
Zheng Liu authored
This commit tries to use kmem_cache_zalloc instead of kmem_cache_alloc/ memset when a new journal head is alloctated. Signed-off-by: -
Lukas Czerner authored
Currently punch hole is disabled in file systems with bigalloc feature enabled. However the recent changes in punch hole patch should make it easier to support punching holes on bigalloc enabled file systems. This commit changes partial_cluster handling in ext4_remove_blocks(), ext4_ext_rm_leaf() and ext4_ext_remove_space(). Currently partial_cluster is unsigned long long type and it makes sure that we will free the partial cluster if all extents has been released from that cluster. However it has been specifically designed only for truncate. With punch hole we can be freeing just some extents in the cluster leaving the rest untouched. So we have to make sure that we will notice cluster which still has some extents. To do this I've changed partial_cluster to be signed long long type. The only scenario where this could be a problem is when cluster_size == block size, however in that case there would not be any partial clusters so we're safe. For bigger clusters the signed type is enough. Now we use the negative value in partial_cluster to mark such cluster used, hence we know that we must not free it even if all other extents has been freed from such cluster. This scenario can be described in simple diagram: |FFF...FF..FF.UUU| ^----------^ punch hole . - free space | - cluster boundary F - freed extent U - used extent Also update respective tracepoints to use signed long long type for partial_cluster. Signed-off-by:
Lukas Czerner <lczerner@redhat.com> Reviewed-by:
-
Lukas Czerner authored
Add "end" variable. Signed-off-by:
-
Lukas Czerner authored
The "head removal" branch in the condition is never used in any code path in ext4 since the function only caller ext4_ext_rm_leaf() will make sure that the extent is properly split before removing blocks. Note that there is a bug in this branch anyway. This commit removes the unused code completely and makes use of ext4_error() instead of printk if dubious range is provided. Signed-off-by:
-
Lukas Czerner authored
The discard_partial_page_buffers is no longer used anywhere so we can simply remove it including the *_no_lock variant and EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED define. Signed-off-by:
-
Lukas Czerner authored
We're doing to get rid of ext4_discard_partial_page_buffers() since it is duplicating some code and also partially duplicating work of truncate_pagecache_range(), moreover the old implementation was much clearer. Now when the truncate_inode_pages_range() can handle truncating non page aligned regions we can use this to invalidate and zero out block aligned region of the punched out range and then use ext4_block_truncate_page() to zero the unaligned blocks on the start and end of the range. This will greatly simplify the punch hole code. Moreover after this commit we can get rid of the ext4_discard_partial_page_buffers() completely. We also introduce function ext4_prepare_punch_hole() to do come common operations before we attempt to do the actual punch hole on indirect or extent file which saves us some code duplication. This has been tested on ppc64 with 1k block size with fsx and xfstests without any problems. Signed-off-by:
-
Lukas Czerner authored
Currently we do not tell mm to zero out tail of the page before truncate in orphan_cleanup(). This is ok, because the page should not be uptodate, however this may eventually change and I might cause problems. Call truncate_inode_pages() as precautionary measure. Thanks Jan Kara for pointing this out. Signed-off-by:
-
Lukas Czerner authored
This reverts commit 189e868f. This commit reintroduces the use of ext4_block_truncate_page() in ext4 truncate operation instead of ext4_discard_partial_page_buffers(). The statement in the commit description that the truncate operation only zero block unaligned portion of the last page is not exactly right, since truncate_pagecache_range() also zeroes and invalidate the unaligned portion of the page. Then there is no need to zero and unmap it once more and ext4_block_truncate_page() was doing the right job, although we still need to update the buffer head containing the last block, which is exactly what ext4_block_truncate_page() is doing. Moreover the problem described in the commit is fixed more properly with commit 15291164 jbd2: clear BH_Delay & BH_Unwritten in journal_unmap_buffer This was tested on ppc64 machine with block size of 1024 bytes without any problems. Signed-off-by:
-
Lukas Czerner authored
In data=ordered mode we should call ext4_jbd2_file_inode() so that crash after the truncate transaction has committed does not expose stall data in the tail of the block. Thanks Jan Kara for pointing that out. Signed-off-by:
-
Lukas Czerner authored
This reverts commit ccb4d7af. This commit reintroduces functions ext4_block_truncate_page() and ext4_block_zero_page_range() which has been previously removed in favour of ext4_discard_partial_page_buffers(). In future commits we want to reintroduce those function and remove ext4_discard_partial_page_buffers() since it is duplicating some code and also partially duplicating work of truncate_pagecache_range(), moreover the old implementation was much clearer. Signed-off-by:
-
Lukas Czerner authored
This commit changes truncate_inode_pages_range() so it can handle non page aligned regions of the truncate. Currently we can hit BUG_ON when the end of the range is not page aligned, but we can handle unaligned start of the range. Being able to handle non page aligned regions of the page can help file system punch_hole implementations and save some work, because once we're holding the page we might as well deal with it right away. In previous commits we've changed ->invalidatepage() prototype to accept 'length' argument to be able to specify range to invalidate. No we can use that new ability in truncate_inode_pages_range(). Signed-off-by:
-
- 22 May, 2013 4 commits
-
-
Lukas Czerner authored
->invalidatepage() aop now accepts range to invalidate so we can make use of it in reiserfs_invalidatepage() Signed-off-by: -
Lukas Czerner authored
->invalidatepage() aop now accepts range to invalidate so we can make use of it in gfs2_invalidatepage(). Signed-off-by:
Steven Whitehouse <swhiteho@redhat.com> Cc: cluster-devel@redhat.com
-
Lukas Czerner authored
->invalidatepage() aop now accepts range to invalidate so we can make use of it in ceph_invalidatepage(). Signed-off-by:
Sage Weil <sage@inktank.com> Cc: ceph-devel@vger.kernel.org
-
Lukas Czerner authored
->invalidatepage() aop now accepts range to invalidate so we can make use of it in ocfs2_invalidatepage(). Signed-off-by:
Joel Becker <jlbec@evilplan.org>
-
