Jan hello
I am referring to xfs awareness over linux software raid .
I noticed that though all single file extents beginnings are aligned
over a raid
stripe unit, they do not end aligned. this thing degrades a sequential read
performance over a raid.
I have fixed the code as follows:
--- linux-2.6.17-SMP/fs/xfs/xfs_iomap.c 2007-01-16 08:53:52.000000000 +0000
+++ linux-2.6.17-Vanilla/fs/xfs/xfs_iomap.c 2006-06-18
01:49:35.000000000 +0000
@@ -441,8 +441,8 @@ xfs_iomap_write_direct(
if (unlikely(rt)) {
if (!(extsz = ip->i_d.di_extsize))
extsz = mp->m_sb.sb_rextsize;
- } else {
- extsz = mp->m_dalign; // raz fix alignment to raid stripe unit
+ } else {
+ extsz = ip->i_d.di_extsize;
}
isize = ip->i_d.di_size;
@@ -663,7 +663,7 @@ xfs_iomap_write_delay(
if (!(extsz = ip->i_d.di_extsize))
extsz = mp->m_sb.sb_rextsize;
} else {
- extsz = mp->m_dalign; // raz fix alignment to raid stripe unit
+ extsz = ip->i_d.di_extsize;
}
offset_fsb = XFS_B_TO_FSBT(mp, offset);
This seems to work.
My question is , is there a mistake that i have made which i do not
see ?
I would realy appreciate any comment .
thank you
--
Raz
-
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
