Writing a large file using direct IO in 16 MB chunks sometimes results in a pathological allocation pattern where 16 MB chunks of large free extent are allocated to a file in a reversed order. So extents of a file look for example as: ext logical physical expected length flags 0 0 13 4550656 1 4550656 188136807 4550668 12562432 2 17113088 200699240 200699238 622592 3 17735680 182046055 201321831 4096 4 17739776 182041959 182050150 4096 5 17743872 182037863 182046054 4096 6 17747968 182033767 182041958 4096 7 17752064 182029671 182037862 4096 ... 6757 45400064 154381644 154389835 4096 6758 45404160 154377548 154385739 4096 6759 45408256 252951571 154381643 73728 eof This happens because XFS_ALLOCTYPE_THIS_BNO allocation fails (the last extent in the file cannot be further extended) so we fall back to XFS_ALLOCTYPE_NEAR_BNO allocation which picks end of a large free extent as the best place to continue the file. Since the chunk at the end of the free extent again cannot be further extended, this behavior repeats until the whole free extent is consumed in a reversed order. For data allocations this backward allocation isn't beneficial so make xfs_alloc_compute_diff() pick start of a free extent instead of its end for them. That avoids the backward allocation pattern. Based on idea by Dave Chinner <dchinner@xxxxxxxxxx>. CC: Dave Chinner <dchinner@xxxxxxxxxx> Signed-off-by: Jan Kara <jack@xxxxxxx> --- fs/xfs/xfs_alloc.c | 22 ++++++++++++++++------ 1 files changed, 16 insertions(+), 6 deletions(-) BTW, I've tested With this patch applied I really cannot reproduce the problematic allocation pattern anymore. diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 0ad2325..64c6247 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -173,6 +173,7 @@ xfs_alloc_compute_diff( xfs_agblock_t wantbno, /* target starting block */ xfs_extlen_t wantlen, /* target length */ xfs_extlen_t alignment, /* target alignment */ + char userdata, /* are we allocating data? */ xfs_agblock_t freebno, /* freespace's starting block */ xfs_extlen_t freelen, /* freespace's length */ xfs_agblock_t *newbnop) /* result: best start block from free */ @@ -187,7 +188,12 @@ xfs_alloc_compute_diff( ASSERT(freelen >= wantlen); freeend = freebno + freelen; wantend = wantbno + wantlen; - if (freebno >= wantbno) { + /* + * We want to allocate from the start of a free extent if it is past + * the desired block or if we are allocating user data and the free + * extent is before desired block. + */ + if (freebno >= wantbno || (userdata && freeend < wantend)) { if ((newbno1 = roundup(freebno, alignment)) >= freeend) newbno1 = NULLAGBLOCK; } else if (freeend >= wantend && alignment > 1) { @@ -772,7 +778,8 @@ xfs_alloc_find_best_extent( xfs_alloc_fix_len(args); sdiff = xfs_alloc_compute_diff(args->agbno, args->len, - args->alignment, *sbnoa, + args->alignment, + args->userdata, *sbnoa, *slena, &new); /* @@ -943,7 +950,8 @@ restart: if (args->len < blen) continue; ltdiff = xfs_alloc_compute_diff(args->agbno, args->len, - args->alignment, ltbnoa, ltlena, <new); + args->alignment, args->userdata, ltbnoa, + ltlena, <new); if (ltnew != NULLAGBLOCK && (args->len > blen || ltdiff < bdiff)) { bdiff = ltdiff; @@ -1095,7 +1103,8 @@ restart: args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen); xfs_alloc_fix_len(args); ltdiff = xfs_alloc_compute_diff(args->agbno, args->len, - args->alignment, ltbnoa, ltlena, <new); + args->alignment, args->userdata, ltbnoa, + ltlena, <new); error = xfs_alloc_find_best_extent(args, &bno_cur_lt, &bno_cur_gt, @@ -1111,7 +1120,8 @@ restart: args->len = XFS_EXTLEN_MIN(gtlena, args->maxlen); xfs_alloc_fix_len(args); gtdiff = xfs_alloc_compute_diff(args->agbno, args->len, - args->alignment, gtbnoa, gtlena, >new); + args->alignment, args->userdata, gtbnoa, + gtlena, >new); error = xfs_alloc_find_best_extent(args, &bno_cur_gt, &bno_cur_lt, @@ -1170,7 +1180,7 @@ restart: } rlen = args->len; (void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment, - ltbnoa, ltlena, <new); + args->userdata, ltbnoa, ltlena, <new); ASSERT(ltnew >= ltbno); ASSERT(ltnew + rlen <= ltbnoa + ltlena); ASSERT(ltnew + rlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length)); -- 1.7.1 _______________________________________________ xfs mailing list xfs@xxxxxxxxxxx http://oss.sgi.com/mailman/listinfo/xfs