linux-stable/fs/xfs/xfs_iomap.c

1314 lines
35 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* Copyright (c) 2016-2018 Christoph Hellwig.
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_trans_space.h"
#include "xfs_inode_item.h"
#include "xfs_iomap.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-14 23:14:59 +00:00
#include "xfs_trace.h"
#include "xfs_quota.h"
#include "xfs_dquot_item.h"
#include "xfs_dquot.h"
#include "xfs_reflink.h"
#define XFS_ALLOC_ALIGN(mp, off) \
(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)
static int
xfs_alert_fsblock_zero(
xfs_inode_t *ip,
xfs_bmbt_irec_t *imap)
{
xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
"Access to block zero in inode %llu "
"start_block: %llx start_off: %llx "
"blkcnt: %llx extent-state: %x",
(unsigned long long)ip->i_ino,
(unsigned long long)imap->br_startblock,
(unsigned long long)imap->br_startoff,
(unsigned long long)imap->br_blockcount,
imap->br_state);
return -EFSCORRUPTED;
}
int
xfs_bmbt_to_iomap(
struct xfs_inode *ip,
struct iomap *iomap,
struct xfs_bmbt_irec *imap,
u16 flags)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_buftarg *target = xfs_inode_buftarg(ip);
if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock)))
return xfs_alert_fsblock_zero(ip, imap);
if (imap->br_startblock == HOLESTARTBLOCK) {
iomap->addr = IOMAP_NULL_ADDR;
iomap->type = IOMAP_HOLE;
} else if (imap->br_startblock == DELAYSTARTBLOCK ||
isnullstartblock(imap->br_startblock)) {
iomap->addr = IOMAP_NULL_ADDR;
iomap->type = IOMAP_DELALLOC;
} else {
iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
if (imap->br_state == XFS_EXT_UNWRITTEN)
iomap->type = IOMAP_UNWRITTEN;
else
iomap->type = IOMAP_MAPPED;
}
iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
iomap->bdev = target->bt_bdev;
iomap->dax_dev = target->bt_daxdev;
iomap->flags = flags;
if (xfs_ipincount(ip) &&
(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
iomap->flags |= IOMAP_F_DIRTY;
return 0;
}
static void
xfs_hole_to_iomap(
struct xfs_inode *ip,
struct iomap *iomap,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb)
{
struct xfs_buftarg *target = xfs_inode_buftarg(ip);
iomap->addr = IOMAP_NULL_ADDR;
iomap->type = IOMAP_HOLE;
iomap->offset = XFS_FSB_TO_B(ip->i_mount, offset_fsb);
iomap->length = XFS_FSB_TO_B(ip->i_mount, end_fsb - offset_fsb);
iomap->bdev = target->bt_bdev;
iomap->dax_dev = target->bt_daxdev;
}
static inline xfs_fileoff_t
xfs_iomap_end_fsb(
struct xfs_mount *mp,
loff_t offset,
loff_t count)
{
ASSERT(offset <= mp->m_super->s_maxbytes);
return min(XFS_B_TO_FSB(mp, offset + count),
XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes));
}
static xfs_extlen_t
xfs_eof_alignment(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
xfs_extlen_t align = 0;
if (!XFS_IS_REALTIME_INODE(ip)) {
/*
* Round up the allocation request to a stripe unit
* (m_dalign) boundary if the file size is >= stripe unit
* size, and we are allocating past the allocation eof.
*
* If mounted with the "-o swalloc" option the alignment is
* increased from the strip unit size to the stripe width.
*/
if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
align = mp->m_swidth;
else if (mp->m_dalign)
align = mp->m_dalign;
if (align && XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, align))
align = 0;
}
return align;
}
/*
* Check if last_fsb is outside the last extent, and if so grow it to the next
* stripe unit boundary.
*/
xfs_fileoff_t
xfs_iomap_eof_align_last_fsb(
struct xfs_inode *ip,
xfs_fileoff_t end_fsb)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
xfs_extlen_t extsz = xfs_get_extsz_hint(ip);
xfs_extlen_t align = xfs_eof_alignment(ip);
struct xfs_bmbt_irec irec;
struct xfs_iext_cursor icur;
ASSERT(!xfs_need_iread_extents(ifp));
/*
* Always round up the allocation request to the extent hint boundary.
*/
if (extsz) {
if (align)
align = roundup_64(align, extsz);
else
align = extsz;
}
if (align) {
xfs_fileoff_t aligned_end_fsb = roundup_64(end_fsb, align);
xfs_iext_last(ifp, &icur);
if (!xfs_iext_get_extent(ifp, &icur, &irec) ||
aligned_end_fsb >= irec.br_startoff + irec.br_blockcount)
return aligned_end_fsb;
}
return end_fsb;
}
int
xfs_iomap_write_direct(
struct xfs_inode *ip,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t count_fsb,
struct xfs_bmbt_irec *imap)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
xfs_filblks_t resaligned;
int nimaps;
unsigned int dblocks, rblocks;
bool force = false;
int error;
int bmapi_flags = XFS_BMAPI_PREALLOC;
int nr_exts = XFS_IEXT_ADD_NOSPLIT_CNT;
ASSERT(count_fsb > 0);
resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb,
xfs_get_extsz_hint(ip));
if (unlikely(XFS_IS_REALTIME_INODE(ip))) {
dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
rblocks = resaligned;
} else {
dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
rblocks = 0;
}
error = xfs_qm_dqattach(ip);
xfs: add missing ilock around dio write last extent alignment The iomap codepath (via get_blocks()) acquires and release the inode lock in the case of a direct write that requires block allocation. This is because xfs_iomap_write_direct() allocates a transaction, which means the ilock must be dropped and reacquired after the transaction is allocated and reserved. xfs_iomap_write_direct() invokes xfs_iomap_eof_align_last_fsb() before the transaction is created and thus before the ilock is reacquired. This can lead to calls to xfs_iread_extents() and reads of the in-core extent list without any synchronization (via xfs_bmap_eof() and xfs_bmap_last_extent()). xfs_iread_extents() assert fails if the ilock is not held, but this is not currently seen in practice as the current callers had already invoked xfs_bmapi_read(). What has been seen in practice are reports of crashes down in the xfs_bmap_eof() codepath on direct writes due to seemingly bogus pointer references from xfs_iext_get_ext(). While an explicit reproducer is not currently available to confirm the cause of the problem, crash analysis and code inspection from David Jeffrey had identified the insufficient locking. xfs_iomap_eof_align_last_fsb() is called from other contexts with the inode lock already held, so we cannot acquire it therein. __xfs_get_blocks() acquires and drops the ilock with variable flags to cover the event that the extent list must be read in. The common case is that __xfs_get_blocks() acquires the shared ilock. To provide locking around the last extent alignment call without adding more lock cycles to the dio path, update xfs_iomap_write_direct() to expect the shared ilock held on entry and do the extent alignment under its protection. Demote the lock, if necessary, from __xfs_get_blocks() and push the xfs_qm_dqattach() call outside of the shared lock critical section. Also, add an assert to document that the extent list is always expected to be present in this path. Otherwise, we risk a call to xfs_iread_extents() while under the shared ilock. This is safe as all current callers have executed an xfs_bmapi_read() call under the current iolock context. Reported-by: David Jeffery <djeffery@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-10-12 04:34:20 +00:00
if (error)
return error;
xfs: Don't use unwritten extents for DAX DAX has a page fault serialisation problem with block allocation. Because it allows concurrent page faults and does not have a page lock to serialise faults to the same page, it can get two concurrent faults to the page that race. When two read faults race, this isn't a huge problem as the data underlying the page is not changing and so "detect and drop" works just fine. The issues are to do with write faults. When two write faults occur, we serialise block allocation in get_blocks() so only one faul will allocate the extent. It will, however, be marked as an unwritten extent, and that is where the problem lies - the DAX fault code cannot differentiate between a block that was just allocated and a block that was preallocated and needs zeroing. The result is that both write faults end up zeroing the block and attempting to convert it back to written. The problem is that the first fault can zero and convert before the second fault starts zeroing, resulting in the zeroing for the second fault overwriting the data that the first fault wrote with zeros. The second fault then attempts to convert the unwritten extent, which is then a no-op because it's already written. Data loss occurs as a result of this race. Because there is no sane locking construct in the page fault code that we can use for serialisation across the page faults, we need to ensure block allocation and zeroing occurs atomically in the filesystem. This means we can still take concurrent page faults and the only time they will serialise is in the filesystem mapping/allocation callback. The page fault code will always see written, initialised extents, so we will be able to remove the unwritten extent handling from the DAX code when all filesystems are converted. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-03 01:37:00 +00:00
/*
* For DAX, we do not allocate unwritten extents, but instead we zero
* the block before we commit the transaction. Ideally we'd like to do
* this outside the transaction context, but if we commit and then crash
* we may not have zeroed the blocks and this will be exposed on
* recovery of the allocation. Hence we must zero before commit.
*
xfs: Don't use unwritten extents for DAX DAX has a page fault serialisation problem with block allocation. Because it allows concurrent page faults and does not have a page lock to serialise faults to the same page, it can get two concurrent faults to the page that race. When two read faults race, this isn't a huge problem as the data underlying the page is not changing and so "detect and drop" works just fine. The issues are to do with write faults. When two write faults occur, we serialise block allocation in get_blocks() so only one faul will allocate the extent. It will, however, be marked as an unwritten extent, and that is where the problem lies - the DAX fault code cannot differentiate between a block that was just allocated and a block that was preallocated and needs zeroing. The result is that both write faults end up zeroing the block and attempting to convert it back to written. The problem is that the first fault can zero and convert before the second fault starts zeroing, resulting in the zeroing for the second fault overwriting the data that the first fault wrote with zeros. The second fault then attempts to convert the unwritten extent, which is then a no-op because it's already written. Data loss occurs as a result of this race. Because there is no sane locking construct in the page fault code that we can use for serialisation across the page faults, we need to ensure block allocation and zeroing occurs atomically in the filesystem. This means we can still take concurrent page faults and the only time they will serialise is in the filesystem mapping/allocation callback. The page fault code will always see written, initialised extents, so we will be able to remove the unwritten extent handling from the DAX code when all filesystems are converted. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-03 01:37:00 +00:00
* Further, if we are mapping unwritten extents here, we need to zero
* and convert them to written so that we don't need an unwritten extent
* callback for DAX. This also means that we need to be able to dip into
* the reserve block pool for bmbt block allocation if there is no space
* left but we need to do unwritten extent conversion.
xfs: Don't use unwritten extents for DAX DAX has a page fault serialisation problem with block allocation. Because it allows concurrent page faults and does not have a page lock to serialise faults to the same page, it can get two concurrent faults to the page that race. When two read faults race, this isn't a huge problem as the data underlying the page is not changing and so "detect and drop" works just fine. The issues are to do with write faults. When two write faults occur, we serialise block allocation in get_blocks() so only one faul will allocate the extent. It will, however, be marked as an unwritten extent, and that is where the problem lies - the DAX fault code cannot differentiate between a block that was just allocated and a block that was preallocated and needs zeroing. The result is that both write faults end up zeroing the block and attempting to convert it back to written. The problem is that the first fault can zero and convert before the second fault starts zeroing, resulting in the zeroing for the second fault overwriting the data that the first fault wrote with zeros. The second fault then attempts to convert the unwritten extent, which is then a no-op because it's already written. Data loss occurs as a result of this race. Because there is no sane locking construct in the page fault code that we can use for serialisation across the page faults, we need to ensure block allocation and zeroing occurs atomically in the filesystem. This means we can still take concurrent page faults and the only time they will serialise is in the filesystem mapping/allocation callback. The page fault code will always see written, initialised extents, so we will be able to remove the unwritten extent handling from the DAX code when all filesystems are converted. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-03 01:37:00 +00:00
*/
if (IS_DAX(VFS_I(ip))) {
bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
if (imap->br_state == XFS_EXT_UNWRITTEN) {
force = true;
nr_exts = XFS_IEXT_WRITE_UNWRITTEN_CNT;
dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
}
xfs: Don't use unwritten extents for DAX DAX has a page fault serialisation problem with block allocation. Because it allows concurrent page faults and does not have a page lock to serialise faults to the same page, it can get two concurrent faults to the page that race. When two read faults race, this isn't a huge problem as the data underlying the page is not changing and so "detect and drop" works just fine. The issues are to do with write faults. When two write faults occur, we serialise block allocation in get_blocks() so only one faul will allocate the extent. It will, however, be marked as an unwritten extent, and that is where the problem lies - the DAX fault code cannot differentiate between a block that was just allocated and a block that was preallocated and needs zeroing. The result is that both write faults end up zeroing the block and attempting to convert it back to written. The problem is that the first fault can zero and convert before the second fault starts zeroing, resulting in the zeroing for the second fault overwriting the data that the first fault wrote with zeros. The second fault then attempts to convert the unwritten extent, which is then a no-op because it's already written. Data loss occurs as a result of this race. Because there is no sane locking construct in the page fault code that we can use for serialisation across the page faults, we need to ensure block allocation and zeroing occurs atomically in the filesystem. This means we can still take concurrent page faults and the only time they will serialise is in the filesystem mapping/allocation callback. The page fault code will always see written, initialised extents, so we will be able to remove the unwritten extent handling from the DAX code when all filesystems are converted. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-03 01:37:00 +00:00
}
error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks,
rblocks, force, &tp);
if (error)
return error;
error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, nr_exts);
if (error)
goto out_trans_cancel;
/*
* From this point onwards we overwrite the imap pointer that the
* caller gave to us.
