From 14b064ceaa6f51a7426cc45b4b43685b94380658 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 27 Jan 2011 12:16:28 +1100 Subject: xfs: limit extent length for allocation to AG size Delayed allocation extents can be larger than AGs, so when trying to convert a large range we may scan every AG inside xfs_bmap_alloc_nullfb() trying to find an AG with a size larger than an AG. We should stop when we find the first AG with a maximum possible allocation size. This causes excessive CPU usage when there are lots of AGs. The same problem occurs when doing preallocation of a range larger than an AG. Fix the problem by limiting real allocation lengths to the maximum that an AG can support. This means if we have empty AGs, we'll stop the search at the first of them. If there are no empty AGs, we'll still scan them all, but that is a different problem.... Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Alex Elder --- fs/xfs/xfs_bmap.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'fs/xfs/xfs_bmap.c') diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 4111cd3966c..f3a3768189b 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -2430,7 +2430,7 @@ xfs_bmap_btalloc_nullfb( startag = ag = 0; pag = xfs_perag_get(mp, ag); - while (*blen < ap->alen) { + while (*blen < args->maxlen) { if (!pag->pagf_init) { error = xfs_alloc_pagf_init(mp, args->tp, ag, XFS_ALLOC_FLAG_TRYLOCK); @@ -2452,7 +2452,7 @@ xfs_bmap_btalloc_nullfb( notinit = 1; if (xfs_inode_is_filestream(ap->ip)) { - if (*blen >= ap->alen) + if (*blen >= args->maxlen) break; if (ap->userdata) { @@ -2498,14 +2498,14 @@ xfs_bmap_btalloc_nullfb( * If the best seen length is less than the request * length, use the best as the minimum. */ - else if (*blen < ap->alen) + else if (*blen < args->maxlen) args->minlen = *blen; /* - * Otherwise we've seen an extent as big as alen, + * Otherwise we've seen an extent as big as maxlen, * use that as the minimum. */ else - args->minlen = ap->alen; + args->minlen = args->maxlen; /* * set the failure fallback case to look in the selected @@ -2573,7 +2573,9 @@ xfs_bmap_btalloc( args.tp = ap->tp; args.mp = mp; args.fsbno = ap->rval; - args.maxlen = MIN(ap->alen, mp->m_sb.sb_agblocks); + + /* Trim the allocation back to the maximum an AG can fit. */ + args.maxlen = MIN(ap->alen, XFS_ALLOC_AG_MAX_USABLE(mp)); args.firstblock = ap->firstblock; blen = 0; if (nullfb) { @@ -2621,7 +2623,7 @@ xfs_bmap_btalloc( /* * Adjust for alignment */ - if (blen > args.alignment && blen <= ap->alen) + if (blen > args.alignment && blen <= args.maxlen) args.minlen = blen - args.alignment; args.minalignslop = 0; } else { @@ -2640,7 +2642,7 @@ xfs_bmap_btalloc( * of minlen+alignment+slop doesn't go up * between the calls. */ - if (blen > mp->m_dalign && blen <= ap->alen) + if (blen > mp->m_dalign && blen <= args.maxlen) nextminlen = blen - mp->m_dalign; else nextminlen = args.minlen; -- cgit v1.2.3-70-g09d2 From 4ce159890c00e2cc705e955a939bf1dca7b07ab8 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 27 Jan 2011 12:17:58 +1100 Subject: xfs: prevent extsize alignment from exceeding maximum extent size When doing delayed allocation, if the allocation size is for a maximally sized extent, extent size alignment can push it over this limit. This results in an assert failure in xfs_bmbt_set_allf() as the extent length is too large to find in the extent record. Fix this by ensuring that we allow for space that extent size alignment requires (up to 2 * (extsize -1) blocks as we have to handle both head and tail alignment) when limiting the maximum size of the extent. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Alex Elder --- fs/xfs/xfs_bmap.