mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 04:31:50 +00:00
xfs: less heavy locks during fstrim [v30.3 14/16]
Congratulations! You have made it to the final patchset of the main online fsck feature! This patchset fixes some stalling behavior that I observed when running FITRIM against large flash-based filesystems with very heavily fragmented free space data. In summary -- the current fstrim implementation optimizes for trimming the largest free extents first, and holds the AGF lock for the duration of the operation. This is great if fstrim is being run as a foreground process by a sysadmin. For xfs_scrub, however, this isn't so good -- we don't really want to block on one huge kernel call while reporting no progress information. We don't want to hold the AGF so long that background processes stall. These problems are easily fixable by issuing smaller FITRIM calls, but there's still the problem of walking the entire cntbt. To solve that second problem, we introduce a new sub-AG FITRIM implementation. To solve the first problem, make it relax the AGF periodically. This has been running on the djcloud for months with no problems. Enjoy! Signed-off-by: Darrick J. Wong <djwong@kernel.org> -----BEGIN PGP SIGNATURE----- iHUEABYKAB0WIQQ2qTKExjcn+O1o2YRKO3ySh0YRpgUCZh23VAAKCRBKO3ySh0YR pnLkAP9dlH5LKtJLK7Wbl3GC0EjPBUaX6a/nmkJPBIMocdautAD/X6J8ItPkx885 26qzJSXeapMIXVS1olUPuUL6B3jW/gE= =HS4c -----END PGP SIGNATURE----- Merge tag 'discard-relax-locks-6.10_2024-04-15' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.10-mergeA xfs: less heavy locks during fstrim Congratulations! You have made it to the final patchset of the main online fsck feature! This patchset fixes some stalling behavior that I observed when running FITRIM against large flash-based filesystems with very heavily fragmented free space data. In summary -- the current fstrim implementation optimizes for trimming the largest free extents first, and holds the AGF lock for the duration of the operation. This is great if fstrim is being run as a foreground process by a sysadmin. For xfs_scrub, however, this isn't so good -- we don't really want to block on one huge kernel call while reporting no progress information. We don't want to hold the AGF so long that background processes stall. These problems are easily fixable by issuing smaller FITRIM calls, but there's still the problem of walking the entire cntbt. To solve that second problem, we introduce a new sub-AG FITRIM implementation. To solve the first problem, make it relax the AGF periodically. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Chandan Babu R <chandanbabu@kernel.org> * tag 'discard-relax-locks-6.10_2024-04-15' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux: xfs: fix performance problems when fstrimming a subset of a fragmented AG
This commit is contained in:
Chandan Babu R
commit
6ad1b91470
@ -145,14 +145,18 @@ xfs_discard_extents(
|
||||
return error;
|
||||
}
|
||||
|
||||
struct xfs_trim_cur {
|
||||
xfs_agblock_t start;
|
||||
xfs_extlen_t count;
|
||||
xfs_agblock_t end;
|
||||
xfs_extlen_t minlen;
|
||||
bool by_bno;
|
||||
};
|
||||
|
||||
static int
|
||||
xfs_trim_gather_extents(
|
||||
struct xfs_perag *pag,
|
||||
xfs_daddr_t start,
|
||||
xfs_daddr_t end,
|
||||
xfs_daddr_t minlen,
|
||||
struct xfs_alloc_rec_incore *tcur,
|
||||
struct xfs_trim_cur *tcur,
|
||||
struct xfs_busy_extents *extents,
|
||||
uint64_t *blocks_trimmed)
|
||||
{
|
||||
@ -179,21 +183,26 @@ xfs_trim_gather_extents(
|
||||
if (error)
|
||||
goto out_trans_cancel;
|
||||
|
||||
cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag);
|
||||
|
||||
/*
|
||||
* Look up the extent length requested in the AGF and start with it.
