![]() | |||||||||||||
Messages in this thread Patch in this message |
hi marcelo- this patch seems to address the extra read at the end of files or devices that end exactly on a page boundary, while retaining the good readahead characteristics of my original patch. i'd like to hear about any testing from folks who have one of: mpt fusion ips (ibm serveraid) promise ata (and maybe sata too) this patch is against 2.4.26-pre1. diff -X ../dont-diff -Naurp 00-stock/mm/filemap.c 01-readahead/mm/filemap.c --- 00-stock/mm/filemap.c 2004-02-18 08:36:32.000000000 -0500 +++ 01-readahead/mm/filemap.c 2004-03-02 00:07:59.000000000 -0500 @@ -1285,7 +1285,8 @@ static void generic_file_readahead(int r unsigned long raend; int max_readahead = get_max_readahead(inode); - end_index = inode->i_size >> PAGE_CACHE_SHIFT; + end_index = ((inode->i_size + ~PAGE_CACHE_MASK) >> + PAGE_CACHE_SHIFT) - 1; raend = filp->f_raend; max_ahead = 0; - Chuck Lever -- corporate: <cel at netapp dot com> personal: <chucklever at bigfoot dot com> - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ | ||||||||||||
| Last update: 2005-03-22 13:01 [W:0.626 / U:0.270 seconds] ©2003-2008 Jasper Spaans | |||||||||||||