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs/xfs/xfs_bmap.c') diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index f3a3768189b..3e9c278a8f7 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -4487,6 +4487,16 @@ xfs_bmapi( /* Figure out the extent size, adjust alen */ extsz = xfs_get_extsz_hint(ip); if (extsz) { + /* + * make sure we don't exceed a single + * extent length when we align the + * extent by reducing length we are + * going to allocate by the maximum + * amount extent size aligment may + * require. + */ + alen = XFS_FILBLKS_MIN(len, + MAXEXTLEN - (2 * extsz - 1)); error = xfs_bmap_extsize_align(mp, &got, &prev, extsz, rt, eof, -- cgit v1.2.3-70-g09d2 From 24446fc66fdebbdd8baca0f44fd2a47ad77ba580 Mon Sep 17 00:00:00 2001 From: "bpm@sgi.com" Date: Wed, 19 Jan 2011 17:41:58 +0000 Subject: xfs: xfs_bmap_add_extent_delay_real should init br_startblock When filling in the middle of a previous delayed allocation in xfs_bmap_add_extent_delay_real, set br_startblock of the new delay extent to the right to nullstartblock instead of 0 before inserting the extent into the ifork (xfs_iext_insert), rather than setting br_startblock afterward. Adding the extent into the ifork with br_startblock=0 can lead to the extent being copied into the btree by xfs_bmap_extent_to_btree if we happen to convert from extents format to btree format before updating br_startblock with the correct value. The unexpected addition of this delay extent to the btree can cause subsequent XFS_WANT_CORRUPTED_GOTO filesystem shutdown in several xfs_bmap_add_extent_delay_real cases where we are converting a delay extent to real and unexpectedly find an extent already inserted. For example: 911 case BMAP_LEFT_FILLING: 912 /* 913 * Filling in the first part of a previous delayed allocation. 914 * The left neighbor is not contiguous. 915 */ 916 trace_xfs_bmap_pre_update(ip, idx, state, _THIS_IP_); 917 xfs_bmbt_set_startoff(ep, new_endoff); 918 temp = PREV.br_blockcount - new->br_blockcount; 919 xfs_bmbt_set_blockcount(ep, temp); 920 xfs_iext_insert(ip, idx, 1, new, state); 921 ip->i_df.if_lastex = idx; 922 ip->i_d.di_nextents++; 923 if (cur == NULL) 924 rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; 925 else { 926 rval = XFS_ILOG_CORE; 927 if ((error = xfs_bmbt_lookup_eq(cur, new->br_startoff, 928 new->br_startblock, new->br_blockcount, 929 &i))) 930 goto done; 931 XFS_WANT_CORRUPTED_GOTO(i == 0, done); With the bogus extent in the btree we shutdown the filesystem at 931. The conversion from extents to btree format happens when the number of extents in the inode increases above ip->i_df.if_ext_max. xfs_bmap_extent_to_btree copies extents from the ifork into the btree, ignoring all delalloc extents which are denoted by br_startblock having some value of nullstartblock. SGI-PV: 1013221 Signed-off-by: Ben Myers Reviewed-by: Dave Chinner Signed-off-by: Alex Elder --- fs/xfs/xfs_bmap.c | 33 +++++++++++++++++++++++++-------- 1 file changed, 25 insertions(+), 8 deletions(-) (limited to 'fs/xfs/xfs_bmap.c') diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 3e9c278a8f7..dc3afd7739f 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -1038,17 +1038,34 @@ xfs_bmap_add_extent_delay_real( * Filling in the middle part of a previous delayed allocation. * Contiguity is impossible here. * This case is avoided almost all the time. + * + * We start with a delayed allocation: + * + * +ddddddddddddddddddddddddddddddddddddddddddddddddddddddd+ + * PREV @ idx + * + * and we are allocating: + * +rrrrrrrrrrrrrrrrr+ + * new + * + * and we set it up for insertion as: + * +ddddddddddddddddddd+rrrrrrrrrrrrrrrrr+ddddddddddddddddd+ + * new + * PREV @ idx LEFT RIGHT + * inserted at idx + 1 */ temp = new->br_startoff - PREV.br_startoff; - trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - r[0] = *new; - r[1].br_state = PREV.br_state; - r[1].br_startblock = 0; - r[1].br_startoff = new_endoff; temp2 = PREV.br_startoff + PREV.br_blockcount - new_endoff; - r[1].br_blockcount = temp2; - xfs_iext_insert(ip, idx + 1, 2, &r[0], state); + trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_); + xfs_bmbt_set_blockcount(ep, temp); /* truncate PREV */ + LEFT = *new; + RIGHT.br_state = PREV.br_state; + RIGHT.br_startblock = nullstartblock( + (int)xfs_bmap_worst_indlen(ip, temp2)); + RIGHT.br_startoff = new_endoff; + RIGHT.br_blockcount = temp2; + /* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */ + xfs_iext_insert(ip, idx + 1, 2, &LEFT, state); ip->i_df.if_lastex = idx + 1; ip->i_d.di_nextents++; if (cur == NULL) -- cgit v1.2.3-70-g09d2