- 28 Oct, 2010 39 commits
-
-
Eric Sandeen authored
As pointed out in a prior patch, updating the mapping's writeback_index based on pages written isn't quite right; what the writeback index is really supposed to reflect is the next page which should be scanned for writeback during periodic flush. As in write_cache_pages(), write_cache_pages_da() does this scanning for us as we assemble the mpd for later writeout. If we keep track of the next page after the current scan, we can easily update writeback_index without worrying about pages written vs. pages skipped, etc. Without this, an fsync will reset writeback_index to 0 (its starting index) + however many pages it wrote, which can mess up the progress of periodic flush. Signed-off-by:
Eric Sandeen <sandeen@redhat.com> Signed-off-by:
"Theodore Ts'o" <tytso@mit.edu>
-
Eric Sandeen authored
This is analogous to Jan Kara's commit, f446daae mm: implement writeback livelock avoidance using page tagging but since we forked write_cache_pages, we need to reimplement it there (and in ext4_da_writepages, since range_cyclic handling was moved to there) If you start a large buffered IO to a file, and then set fsync after it, you'll find that fsync does not complete until the other IO stops. If you continue re-dirtying the file (say, putting dd with conv=notrunc in a loop), when fsync finally completes (after all IO is done), it reports via tracing that it has written many more pages than the file contains; in other words it has synced and re-synced pages in the file multiple times. This then leads to problems with our writeback_index update, since it advances it by pages written, and essentially sets writeback_index off the end of the file... With the following patch, we only sync as much as was dirty at the time of the sync. Signed-off-by:
-
Eric Sandeen authored
This doesn't fix anything at all, it just removes a vestige of prior use from __mpage_da_writepage() __mpage_da_writepage() had a *void argument leftover from its previous life as a callback; make it reflect the actual type. Fixing this up makes it slightly more obvious to read, and enables proper typechecking. Signed-off-by:
-
Lukas Czerner authored
Should be applied on the top of "lazy inode table initialization" and "batched discard support" patch-sets. Signed-off-by:
Lukas Czerner <lczerner@redhat.com> Signed-off-by:
-
Lukas Czerner authored
Walk through allocation groups and trim all free extents. It can be invoked through FITRIM ioctl on the file system. The main idea is to provide a way to trim the whole file system if needed, since some SSD's may suffer from performance loss after the whole device was filled (it does not mean that fs is full!). It search for free extents in allocation groups specified by Byte range start -> start+len. When the free extent is within this range, blocks are marked as used and then trimmed. Afterwards these blocks are marked as free in per-group bitmap. Since fstrim is a long operation it is good to have an ability to interrupt it by a signal. This was added by Dmitry Monakhov. Thanks Dimitry. Signed-off-by:
Dmitry Monakhov <dmonakhov@openvz.org> Reviewed-by:
Jan Kara <jack@suse.cz> Reviewed-by:
-
Lukas Czerner authored
Adds an filesystem independent ioctl to allow implementation of file system batched discard support. I takes fstrim_range structure as an argument. fstrim_range is definec in the include/fs.h and its definition is as follows. struct fstrim_range { start; len; minlen; } start - first Byte to trim len - number of Bytes to trim from start minlen - minimum extent length to trim, free extents shorter than this number of Bytes will be ignored. This will be rounded up to fs block size. It is also possible to specify NULL as an argument. In this case the arguments will set itself as follows: start = 0; len = ULLONG_MAX; minlen = 0; So it will trim the whole file system at one run. After the FITRIM is done, the number of actually discarded Bytes is stored in fstrim_range.len to give the user better insight on how much storage space has been really released for wear-leveling. Signed-off-by: -
Lukas Czerner authored
