GFS2: Implement a "rgrp has no extents longer than X" scheme

With the preceding patch, we started accepting block reservations
smaller than the ideal size, which requires a lot more parsing of the
bitmaps. To reduce the amount of bitmap searching, this patch
implements a scheme whereby each rgrp keeps track of the point
at this multi-block reservations will fail.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index ba1ea67f4eeb1c99e826f54be8b9b6d8d57909f8..01328162c9527503536e4e95c4a6fdcb3d4caa58 100644 (file)
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -93,6 +93,7 @@ struct gfs2_rgrpd {
        struct gfs2_rgrp_lvb *rd_rgl;
        u32 rd_last_alloc;
        u32 rd_flags;
+       u32 rd_extfail_pt;              /* extent failure point */
 #define GFS2_RDF_CHECK         0x10000000 /* check for unlinked inodes */
 #define GFS2_RDF_UPTODATE      0x20000000 /* rg is up to date */
 #define GFS2_RDF_ERROR         0x40000000 /* error in rg */

diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 010b9fb9fec6e781cb80a6982d746896ba6cffdb..cdadb92372f23e9a2d4ce6ed56306b019e7535fb 100644 (file)
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -83,6 +83,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd)
               bd->bd_bh->b_data + bi->bi_offset, bi->bi_len);
        clear_bit(GBF_FULL, &bi->bi_flags);
        rgd->rd_free_clone = rgd->rd_free;
+       rgd->rd_extfail_pt = rgd->rd_free;
 }
 
 /**

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 1ccf89ab42b676c4abd7047819074316c9255fc8..797f1d3114ef22684fed08d076e9d329d01c8807 100644 (file)
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -641,9 +641,13 @@ static void __rs_deltree(struct gfs2_blkreserv *rs)
                /* return reserved blocks to the rgrp */
                BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free);
                rs->rs_rbm.rgd->rd_reserved -= rs->rs_free;
+               /* The rgrp extent failure point is likely not to increase;
+                  it will only do so if the freed blocks are somehow
+                  contiguous with a span of free blocks that follows. Still,
+                  it will force the number to be recalculated later. */
+               rgd->rd_extfail_pt += rs->rs_free;
                rs->rs_free = 0;
                clear_bit(GBF_FULL, &bi->bi_flags);
-               smp_mb__after_clear_bit();
        }
 }
 
@@ -1132,6 +1136,8 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
                gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
                rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
                rgd->rd_free_clone = rgd->rd_free;
+               /* max out the rgrp allocation failure point */
+               rgd->rd_extfail_pt = rgd->rd_free;
        }
        if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) {
                rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd));
@@ -1593,6 +1599,8 @@ fail:
  * Side effects:
  * - If looking for free blocks, we set GBF_FULL on each bitmap which
  *   has no free blocks in it.
+ * - If looking for free blocks, we set rd_extfail_pt on each rgrp which
+ *   has come up short on a free block search.
  *
  * Returns: 0 on success, -ENOSPC if there is no block of the requested state
  */
@@ -1604,6 +1612,8 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
        struct buffer_head *bh;
        int initial_bii;
        u32 initial_offset;
+       int first_bii = rbm->bii;
+       u32 first_offset = rbm->offset;
        u32 offset;
        u8 *buffer;
        int n = 0;
@@ -1679,6 +1689,13 @@ next_iter:
        if (minext == NULL || state != GFS2_BLKST_FREE)
                return -ENOSPC;
 
+       /* If the extent was too small, and it's smaller than the smallest
+          to have failed before, remember for future reference that it's
+          useless to search this rgrp again for this amount or more. */
+       if ((first_offset == 0) && (first_bii == 0) &&
+           (*minext < rbm->rgd->rd_extfail_pt))
+               rbm->rgd->rd_extfail_pt = *minext;
+
        /* If the maximum extent we found is big enough to fulfill the
           minimum requirements, use it anyway. */
        if (maxext.len) {
@@ -1924,7 +1941,9 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a
                }
 
                /* Skip unuseable resource groups */
-               if (rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR))
+               if ((rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC |
+                                                GFS2_RDF_ERROR)) ||
+                   (ap && (ap->target > rs->rs_rbm.rgd->rd_extfail_pt)))
                        goto skip_rgrp;
 
                if (sdp->sd_args.ar_rgrplvb)
@@ -2106,10 +2125,10 @@ int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl)
 
        if (rgd == NULL)
                return 0;
-       gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u r:%u\n",
+       gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u r:%u e:%u\n",
                       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
                       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes,
-                      rgd->rd_reserved);
+                      rgd->rd_reserved, rgd->rd_extfail_pt);
        spin_lock(&rgd->rd_rsspin);
        for (n = rb_first(&rgd->rd_rstree); n; n = rb_next(&trs->rs_node)) {
                trs = rb_entry(n, struct gfs2_blkreserv, rs_node);
@@ -2228,9 +2247,10 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 
        /* Since all blocks are reserved in advance, this shouldn't happen */
        if (error) {
-               fs_warn(sdp, "inum=%llu error=%d, nblocks=%u, full=%d\n",
+               fs_warn(sdp, "inum=%llu error=%d, nblocks=%u, full=%d fail_pt=%d\n",
                        (unsigned long long)ip->i_no_addr, error, *nblocks,
-                       test_bit(GBF_FULL, &rbm.rgd->rd_bits->bi_flags));
+                       test_bit(GBF_FULL, &rbm.rgd->rd_bits->bi_flags),
+                       rbm.rgd->rd_extfail_pt);
                goto rgrp_error;
        }