*/
nimaps = 1;
xfs: don't set bmapi total block req where minleft is xfs_bmapi_write() takes a total block requirement parameter that is passed down to the block allocation code and is used to specify the total block requirement of the associated transaction. This is used to try and select an AG that can not only satisfy the requested extent allocation, but can also accommodate subsequent allocations that might be required to complete the transaction. For example, additional bmbt block allocations may be required on insertion of the resulting extent to an inode data fork. While it's important for callers to calculate and reserve such extra blocks in the transaction, it is not necessary to pass the total value to xfs_bmapi_write() in all cases. The latter automatically sets minleft to ensure that sufficient free blocks remain after the allocation attempt to expand the format of the associated inode (i.e., such as extent to btree conversion, btree splits, etc). Therefore, any callers that pass a total block requirement of the bmap mapping length plus worst case bmbt expansion essentially specify the additional reservation requirement twice. These callers can pass a total of zero to rely on the bmapi minleft policy. Beyond being superfluous, the primary motivation for this change is that the total reservation logic in the bmbt code is dubious in scenarios where minlen < maxlen and a maxlen extent cannot be allocated (which is more common for data extent allocations where contiguity is not required). The total value is based on maxlen in the xfs_bmapi_write() caller. If the bmbt code falls back to an allocation between minlen and maxlen, that allocation will not succeed until total is reset to minlen, which essentially throws away any additional reservation included in total by the caller. In addition, the total value is not reset until after alignment is dropped, which means that such callers drop alignment far too aggressively than necessary. Update all callers of xfs_bmapi_write() that pass a total block value of the mapping length plus bmbt reservation to instead pass zero and rely on xfs_bmapi_minleft() to enforce the bmbt reservation requirement. This trades off slightly less conservative AG selection for the ability to preserve alignment in more scenarios. xfs_bmapi_write() callers that incorporate unrelated or additional reservations in total beyond what is already included in minleft must continue to use the former. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-10-21 16:26:48 +00:00
error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flags, 0,
imap, &nimaps);
if (error)
goto out_trans_cancel;
/*
* Complete the transaction
*/
error = xfs_trans_commit(tp);
if (error)
goto out_unlock;
/*
* Copy any maps to caller's array and return any error.
*/
if (nimaps == 0) {
error = -ENOSPC;
goto out_unlock;
}
if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock)))
error = xfs_alert_fsblock_zero(ip, imap);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
goto out_unlock;
}
STATIC bool
xfs_quota_need_throttle(
struct xfs_inode *ip,
xfs_dqtype_t type,
xfs_fsblock_t alloc_blocks)
{
struct xfs_dquot *dq = xfs_inode_dquot(ip, type);
if (!dq || !xfs_this_quota_on(ip->i_mount, type))
return false;
/* no hi watermark, no throttle */
if (!dq->q_prealloc_hi_wmark)
return false;
/* under the lo watermark, no throttle */
if (dq->q_blk.reserved + alloc_blocks < dq->q_prealloc_lo_wmark)
return false;
return true;
}
STATIC void
xfs_quota_calc_throttle(
struct xfs_inode *ip,
xfs_dqtype_t type,
xfs_fsblock_t *qblocks,
int *qshift,
int64_t *qfreesp)
{
struct xfs_dquot *dq = xfs_inode_dquot(ip, type);
int64_t freesp;
int shift = 0;
/* no dq, or over hi wmark, squash the prealloc completely */
if (!dq || dq->q_blk.reserved >= dq->q_prealloc_hi_wmark) {
*qblocks = 0;
*qfreesp = 0;
return;
}
freesp = dq->q_prealloc_hi_wmark - dq->q_blk.reserved;
if (freesp < dq->q_low_space[XFS_QLOWSP_5_PCNT]) {
shift = 2;
if (freesp < dq->q_low_space[XFS_QLOWSP_3_PCNT])
shift += 2;
if (freesp < dq->q_low_space[XFS_QLOWSP_1_PCNT])
shift += 2;
}
if (freesp < *qfreesp)
*qfreesp = freesp;
/* only overwrite the throttle values if we are more aggressive */
if ((freesp >> shift) < (*qblocks >> *qshift)) {
*qblocks = freesp;
*qshift = shift;
}
}
xfs: dynamic speculative EOF preallocation Currently the size of the speculative preallocation during delayed allocation is fixed by either the allocsize mount option of a default size. We are seeing a lot of cases where we need to recommend using the allocsize mount option to prevent fragmentation when buffered writes land in the same AG. Rather than using a fixed preallocation size by default (up to 64k), make it dynamic by basing it on the current inode size. That way the EOF preallocation will increase as the file size increases. Hence for streaming writes we are much more likely to get large preallocations exactly when we need it to reduce fragementation. For default settings, the size of the initial extents is determined by the number of parallel writers and the amount of memory in the machine. For 4GB RAM and 4 concurrent 32GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576 1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576 2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152 3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304 4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608 5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208 6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088 7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088 and for 16 concurrent 16GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144 1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144 2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288 3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576 4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152 5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304 6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608 7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208 Because it is hard to take back specualtive preallocation, cases where there are large slow growing log files on a nearly full filesystem may cause premature ENOSPC. Hence as the filesystem nears full, the maximum dynamic prealloc size іs reduced according to this table (based on 4k block size): freespace max prealloc size >5% full extent (8GB) 4-5% 2GB (8GB >> 2) 3-4% 1GB (8GB >> 3) 2-3% 512MB (8GB >> 4) 1-2% 256MB (8GB >> 5) <1% 128MB (8GB >> 6) This should reduce the amount of space held in speculative preallocation for such cases. The allocsize mount option turns off the dynamic behaviour and fixes the prealloc size to whatever the mount option specifies. i.e. the behaviour is unchanged. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2011-01-04 00:35:03 +00:00
/*
* If we don't have a user specified preallocation size, dynamically increase
* the preallocation size as the size of the file grows. Cap the maximum size
xfs: dynamic speculative EOF preallocation Currently the size of the speculative preallocation during delayed allocation is fixed by either the allocsize mount option of a default size. We are seeing a lot of cases where we need to recommend using the allocsize mount option to prevent fragmentation when buffered writes land in the same AG. Rather than using a fixed preallocation size by default (up to 64k), make it dynamic by basing it on the current inode size. That way the EOF preallocation will increase as the file size increases. Hence for streaming writes we are much more likely to get large preallocations exactly when we need it to reduce fragementation. For default settings, the size of the initial extents is determined by the number of parallel writers and the amount of memory in the machine. For 4GB RAM and 4 concurrent 32GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576 1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576 2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152 3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304 4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608 5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208 6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088 7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088 and for 16 concurrent 16GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144 1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144 2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288 3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576 4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152 5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304 6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608 7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208 Because it is hard to take back specualtive preallocation, cases where there are large slow growing log files on a nearly full filesystem may cause premature ENOSPC. Hence as the filesystem nears full, the maximum dynamic prealloc size іs reduced according to this table (based on 4k block size): freespace max prealloc size >5% full extent (8GB) 4-5% 2GB (8GB >> 2) 3-4% 1GB (8GB >> 3) 2-3% 512MB (8GB >> 4) 1-2% 256MB (8GB >> 5) <1% 128MB (8GB >> 6) This should reduce the amount of space held in speculative preallocation for such cases. The allocsize mount option turns off the dynamic behaviour and fixes the prealloc size to whatever the mount option specifies. i.e. the behaviour is unchanged. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2011-01-04 00:35:03 +00:00
* at a single extent or less if the filesystem is near full. The closer the
* filesystem is to being full, the smaller the maximum preallocation.