Use return value from sb_issue_discard() as return value in ext4_issue_discard(). Since sb_issue_discard() may result in more serious errors than just -EOPNOTSUPP it is worth to inform user of this function about them to handle error cases properly. Signed-off-by:
-
Namhyung Kim authored
Fail block allocation if sb_getblk() returns NULL. In that case, sb_find_get_block() also likely to fail so that it should skip calling ext4_forget(). Signed-off-by:
Namhyung Kim <namhyung@gmail.com> Signed-off-by:
-
Theodore Ts'o authored
Call the block I/O layer directly instad of going through the buffer layer. This should give us much better performance and scalability, as well as lowering our CPU utilization when doing buffered writeback. Signed-off-by: -
Theodore Ts'o authored
This massively simplifies the ext4_da_writepages() code path by completely removing mpage_put_bnr_bhs(), which is almost 100 lines of code iterating over a set of pages using pagevec_lookup(), and folds that functionality into mpage_da_submit_io()'s existing pagevec_lookup() loop. Signed-off-by: -
Theodore Ts'o authored
Expand the call: if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, ext4_bh_delay_or_unwritten)) goto redirty_page into mpage_da_submit_io(). This will allow us to merge in mpage_put_bnr_to_bhs() in the next patch. Signed-off-by: -
Theodore Ts'o authored
As a prepratory step to switching to bio_submit, inline ext4_writepage() into mpage_da_submit() and then simplify things a bit. This makes it clearer what mpage_da_submit needs to do. Also, move the ClearPageChecked(page) call into __ext4_journalled_writepage(), as a minor bit of cleanup refactoring. This also allows us to pull i_size_read() and ext4_should_journal_data() out of the loop, which should be a very minor CPU savings. Signed-off-by: -
Theodore Ts'o authored
The actual code in ext4_writepage() is unnecessarily convoluted. Simplify it so it is easier to understand, but otherwise logically equivalent. Signed-off-by: -
Theodore Ts'o authored
Eventually we need to completely reorganize the ext4 writepage callpath, but for now, we simplify things a little by calling mpage_da_submit_io() from mpage_da_map_blocks(), since all of the places where we call mpage_da_map_blocks() it is followed up by a call to mpage_da_submit_io(). We're also a wee bit better with respect to error handling, but there are still a number of issues where it's not clear what the right thing is to do with ext4 functions deep in the writeback codepath fails. Signed-off-by: -
Theodore Ts'o authored
Also remove the SLAB_RECLAIM_ACCOUNT flag from the system zone kmem cache. This slab tends to be fairly static, so it shouldn't be marked as likely to have free pages that can be reclaimed. Signed-off-by: -
Theodore Ts'o authored
Use the search_dirblock() in ext4_dx_find_entry(). It makes the code easier to read, and it takes advantage of common code. It also saves 100 bytes or so of text space. Signed-off-by: -
Theodore Ts'o authored
If the first block of htree directory is missing '.' or '..' but is otherwise a valid directory, and we do a lookup for '.' or '..', it's possible to dereference an uninitialized memory pointer in ext4_htree_next_block(). We avoid this by moving the special case from ext4_dx_find_entry() to ext4_find_entry(); this also means we can optimize ext4_find_entry() slightly when NFS looks up "..". Thanks to Brad Spengler for pointing a Clang warning that led me to look more closely at this code. The warning was harmless, but it was useful in pointing out code that was too ugly to live. This warning was also reported by Roman Borisov. Signed-off-by: -
Eric Sandeen authored
Not that these take up a lot of room, but the structure is long enough as it is, and there's no need to confuse people with these various undocumented & unused structure members... Signed-off-by:
Eric Sandeen <sandeen@redaht.com> Signed-off-by:
-
Eric Sandeen authored
By queuing the io end on the unwritten workqueue before adding it to our inode's list of completed IOs, I think we run the risk of the work getting completed, and the IO freed, before we try to add it to the inode's i_completed_io_list. It should be safe to add it to the inode's list of completed IOs, and -then- queue it for completion, I think. Thanks to Dave Chinner for pointing out the race. Signed-off-by:
Jiaying Zhang <jiayingz@google.com> Signed-off-by:
-
Eric Sandeen authored
Many tracepoints were populating an ext4_allocation_context to pass in, but this requires a slab allocation even when tracepoints are off. In fact, 4 of 5 of these allocations were only for tracing. In addition, we were only using a small fraction of the 144 bytes of this structure for this purpose. We can do away with all these alloc/frees of the ac and simply pass in the bits we care about, instead. I tested this by turning on tracing and running through xfstests on x86_64. I did not actually do anything with the trace output, however. Signed-off-by:
-
Eric Sandeen authored
Our QA reported an oops in the ext4_mb_release_group_pa tracing, and Josef Bacik pointed out that it was because we may have a non-null but uninitialized ac_inode in the allocation context. I can reproduce it when running xfstests with ext4 tracepoints on, on a CONFIG_SLAB_DEBUG kernel. We call trace_ext4_mb_release_group_pa from 2 places, ext4_mb_discard_group_preallocations and ext4_mb_discard_lg_preallocations In both cases we allocate an ac as a container just for tracing (!) and never fill in the ac_inode. There's no reason to be assigning, testing, or printing it as far as I can see, so just remove it from the tracepoint. Signed-off-by:
Josef Bacik <josef@redhat.com> Signed-off-by:
-
Toshiyuki Okajima authored
On linux-2.6.36-rc2, if we execute the following script, we can hang the system when the /bin/sync command is executed: ======================================================================== #!/bin/sh echo -n "HANG UP TEST: " /bin/dd if=/dev/zero of=/tmp/img bs=1k count=1 seek=1M 2> /dev/null /sbin/mkfs.ext4 -Fq /tmp/img /bin/mount -o loop -t ext4 /tmp/img /mnt /bin/dd if=/dev/zero of=/mnt/file bs=1 count=1 \ seek=$((16*1024*1024*1024*1024-4096)) 2> /dev/null /bin/sync /bin/umount /mnt echo "DONE" exit 0 ======================================================================== We can see the following backtrace if we get the kdump when this hangup occurs: ====================================================================== kthread() => bdi_writeback_thread() => wb_do_writeback() => wb_writeback() => writeback_inodes_wb() => writeback_sb_inodes() => writeback_single_inode() => ext4_da_writepages() ---+ ^ infinite | | loop | +-------------+ ====================================================================== The reason why this hangup happens is described as follows: 1) We write the last extent block of the file whose size is the filesystem maximum size. 2) "BH_Delay" flag is set on the buffer_head of its block. 3) - the member, "m_lblk" of struct mpage_da_data is 4294967295 (UINT_MAX) - the member, "m_len" of struct mpage_da_data is 1 mpage_put_bnr_to_bhs() which is called via ext4_da_writepages() cannot clear "BH_Delay" flag of the buffer_head because the type of m_lblk is ext4_lblk_t and then m_lblk + m_len is overflow. Therefore an infinite loop occurs because ext4_da_writepages() cannot write the page (which corresponds to the block) since "BH_Delay" flag isn't cleared. ---------------------------------------------------------------------- static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, struct ext4_map_blocks *map) { ... int blocks = map->m_len; ... do { // cur_logical = 4294967295 // map->m_lblk = 4294967295 // blocks = 1 // *** map->m_lblk + blocks == 0 (OVERFLOW!) *** // (cur_logical >= map->m_lblk + blocks) => true if (cur_logical >= map->m_lblk + blocks) break; ---------------------------------------------------------------------- NOTE: Mounting with the nodelalloc option will avoid this codepath, and thus, avoid this hang Signed-off-by:Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by:
-
Toshiyuki Okajima authored
