From: Andrew Morton <akpm@zip.com.au> To: lkml <linux-kernel@vger.kernel.org> Subject: aa-150-read_write_tweaks Date: Tue, 19 Mar 2002 20:00:48 -0800 - Don't do flush_page_to_ram() on the page fault-in path. That's handled in mm/memory.c, and filemap.c doesn't need to do it. - In generic_file_write(), only set the page's Referenced bit once, when the write touches the start of the page. This is a microoptimisation. Seemingly a buggy one too - lseek exists... ===================================== --- 2.4.19-pre3/mm/filemap.c~aa-150-read_write_tweaks Tue Mar 19 19:49:02 2002 +++ 2.4.19-pre3-akpm/mm/filemap.c Tue Mar 19 19:49:02 2002 @@ -1968,7 +1968,6 @@ success: * and possibly copy it over to another page.. */ mark_page_accessed(page); - flush_page_to_ram(page); return page; no_cached_page: @@ -3089,8 +3088,15 @@ generic_file_write(struct file *file,con } unlock: kunmap(page); + + /* + * Mark the page accessed if we wrote the + * beginning or we just did an lseek. + */ + if (!offset || !file->f_reada) + SetPageReferenced(page); + /* Mark it unlocked again and drop the page.. */ - SetPageReferenced(page); UnlockPage(page); page_cache_release(page); - - 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/