xfs: dynamic speculative EOF preallocation Currently the size of the speculative preallocation during delayed allocation is fixed by either the allocsize mount option of a default size. We are seeing a lot of cases where we need to recommend using the allocsize mount option to prevent fragmentation when buffered writes land in the same AG. Rather than using a fixed preallocation size by default (up to 64k), make it dynamic by basing it on the current inode size. That way the EOF preallocation will increase as the file size increases. Hence for streaming writes we are much more likely to get large preallocations exactly when we need it to reduce fragementation. For default settings, the size of the initial extents is determined by the number of parallel writers and the amount of memory in the machine. For 4GB RAM and 4 concurrent 32GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576 1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576 2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152 3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304 4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608 5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208 6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088 7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088 and for 16 concurrent 16GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144 1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144 2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288 3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576 4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152 5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304 6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608 7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208 Because it is hard to take back specualtive preallocation, cases where there are large slow growing log files on a nearly full filesystem may cause premature ENOSPC. Hence as the filesystem nears full, the maximum dynamic prealloc size іs reduced according to this table (based on 4k block size): freespace max prealloc size >5% full extent (8GB) 4-5% 2GB (8GB >> 2) 3-4% 1GB (8GB >> 3) 2-3% 512MB (8GB >> 4) 1-2% 256MB (8GB >> 5) <1% 128MB (8GB >> 6) This should reduce the amount of space held in speculative preallocation for such cases. The allocsize mount option turns off the dynamic behaviour and fixes the prealloc size to whatever the mount option specifies. i.e. the behaviour is unchanged. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2011-01-04 00:35:03 +00:00
*/
STATIC xfs_fsblock_t
xfs_iomap_prealloc_size(
xfs: limit speculative prealloc size on sparse files Speculative preallocation based on the current file size works well for contiguous files, but is sub-optimal for sparse files where the EOF preallocation can fill holes and result in large amounts of zeros being written when it is not necessary. The algorithm is modified to prevent EOF speculative preallocation from triggering larger allocations on IO patterns of truncate--to-zero-seek-write-seek-write-.... which results in non-sparse files for large files. This, unfortunately, is the way cp now behaves when copying sparse files and so needs to be fixed. What this code does is that it looks at the existing extent adjacent to the current EOF and if it determines that it is a hole we disable speculative preallocation altogether. To avoid the next write from doing a large prealloc, it takes the size of subsequent preallocations from the current size of the existing EOF extent. IOWs, if you leave a hole in the file, it resets preallocation behaviour to the same as if it was a zero size file. Example new behaviour: $ xfs_io -f -c "pwrite 0 31m" \ -c "pwrite 33m 1m" \ -c "pwrite 128m 1m" \ -c "fiemap -v" /mnt/scratch/blah wrote 32505856/32505856 bytes at offset 0 31 MiB, 7936 ops; 0.0000 sec (1.608 GiB/sec and 421432.7439 ops/sec) wrote 1048576/1048576 bytes at offset 34603008 1 MiB, 256 ops; 0.0000 sec (1.462 GiB/sec and 383233.5329 ops/sec) wrote 1048576/1048576 bytes at offset 134217728 1 MiB, 256 ops; 0.0000 sec (1.719 GiB/sec and 450704.2254 ops/sec) /mnt/scratch/blah: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..65535]: 96..65631 65536 0x0 1: [65536..67583]: hole 2048 2: [67584..69631]: 67680..69727 2048 0x0 3: [69632..262143]: hole 192512 4: [262144..264191]: 262240..264287 2048 0x1 Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-02-11 05:05:01 +00:00
struct xfs_inode *ip,
xfs: introduce an always_cow mode Add a mode where XFS never overwrites existing blocks in place. This is to aid debugging our COW code, and also put infatructure in place for things like possible future support for zoned block devices, which can't support overwrites. This mode is enabled globally by doing a: echo 1 > /sys/fs/xfs/debug/always_cow Note that the parameter is global to allow running all tests in xfstests easily in this mode, which would not easily be possible with a per-fs sysfs file. In always_cow mode persistent preallocations are disabled, and fallocate will fail when called with a 0 mode (with our without FALLOC_FL_KEEP_SIZE), and not create unwritten extent for zeroed space when called with FALLOC_FL_ZERO_RANGE or FALLOC_FL_UNSHARE_RANGE. There are a few interesting xfstests failures when run in always_cow mode: - generic/392 fails because the bytes used in the file used to test hole punch recovery are less after the log replay. This is because the blocks written and then punched out are only freed with a delay due to the logging mechanism. - xfs/170 will fail as the already fragile file streams mechanism doesn't seem to interact well with the COW allocator - xfs/180 xfs/182 xfs/192 xfs/198 xfs/204 and xfs/208 will claim the file system is badly fragmented, but there is not much we can do to avoid that when always writing out of place - xfs/205 fails because overwriting a file in always_cow mode will require new space allocation and the assumption in the test thus don't work anymore. - xfs/326 fails to modify the file at all in always_cow mode after injecting the refcount error, leading to an unexpected md5sum after the remount, but that again is expected Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-02-18 17:38:49 +00:00
int whichfork,
loff_t offset,
loff_t count,
struct xfs_iext_cursor *icur)
xfs: dynamic speculative EOF preallocation Currently the size of the speculative preallocation during delayed allocation is fixed by either the allocsize mount option of a default size. We are seeing a lot of cases where we need to recommend using the allocsize mount option to prevent fragmentation when buffered writes land in the same AG. Rather than using a fixed preallocation size by default (up to 64k), make it dynamic by basing it on the current inode size. That way the EOF preallocation will increase as the file size increases. Hence for streaming writes we are much more likely to get large preallocations exactly when we need it to reduce fragementation. For default settings, the size of the initial extents is determined by the number of parallel writers and the amount of memory in the machine. For 4GB RAM and 4 concurrent 32GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576 1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576 2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152 3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304 4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608 5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208 6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088 7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088 and for 16 concurrent 16GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144 1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144 2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288 3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576 4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152 5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304 6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608 7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208 Because it is hard to take back specualtive preallocation, cases where there are large slow growing log files on a nearly full filesystem may cause premature ENOSPC. Hence as the filesystem nears full, the maximum dynamic prealloc size іs reduced according to this table (based on 4k block size): freespace max prealloc size >5% full extent (8GB) 4-5% 2GB (8GB >> 2) 3-4% 1GB (8GB >> 3) 2-3% 512MB (8GB >> 4) 1-2% 256MB (8GB >> 5) <1% 128MB (8GB >> 6) This should reduce the amount of space held in speculative preallocation for such cases. The allocsize mount option turns off the dynamic behaviour and fixes the prealloc size to whatever the mount option specifies. i.e. the behaviour is unchanged. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2011-01-04 00:35:03 +00:00
{
struct xfs_iext_cursor ncur = *icur;
struct xfs_bmbt_irec prev, got;
struct xfs_mount *mp = ip->i_mount;
xfs: introduce an always_cow mode Add a mode where XFS never overwrites existing blocks in place. This is to aid debugging our COW code, and also put infatructure in place for things like possible future support for zoned block devices, which can't support overwrites. This mode is enabled globally by doing a: echo 1 > /sys/fs/xfs/debug/always_cow Note that the parameter is global to allow running all tests in xfstests easily in this mode, which would not easily be possible with a per-fs sysfs file. In always_cow mode persistent preallocations are disabled, and fallocate will fail when called with a 0 mode (with our without FALLOC_FL_KEEP_SIZE), and not create unwritten extent for zeroed space when called with FALLOC_FL_ZERO_RANGE or FALLOC_FL_UNSHARE_RANGE. There are a few interesting xfstests failures when run in always_cow mode: - generic/392 fails because the bytes used in the file used to test hole punch recovery are less after the log replay. This is because the blocks written and then punched out are only freed with a delay due to the logging mechanism. - xfs/170 will fail as the already fragile file streams mechanism doesn't seem to interact well with the COW allocator - xfs/180 xfs/182 xfs/192 xfs/198 xfs/204 and xfs/208 will claim the file system is badly fragmented, but there is not much we can do to avoid that when always writing out of place - xfs/205 fails because overwriting a file in always_cow mode will require new space allocation and the assumption in the test thus don't work anymore. - xfs/326 fails to modify the file at all in always_cow mode after injecting the refcount error, leading to an unexpected md5sum after the remount, but that again is expected Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-02-18 17:38:49 +00:00
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
int64_t freesp;
xfs_fsblock_t qblocks;
xfs_fsblock_t alloc_blocks = 0;
xfs_extlen_t plen;
int shift = 0;
int qshift = 0;
/*
* As an exception we don't do any preallocation at all if the file is
* smaller than the minimum preallocation and we are using the default
* dynamic preallocation scheme, as it is likely this is the only write
* to the file that is going to be done.
*/
if (XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_allocsize_blocks))
return 0;
/*
* Use the minimum preallocation size for small files or if we are
* writing right after a hole.
*/
if (XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_dalign) ||
!xfs_iext_prev_extent(ifp, &ncur, &prev) ||
prev.br_startoff + prev.br_blockcount < offset_fsb)
return mp->m_allocsize_blocks;
xfs: dynamic speculative EOF preallocation Currently the size of the speculative preallocation during delayed allocation is fixed by either the allocsize mount option of a default size. We are seeing a lot of cases where we need to recommend using the allocsize mount option to prevent fragmentation when buffered writes land in the same AG. Rather than using a fixed preallocation size by default (up to 64k), make it dynamic by basing it on the current inode size. That way the EOF preallocation will increase as the file size increases. Hence for streaming writes we are much more likely to get large preallocations exactly when we need it to reduce fragementation. For default settings, the size of the initial extents is determined by the number of parallel writers and the amount of memory in the machine. For 4GB RAM and 4 concurrent 32GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576 1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576 2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152 3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304 4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608 5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208 6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088 7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088 and for 16 concurrent 16GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144 1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144 2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288 3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576 4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152 5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304 6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608 7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208 Because it is hard to take back specualtive preallocation, cases where there are large slow growing log files on a nearly full filesystem may cause premature ENOSPC. Hence as the filesystem nears full, the maximum dynamic prealloc size іs reduced according to this table (based on 4k block size): freespace max prealloc size >5% full extent (8GB) 4-5% 2GB (8GB >> 2) 3-4% 1GB (8GB >> 3) 2-3% 512MB (8GB >> 4) 1-2% 256MB (8GB >> 5) <1% 128MB (8GB >> 6) This should reduce the amount of space held in speculative preallocation for such cases. The allocsize mount option turns off the dynamic behaviour and fixes the prealloc size to whatever the mount option specifies. i.e. the behaviour is unchanged. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2011-01-04 00:35:03 +00:00
/*
* Take the size of the preceding data extents as the basis for the
* preallocation size. Note that we don't care if the previous extents
* are written or not.
*/
plen = prev.br_blockcount;
while (xfs_iext_prev_extent(ifp, &ncur, &got)) {
if (plen > MAXEXTLEN / 2 ||
isnullstartblock(got.br_startblock) ||
got.br_startoff + got.br_blockcount != prev.br_startoff ||
got.br_startblock + got.br_blockcount != prev.br_startblock)
break;
plen += got.br_blockcount;
prev = got;
}
/*
* If the size of the extents is greater than half the maximum extent
* length, then use the current offset as the basis. This ensures that
* for large files the preallocation size always extends to MAXEXTLEN
* rather than falling short due to things like stripe unit/width
* alignment of real extents.
*/
alloc_blocks = plen * 2;
if (alloc_blocks > MAXEXTLEN)
alloc_blocks = XFS_B_TO_FSB(mp, offset);
qblocks = alloc_blocks;
/*
* MAXEXTLEN is not a power of two value but we round the prealloc down
* to the nearest power of two value after throttling. To prevent the
* round down from unconditionally reducing the maximum supported
* prealloc size, we round up first, apply appropriate throttling,
* round down and cap the value to MAXEXTLEN.
*/
alloc_blocks = XFS_FILEOFF_MIN(roundup_pow_of_two(MAXEXTLEN),
alloc_blocks);
freesp = percpu_counter_read_positive(&mp->m_fdblocks);
if (freesp < mp->m_low_space[XFS_LOWSP_5_PCNT]) {
shift = 2;
if (freesp < mp->m_low_space[XFS_LOWSP_4_PCNT])
shift++;
if (freesp < mp->m_low_space[XFS_LOWSP_3_PCNT])
shift++;
if (freesp < mp->m_low_space[XFS_LOWSP_2_PCNT])
shift++;
if (freesp < mp->m_low_space[XFS_LOWSP_1_PCNT])
shift++;
xfs: dynamic speculative EOF preallocation Currently the size of the speculative preallocation during delayed allocation is fixed by either the allocsize mount option of a default size. We are seeing a lot of cases where we need to recommend using the allocsize mount option to prevent fragmentation when buffered writes land in the same AG. Rather than using a fixed preallocation size by default (up to 64k), make it dynamic by basing it on the current inode size. That way the EOF preallocation will increase as the file size increases. Hence for streaming writes we are much more likely to get large preallocations exactly when we need it to reduce fragementation. For default settings, the size of the initial extents is determined by the number of parallel writers and the amount of memory in the machine. For 4GB RAM and 4 concurrent 32GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576 1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576 2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152 3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304 4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608 5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208 6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088 7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088 and for 16 concurrent 16GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144 1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144 2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288 3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576 4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152 5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304 6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608 7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208 Because it is hard to take back specualtive preallocation, cases where there are large slow growing log files on a nearly full filesystem may cause premature ENOSPC. Hence as the filesystem nears full, the maximum dynamic prealloc size іs reduced according to this table (based on 4k block size): freespace max prealloc size >5% full extent (8GB) 4-5% 2GB (8GB >> 2) 3-4% 1GB (8GB >> 3) 2-3% 512MB (8GB >> 4) 1-2% 256MB (8GB >> 5) <1% 128MB (8GB >> 6) This should reduce the amount of space held in speculative preallocation for such cases. The allocsize mount option turns off the dynamic behaviour and fixes the prealloc size to whatever the mount option specifies. i.e. the behaviour is unchanged. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2011-01-04 00:35:03 +00:00
}
/*
* Check each quota to cap the prealloc size, provide a shift value to
* throttle with and adjust amount of available space.
*/
if (xfs_quota_need_throttle(ip, XFS_DQTYPE_USER, alloc_blocks))
xfs_quota_calc_throttle(ip, XFS_DQTYPE_USER, &qblocks, &qshift,
&freesp);
if (xfs_quota_need_throttle(ip, XFS_DQTYPE_GROUP, alloc_blocks))
xfs_quota_calc_throttle(ip, XFS_DQTYPE_GROUP, &qblocks, &qshift,
&freesp);
if (xfs_quota_need_throttle(ip, XFS_DQTYPE_PROJ, alloc_blocks))
xfs_quota_calc_throttle(ip, XFS_DQTYPE_PROJ, &qblocks, &qshift,
&freesp);
/*
* The final prealloc size is set to the minimum of free space available
* in each of the quotas and the overall filesystem.
*
* The shift throttle value is set to the maximum value as determined by
* the global low free space values and per-quota low free space values.
*/
alloc_blocks = min(alloc_blocks, qblocks);
shift = max(shift, qshift);
if (shift)
alloc_blocks >>= shift;
/*
* rounddown_pow_of_two() returns an undefined result if we pass in
* alloc_blocks = 0.
*/
if (alloc_blocks)
alloc_blocks = rounddown_pow_of_two(alloc_blocks);
if (alloc_blocks > MAXEXTLEN)
alloc_blocks = MAXEXTLEN;
/*
* If we are still trying to allocate more space than is
* available, squash the prealloc hard. This can happen if we
* have a large file on a small filesystem and the above
* lowspace thresholds are smaller than MAXEXTLEN.
