- 17 Dec, 2012 31 commits
-
-
Miao Xie authored
Steps to reproduce: # mkfs.btrfs <disk> # mount <disk> <mnt> # dd if=/dev/zero of=<mnt>/<file> bs=512 seek=5 count=8 # fallocate -p -o 2048 -l 16384 <mnt>/<file> # dd if=/dev/zero of=<mnt>/<file> bs=4096 seek=3 count=8 conv=notrunc,nocreat # umount <mnt> # dmesg WARNING: at fs/btrfs/inode.c:7140 btrfs_destroy_inode+0x2eb/0x330 The reason is that we inputed a range which is beyond the end of the file. And because the end of this range was not page-aligned, we had to truncate the last page in this range, this operation is similar to a buffered file write. In other words, we reserved enough space and clear the data which was in the hole range on that page. But when we expanded that test file, write the data into the same page, we forgot that we have reserved enough space for the buffered write of that page because in most cases there is no page that is beyond the end of the file. As a result, we reserved the space twice. In fact, we needn't truncate the page if it is beyond the end of the file, just release the allocated space in that range. Fix the above problem by this way. Signed-off-by:
Miao Xie <miaox@cn.fujitsu.com> Signed-off-by:
Chris Mason <chris.mason@fusionio.com>
-
Miao Xie authored
(start + len) is the start of the adjacent extent, not the end of the current extent, so we should not use it to check the hole is on the same page or not. Signed-off-by:
-
Miao Xie authored
We forget to release the reserved space in the error path of delalloc reservatiom, fix it. Signed-off-by:
-
Miao Xie authored
If we runt the direct IO, we should not run auto defrag, because it may introduce buffered IO vs direcIO problem, and make direct IO slow down. Signed-off-by:
-
Liu Bo authored
Value 0 is not a tree id, so besides an upper limit, a lower limit is necessary as well while parsing root types of tracepoint. Signed-off-by:
Liu Bo <bo.li.liu@oracle.com> Signed-off-by:
-
Wang Sheng-Hui authored
We should use ctl->unit for free space calculation instead of block_group->sectorsize even though for free space use_bitmap or free space cluster we only have sectorsize assigned to ctl->unit currently. Also, we can keep it consisten in code style. Signed-off-by:
Wang Sheng-Hui <shhuiw@gmail.com> Signed-off-by:
-
Filipe Brandenburger authored
Refactor it by checking whether the inode has been created and needs to be dropped (drop_inode_on_err) and also if the err variable is set. That way the variable doesn't need to be set on each and every error handling block. Signed-off-by:
Filipe Brandenburger <filbranden@google.com> Signed-off-by:
-
Filipe Brandenburger authored
When a new file is created with btrfs_create(), the inode will initially be created with permissions 0666 and later on in btrfs_init_acl() it will be adapted to mask out the umask bits. The problem is that this change won't make it into the btrfs_inode unless there's another change to the inode (e.g. writing content changing the size or touching the file changing the mtime.) This fix adds a call to btrfs_update_inode() to btrfs_create() to make sure that the change will not get lost if the in-memory inode is flushed before other changes are made to the file. Signed-off-by:
-
Tsutomu Itoh authored
When the flag not supported is specified, it is necessary to return the error to the caller. So, we add the validity check of the fiemap's flag. Signed-off-by:
Tsutomu Itoh <t-itoh@jp.fujitsu.com> Signed-off-by:
-
Liu Bo authored
Passing a null extended attribute value means to remove the attribute, but we don't have to add a new NULL extended attribute. Signed-off-by:
-
Liu Bo authored
If the acl can be exactly represented in the traditional file mode permission bits, we don't set another acl attribute. Signed-off-by:
-
Miao Xie authored
alloc_end is not the real end of the current extent, it is the start of the next adjoining extent. So we needn't +1 when calculating the size the space that is about to be reserved. Signed-off-by:
-
Miao Xie authored
The kernel developers have implemented some often-used align macros, we should use them instead of the complex code. Signed-off-by:
-
Stefan Behrens authored
This regression was introduced by the device-replace patches. Scrub immediately stops checking those disks that have write errors. This is nothing that happens in the real world, but it is wrong since scrub is the tool to detect and repair defects. Fix it. Signed-off-by:
Stefan Behrens <sbehrens@giantdisaster.de> Signed-off-by:
-
Stefan Behrens authored
This issue was detected by the "0-DAY kernel build testing". fs/btrfs/volumes.c: In function 'btrfs_rm_device': fs/btrfs/volumes.c:1505:1: warning: label 'error_close' defined but not used [-Wunused-label] Signed-off-by:
-
Stefan Behrens authored
The structure member mirror_num is modified concurrently to the structure member is_iodone. This doesn't require any locking by design, unless everything is stored in the same 32 bits of a bit field. This was the case and xfstest 284 was able to trigger false warnings from the checker code. This patch seperates the bits and fixes the race. Signed-off-by:
-
Miao Xie authored
If we freeze the fs, the auto defragment should not run. Fix it. Signed-off-by:
-
Miao Xie authored
This patch restructure btrfs_run_defrag_inodes() and make the code of the auto defragment more readable. Signed-off-by:
-
Miao Xie authored
We forget to get the defrag lock when we re-add the defragable inode, Fix it. Signed-off-by:
-
Miao Xie authored
The auto defrag allocation is in the fast path of the IO, so use slabs to improve the speed of the allocation. And besides that, it can do check for leaked objects when the module is removed. Signed-off-by:
-
Miao Xie authored
We need get write access for qgroup operations, or we will modify the R/O fs. Signed-off-by:
-
Miao Xie authored
We need get write access for scrub, or we will modify the R/O fs. Signed-off-by:
-
Miao Xie authored
Steps to reproduce: # mkfs.btrfs -d single -m single <disk0> <disk1> # mount -o ro <disk0> <mnt0> # mount -o ro <disk0> <mnt1> # mount -o remount,rw <mnt0> # umount <mnt0> # btrfs device delete <disk1> <mnt1> We can remove a device from a R/O filesystem. The reason is that we just check the R/O flag of the super block object. It is not enough, because the kernel may set the R/O flag only for the mount point. We need invoke mnt_want_write_file() to do a full check. Signed-off-by:
-
Miao Xie authored
Steps to reproduce: # mkfs.btrfs <partition> # mount -o ro <partition> <mnt0> # mount -o ro <partition> <mnt1> # mount -o remount,rw <mnt0> # umount <mnt0> # btrfs fi resize 10g <mnt1> We re-sized a R/O filesystem. The reason is that we just check the R/O flag of the super block object. It is not enough, because the kernel may set the R/O flag only for the mount point. We need invoke mnt_want_write_file() to do a full check. Signed-off-by:
-
Miao Xie authored
When wen want to set the default subvolume, we must get write access, or we will change the R/O file system. Signed-off-by:
-
Miao Xie authored
If the id of the existed transaction is more than the one we specified, it means the specified transaction was commited, so we should return 0, not EINVAL. Signed-off-by:
-
Miao Xie authored
If there is no running transaction in the fs, we needn't start a new one when we want to start sync. Signed-off-by:
-
Miao Xie authored
Since we have gotten the root in the caller, just pass it into btrfs_ioctl_{start, wait}_sync() directly. Signed-off-by: -
Liu Bo authored
If we found an invalid xattr dir item, we'd better try the next one instead. Signed-off-by:
-
Wang Sheng-Hui authored
io_ctl_map_page is called by many functions in free-space-cache. In most scenarios, the ->cur is not null, e.g. io_ctl_add_entry. I think we'd better remove the warn_on here. Signed-off-by:
-
Stefan Behrens authored
This is the commit that allows to start the device replace procedure. An ioctl() interface is added that supports starting and canceling the device replace procedure, and to retrieve the status and progress. Signed-off-by:
-
- 12 Dec, 2012 9 commits
-
-
Stefan Behrens authored
Make the target disk of a running device replace operation available for reading. This is only used as a last ressort for the defect repair procedure. And it is dependent on the location of the data block to read, because during an ongoing device replace operation, the target drive is only partially filled with the filesystem data. Signed-off-by:
-
Stefan Behrens authored
This change of the define is effective in all modes, it is required and used only in the case when a device replace procedure is running. The reason is that during an active device replace procedure, the target device of the copy operation is a mirror for the filesystem data as well that can be used to read data in order to repair read errors on other disks. Signed-off-by:
-
Stefan Behrens authored
It is desirable to be able to configure the device replace procedure to avoid reading the source drive (the one to be copied) whenever possible. This is useful when the number of read errors on this disk is high, because it would delay the copy procedure alot. Therefore there is an option to avoid reading from the source disk unless the repair procedure really needs to access it. The regular read req asks for mapping the block with mirror_num == 0, in this case the source disk is avoided whenever possible. The repair code selects the mirror_num explicitly (mirror_num != 0), this case is not changed by this commit. Signed-off-by:
-
Stefan Behrens authored
During a running dev replace operation, all write requests to the live filesystem are duplicated to also write to the target drive. Therefore btrfs_map_block() is changed to duplicate stripes that are written to the source disk of a device replace procedure to be written to the target disk as well. Signed-off-by:
-
Stefan Behrens authored
Before this commit, btrfs_map_block() was called with REQ_WRITE in order to retrieve the list of mirrors for a disk block. This needs to be changed for the device replace procedure since it makes a difference whether you are asking for read mirrors or for locations to write to. GET_READ_MIRRORS is introduced as a new interface to call btrfs_map_block(). In the current commit, the functionality is not yet changed, only the interface for GET_READ_MIRRORS is introduced and all the places that should use this new interface are adapted. The reason that REQ_WRITE cannot be abused anymore to retrieve a list of read mirrors is that during a running dev replace operation all write requests to the live filesystem are duplicated to also write to the target drive. Keep in mind that the target disk is only partially a valid copy of the source disk while the operation is ongoing. All writes go to the target disk, but not all reads would return valid data on the target disk. Therefore it is not possible anymore to abuse a REQ_WRITE interface to find valid mirrors for a REQ_READ. Signed-off-by:
-
Stefan Behrens authored
This commit contains all the essential changes to the core code of Btrfs for support of the device replace procedure. Signed-off-by:
-
Stefan Behrens authored
This adds a new file to the sources together with the header file and the changes to ioctl.h and ctree.h that are required by the new C source file. Additionally, 4 new functions are added to volume.c that deal with device creation and destruction. Signed-off-by:
-
Stefan Behrens authored
The device replace procedure makes use of the scrub code. The scrub code is the most efficient code to read the allocated data of a disk, i.e. it reads sequentially in order to avoid disk head movements, it skips unallocated blocks, it uses read ahead mechanisms, and it contains all the code to detect and repair defects. This commit adds code to scrub to allow the scrub code to copy read data to another disk. One goal is to be able to perform as fast as possible. Therefore the write requests are collected until huge bios are built, and the write process is decoupled from the read process with some kind of flow control, of course, in order to limit the allocated memory. The best performance on spinning disks could by reached when the head movements are avoided as much as possible. Therefore a single worker is used to interface the read process with the write process. The regular scrub operation works as fast as before, it is not negatively influenced and actually it is more or less unchanged. Signed-off-by:
-
Stefan Behrens authored
With the addition of the device replace procedure, it is possible for btrfs_map_bio(READ) to report an error. This happens when the specific mirror is requested which is located on the target disk, and the copy operation has not yet copied this block. Hence the block cannot be read and this error state is indicated by returning EIO. Some background information follows now. A new mirror is added while the device replace procedure is running. btrfs_get_num_copies() returns one more, and btrfs_map_bio(GET_READ_MIRROR) adds one more mirror if a disk location is involved that was already handled by the device replace copy operation. The assigned mirror num is the highest mirror number, e.g. the value 3 in case of RAID1. If btrfs_map_bio() is invoked with mirror_num == 0 (i.e., select any mirror), the copy on the target drive is never selected because that disk shall be able to perform the write requests as quickly as possible. The parallel execution of read requests would only slow down the disk copy procedure. Second case is that btrfs_map_bio() is called with mirror_num > 0. This is done from the repair code only. In this case, the highest mirror num is assigned to the target disk, since it is used last. And when this mirror is not available because the copy procedure has not yet handled this area, an error is returned. Everywhere in the code the handling of such errors is added now. Signed-off-by:
-
