|| ||Balbir Singh <firstname.lastname@example.org> |
|| ||Andrew Morton <email@example.com>,
KAMEZAWA Hiroyuki <firstname.lastname@example.org> |
|| ||[RFC][PATCH 0/5] Memory controller soft limit patches (v9) |
|| ||Fri, 10 Jul 2009 18:29:50 +0530|
|| ||email@example.com, Balbir Singh <firstname.lastname@example.org>,
KOSAKI Motohiro <email@example.com>|
|| ||Article, Thread
From: Balbir Singh <firstname.lastname@example.org>
New Feature: Soft limits for memory resource controller.
Here is v9 of the new soft limit implementation. Soft limits is a new feature
for the memory resource controller, something similar has existed in the
group scheduler in the form of shares. The CPU controllers interpretation
of shares is very different though.
Soft limits are the most useful feature to have for environments where
the administrator wants to overcommit the system, such that only on memory
contention do the limits become active. The current soft limits implementation
provides a soft_limit_in_bytes interface for the memory controller and not
for memory+swap controller. The implementation maintains an RB-Tree of groups
that exceed their soft limit and starts reclaiming from the group that
exceeds this limit by the maximum amount.
v9 attempts to address several review comments for v8 by Kamezawa, including
moving over to an event based approach for soft limit rb tree management,
simplification of data structure names and many others. Comments not
addressed have been answered via email or I've added comments in the code.
1. The current implementation maintains the delta from the soft limit
and pushes back groups to their soft limits, a ratio of delta/soft_limit
might be more useful
I've run two memory intensive workloads with differing soft limits and
seen that they are pushed back to their soft limit on contention. Their usage
was their soft limit plus additional memory that they were able to grab
on the system. Soft limit can take a while before we see the expected
I ran overhead tests (reaim) and found no significant overhead as a result
of these patches.
Please review, comment.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to email@example.com
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/