Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-26 06:02:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

xfs: stop artificially limiting the length of bunmap calls

Browse Source 
In commit e1a4e37cc7, we clamped the length of bunmapi calls on the
data forks of shared files to avoid two failure scenarios: one where the
extent being unmapped is so sparsely shared that we exceed the
transaction reservation with the sheer number of refcount btree updates
and EFI intent items; and the other where we attach so many deferred
updates to the transaction that we pin the log tail and later the log
head meets the tail, causing the log to livelock.

We avoid triggering the first problem by tracking the number of ops in
the refcount btree cursor and forcing a requeue of the refcount intent
item any time we think that we might be close to overflowing.  This has
been baked into XFS since before the original e1a4 patch.

A recent patchset fixed the second problem by changing the deferred ops
code to finish all the work items created by each round of trying to
complete a refcount intent item, which eliminates the long chains of
deferred items (27dad); and causing long-running transactions to relog
their intent log items when space in the log gets low (74f4d).

Because this clamp affects /any/ unmapping request regardless of the
sharing factors of the component blocks, it degrades the performance of
all large unmapping requests -- whereas with an unshared file we can
unmap millions of blocks in one go, shared files are limited to
unmapping a few thousand blocks at a time, which causes the upper level
code to spin in a bunmapi loop even if it wasn't needed.

This also eliminates one more place where log recovery behavior can
differ from online behavior, because bunmapi operations no longer need
to requeue.  The fstest generic/447 was created to test the old fix, and
it still passes with this applied.

Partial-revert-of: e1a4e37cc7 ("xfs: try to avoid blowing out the transaction reservation when bunmaping a shared extent")
Depends: 27dada070d ("xfs: change the order in which child and parent defer ops ar finished")
Depends: 74f4d6a1e0 ("xfs: only relog deferred intent items if free space in the log gets low")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
This commit is contained in:
Darrick J. Wong 2022-04-25 18:37:15 -07:00
parent c47260d4ea
commit 4ed6435cc3
2 changed files with 1 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
fs/xfs/libxfs/xfs_bmap.c
View File

@ -5280,7 +5280,6 @@ __xfs_bunmapi(
int whichfork; /* data or attribute fork */ int whichfork; /* data or attribute fork */
xfs_fsblock_t sum; xfs_fsblock_t sum;
xfs_filblks_t len = *rlen; /* length to unmap in file */ xfs_filblks_t len = *rlen; /* length to unmap in file */
xfs_fileoff_t max_len;
xfs_fileoff_t end; xfs_fileoff_t end;
struct xfs_iext_cursor icur; struct xfs_iext_cursor icur;
bool done = false; bool done = false;
@ -5299,16 +5298,6 @@ __xfs_bunmapi(
ASSERT(len > 0); ASSERT(len > 0);
ASSERT(nexts >= 0); ASSERT(nexts >= 0);
/*
* Guesstimate how many blocks we can unmap without running the risk of
* blowing out the transaction with a mix of EFIs and reflink
* adjustments.
*/
if (tp && xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res));
else
max_len = len;
error = xfs_iread_extents(tp, ip, whichfork); error = xfs_iread_extents(tp, ip, whichfork);
if (error) if (error)
return error; return error;
@ -5347,7 +5336,7 @@ __xfs_bunmapi(
extno = 0; extno = 0;
while (end != (xfs_fileoff_t)-1 && end >= start && while (end != (xfs_fileoff_t)-1 && end >= start &&
(nexts == 0 || extno < nexts) && max_len > 0) { (nexts == 0 || extno < nexts)) {
/* /*
* Is the found extent after a hole in which end lives? * Is the found extent after a hole in which end lives?
* Just back up to the previous extent, if so. * Just back up to the previous extent, if so.
@ -5381,14 +5370,6 @@ __xfs_bunmapi(
if (del.br_startoff + del.br_blockcount > end + 1) if (del.br_startoff + del.br_blockcount > end + 1)
del.br_blockcount = end + 1 - del.br_startoff; del.br_blockcount = end + 1 - del.br_startoff;
/* How much can we safely unmap? */
if (max_len < del.br_blockcount) {
del.br_startoff += del.br_blockcount - max_len;
if (!wasdel)
del.br_startblock += del.br_blockcount - max_len;
del.br_blockcount = max_len;
}
if (!isrt) if (!isrt)
goto delete; goto delete;
@ -5524,7 +5505,6 @@ delete:
if (error) if (error)
goto error0; goto error0;
max_len -= del.br_blockcount;
end = del.br_startoff - 1; end = del.br_startoff - 1;
nodelete: nodelete:
/* /*

5
fs/xfs/libxfs/xfs_refcount.h
View File

@ -78,11 +78,6 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
*/ */
#define XFS_REFCOUNT_ITEM_OVERHEAD 32 #define XFS_REFCOUNT_ITEM_OVERHEAD 32
static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
{
return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
}
extern int xfs_refcount_has_record(struct xfs_btree_cur *cur, extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
xfs_agblock_t bno, xfs_extlen_t len, bool *exists); xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
union xfs_btree_rec; union xfs_btree_rec;