Hi, On Monday 02 July 2007 02:38 pm, Bernd Schubert wrote: ... <snip> > PS: I took over this bug from the ldiskfs patch-sets of lustre-1.6.0.1 for > linux-2.6.18, so the very same bug is also present there. > In bug#11039 are more recent extents/mballoc patches for linux-2.6.18 and I > used these patches to fix the problem.
can someone help me which patches one should use in addition or instead of the patches for the lustre 1.6.0.1 2.6.18-vanilla patch series, to avoid data corruption with kernel 2.6.18? I'm a little bit confused, because I'm using lustre-1.6.0.1 on debian sarge with vanilla kernel 2.6.18.8 since a couple of weeks without any problem. (32-Bit only 1 MDS/MGS shared, 2 OSS with 3 OST each, about 40 clients) Therefore I don't want to make things worse by applying a wrong patch. But on the other hand I don't want to wait until I get a corrupted file system. Thanks in advance Harald _______________________________________________ Lustre-discuss mailing list [email protected] https://mail.clusterfs.com/mailman/listinfo/lustre-discuss