|
||||
*/
|
||||
if (tcur->ar_startblock == NULLAGBLOCK)
|
||||
error = xfs_alloc_lookup_ge(cur, 0, tcur->ar_blockcount, &i);
|
||||
else
|
||||
error = xfs_alloc_lookup_le(cur, tcur->ar_startblock,
|
||||
tcur->ar_blockcount, &i);
|
||||
if (tcur->by_bno) {
|
||||
/* sub-AG discard request always starts at tcur->start */
|
||||
cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag);
|
||||
error = xfs_alloc_lookup_le(cur, tcur->start, 0, &i);
|
||||
if (!error && !i)
|
||||
error = xfs_alloc_lookup_ge(cur, tcur->start, 0, &i);
|
||||
} else if (tcur->start == 0) {
|
||||
/* first time through a by-len starts with max length */
|
||||
cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag);
|
||||
error = xfs_alloc_lookup_ge(cur, 0, tcur->count, &i);
|
||||
} else {
|
||||
/* nth time through a by-len starts where we left off */
|
||||
cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag);
|
||||
error = xfs_alloc_lookup_le(cur, tcur->start, tcur->count, &i);
|
||||
}
|
||||
if (error)
|
||||
goto out_del_cursor;
|
||||
if (i == 0) {
|
||||
/* nothing of that length left in the AG, we are done */
|
||||
tcur->ar_blockcount = 0;
|
||||
tcur->count = 0;
|
||||
goto out_del_cursor;
|
||||
}
|
||||
|
||||
@ -204,8 +213,6 @@ xfs_trim_gather_extents(
|
||||
while (i) {
|
||||
xfs_agblock_t fbno;
|
||||
xfs_extlen_t flen;
|
||||
xfs_daddr_t dbno;
|
||||
xfs_extlen_t dlen;
|
||||
|
||||
error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
|
||||
if (error)
|
||||
@ -221,37 +228,45 @@ xfs_trim_gather_extents(
|
||||
* Update the cursor to point at this extent so we
|
||||
* restart the next batch from this extent.
|
||||
*/
|
||||
tcur->ar_startblock = fbno;
|
||||
tcur->ar_blockcount = flen;
|
||||
break;
|
||||
}
|
||||
|
||||
/*
|
||||
* use daddr format for all range/len calculations as that is
|
||||
* the format the range/len variables are supplied in by
|
||||
* userspace.
|
||||
*/
|
||||
dbno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, fbno);
|
||||
dlen = XFS_FSB_TO_BB(mp, flen);
|
||||
|
||||
/*
|
||||
* Too small? Give up.
|
||||
*/
|
||||
if (dlen < minlen) {
|
||||
trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
|
||||
tcur->ar_blockcount = 0;
|
||||
tcur->start = fbno;
|
||||
tcur->count = flen;
|
||||
break;
|
||||
}
|
||||
|
||||
/*
|
||||
* If the extent is entirely outside of the range we are
|
||||
* supposed to discard skip it. Do not bother to trim
|
||||
* down partially overlapping ranges for now.
|
||||
* supposed to skip it. Do not bother to trim down partially
|
||||
* overlapping ranges for now.
|
||||
*/
|
||||
if (dbno + dlen < start || dbno > end) {
|
||||
if (fbno + flen < tcur->start) {
|
||||
trace_xfs_discard_exclude(mp, pag->pag_agno, fbno, flen);
|
||||
goto next_extent;
|
||||
}
|
||||
if (fbno > tcur->end) {
|
||||
trace_xfs_discard_exclude(mp, pag->pag_agno, fbno, flen);
|
||||
if (tcur->by_bno) {
|
||||
tcur->count = 0;
|
||||
break;
|
||||
}
|
||||
goto next_extent;
|
||||
}
|
||||
|
||||
/* Trim the extent returned to the range we want. */
|
||||
if (fbno < tcur->start) {
|
||||
flen -= tcur->start - fbno;
|
||||
fbno = tcur->start;
|
||||
}
|
||||
if (fbno + flen > tcur->end + 1)
|
||||
flen = tcur->end - fbno + 1;
|
||||
|
||||
/* Too small? Give up. */
|
||||
if (flen < tcur->minlen) {
|
||||
trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
|
||||
if (tcur->by_bno)
|
||||
goto next_extent;
|
||||
tcur->count = 0;
|
||||
break;
|
||||
}
|
||||
|
||||
/*
|
||||
* If any blocks in the range are still busy, skip the
|
||||
@ -266,7 +281,10 @@ xfs_trim_gather_extents(
|
||||
&extents->extent_list);
|
||||
*blocks_trimmed += flen;
|
||||
next_extent:
|
||||
error = xfs_btree_decrement(cur, 0, &i);
|
||||
if (tcur->by_bno)
|
||||
error = xfs_btree_increment(cur, 0, &i);
|
||||
else
|
||||
error = xfs_btree_decrement(cur, 0, &i);
|
||||
if (error)
|
||||
break;
|
||||
|
||||
@ -276,7 +294,7 @@ next_extent:
|
||||
* is no more extents to search.