*/
while (alloc_blocks && alloc_blocks >= freesp)
alloc_blocks >>= 4;
if (alloc_blocks < mp->m_allocsize_blocks)
alloc_blocks = mp->m_allocsize_blocks;
trace_xfs_iomap_prealloc_size(ip, alloc_blocks, shift,
mp->m_allocsize_blocks);
xfs: dynamic speculative EOF preallocation Currently the size of the speculative preallocation during delayed allocation is fixed by either the allocsize mount option of a default size. We are seeing a lot of cases where we need to recommend using the allocsize mount option to prevent fragmentation when buffered writes land in the same AG. Rather than using a fixed preallocation size by default (up to 64k), make it dynamic by basing it on the current inode size. That way the EOF preallocation will increase as the file size increases. Hence for streaming writes we are much more likely to get large preallocations exactly when we need it to reduce fragementation. For default settings, the size of the initial extents is determined by the number of parallel writers and the amount of memory in the machine. For 4GB RAM and 4 concurrent 32GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576 1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576 2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152 3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304 4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608 5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208 6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088 7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088 and for 16 concurrent 16GB file writes: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL 0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144 1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144 2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288 3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576 4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152 5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304 6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608 7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208 Because it is hard to take back specualtive preallocation, cases where there are large slow growing log files on a nearly full filesystem may cause premature ENOSPC. Hence as the filesystem nears full, the maximum dynamic prealloc size іs reduced according to this table (based on 4k block size): freespace max prealloc size >5% full extent (8GB) 4-5% 2GB (8GB >> 2) 3-4% 1GB (8GB >> 3) 2-3% 512MB (8GB >> 4) 1-2% 256MB (8GB >> 5) <1% 128MB (8GB >> 6) This should reduce the amount of space held in speculative preallocation for such cases. The allocsize mount option turns off the dynamic behaviour and fixes the prealloc size to whatever the mount option specifies. i.e. the behaviour is unchanged. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2011-01-04 00:35:03 +00:00
return alloc_blocks;
}
int
xfs_iomap_write_unwritten(
xfs_inode_t *ip,
xfs_off_t offset,
xfs_off_t count,
bool update_isize)
{
xfs_mount_t *mp = ip->i_mount;
xfs_fileoff_t offset_fsb;
xfs_filblks_t count_fsb;
xfs_filblks_t numblks_fsb;
int nimaps;
xfs_trans_t *tp;
xfs_bmbt_irec_t imap;
struct inode *inode = VFS_I(ip);
xfs_fsize_t i_size;
uint resblks;
int error;
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-14 23:14:59 +00:00
trace_xfs_unwritten_convert(ip, offset, count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
count_fsb = (xfs_filblks_t)(count_fsb - offset_fsb);
/*
* Reserve enough blocks in this transaction for two complete extent
* btree splits. We may be converting the middle part of an unwritten
* extent and in this case we will insert two new extents in the btree
* each of which could cause a full split.
*
* This reservation amount will be used in the first call to
* xfs_bmbt_split() to select an AG with enough space to satisfy the
* rest of the operation.
*/
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
/* Attach dquots so that bmbt splits are accounted correctly. */
error = xfs_qm_dqattach(ip);
if (error)
return error;
do {
/*
* Set up a transaction to convert the range of extents
* from unwritten to real. Do allocations in a loop until
* we have covered the range passed in.
*
* Note that we can't risk to recursing back into the filesystem
* here as we might be asked to write out the same inode that we
* complete here and might deadlock on the iolock.
*/
error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks,
0, true, &tp);
if (error)
return error;
error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
XFS_IEXT_WRITE_UNWRITTEN_CNT);
if (error)
goto error_on_bmapi_transaction;
/*
* Modify the unwritten extent state of the buffer.
*/
nimaps = 1;
error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
XFS_BMAPI_CONVERT, resblks, &imap,
&nimaps);
if (error)
goto error_on_bmapi_transaction;
/*
* Log the updated inode size as we go. We have to be careful
* to only log it up to the actual write offset if it is
* halfway into a block.
*/
i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb);
if (i_size > offset + count)
i_size = offset + count;
if (update_isize && i_size > i_size_read(inode))
i_size_write(inode, i_size);
i_size = xfs_new_eof(ip, i_size);
if (i_size) {
ip->i_disk_size = i_size;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
if (unlikely(!xfs_valid_startblock(ip, imap.br_startblock)))
return xfs_alert_fsblock_zero(ip, &imap);
if ((numblks_fsb = imap.br_blockcount) == 0) {
/*
* The numblks_fsb value should always get
* smaller, otherwise the loop is stuck.
*/
ASSERT(imap.br_blockcount);
break;
}
offset_fsb += numblks_fsb;
count_fsb -= numblks_fsb;
} while (count_fsb > 0);
return 0;
error_on_bmapi_transaction:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
static inline bool
imap_needs_alloc(
struct inode *inode,
unsigned flags,
struct xfs_bmbt_irec *imap,
int nimaps)
{
/* don't allocate blocks when just zeroing */
if (flags & IOMAP_ZERO)
return false;
if (!nimaps ||
imap->br_startblock == HOLESTARTBLOCK ||
imap->br_startblock == DELAYSTARTBLOCK)
return true;
/* we convert unwritten extents before copying the data for DAX */
if (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN)
return true;
return false;
}
static inline bool
imap_needs_cow(
struct xfs_inode *ip,
unsigned int flags,
struct xfs_bmbt_irec *imap,
int nimaps)
{
if (!xfs_is_cow_inode(ip))
return false;
/* when zeroing we don't have to COW holes or unwritten extents */
if (flags & IOMAP_ZERO) {
if (!nimaps ||
imap->br_startblock == HOLESTARTBLOCK ||
imap->br_state == XFS_EXT_UNWRITTEN)
return false;
}
return true;
}
static int
xfs_ilock_for_iomap(
struct xfs_inode *ip,
unsigned flags,
unsigned *lockmode)
{
unsigned mode = XFS_ILOCK_SHARED;
xfs: recheck reflink state after grabbing ILOCK_SHARED for a write The reflink iflag could have changed since the earlier unlocked check, so if we got ILOCK_SHARED for a write and but we're now a reflink inode we have to switch to ILOCK_EXCL and relock. This helps us avoid blowing lock assertions in things like generic/166: XFS: Assertion failed: xfs_isilocked(ip, XFS_ILOCK_EXCL), file: fs/xfs/xfs_reflink.c, line: 383 WARNING: CPU: 1 PID: 24707 at fs/xfs/xfs_message.c:104 assfail+0x25/0x30 [xfs] Modules linked in: deadline_iosched dm_snapshot dm_bufio ext4 mbcache jbd2 dm_flakey xfs libcrc32c dax_pmem device_dax nd_pmem sch_fq_codel af_packet [last unloaded: scsi_debug] CPU: 1 PID: 24707 Comm: xfs_io Not tainted 4.18.0-rc1-djw #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:assfail+0x25/0x30 [xfs] Code: ff 0f 0b c3 90 66 66 66 66 90 48 89 f1 41 89 d0 48 c7 c6 e8 ef 1b a0 48 89 fa 31 ff e8 54 f9 ff ff 80 3d fd ba 0f 00 00 75 03 <0f> 0b c3 0f 0b 66 0f 1f 44 00 00 66 66 66 66 90 48 63 f6 49 89 f9 RSP: 0018:ffffc90006423ad8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880030b65e80 RCX: 0000000000000000 RDX: 00000000ffffffc0 RSI: 000000000000000a RDI: ffffffffa01b0447 RBP: ffffc90006423c10 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88003d43fc30 R11: f000000000000000 R12: ffff880077cda000 R13: 0000000000000000 R14: ffffc90006423c30 R15: ffffc90006423bf9 FS: 00007feba8986800(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000138ab58 CR3: 000000003d40a000 CR4: 00000000000006a0 Call Trace: xfs_reflink_allocate_cow+0x24c/0x3d0 [xfs] xfs_file_iomap_begin+0x6d2/0xeb0 [xfs] ? iomap_to_fiemap+0x80/0x80 iomap_apply+0x5e/0x130 iomap_dio_rw+0x2e0/0x400 ? iomap_to_fiemap+0x80/0x80 ? xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_write_iter+0x7b/0xb0 [xfs] __vfs_write+0x16f/0x1f0 vfs_write+0xc8/0x1c0 ksys_pwrite64+0x74/0x90 do_syscall_64+0x56/0x180 entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2018-06-22 06:26:57 +00:00
bool is_write = flags & (IOMAP_WRITE | IOMAP_ZERO);
/*
* COW writes may allocate delalloc space or convert unwritten COW
* extents, so we need to make sure to take the lock exclusively here.
*/
if (xfs_is_cow_inode(ip) && is_write)
mode = XFS_ILOCK_EXCL;
/*
* Extents not yet cached requires exclusive access, don't block. This
* is an opencoded xfs_ilock_data_map_shared() call but with
* non-blocking behaviour.
*/
if (xfs_need_iread_extents(&ip->i_df)) {
if (flags & IOMAP_NOWAIT)
return -EAGAIN;
mode = XFS_ILOCK_EXCL;
}
xfs: recheck reflink state after grabbing ILOCK_SHARED for a write The reflink iflag could have changed since the earlier unlocked check, so if we got ILOCK_SHARED for a write and but we're now a reflink inode we have to switch to ILOCK_EXCL and relock. This helps us avoid blowing lock assertions in things like generic/166: XFS: Assertion failed: xfs_isilocked(ip, XFS_ILOCK_EXCL), file: fs/xfs/xfs_reflink.c, line: 383 WARNING: CPU: 1 PID: 24707 at fs/xfs/xfs_message.c:104 assfail+0x25/0x30 [xfs] Modules linked in: deadline_iosched dm_snapshot dm_bufio ext4 mbcache jbd2 dm_flakey xfs libcrc32c dax_pmem device_dax nd_pmem sch_fq_codel af_packet [last unloaded: scsi_debug] CPU: 1 PID: 24707 Comm: xfs_io Not tainted 4.18.0-rc1-djw #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:assfail+0x25/0x30 [xfs] Code: ff 0f 0b c3 90 66 66 66 66 90 48 89 f1 41 89 d0 48 c7 c6 e8 ef 1b a0 48 89 fa 31 ff e8 54 f9 ff ff 80 3d fd ba 0f 00 00 75 03 <0f> 0b c3 0f 0b 66 0f 1f 44 00 00 66 66 66 66 90 48 63 f6 49 89 f9 RSP: 0018:ffffc90006423ad8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880030b65e80 RCX: 0000000000000000 RDX: 00000000ffffffc0 RSI: 000000000000000a RDI: ffffffffa01b0447 RBP: ffffc90006423c10 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88003d43fc30 R11: f000000000000000 R12: ffff880077cda000 R13: 0000000000000000 R14: ffffc90006423c30 R15: ffffc90006423bf9 FS: 00007feba8986800(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000138ab58 CR3: 000000003d40a000 CR4: 00000000000006a0 Call Trace: xfs_reflink_allocate_cow+0x24c/0x3d0 [xfs] xfs_file_iomap_begin+0x6d2/0xeb0 [xfs] ? iomap_to_fiemap+0x80/0x80 iomap_apply+0x5e/0x130 iomap_dio_rw+0x2e0/0x400 ? iomap_to_fiemap+0x80/0x80 ? xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_write_iter+0x7b/0xb0 [xfs] __vfs_write+0x16f/0x1f0 vfs_write+0xc8/0x1c0 ksys_pwrite64+0x74/0x90 do_syscall_64+0x56/0x180 entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2018-06-22 06:26:57 +00:00
relock:
if (flags & IOMAP_NOWAIT) {
if (!xfs_ilock_nowait(ip, mode))
return -EAGAIN;
} else {
xfs_ilock(ip, mode);
}
xfs: recheck reflink state after grabbing ILOCK_SHARED for a write The reflink iflag could have changed since the earlier unlocked check, so if we got ILOCK_SHARED for a write and but we're now a reflink inode we have to switch to ILOCK_EXCL and relock. This helps us avoid blowing lock assertions in things like generic/166: XFS: Assertion failed: xfs_isilocked(ip, XFS_ILOCK_EXCL), file: fs/xfs/xfs_reflink.c, line: 383 WARNING: CPU: 1 PID: 24707 at fs/xfs/xfs_message.c:104 assfail+0x25/0x30 [xfs] Modules linked in: deadline_iosched dm_snapshot dm_bufio ext4 mbcache jbd2 dm_flakey xfs libcrc32c dax_pmem device_dax nd_pmem sch_fq_codel af_packet [last unloaded: scsi_debug] CPU: 1 PID: 24707 Comm: xfs_io Not tainted 4.18.0-rc1-djw #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:assfail+0x25/0x30 [xfs] Code: ff 0f 0b c3 90 66 66 66 66 90 48 89 f1 41 89 d0 48 c7 c6 e8 ef 1b a0 48 89 fa 31 ff e8 54 f9 ff ff 80 3d fd ba 0f 00 00 75 03 <0f> 0b c3 0f 0b 66 0f 1f 44 00 00 66 66 66 66 90 48 63 f6 49 89 f9 RSP: 0018:ffffc90006423ad8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880030b65e80 RCX: 0000000000000000 RDX: 00000000ffffffc0 RSI: 000000000000000a RDI: ffffffffa01b0447 RBP: ffffc90006423c10 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88003d43fc30 R11: f000000000000000 R12: ffff880077cda000 R13: 0000000000000000 R14: ffffc90006423c30 R15: ffffc90006423bf9 FS: 00007feba8986800(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000138ab58 CR3: 000000003d40a000 CR4: 00000000000006a0 Call Trace: xfs_reflink_allocate_cow+0x24c/0x3d0 [xfs] xfs_file_iomap_begin+0x6d2/0xeb0 [xfs] ? iomap_to_fiemap+0x80/0x80 iomap_apply+0x5e/0x130 iomap_dio_rw+0x2e0/0x400 ? iomap_to_fiemap+0x80/0x80 ? xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_write_iter+0x7b/0xb0 [xfs] __vfs_write+0x16f/0x1f0 vfs_write+0xc8/0x1c0 ksys_pwrite64+0x74/0x90 do_syscall_64+0x56/0x180 entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2018-06-22 06:26:57 +00:00
/*
* The reflink iflag could have changed since the earlier unlocked
* check, so if we got ILOCK_SHARED for a write and but we're now a
* reflink inode we have to switch to ILOCK_EXCL and relock.
