commit 6d2be915 (mm/readahead.c: fix readahead failure for memoryless NUMA nodes and limit readahead pages) imposed 2MB limits to readahed that yielded good performance since it avoided unnecessay page caching. However it broke sys_readahead semantics: 'readahead() blocks until the specified data has been read' This patch still retains the fix for memoryless nodes which used to return zero and limits its readahead to 2MB to avoid unnecessary page cache thrashing but reverts to old sanitized readahead for cpu with memory nodes. link: https://bugzilla.kernel.org/show_bug.cgi?id=79111 Signed-off-by: Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx> --- mm/readahead.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/mm/readahead.c b/mm/readahead.c index 0ca36a7..4514cf6 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -239,6 +239,24 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, */ unsigned long max_sane_readahead(unsigned long nr) { + unsigned long local_free_page; + int nid; + + nid = numa_node_id(); + if (node_present_pages(nid)) { + /* + * We sanitize readahead size depending on free memory in + * the local node. + */ + local_free_page = node_page_state(nid, NR_INACTIVE_FILE) + + node_page_state(nid, NR_FREE_PAGES); + return min(nr, local_free_page / 2); + } + /* + * Readahead onto remote memory is better than no readahead when local + * numa node does not have memory. We limit the readahead to 2MB to + * avoid trashing page cache. + */ return min(nr, MAX_READAHEAD); } -- 1.7.11.7 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>