Commit 65adc273 authored by Andrew Price's avatar Andrew Price Committed by Bob Peterson

gfs2: Add a next-resource-group pointer to resource groups

Add a new rg_skip field to struct gfs2_rgrp, replacing __pad. The
rg_skip field has the following meaning:

- If rg_skip is zero, it is considered unset and not useful.
- If rg_skip is non-zero, its value will be the number of blocks between
  this rgrp's address and the next rgrp's address. This can be used as a
  hint by fsck.gfs2 when rebuilding a bad rindex, for example.

This will provide less dependency on the rindex in future, and allow
tools such as fsck.gfs2 to iterate the resource groups without keeping
the rindex around.

The field is updated in gfs2_rgrp_out() so that existing file systems
will have it set. This means that any resource groups that aren't ever
written will not be updated. The final rgrp is a special case as there
is no next rgrp, so it will always have a rg_skip of 0 (unless the fs is
extended).

Before this patch, gfs2_rgrp_out() zeroes the __pad field explicitly, so
the rg_skip field can get set back to 0 in cases where nodes with and
without this patch are mixed in a cluster. In some cases, the field may
bounce between being set by one node and then zeroed by another which
may harm performance slightly, e.g. when two nodes create many small
files. In testing this situation is rare but it becomes more likely as
the filesystem fills up and there are fewer resource groups to choose
from. The problem goes away when all nodes are running with this patch.
Dipping into the space currently occupied by the rg_reserved field would
have resulted in the same problem as it is also explicitly zeroed, so
unfortunately there is no other way around it.
Signed-off-by: default avatarAndrew Price <anprice@redhat.com>
Signed-off-by: default avatarBob Peterson <rpeterso@redhat.com>
parent 9aa01593
...@@ -1044,12 +1044,16 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf) ...@@ -1044,12 +1044,16 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf) static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
{ {
struct gfs2_rgrpd *next = gfs2_rgrpd_get_next(rgd);
struct gfs2_rgrp *str = buf; struct gfs2_rgrp *str = buf;
str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK); str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK);
str->rg_free = cpu_to_be32(rgd->rd_free); str->rg_free = cpu_to_be32(rgd->rd_free);
str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes); str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes);
str->__pad = cpu_to_be32(0); if (next == NULL)
str->rg_skip = 0;
else if (next->rd_addr > rgd->rd_addr)
str->rg_skip = cpu_to_be32(next->rd_addr - rgd->rd_addr);
str->rg_igeneration = cpu_to_be64(rgd->rd_igeneration); str->rg_igeneration = cpu_to_be64(rgd->rd_igeneration);
memset(&str->rg_reserved, 0, sizeof(str->rg_reserved)); memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
} }
......
...@@ -187,7 +187,10 @@ struct gfs2_rgrp { ...@@ -187,7 +187,10 @@ struct gfs2_rgrp {
__be32 rg_flags; __be32 rg_flags;
__be32 rg_free; __be32 rg_free;
__be32 rg_dinodes; __be32 rg_dinodes;
union {
__be32 __pad; __be32 __pad;
__be32 rg_skip; /* Distance to the next rgrp in fs blocks */
};
__be64 rg_igeneration; __be64 rg_igeneration;
__u8 rg_reserved[80]; /* Several fields from gfs1 now reserved */ __u8 rg_reserved[80]; /* Several fields from gfs1 now reserved */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment