| To: | Stephen Lord <lord@xxxxxxx> |
|---|---|
| Subject: | Re: TAKE - make xfs's in memory extents host byte ordered |
| From: | Andi Kleen <ak@xxxxxxx> |
| Date: | Fri, 11 Oct 2002 03:04:51 +0200 |
| Cc: | Andi Kleen <ak@xxxxxxx>, linux-xfs@xxxxxxxxxxx |
| In-reply-to: | <1034296295.1074.28.camel@laptop.americas.sgi.com> |
| References: | <200210101909.g9AJ9pd12773@jen.americas.sgi.com> <20021010213259.A23019@wotan.suse.de> <1034296295.1074.28.camel@laptop.americas.sgi.com> |
| Sender: | linux-xfs-bounce@xxxxxxxxxxx |
| User-agent: | Mutt/1.3.22.1i |
Try this patch and see if it fixes the performance problem without
your XFS change.
Without it the 64bit change would not use BSWAP, but some horribly
handcoded version.
-Andi
--- linux/include/linux/byteorder/swab.h-o 2001-07-26 22:45:47.000000000
+0200
+++ linux/include/linux/byteorder/swab.h 2002-10-11 03:03:32.000000000
+0200
@@ -167,11 +167,11 @@
}
static __inline__ __u64 __swab64p(__u64 *x)
{
- return __arch__swab64p(x);
+ *x = __fswab64(*addr);
}
static __inline__ void __swab64s(__u64 *addr)
{
- __arch__swab64s(addr);
+ *addr = __fswab64(*addr);
}
#endif /* __BYTEORDER_HAS_U64__ */
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Xfs_force_shutdown on recent XFS CVS, Chris Wedgwood |
|---|---|
| Next by Date: | correct patch was Re: TAKE - make xfs's in memory extents host byte ordered, Andi Kleen |
| Previous by Thread: | Re: TAKE - make xfs's in memory extents host byte ordered, Stephen Lord |
| Next by Thread: | correct patch was Re: TAKE - make xfs's in memory extents host byte ordered, Andi Kleen |
| Indexes: | [Date] [Thread] [Top] [All Lists] |