*/
xfs: introduce an always_cow mode Add a mode where XFS never overwrites existing blocks in place. This is to aid debugging our COW code, and also put infatructure in place for things like possible future support for zoned block devices, which can't support overwrites. This mode is enabled globally by doing a: echo 1 > /sys/fs/xfs/debug/always_cow Note that the parameter is global to allow running all tests in xfstests easily in this mode, which would not easily be possible with a per-fs sysfs file. In always_cow mode persistent preallocations are disabled, and fallocate will fail when called with a 0 mode (with our without FALLOC_FL_KEEP_SIZE), and not create unwritten extent for zeroed space when called with FALLOC_FL_ZERO_RANGE or FALLOC_FL_UNSHARE_RANGE. There are a few interesting xfstests failures when run in always_cow mode: - generic/392 fails because the bytes used in the file used to test hole punch recovery are less after the log replay. This is because the blocks written and then punched out are only freed with a delay due to the logging mechanism. - xfs/170 will fail as the already fragile file streams mechanism doesn't seem to interact well with the COW allocator - xfs/180 xfs/182 xfs/192 xfs/198 xfs/204 and xfs/208 will claim the file system is badly fragmented, but there is not much we can do to avoid that when always writing out of place - xfs/205 fails because overwriting a file in always_cow mode will require new space allocation and the assumption in the test thus don't work anymore. - xfs/326 fails to modify the file at all in always_cow mode after injecting the refcount error, leading to an unexpected md5sum after the remount, but that again is expected Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-02-18 17:38:49 +00:00
if (mode == XFS_ILOCK_SHARED && is_write && xfs_is_cow_inode(ip)) {
xfs: recheck reflink state after grabbing ILOCK_SHARED for a write The reflink iflag could have changed since the earlier unlocked check, so if we got ILOCK_SHARED for a write and but we're now a reflink inode we have to switch to ILOCK_EXCL and relock. This helps us avoid blowing lock assertions in things like generic/166: XFS: Assertion failed: xfs_isilocked(ip, XFS_ILOCK_EXCL), file: fs/xfs/xfs_reflink.c, line: 383 WARNING: CPU: 1 PID: 24707 at fs/xfs/xfs_message.c:104 assfail+0x25/0x30 [xfs] Modules linked in: deadline_iosched dm_snapshot dm_bufio ext4 mbcache jbd2 dm_flakey xfs libcrc32c dax_pmem device_dax nd_pmem sch_fq_codel af_packet [last unloaded: scsi_debug] CPU: 1 PID: 24707 Comm: xfs_io Not tainted 4.18.0-rc1-djw #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:assfail+0x25/0x30 [xfs] Code: ff 0f 0b c3 90 66 66 66 66 90 48 89 f1 41 89 d0 48 c7 c6 e8 ef 1b a0 48 89 fa 31 ff e8 54 f9 ff ff 80 3d fd ba 0f 00 00 75 03 <0f> 0b c3 0f 0b 66 0f 1f 44 00 00 66 66 66 66 90 48 63 f6 49 89 f9 RSP: 0018:ffffc90006423ad8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880030b65e80 RCX: 0000000000000000 RDX: 00000000ffffffc0 RSI: 000000000000000a RDI: ffffffffa01b0447 RBP: ffffc90006423c10 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88003d43fc30 R11: f000000000000000 R12: ffff880077cda000 R13: 0000000000000000 R14: ffffc90006423c30 R15: ffffc90006423bf9 FS: 00007feba8986800(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000138ab58 CR3: 000000003d40a000 CR4: 00000000000006a0 Call Trace: xfs_reflink_allocate_cow+0x24c/0x3d0 [xfs] xfs_file_iomap_begin+0x6d2/0xeb0 [xfs] ? iomap_to_fiemap+0x80/0x80 iomap_apply+0x5e/0x130 iomap_dio_rw+0x2e0/0x400 ? iomap_to_fiemap+0x80/0x80 ? xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_dio_aio_write+0x133/0x4a0 [xfs] xfs_file_write_iter+0x7b/0xb0 [xfs] __vfs_write+0x16f/0x1f0 vfs_write+0xc8/0x1c0 ksys_pwrite64+0x74/0x90 do_syscall_64+0x56/0x180 entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2018-06-22 06:26:57 +00:00
xfs_iunlock(ip, mode);
mode = XFS_ILOCK_EXCL;
goto relock;
}
*lockmode = mode;
return 0;
}
xfs: don't allow NOWAIT DIO across extent boundaries Jens has reported a situation where partial direct IOs can be issued and completed yet still return -EAGAIN. We don't want this to report a short IO as we want XFS to complete user DIO entirely or not at all. This partial IO situation can occur on a write IO that is split across an allocated extent and a hole, and the second mapping is returning EAGAIN because allocation would be required. The trivial reproducer: $ sudo xfs_io -fdt -c "pwrite 0 4k" -c "pwrite -V 1 -b 8k -N 0 8k" /mnt/scr/foo wrote 4096/4096 bytes at offset 0 4 KiB, 1 ops; 0.0001 sec (27.509 MiB/sec and 7042.2535 ops/sec) pwrite: Resource temporarily unavailable $ The pwritev2(0, 8kB, RWF_NOWAIT) call returns EAGAIN having done the first 4kB write: xfs_file_direct_write: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 0x2000 iomap_apply: dev 259:1 ino 0x83 pos 0 length 8192 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin xfs_iomap_found: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 8192 fork data startoff 0x0 startblock 24 blockcount 0x1 iomap_apply_dstmap: dev 259:1 ino 0x83 bdev 259:1 addr 102400 offset 0 length 4096 type MAPPED flags DIRTY Here the first iomap loop has mapped the first 4kB of the file and issued the IO, and we enter the second iomap_apply loop: iomap_apply: dev 259:1 ino 0x83 pos 4096 length 4096 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin And we exit with -EAGAIN out because we hit the allocate case trying to make the second 4kB block. Then IO completes on the first 4kB and the original IO context completes and unlocks the inode, returning -EAGAIN to userspace: xfs_end_io_direct_write: dev 259:1 ino 0x83 isize 0x1000 disize 0x1000 offset 0x0 count 4096 xfs_iunlock: dev 259:1 ino 0x83 flags IOLOCK_SHARED caller xfs_file_dio_aio_write There are other vectors to the same problem when we re-enter the mapping code if we have to make multiple mappinfs under NOWAIT conditions. e.g. failing trylocks, COW extents being found, allocation being required, and so on. Avoid all these potential problems by only allowing IOMAP_NOWAIT IO to go ahead if the mapping we retrieve for the IO spans an entire allocated extent. This avoids the possibility of subsequent mappings to complete the IO from triggering NOWAIT semantics by any means as NOWAIT IO will now only enter the mapping code once per NOWAIT IO. Reported-and-tested-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2020-11-19 16:59:11 +00:00
/*
* Check that the imap we are going to return to the caller spans the entire
* range that the caller requested for the IO.
*/
static bool
imap_spans_range(
struct xfs_bmbt_irec *imap,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb)
{
if (imap->br_startoff > offset_fsb)
return false;
if (imap->br_startoff + imap->br_blockcount < end_fsb)
return false;
return true;
}
static int
xfs_direct_write_iomap_begin(
struct inode *inode,
loff_t offset,
loff_t length,
unsigned flags,
struct iomap *iomap,
struct iomap *srcmap)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec imap, cmap;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, length);
int nimaps = 1, error = 0;
bool shared = false;
u16 iomap_flags = 0;
unsigned lockmode;
ASSERT(flags & (IOMAP_WRITE | IOMAP_ZERO));
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Writes that span EOF might trigger an IO size update on completion,
* so consider them to be dirty for the purposes of O_DSYNC even if
* there is no other metadata changes pending or have been made here.
*/
if (offset + length > i_size_read(inode))
iomap_flags |= IOMAP_F_DIRTY;
error = xfs_ilock_for_iomap(ip, flags, &lockmode);
if (error)
return error;
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
&nimaps, 0);
if (error)
goto out_unlock;
if (imap_needs_cow(ip, flags, &imap, nimaps)) {
error = -EAGAIN;
if (flags & IOMAP_NOWAIT)
goto out_unlock;
/* may drop and re-acquire the ilock */
error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
&lockmode, flags & IOMAP_DIRECT);
if (error)
goto out_unlock;
if (shared)
goto out_found_cow;
end_fsb = imap.br_startoff + imap.br_blockcount;
length = XFS_FSB_TO_B(mp, end_fsb) - offset;
}
if (imap_needs_alloc(inode, flags, &imap, nimaps))
goto allocate_blocks;
xfs: don't allow NOWAIT DIO across extent boundaries Jens has reported a situation where partial direct IOs can be issued and completed yet still return -EAGAIN. We don't want this to report a short IO as we want XFS to complete user DIO entirely or not at all. This partial IO situation can occur on a write IO that is split across an allocated extent and a hole, and the second mapping is returning EAGAIN because allocation would be required. The trivial reproducer: $ sudo xfs_io -fdt -c "pwrite 0 4k" -c "pwrite -V 1 -b 8k -N 0 8k" /mnt/scr/foo wrote 4096/4096 bytes at offset 0 4 KiB, 1 ops; 0.0001 sec (27.509 MiB/sec and 7042.2535 ops/sec) pwrite: Resource temporarily unavailable $ The pwritev2(0, 8kB, RWF_NOWAIT) call returns EAGAIN having done the first 4kB write: xfs_file_direct_write: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 0x2000 iomap_apply: dev 259:1 ino 0x83 pos 0 length 8192 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin xfs_iomap_found: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 8192 fork data startoff 0x0 startblock 24 blockcount 0x1 iomap_apply_dstmap: dev 259:1 ino 0x83 bdev 259:1 addr 102400 offset 0 length 4096 type MAPPED flags DIRTY Here the first iomap loop has mapped the first 4kB of the file and issued the IO, and we enter the second iomap_apply loop: iomap_apply: dev 259:1 ino 0x83 pos 4096 length 4096 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin And we exit with -EAGAIN out because we hit the allocate case trying to make the second 4kB block. Then IO completes on the first 4kB and the original IO context completes and unlocks the inode, returning -EAGAIN to userspace: xfs_end_io_direct_write: dev 259:1 ino 0x83 isize 0x1000 disize 0x1000 offset 0x0 count 4096 xfs_iunlock: dev 259:1 ino 0x83 flags IOLOCK_SHARED caller xfs_file_dio_aio_write There are other vectors to the same problem when we re-enter the mapping code if we have to make multiple mappinfs under NOWAIT conditions. e.g. failing trylocks, COW extents being found, allocation being required, and so on. Avoid all these potential problems by only allowing IOMAP_NOWAIT IO to go ahead if the mapping we retrieve for the IO spans an entire allocated extent. This avoids the possibility of subsequent mappings to complete the IO from triggering NOWAIT semantics by any means as NOWAIT IO will now only enter the mapping code once per NOWAIT IO. Reported-and-tested-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2020-11-19 16:59:11 +00:00
/*
xfs: reduce exclusive locking on unaligned dio Attempt shared locking for unaligned DIO, but only if the the underlying extent is already allocated and in written state. On failure, retry with the existing exclusive locking. Test case is fio randrw of 512 byte IOs using AIO and an iodepth of 32 IOs. Vanilla: READ: bw=4560KiB/s (4670kB/s), 4560KiB/s-4560KiB/s (4670kB/s-4670kB/s), io=134MiB (140MB), run=30001-30001msec WRITE: bw=4567KiB/s (4676kB/s), 4567KiB/s-4567KiB/s (4676kB/s-4676kB/s), io=134MiB (140MB), run=30001-30001msec Patched: READ: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1127MiB (1182MB), run=30002-30002msec WRITE: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1128MiB (1183MB), run=30002-30002msec That's an improvement from ~18k IOPS to a ~150k IOPS, which is about the IOPS limit of the VM block device setup I'm testing on. 4kB block IO comparison: READ: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8868MiB (9299MB), run=30002-30002msec WRITE: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8878MiB (9309MB), run=30002-30002msec Which is ~150k IOPS, same as what the test gets for sub-block AIO+DIO writes with this patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> [hch: rebased, split unaligned from nowait] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2021-01-23 18:06:31 +00:00
* NOWAIT and OVERWRITE I/O needs to span the entire requested I/O with
* a single map so that we avoid partial IO failures due to the rest of
* the I/O range not covered by this map triggering an EAGAIN condition
* when it is subsequently mapped and aborting the I/O.