|
||||
*/
|
||||
if (i == 0)
|
||||
tcur->ar_blockcount = 0;
|
||||
tcur->count = 0;
|
||||
}
|
||||
|
||||
/*
|
||||
@ -306,17 +324,22 @@ xfs_trim_should_stop(void)
|
||||
static int
|
||||
xfs_trim_extents(
|
||||
struct xfs_perag *pag,
|
||||
xfs_daddr_t start,
|
||||
xfs_daddr_t end,
|
||||
xfs_daddr_t minlen,
|
||||
xfs_agblock_t start,
|
||||
xfs_agblock_t end,
|
||||
xfs_extlen_t minlen,
|
||||
uint64_t *blocks_trimmed)
|
||||
{
|
||||
struct xfs_alloc_rec_incore tcur = {
|
||||
.ar_blockcount = pag->pagf_longest,
|
||||
.ar_startblock = NULLAGBLOCK,
|
||||
struct xfs_trim_cur tcur = {
|
||||
.start = start,
|
||||
.count = pag->pagf_longest,
|
||||
.end = end,
|
||||
.minlen = minlen,
|
||||
};
|
||||
int error = 0;
|
||||
|
||||
if (start != 0 || end != pag->block_count)
|
||||
tcur.by_bno = true;
|
||||
|
||||
do {
|
||||
struct xfs_busy_extents *extents;
|
||||
|
||||
@ -330,8 +353,8 @@ xfs_trim_extents(
|
||||
extents->owner = extents;
|
||||
INIT_LIST_HEAD(&extents->extent_list);
|
||||
|
||||
error = xfs_trim_gather_extents(pag, start, end, minlen,
|
||||
&tcur, extents, blocks_trimmed);
|
||||
error = xfs_trim_gather_extents(pag, &tcur, extents,
|
||||
blocks_trimmed);
|
||||
if (error) {
|
||||
kfree(extents);
|
||||
break;
|
||||
@ -354,7 +377,7 @@ xfs_trim_extents(
|
||||
if (xfs_trim_should_stop())
|
||||
break;
|
||||
|
||||
} while (tcur.ar_blockcount != 0);
|
||||
} while (tcur.count != 0);
|
||||
|
||||
return error;
|
||||
|
||||
@ -378,8 +401,10 @@ xfs_ioc_trim(
|
||||
unsigned int granularity =
|
||||
bdev_discard_granularity(mp->m_ddev_targp->bt_bdev);
|
||||
struct fstrim_range range;
|
||||
xfs_daddr_t start, end, minlen;
|
||||
xfs_agnumber_t agno;
|
||||
xfs_daddr_t start, end;
|
||||
xfs_extlen_t minlen;
|
||||
xfs_agnumber_t start_agno, end_agno;
|
||||
xfs_agblock_t start_agbno, end_agbno;
|
||||
uint64_t blocks_trimmed = 0;
|
||||
int error, last_error = 0;
|
||||
|
||||
@ -399,7 +424,8 @@ xfs_ioc_trim(
|
||||
return -EFAULT;
|
||||
|
||||
range.minlen = max_t(u64, granularity, range.minlen);
|
||||
minlen = BTOBB(range.minlen);
|
||||
minlen = XFS_B_TO_FSB(mp, range.minlen);
|
||||
|
||||
/*
|
||||
* Truncating down the len isn't actually quite correct, but using
|
||||
* BBTOB would mean we trivially get overflows for values
|
||||
@ -413,15 +439,21 @@ xfs_ioc_trim(
|
||||
return -EINVAL;
|
||||
|
||||
start = BTOBB(range.start);
|
||||
end = start + BTOBBT(range.len) - 1;
|
||||
end = min_t(xfs_daddr_t, start + BTOBBT(range.len),
|
||||
XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) - 1;
|
||||
|
||||
if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
|
||||
end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1;
|
||||
start_agno = xfs_daddr_to_agno(mp, start);
|
||||
start_agbno = xfs_daddr_to_agbno(mp, start);
|
||||
end_agno = xfs_daddr_to_agno(mp, end);
|
||||
end_agbno = xfs_daddr_to_agbno(mp, end);
|
||||
|
||||
agno = xfs_daddr_to_agno(mp, start);
|
||||
for_each_perag_range(mp, agno, xfs_daddr_to_agno(mp, end), pag) {
|
||||
error = xfs_trim_extents(pag, start, end, minlen,
|
||||
&blocks_trimmed);
|
||||
for_each_perag_range(mp, start_agno, end_agno, pag) {
|
||||
xfs_agblock_t agend = pag->block_count;
|
||||
|
||||
if (start_agno == end_agno)
|
||||
agend = end_agbno;
|
||||
error = xfs_trim_extents(pag, start_agbno, agend, minlen,
|
||||
&blocks_trimmed);
|
||||
if (error)
|
||||
last_error = error;
|
||||
|
||||
@ -429,6 +461,7 @@ xfs_ioc_trim(
|
||||
xfs_perag_rele(pag);
|
||||
break;
|
||||
}
|
||||
start_agbno = 0;
|
||||
}
|
||||
|
||||
if (last_error)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user