[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1553316275-21985-10-git-send-email-yang.shi@linux.alibaba.com>
Date: Sat, 23 Mar 2019 12:44:34 +0800
From: Yang Shi <yang.shi@...ux.alibaba.com>
To: mhocko@...e.com, mgorman@...hsingularity.net, riel@...riel.com,
hannes@...xchg.org, akpm@...ux-foundation.org,
dave.hansen@...el.com, keith.busch@...el.com,
dan.j.williams@...el.com, fengguang.wu@...el.com, fan.du@...el.com,
ying.huang@...el.com
Cc: yang.shi@...ux.alibaba.com, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: [PATCH 09/10] doc: add description for MPOL_HYBRID mode
Add description for MPOL_HYBRID mode in kernel documentation.
Signed-off-by: Yang Shi <yang.shi@...ux.alibaba.com>
---
Documentation/admin-guide/mm/numa_memory_policy.rst | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
index d78c5b3..3db8257 100644
--- a/Documentation/admin-guide/mm/numa_memory_policy.rst
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -198,6 +198,16 @@ MPOL_BIND
the node in the set with sufficient free memory that is
closest to the node where the allocation takes place.
+MPOL_HYBRID
+ This mode specifies that the page allocation must happen on the
+ nodes specified by the policy. If both DRAM and non-DRAM nodes
+ are specified, NUMA balancing may promote the pages from non-DRAM
+ nodes to the specified DRAM nodes. If only non-DRAM nodes are
+ specified, NUMA balancing may promote the pages to any available
+ DRAM nodes. Any other policy doesn't do such page promotion. The
+ default mode may do NUMA balancing, but non-DRAM nodes are masked
+ off for default mode.
+
MPOL_PREFERRED
This mode specifies that the allocation should be attempted
from the single node specified in the policy. If that
--
1.8.3.1
Powered by blists - more mailing lists