xfs: don't allow NOWAIT DIO across extent boundaries Jens has reported a situation where partial direct IOs can be issued and completed yet still return -EAGAIN. We don't want this to report a short IO as we want XFS to complete user DIO entirely or not at all. This partial IO situation can occur on a write IO that is split across an allocated extent and a hole, and the second mapping is returning EAGAIN because allocation would be required. The trivial reproducer: $ sudo xfs_io -fdt -c "pwrite 0 4k" -c "pwrite -V 1 -b 8k -N 0 8k" /mnt/scr/foo wrote 4096/4096 bytes at offset 0 4 KiB, 1 ops; 0.0001 sec (27.509 MiB/sec and 7042.2535 ops/sec) pwrite: Resource temporarily unavailable $ The pwritev2(0, 8kB, RWF_NOWAIT) call returns EAGAIN having done the first 4kB write: xfs_file_direct_write: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 0x2000 iomap_apply: dev 259:1 ino 0x83 pos 0 length 8192 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin xfs_iomap_found: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 8192 fork data startoff 0x0 startblock 24 blockcount 0x1 iomap_apply_dstmap: dev 259:1 ino 0x83 bdev 259:1 addr 102400 offset 0 length 4096 type MAPPED flags DIRTY Here the first iomap loop has mapped the first 4kB of the file and issued the IO, and we enter the second iomap_apply loop: iomap_apply: dev 259:1 ino 0x83 pos 4096 length 4096 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin And we exit with -EAGAIN out because we hit the allocate case trying to make the second 4kB block. Then IO completes on the first 4kB and the original IO context completes and unlocks the inode, returning -EAGAIN to userspace: xfs_end_io_direct_write: dev 259:1 ino 0x83 isize 0x1000 disize 0x1000 offset 0x0 count 4096 xfs_iunlock: dev 259:1 ino 0x83 flags IOLOCK_SHARED caller xfs_file_dio_aio_write There are other vectors to the same problem when we re-enter the mapping code if we have to make multiple mappinfs under NOWAIT conditions. e.g. failing trylocks, COW extents being found, allocation being required, and so on. Avoid all these potential problems by only allowing IOMAP_NOWAIT IO to go ahead if the mapping we retrieve for the IO spans an entire allocated extent. This avoids the possibility of subsequent mappings to complete the IO from triggering NOWAIT semantics by any means as NOWAIT IO will now only enter the mapping code once per NOWAIT IO. Reported-and-tested-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2020-11-19 16:59:11 +00:00
*/
xfs: reduce exclusive locking on unaligned dio Attempt shared locking for unaligned DIO, but only if the the underlying extent is already allocated and in written state. On failure, retry with the existing exclusive locking. Test case is fio randrw of 512 byte IOs using AIO and an iodepth of 32 IOs. Vanilla: READ: bw=4560KiB/s (4670kB/s), 4560KiB/s-4560KiB/s (4670kB/s-4670kB/s), io=134MiB (140MB), run=30001-30001msec WRITE: bw=4567KiB/s (4676kB/s), 4567KiB/s-4567KiB/s (4676kB/s-4676kB/s), io=134MiB (140MB), run=30001-30001msec Patched: READ: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1127MiB (1182MB), run=30002-30002msec WRITE: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1128MiB (1183MB), run=30002-30002msec That's an improvement from ~18k IOPS to a ~150k IOPS, which is about the IOPS limit of the VM block device setup I'm testing on. 4kB block IO comparison: READ: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8868MiB (9299MB), run=30002-30002msec WRITE: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8878MiB (9309MB), run=30002-30002msec Which is ~150k IOPS, same as what the test gets for sub-block AIO+DIO writes with this patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> [hch: rebased, split unaligned from nowait] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2021-01-23 18:06:31 +00:00
if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY)) {
xfs: don't allow NOWAIT DIO across extent boundaries Jens has reported a situation where partial direct IOs can be issued and completed yet still return -EAGAIN. We don't want this to report a short IO as we want XFS to complete user DIO entirely or not at all. This partial IO situation can occur on a write IO that is split across an allocated extent and a hole, and the second mapping is returning EAGAIN because allocation would be required. The trivial reproducer: $ sudo xfs_io -fdt -c "pwrite 0 4k" -c "pwrite -V 1 -b 8k -N 0 8k" /mnt/scr/foo wrote 4096/4096 bytes at offset 0 4 KiB, 1 ops; 0.0001 sec (27.509 MiB/sec and 7042.2535 ops/sec) pwrite: Resource temporarily unavailable $ The pwritev2(0, 8kB, RWF_NOWAIT) call returns EAGAIN having done the first 4kB write: xfs_file_direct_write: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 0x2000 iomap_apply: dev 259:1 ino 0x83 pos 0 length 8192 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin xfs_iomap_found: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 8192 fork data startoff 0x0 startblock 24 blockcount 0x1 iomap_apply_dstmap: dev 259:1 ino 0x83 bdev 259:1 addr 102400 offset 0 length 4096 type MAPPED flags DIRTY Here the first iomap loop has mapped the first 4kB of the file and issued the IO, and we enter the second iomap_apply loop: iomap_apply: dev 259:1 ino 0x83 pos 4096 length 4096 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin And we exit with -EAGAIN out because we hit the allocate case trying to make the second 4kB block. Then IO completes on the first 4kB and the original IO context completes and unlocks the inode, returning -EAGAIN to userspace: xfs_end_io_direct_write: dev 259:1 ino 0x83 isize 0x1000 disize 0x1000 offset 0x0 count 4096 xfs_iunlock: dev 259:1 ino 0x83 flags IOLOCK_SHARED caller xfs_file_dio_aio_write There are other vectors to the same problem when we re-enter the mapping code if we have to make multiple mappinfs under NOWAIT conditions. e.g. failing trylocks, COW extents being found, allocation being required, and so on. Avoid all these potential problems by only allowing IOMAP_NOWAIT IO to go ahead if the mapping we retrieve for the IO spans an entire allocated extent. This avoids the possibility of subsequent mappings to complete the IO from triggering NOWAIT semantics by any means as NOWAIT IO will now only enter the mapping code once per NOWAIT IO. Reported-and-tested-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2020-11-19 16:59:11 +00:00
error = -EAGAIN;
xfs: reduce exclusive locking on unaligned dio Attempt shared locking for unaligned DIO, but only if the the underlying extent is already allocated and in written state. On failure, retry with the existing exclusive locking. Test case is fio randrw of 512 byte IOs using AIO and an iodepth of 32 IOs. Vanilla: READ: bw=4560KiB/s (4670kB/s), 4560KiB/s-4560KiB/s (4670kB/s-4670kB/s), io=134MiB (140MB), run=30001-30001msec WRITE: bw=4567KiB/s (4676kB/s), 4567KiB/s-4567KiB/s (4676kB/s-4676kB/s), io=134MiB (140MB), run=30001-30001msec Patched: READ: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1127MiB (1182MB), run=30002-30002msec WRITE: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1128MiB (1183MB), run=30002-30002msec That's an improvement from ~18k IOPS to a ~150k IOPS, which is about the IOPS limit of the VM block device setup I'm testing on. 4kB block IO comparison: READ: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8868MiB (9299MB), run=30002-30002msec WRITE: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8878MiB (9309MB), run=30002-30002msec Which is ~150k IOPS, same as what the test gets for sub-block AIO+DIO writes with this patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> [hch: rebased, split unaligned from nowait] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2021-01-23 18:06:31 +00:00
if (!imap_spans_range(&imap, offset_fsb, end_fsb))
goto out_unlock;
}
/*
* For overwrite only I/O, we cannot convert unwritten extents without
* requiring sub-block zeroing. This can only be done under an
* exclusive IOLOCK, hence return -EAGAIN if this is not a written
* extent to tell the caller to try again.
*/
if (flags & IOMAP_OVERWRITE_ONLY) {
error = -EAGAIN;
if (imap.br_state != XFS_EXT_NORM &&
((offset | length) & mp->m_blockmask))
goto out_unlock;
xfs: don't allow NOWAIT DIO across extent boundaries Jens has reported a situation where partial direct IOs can be issued and completed yet still return -EAGAIN. We don't want this to report a short IO as we want XFS to complete user DIO entirely or not at all. This partial IO situation can occur on a write IO that is split across an allocated extent and a hole, and the second mapping is returning EAGAIN because allocation would be required. The trivial reproducer: $ sudo xfs_io -fdt -c "pwrite 0 4k" -c "pwrite -V 1 -b 8k -N 0 8k" /mnt/scr/foo wrote 4096/4096 bytes at offset 0 4 KiB, 1 ops; 0.0001 sec (27.509 MiB/sec and 7042.2535 ops/sec) pwrite: Resource temporarily unavailable $ The pwritev2(0, 8kB, RWF_NOWAIT) call returns EAGAIN having done the first 4kB write: xfs_file_direct_write: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 0x2000 iomap_apply: dev 259:1 ino 0x83 pos 0 length 8192 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin xfs_iomap_found: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 8192 fork data startoff 0x0 startblock 24 blockcount 0x1 iomap_apply_dstmap: dev 259:1 ino 0x83 bdev 259:1 addr 102400 offset 0 length 4096 type MAPPED flags DIRTY Here the first iomap loop has mapped the first 4kB of the file and issued the IO, and we enter the second iomap_apply loop: iomap_apply: dev 259:1 ino 0x83 pos 4096 length 4096 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin And we exit with -EAGAIN out because we hit the allocate case trying to make the second 4kB block. Then IO completes on the first 4kB and the original IO context completes and unlocks the inode, returning -EAGAIN to userspace: xfs_end_io_direct_write: dev 259:1 ino 0x83 isize 0x1000 disize 0x1000 offset 0x0 count 4096 xfs_iunlock: dev 259:1 ino 0x83 flags IOLOCK_SHARED caller xfs_file_dio_aio_write There are other vectors to the same problem when we re-enter the mapping code if we have to make multiple mappinfs under NOWAIT conditions. e.g. failing trylocks, COW extents being found, allocation being required, and so on. Avoid all these potential problems by only allowing IOMAP_NOWAIT IO to go ahead if the mapping we retrieve for the IO spans an entire allocated extent. This avoids the possibility of subsequent mappings to complete the IO from triggering NOWAIT semantics by any means as NOWAIT IO will now only enter the mapping code once per NOWAIT IO. Reported-and-tested-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2020-11-19 16:59:11 +00:00
}
xfs_iunlock(ip, lockmode);
trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
allocate_blocks:
error = -EAGAIN;
xfs: reduce exclusive locking on unaligned dio Attempt shared locking for unaligned DIO, but only if the the underlying extent is already allocated and in written state. On failure, retry with the existing exclusive locking. Test case is fio randrw of 512 byte IOs using AIO and an iodepth of 32 IOs. Vanilla: READ: bw=4560KiB/s (4670kB/s), 4560KiB/s-4560KiB/s (4670kB/s-4670kB/s), io=134MiB (140MB), run=30001-30001msec WRITE: bw=4567KiB/s (4676kB/s), 4567KiB/s-4567KiB/s (4676kB/s-4676kB/s), io=134MiB (140MB), run=30001-30001msec Patched: READ: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1127MiB (1182MB), run=30002-30002msec WRITE: bw=37.6MiB/s (39.4MB/s), 37.6MiB/s-37.6MiB/s (39.4MB/s-39.4MB/s), io=1128MiB (1183MB), run=30002-30002msec That's an improvement from ~18k IOPS to a ~150k IOPS, which is about the IOPS limit of the VM block device setup I'm testing on. 4kB block IO comparison: READ: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8868MiB (9299MB), run=30002-30002msec WRITE: bw=296MiB/s (310MB/s), 296MiB/s-296MiB/s (310MB/s-310MB/s), io=8878MiB (9309MB), run=30002-30002msec Which is ~150k IOPS, same as what the test gets for sub-block AIO+DIO writes with this patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> [hch: rebased, split unaligned from nowait] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2021-01-23 18:06:31 +00:00
if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY))
goto out_unlock;
/*
* We cap the maximum length we map to a sane size to keep the chunks
* of work done where somewhat symmetric with the work writeback does.
