Re: [PATCH 2/2] xfs: retry allocations when locality-based search fails
From: Allison Henderson <hidden>
Date: 2021-05-06 05:26:38
On 5/3/21 2:34 PM, Darrick J. Wong wrote:
From: Darrick J. Wong <djwong@kernel.org> If a realtime allocation fails because we can't find a sufficiently large free extent satisfying locality rules, relax the locality rules and try again. This reduces the occurrence of short writes to realtime files when the write size is large and the free space is fragmented. This was originally discovered by running generic/186 with the realtime reflink patchset and a 128k cow extent size hint, but the same problem can manifest with a 128k extent size hint, so applies the fix now. Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Ok, makes sense. Reviewed-by: Allison Henderson <redacted>
quoted hunk ↗ jump to hunk
--- fs/xfs/xfs_bmap_util.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index c9381bf4f04b..0936f3a96fe6 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c@@ -84,6 +84,7 @@ xfs_bmap_rtalloc( xfs_extlen_t minlen = mp->m_sb.sb_rextsize; xfs_extlen_t raminlen; bool rtlocked = false; + bool ignore_locality = false; int error; align = xfs_get_extsz_hint(ap->ip);@@ -158,7 +159,10 @@ xfs_bmap_rtalloc( /* * Realtime allocation, done through xfs_rtallocate_extent. */ - do_div(ap->blkno, mp->m_sb.sb_rextsize); + if (ignore_locality) + ap->blkno = 0; + else + do_div(ap->blkno, mp->m_sb.sb_rextsize); rtb = ap->blkno; ap->length = ralen; raminlen = max_t(xfs_extlen_t, 1, minlen / mp->m_sb.sb_rextsize);@@ -197,6 +201,15 @@ xfs_bmap_rtalloc( goto retry; } + if (!ignore_locality && ap->blkno != 0) { + /* + * If we can't allocate near a specific rt extent, try again + * without locality criteria. + */ + ignore_locality = true; + goto retry; + } + ap->blkno = NULLFSBLOCK; ap->length = 0; return 0;