The llseek system call should return EINVAL if passed a seek offset which results in a write error. What this maximum offset should be depends on whether or not the huge_file file system feature is set, and whether or not the file is extent based or not. If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be written (write systemcall) is different from the maximum size which can be sought (lseek systemcall). For example, the following 2 cases demonstrates the differences between the maximum size which can be written, versus the seek offset allowed by the llseek system call: #1: mkfs.ext3 <dev>; mount -t ext4 <dev> #2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev> Table. the max file size which we can write or seek at each filesystem feature tuning and file flag setting +============+===============================+===============================+ | \ File flag| | | | \ | !EXT4_EXTENTS_FL | EXT4_EXTETNS_FL | |case \| | | +------------+-------------------------------+-------------------------------+ | #1 | write: 2194719883264 | write: -------------- | | | seek: 2199023251456 | seek: -------------- | +------------+-------------------------------+-------------------------------+ | #2 | write: 4402345721856 | write: 17592186044415 | | | seek: 17592186044415 | seek: 17592186044415 | +------------+-------------------------------+-------------------------------+ The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes (= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped maxbytes). Although generic_file_llseek uses only extent-mapped maxbytes. (llseek of ext4_file_operations is generic_file_llseek which uses sb->s_maxbytes.) Therefore we create ext4 llseek function which uses 2 maxbytes. The new own function originates from generic_file_llseek(). If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes. Signed-off-by: -
Maciej Żenczykowski authored
An ext4 filesystem on a read-only device, with an external journal which is at a different device number then recorded in the superblock will fail to honor the read-only setting of the device and trigger a superblock update (write). For example: - ext4 on a software raid which is in read-only mode - external journal on a read-write device which has changed device num - attempt to mount with -o journal_dev=<new_number> - hits BUG_ON(mddev->ro = 1) in md.c Cc: Theodore Ts'o <tytso@mit.edu> Signed-off-by:
Maciej Żenczykowski <zenczykowski@gmail.com> Signed-off-by:
-
Lukas Czerner authored
Change ext4_ext_zeroout to use sb_issue_zeroout instead of its own approach to zero out extents. Signed-off-by:
-
Lukas Czerner authored
Use sb_issue_zeroout to zero out inode table and descriptor table blocks instead of old approach which involves journaling. Signed-off-by:
-
Lukas Czerner authored
User-space should have the opportunity to check what features doest ext4 support in each particular copy. This adds easy interface by creating new "features" directory in sys/fs/ext4/. In that directory files advertising feature names can be created. Add lazy_itable_init to the feature list. Signed-off-by:
-
Lukas Czerner authored
When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by:
-
Lukas Czerner authored
This is done the same way as helper sb_issue_discard for blkdev_issue_discard. Signed-off-by:
-
Theodore Ts'o authored
An attempt to modify the file system during the call to jbd2_destroy_journal() can lead to a system lockup. So add some checking to make it much more obvious when this happens to and to determine where the offending code is located. Signed-off-by: -
Sergey Senozhatsky authored
Fix NULL pointer dereference in print_daily_error_info, when called on unmounted fs (EXT4_SB(sb) returns NULL), by removing error reporting timer in ext4_put_super. Google-Bug-Id: 3017663 Signed-off-by:
Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by:
-
Lukas Czerner authored
We can't hold the block group spinlock because we ext4_issue_discard() calls wait and hence can get rescheduled. Google-Bug-Id: 3017678 Signed-off-by:
-
Lukas Czerner authored
sb_issue_discard() is returning negative error code, so check for -EOPNOTSUPP. Signed-off-by:
-
Eric Sandeen authored
I'm uneasy with lots of stuff going on in ext4_da_writepages(), but bumping nr_to_write from LLONG_MAX to -8 clearly isn't making anything better, so avoid the multiplier in that case. Signed-off-by:
-
Eric Sandeen authored
Today we simply break out of the inner loop when we have accumulated max_pages; this keeps scanning forwad and doing pagevec_lookup_tag() in the while (!done) loop, this does potentially a lot of work with no net effect. When we have accumulated max_pages, just clean up and return. Signed-off-by:
-
Curt Wohlgemuth authored
ext4_group_info structures are currently allocated with kmalloc(). With a typical 4K block size, these are 136 bytes each -- meaning they'll each consume a 256-byte slab object. On a system with many ext4 large partitions, that's a lot of wasted kernel slab space. (E.g., a single 1TB partition will have about 8000 block groups, using about 2MB of slab, of which nearly 1MB is wasted.) This patch creates an array of slab pointers created as needed -- depending on the superblock block size -- and uses these slabs to allocate the group info objects. Google-Bug-Id: 2980809 Signed-off-by:
Curt Wohlgemuth <curtw@google.com> Signed-off-by:
-
Wen Congyang authored
ac->inode is set to null in function ext4_mb_release_group_pa(), and then trace_ext4_mballoc_discard(ac) is called, the kernel will panic. BUG: unable to handle kernel NULL pointer dereference at 000000a4 IP: [<f87e1714>] ftrace_raw_event_ext4__mballoc+0x54/0xc0 [ext4] *pdpt = 0000000000abd001 *pde = 0000000000000000 Oops: 0000 [#1] SMP Pid: 550, comm: flush-8:16 Not tainted 2.6.36-rc1 #1 SE7320EP2/Altos G530 EIP: 0060:[<f87e1714>] EFLAGS: 00010206 CPU: 1 EIP is at ftrace_raw_event_ext4__mballoc+0x54/0xc0 [ext4] EAX: f32ac840 EBX: f3f1cf88 ECX: f32ac840 EDX: 00000000 ESI: f32ac83c EDI: f880b9d8 EBP: 00000000 ESP: f4b77ae4 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 Process flush-8:16 (pid: 550, ti=f4b76000 task=f613e540 task.ti=f4b76000) Call Trace: [<f87f5ac1>] ? ext4_mb_release_group_pa+0x121/0x150 [ext4] [<f87f8356>] ? ext4_mb_discard_group_preallocations+0x336/0x400 [ext4] [<f87fb7f1>] ? ext4_mb_new_blocks+0x3d1/0x4f0 [ext4] [<c05a6c5b>] ? __make_request+0x10b/0x440 [<f87f1fb4>] ? ext4_ext_map_blocks+0x1334/0x1980 [ext4] [<c04ac78a>] ? rb_reserve_next_event+0xaa/0x3b0 [<f87d18d6>] ? ext4_map_blocks+0xd6/0x1d0 [ext4] [<f87d2da7>] ? mpage_da_map_blocks+0xc7/0x8a0 [ext4] [<c04c8a68>] ? find_get_pages_tag+0x38/0x110 [<c04d23a5>] ? __pagevec_release+0x15/0x20 [<f87d3ca5>] ? ext4_da_writepages+0x2b5/0x5d0 [ext4] [<c04cfbe0>] ? __writepage+0x0/0x30 [<c04d0e34>] ? do_writepages+0x14/0x30 [<c0526600>] ? writeback_single_inode+0xa0/0x240 [<c0526971>] ? writeback_sb_inodes+0xc1/0x180 [<c0526ab8>] ? writeback_inodes_wb+0x88/0x140 [<c0526d7b>] ? wb_writeback+0x20b/0x320 [<c045aca7>] ? lock_timer_base+0x27/0x50 [<c0526fe0>] ? wb_do_writeback+0x150/0x190 [<c05270a8>] ? bdi_writeback_thread+0x88/0x1f0 [<c043b680>] ? complete+0x40/0x60 [<c0527020>] ? bdi_writeback_thread+0x0/0x1f0 [<c0469474>] ? kthread+0x74/0x80 [<c0469400>] ? kthread+0x0/0x80 [<c040a23e>] ? kernel_thread_helper+0x6/0x10 Signed-off-by:
Wen Congyang <wency@cn.fujitsu.com> Acked-by:
Steven Rostedt <rostedt@goodmis.org> Signed-off-by:
-
Brian King authored
This fixes a hang seen in jbd2_journal_release_jbd_inode on a lot of Power 6 systems running with ext4. When we get in the hung state, all I/O to the disk in question gets blocked where we stay indefinitely. Looking at the task list, I can see we are stuck in jbd2_journal_release_jbd_inode waiting on a wake up. I added some debug code to detect this scenario and dump additional data if we were stuck in jbd2_journal_release_jbd_inode for longer than 30 minutes. When it hit, I was able to see that i_flags was 0, suggesting we missed the wake up. This patch changes i_flags to be an unsigned long, uses bit operators to access it, and adds barriers around the accesses. Prior to applying this patch, we were regularly hitting this hang on numerous systems in our test environment. After applying the patch, the hangs no longer occur. Signed-off-by:
Brian King <brking@linux.vnet.ibm.com> Signed-off-by:
-
Theodore Ts'o authored
It turns out we have several problems with how EOFBLOCKS_FL is handled. First of all, there was a fencepost error where we were not clearing the EOFBLOCKS_FL when fill in the last uninitialized block, but rather when we allocate the next block _after_ the uninitalized block. Secondly we were not testing to see if we needed to clear the EOFBLOCKS_FL when writing to the file O_DIRECT or when were converting an uninitialized block (which is the most common case). Google-Bug-Id: 2928259 Signed-off-by:
-
- 29 Sep, 2010 1 commit
-
-
Linus Torvalds authored
-