* This is a completely arbitrary number pulled out of thin air as a
* best guess for initial testing.
*
* Note that the values needs to be less than 32-bits wide until the
* lower level functions are updated.
*/
length = min_t(loff_t, length, 1024 * PAGE_SIZE);
end_fsb = xfs_iomap_end_fsb(mp, offset, length);
if (offset + length > XFS_ISIZE(ip))
end_fsb = xfs_iomap_eof_align_last_fsb(ip, end_fsb);
else if (nimaps && imap.br_startblock == HOLESTARTBLOCK)
end_fsb = min(end_fsb, imap.br_startoff + imap.br_blockcount);
xfs_iunlock(ip, lockmode);
error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb,
&imap);
if (error)
return error;
trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags | IOMAP_F_NEW);
out_found_cow:
xfs_iunlock(ip, lockmode);
length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
if (imap.br_startblock != HOLESTARTBLOCK) {
error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
if (error)
return error;
}
return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
out_unlock:
if (lockmode)
xfs_iunlock(ip, lockmode);
return error;
}
const struct iomap_ops xfs_direct_write_iomap_ops = {
.iomap_begin = xfs_direct_write_iomap_begin,
};
static int
xfs_buffered_write_iomap_begin(
struct inode *inode,
loff_t offset,
loff_t count,
unsigned flags,
struct iomap *iomap,
struct iomap *srcmap)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, count);
struct xfs_bmbt_irec imap, cmap;
struct xfs_iext_cursor icur, ccur;
xfs_fsblock_t prealloc_blocks = 0;
bool eof = false, cow_eof = false, shared = false;
int allocfork = XFS_DATA_FORK;
int error = 0;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/* we can't use delayed allocations when using extent size hints */
if (xfs_get_extsz_hint(ip))
return xfs_direct_write_iomap_begin(inode, offset, count,
flags, iomap, srcmap);
ASSERT(!XFS_IS_REALTIME_INODE(ip));
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
error = -EFSCORRUPTED;
goto out_unlock;
}
XFS_STATS_INC(mp, xs_blk_mapw);
error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
if (error)
goto out_unlock;
/*
* Search the data fork first to look up our source mapping. We
* always need the data fork map, as we have to return it to the
* iomap code so that the higher level write code can read data in to
* perform read-modify-write cycles for unaligned writes.
*/
eof = !xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap);
if (eof)
imap.br_startoff = end_fsb; /* fake hole until the end */
/* We never need to allocate blocks for zeroing a hole. */
if ((flags & IOMAP_ZERO) && imap.br_startoff > offset_fsb) {
xfs_hole_to_iomap(ip, iomap, offset_fsb, imap.br_startoff);
goto out_unlock;
}
/*
* Search the COW fork extent list even if we did not find a data fork
* extent. This serves two purposes: first this implements the
* speculative preallocation using cowextsize, so that we also unshare
* block adjacent to shared blocks instead of just the shared blocks
* themselves. Second the lookup in the extent list is generally faster
* than going out to the shared extent tree.
*/
if (xfs_is_cow_inode(ip)) {
if (!ip->i_cowfp) {
ASSERT(!xfs_is_reflink_inode(ip));
xfs_ifork_init_cow(ip);
}
cow_eof = !xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb,
&ccur, &cmap);
if (!cow_eof && cmap.br_startoff <= offset_fsb) {
trace_xfs_reflink_cow_found(ip, &cmap);
goto found_cow;
}
}
if (imap.br_startoff <= offset_fsb) {
/*
* For reflink files we may need a delalloc reservation when
* overwriting shared extents. This includes zeroing of
* existing extents that contain data.
*/
if (!xfs_is_cow_inode(ip) ||
((flags & IOMAP_ZERO) && imap.br_state != XFS_EXT_NORM)) {
trace_xfs_iomap_found(ip, offset, count, XFS_DATA_FORK,
&imap);
goto found_imap;
}
xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);
/* Trim the mapping to the nearest shared extent boundary. */
error = xfs_bmap_trim_cow(ip, &imap, &shared);
if (error)
goto out_unlock;
/* Not shared? Just report the (potentially capped) extent. */
if (!shared) {
trace_xfs_iomap_found(ip, offset, count, XFS_DATA_FORK,
&imap);
goto found_imap;
}
/*
* Fork all the shared blocks from our write offset until the
* end of the extent.
*/
allocfork = XFS_COW_FORK;
end_fsb = imap.br_startoff + imap.br_blockcount;
} else {
/*
* We cap the maximum length we map here to MAX_WRITEBACK_PAGES
* pages to keep the chunks of work done where somewhat
* symmetric with the work writeback does. This is a completely
* arbitrary number pulled out of thin air.
*
* Note that the values needs to be less than 32-bits wide until
* the lower level functions are updated.
*/
count = min_t(loff_t, count, 1024 * PAGE_SIZE);
end_fsb = xfs_iomap_end_fsb(mp, offset, count);
if (xfs_is_always_cow_inode(ip))
allocfork = XFS_COW_FORK;
}
error = xfs_qm_dqattach_locked(ip, false);
if (error)
goto out_unlock;
if (eof && offset + count > XFS_ISIZE(ip)) {
/*
* Determine the initial size of the preallocation.
* We clean up any extra preallocation when the file is closed.
*/
if (mp->m_flags & XFS_MOUNT_ALLOCSIZE)
prealloc_blocks = mp->m_allocsize_blocks;
else
prealloc_blocks = xfs_iomap_prealloc_size(ip, allocfork,
offset, count, &icur);
if (prealloc_blocks) {
xfs_extlen_t align;
xfs_off_t end_offset;
xfs_fileoff_t p_end_fsb;
end_offset = XFS_ALLOC_ALIGN(mp, offset + count - 1);
p_end_fsb = XFS_B_TO_FSBT(mp, end_offset) +
prealloc_blocks;
align = xfs_eof_alignment(ip);
if (align)
p_end_fsb = roundup_64(p_end_fsb, align);
p_end_fsb = min(p_end_fsb,
XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes));
ASSERT(p_end_fsb > offset_fsb);
prealloc_blocks = p_end_fsb - end_fsb;
}
}
retry:
error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
end_fsb - offset_fsb, prealloc_blocks,
allocfork == XFS_DATA_FORK ? &imap : &cmap,
allocfork == XFS_DATA_FORK ? &icur : &ccur,
allocfork == XFS_DATA_FORK ? eof : cow_eof);
switch (error) {
case 0:
break;
case -ENOSPC:
case -EDQUOT:
/* retry without any preallocation */
trace_xfs_delalloc_enospc(ip, offset, count);
if (prealloc_blocks) {
prealloc_blocks = 0;
goto retry;
}
xfs: Fix fall-through warnings for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix the following warnings by replacing /* fall through */ comments, and its variants, with the new pseudo-keyword macro fallthrough: fs/xfs/libxfs/xfs_alloc.c:3167:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_da_btree.c:286:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_ag_resv.c:346:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_ag_resv.c:388:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_bmap_util.c:246:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_export.c:88:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_export.c:96:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_file.c:867:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_ioctl.c:562:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_ioctl.c:1548:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_iomap.c:1040:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_inode.c:852:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_log.c:2627:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/xfs_trans_buf.c:298:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/bmap.c:275:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/btree.c:48:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/common.c:85:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/common.c:138:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/common.c:698:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/dabtree.c:51:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/repair.c:951:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/scrub/agheader.c:89:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Notice that Clang doesn't recognize /* fall through */ comments as implicit fall-through markings, so in order to globally enable -Wimplicit-fallthrough for Clang, these comments need to be replaced with fallthrough; in the whole codebase. Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
2021-04-20 22:54:36 +00:00
fallthrough;
default:
goto out_unlock;
}
if (allocfork == XFS_COW_FORK) {
trace_xfs_iomap_alloc(ip, offset, count, allocfork, &cmap);
goto found_cow;
}
/*
* Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
* them out if the write happens to fail.
*/
xfs_iunlock(ip, XFS_ILOCK_EXCL);
trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap);
return xfs_bmbt_to_iomap(ip, iomap, &imap, IOMAP_F_NEW);
found_imap:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
found_cow:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (imap.br_startoff <= offset_fsb) {
error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
if (error)
return error;
} else {
xfs_trim_extent(&cmap, offset_fsb,
imap.br_startoff - offset_fsb);
}
return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
static int
xfs_buffered_write_iomap_end(
struct inode *inode,
loff_t offset,
loff_t length,
xfs: use iomap new flag for newly allocated delalloc blocks Commit fa7f138 ("xfs: clear delalloc and cache on buffered write failure") fixed one regression in the iomap error handling code and exposed another. The fundamental problem is that if a buffered write is a rewrite of preexisting delalloc blocks and the write fails, the failure handling code can punch out preexisting blocks with valid file data. This was reproduced directly by sub-block writes in the LTP kernel/syscalls/write/write03 test. A first 100 byte write allocates a single block in a file. A subsequent 100 byte write fails and punches out the block, including the data successfully written by the previous write. To address this problem, update the ->iomap_begin() handler to distinguish newly allocated delalloc blocks from preexisting delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the ->iomap_end() handler to decide when a failed or short write should punch out delalloc blocks. This introduces the subtle requirement that ->iomap_begin() should never combine newly allocated delalloc blocks with existing blocks in the resulting iomap descriptor. This can occur when a new delalloc reservation merges with a neighboring extent that is part of the current write, for example. Therefore, drop the post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and just return the record inserted into the fork. This ensures only new blocks are returned and thus that preexisting delalloc blocks are always handled as "found" blocks and not punched out on a failed rewrite. Reported-by: Xiong Zhou <xzhou@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-03-08 17:58:08 +00:00
ssize_t written,
unsigned flags,
xfs: use iomap new flag for newly allocated delalloc blocks Commit fa7f138 ("xfs: clear delalloc and cache on buffered write failure") fixed one regression in the iomap error handling code and exposed another. The fundamental problem is that if a buffered write is a rewrite of preexisting delalloc blocks and the write fails, the failure handling code can punch out preexisting blocks with valid file data. This was reproduced directly by sub-block writes in the LTP kernel/syscalls/write/write03 test. A first 100 byte write allocates a single block in a file. A subsequent 100 byte write fails and punches out the block, including the data successfully written by the previous write. To address this problem, update the ->iomap_begin() handler to distinguish newly allocated delalloc blocks from preexisting delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the ->iomap_end() handler to decide when a failed or short write should punch out delalloc blocks. This introduces the subtle requirement that ->iomap_begin() should never combine newly allocated delalloc blocks with existing blocks in the resulting iomap descriptor. This can occur when a new delalloc reservation merges with a neighboring extent that is part of the current write, for example. Therefore, drop the post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and just return the record inserted into the fork. This ensures only new blocks are returned and thus that preexisting delalloc blocks are always handled as "found" blocks and not punched out on a failed rewrite. Reported-by: Xiong Zhou <xzhou@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-03-08 17:58:08 +00:00
struct iomap *iomap)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t start_fsb;
xfs_fileoff_t end_fsb;
int error = 0;
if (iomap->type != IOMAP_DELALLOC)
return 0;
xfs: use iomap new flag for newly allocated delalloc blocks Commit fa7f138 ("xfs: clear delalloc and cache on buffered write failure") fixed one regression in the iomap error handling code and exposed another. The fundamental problem is that if a buffered write is a rewrite of preexisting delalloc blocks and the write fails, the failure handling code can punch out preexisting blocks with valid file data. This was reproduced directly by sub-block writes in the LTP kernel/syscalls/write/write03 test. A first 100 byte write allocates a single block in a file. A subsequent 100 byte write fails and punches out the block, including the data successfully written by the previous write. To address this problem, update the ->iomap_begin() handler to distinguish newly allocated delalloc blocks from preexisting delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the ->iomap_end() handler to decide when a failed or short write should punch out delalloc blocks. This introduces the subtle requirement that ->iomap_begin() should never combine newly allocated delalloc blocks with existing blocks in the resulting iomap descriptor. This can occur when a new delalloc reservation merges with a neighboring extent that is part of the current write, for example. Therefore, drop the post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and just return the record inserted into the fork. This ensures only new blocks are returned and thus that preexisting delalloc blocks are always handled as "found" blocks and not punched out on a failed rewrite. Reported-by: Xiong Zhou <xzhou@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-03-08 17:58:08 +00:00
/*
* Behave as if the write failed if drop writes is enabled. Set the NEW
* flag to force delalloc cleanup.
*/
if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) {
xfs: use iomap new flag for newly allocated delalloc blocks Commit fa7f138 ("xfs: clear delalloc and cache on buffered write failure") fixed one regression in the iomap error handling code and exposed another. The fundamental problem is that if a buffered write is a rewrite of preexisting delalloc blocks and the write fails, the failure handling code can punch out preexisting blocks with valid file data. This was reproduced directly by sub-block writes in the LTP kernel/syscalls/write/write03 test. A first 100 byte write allocates a single block in a file. A subsequent 100 byte write fails and punches out the block, including the data successfully written by the previous write. To address this problem, update the ->iomap_begin() handler to distinguish newly allocated delalloc blocks from preexisting delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the ->iomap_end() handler to decide when a failed or short write should punch out delalloc blocks. This introduces the subtle requirement that ->iomap_begin() should never combine newly allocated delalloc blocks with existing blocks in the resulting iomap descriptor. This can occur when a new delalloc reservation merges with a neighboring extent that is part of the current write, for example. Therefore, drop the post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and just return the record inserted into the fork. This ensures only new blocks are returned and thus that preexisting delalloc blocks are always handled as "found" blocks and not punched out on a failed rewrite. Reported-by: Xiong Zhou <xzhou@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-03-08 17:58:08 +00:00
iomap->flags |= IOMAP_F_NEW;
written = 0;
xfs: use iomap new flag for newly allocated delalloc blocks Commit fa7f138 ("xfs: clear delalloc and cache on buffered write failure") fixed one regression in the iomap error handling code and exposed another. The fundamental problem is that if a buffered write is a rewrite of preexisting delalloc blocks and the write fails, the failure handling code can punch out preexisting blocks with valid file data. This was reproduced directly by sub-block writes in the LTP kernel/syscalls/write/write03 test. A first 100 byte write allocates a single block in a file. A subsequent 100 byte write fails and punches out the block, including the data successfully written by the previous write. To address this problem, update the ->iomap_begin() handler to distinguish newly allocated delalloc blocks from preexisting delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the ->iomap_end() handler to decide when a failed or short write should punch out delalloc blocks. This introduces the subtle requirement that ->iomap_begin() should never combine newly allocated delalloc blocks with existing blocks in the resulting iomap descriptor. This can occur when a new delalloc reservation merges with a neighboring extent that is part of the current write, for example. Therefore, drop the post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and just return the record inserted into the fork. This ensures only new blocks are returned and thus that preexisting delalloc blocks are always handled as "found" blocks and not punched out on a failed rewrite. Reported-by: Xiong Zhou <xzhou@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-03-08 17:58:08 +00:00
}
/*
* start_fsb refers to the first unused block after a short write. If
* nothing was written, round offset down to point at the first block in
* the range.
*/
if (unlikely(!written))
start_fsb = XFS_B_TO_FSBT(mp, offset);
else
start_fsb = XFS_B_TO_FSB(mp, offset + written);
end_fsb = XFS_B_TO_FSB(mp, offset + length);
/*
xfs: use iomap new flag for newly allocated delalloc blocks Commit fa7f138 ("xfs: clear delalloc and cache on buffered write failure") fixed one regression in the iomap error handling code and exposed another. The fundamental problem is that if a buffered write is a rewrite of preexisting delalloc blocks and the write fails, the failure handling code can punch out preexisting blocks with valid file data. This was reproduced directly by sub-block writes in the LTP kernel/syscalls/write/write03 test. A first 100 byte write allocates a single block in a file. A subsequent 100 byte write fails and punches out the block, including the data successfully written by the previous write. To address this problem, update the ->iomap_begin() handler to distinguish newly allocated delalloc blocks from preexisting delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the ->iomap_end() handler to decide when a failed or short write should punch out delalloc blocks. This introduces the subtle requirement that ->iomap_begin() should never combine newly allocated delalloc blocks with existing blocks in the resulting iomap descriptor. This can occur when a new delalloc reservation merges with a neighboring extent that is part of the current write, for example. Therefore, drop the post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and just return the record inserted into the fork. This ensures only new blocks are returned and thus that preexisting delalloc blocks are always handled as "found" blocks and not punched out on a failed rewrite. Reported-by: Xiong Zhou <xzhou@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-03-08 17:58:08 +00:00
* Trim delalloc blocks if they were allocated by this write and we
* didn't manage to write the whole range.
*
* We don't need to care about racing delalloc as we hold i_mutex
* across the reserve/allocate/unreserve calls. If there are delalloc
* blocks in the range, they are ours.
*/
xfs: use iomap new flag for newly allocated delalloc blocks Commit fa7f138 ("xfs: clear delalloc and cache on buffered write failure") fixed one regression in the iomap error handling code and exposed another. The fundamental problem is that if a buffered write is a rewrite of preexisting delalloc blocks and the write fails, the failure handling code can punch out preexisting blocks with valid file data. This was reproduced directly by sub-block writes in the LTP kernel/syscalls/write/write03 test. A first 100 byte write allocates a single block in a file. A subsequent 100 byte write fails and punches out the block, including the data successfully written by the previous write. To address this problem, update the ->iomap_begin() handler to distinguish newly allocated delalloc blocks from preexisting delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the ->iomap_end() handler to decide when a failed or short write should punch out delalloc blocks. This introduces the subtle requirement that ->iomap_begin() should never combine newly allocated delalloc blocks with existing blocks in the resulting iomap descriptor. This can occur when a new delalloc reservation merges with a neighboring extent that is part of the current write, for example. Therefore, drop the post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and just return the record inserted into the fork. This ensures only new blocks are returned and thus that preexisting delalloc blocks are always handled as "found" blocks and not punched out on a failed rewrite. Reported-by: Xiong Zhou <xzhou@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-03-08 17:58:08 +00:00
if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
XFS_FSB_TO_B(mp, end_fsb) - 1);
error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
end_fsb - start_fsb);
if (error && !XFS_FORCED_SHUTDOWN(mp)) {
xfs_alert(mp, "%s: unable to clean up ino %lld",
__func__, ip->i_ino);
return error;
}
}
return 0;
}
const struct iomap_ops xfs_buffered_write_iomap_ops = {
.iomap_begin = xfs_buffered_write_iomap_begin,
.iomap_end = xfs_buffered_write_iomap_end,
};
static int
xfs_read_iomap_begin(
struct inode *inode,
loff_t offset,
loff_t length,
unsigned flags,
struct iomap *iomap,
struct iomap *srcmap)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec imap;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, length);
int nimaps = 1, error = 0;
bool shared = false;
unsigned lockmode;
ASSERT(!(flags & (IOMAP_WRITE | IOMAP_ZERO)));
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
error = xfs_ilock_for_iomap(ip, flags, &lockmode);
if (error)
return error;
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
&nimaps, 0);
if (!error && (flags & IOMAP_REPORT))
error = xfs_reflink_trim_around_shared(ip, &imap, &shared);
xfs_iunlock(ip, lockmode);
if (error)
return error;
trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
return xfs_bmbt_to_iomap(ip, iomap, &imap, shared ? IOMAP_F_SHARED : 0);
}
const struct iomap_ops xfs_read_iomap_ops = {
.iomap_begin = xfs_read_iomap_begin,
};
static int
xfs_seek_iomap_begin(
struct inode *inode,
loff_t offset,
loff_t length,
unsigned flags,
struct iomap *iomap,
struct iomap *srcmap)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length);
xfs_fileoff_t cow_fsb = NULLFILEOFF, data_fsb = NULLFILEOFF;
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec imap, cmap;
int error = 0;
unsigned lockmode;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
lockmode = xfs_ilock_data_map_shared(ip);
error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
if (error)
goto out_unlock;
if (xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap)) {
/*
* If we found a data extent we are done.
*/
if (imap.br_startoff <= offset_fsb)
goto done;
data_fsb = imap.br_startoff;
} else {
/*
* Fake a hole until the end of the file.
*/
data_fsb = xfs_iomap_end_fsb(mp, offset, length);
}
/*
* If a COW fork extent covers the hole, report it - capped to the next
* data fork extent:
*/
if (xfs_inode_has_cow_data(ip) &&
xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
cow_fsb = cmap.br_startoff;
if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
if (data_fsb < cow_fsb + cmap.br_blockcount)
end_fsb = min(end_fsb, data_fsb);
xfs_trim_extent(&cmap, offset_fsb, end_fsb);
error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
/*
* This is a COW extent, so we must probe the page cache
* because there could be dirty page cache being backed
* by this extent.
*/
iomap->type = IOMAP_UNWRITTEN;
goto out_unlock;
}
/*
* Else report a hole, capped to the next found data or COW extent.
*/
if (cow_fsb != NULLFILEOFF && cow_fsb < data_fsb)
imap.br_blockcount = cow_fsb - offset_fsb;
else
imap.br_blockcount = data_fsb - offset_fsb;
imap.br_startoff = offset_fsb;
imap.br_startblock = HOLESTARTBLOCK;
imap.br_state = XFS_EXT_NORM;
done:
xfs_trim_extent(&imap, offset_fsb, end_fsb);
error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
out_unlock:
xfs_iunlock(ip, lockmode);
return error;
}
const struct iomap_ops xfs_seek_iomap_ops = {
.iomap_begin = xfs_seek_iomap_begin,
};
static int
xfs_xattr_iomap_begin(
struct inode *inode,
loff_t offset,
loff_t length,
unsigned flags,
struct iomap *iomap,
struct iomap *srcmap)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length);
struct xfs_bmbt_irec imap;
int nimaps = 1, error = 0;
unsigned lockmode;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
lockmode = xfs_ilock_attr_map_shared(ip);
/* if there are no attribute fork or extents, return ENOENT */
if (!XFS_IFORK_Q(ip) || !ip->i_afp->if_nextents) {
error = -ENOENT;
goto out_unlock;
}
ASSERT(ip->i_afp->if_format != XFS_DINODE_FMT_LOCAL);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
&nimaps, XFS_BMAPI_ATTRFORK);
out_unlock:
xfs_iunlock(ip, lockmode);
if (error)
return error;
ASSERT(nimaps);
return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
}
const struct iomap_ops xfs_xattr_iomap_ops = {
.iomap_begin = xfs_xattr_iomap_begin,
};