Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
docs, nvme: introduce nvme-multipath document
This adds a document about nvme-multipath and policies supported
by the Linux NVMe host driver, and also each policy's best scenario.
Signed-off-by: Guixin Liu <kanie@linux.alibaba.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20241209071127.22922-1-kanie@linux.alibaba.com
authored by
Guixin Liu
and committed by
Jonathan Corbet
80568f47
dfddf353
+73
+1
Documentation/admin-guide/index.rst
+1
Documentation/admin-guide/index.rst
+72
Documentation/admin-guide/nvme-multipath.rst
+72
Documentation/admin-guide/nvme-multipath.rst
···
1
+
.. SPDX-License-Identifier: GPL-2.0
2
+
3
+
====================
4
+
Linux NVMe multipath
5
+
====================
6
+
7
+
This document describes NVMe multipath and its path selection policies supported
8
+
by the Linux NVMe host driver.
9
+
10
+
11
+
Introduction
12
+
============
13
+
14
+
The NVMe multipath feature in Linux integrates namespaces with the same
15
+
identifier into a single block device. Using multipath enhances the reliability
16
+
and stability of I/O access while improving bandwidth performance. When a user
17
+
sends I/O to this merged block device, the multipath mechanism selects one of
18
+
the underlying block devices (paths) according to the configured policy.
19
+
Different policies result in different path selections.
20
+
21
+
22
+
Policies
23
+
========
24
+
25
+
All policies follow the ANA (Asymmetric Namespace Access) mechanism, meaning
26
+
that when an optimized path is available, it will be chosen over a non-optimized
27
+
one. Current the NVMe multipath policies include numa(default), round-robin and
28
+
queue-depth.
29
+
30
+
To set the desired policy (e.g., round-robin), use one of the following methods:
31
+
1. echo -n "round-robin" > /sys/module/nvme_core/parameters/iopolicy
32
+
2. or add the "nvme_core.iopolicy=round-robin" to cmdline.
33
+
34
+
35
+
NUMA
36
+
----
37
+
38
+
The NUMA policy selects the path closest to the NUMA node of the current CPU for
39
+
I/O distribution. This policy maintains the nearest paths to each NUMA node
40
+
based on network interface connections.
41
+
42
+
When to use the NUMA policy:
43
+
1. Multi-core Systems: Optimizes memory access in multi-core and
44
+
multi-processor systems, especially under NUMA architecture.
45
+
2. High Affinity Workloads: Binds I/O processing to the CPU to reduce
46
+
communication and data transfer delays across nodes.
47
+
48
+
49
+
Round-Robin
50
+
-----------
51
+
52
+
The round-robin policy distributes I/O requests evenly across all paths to
53
+
enhance throughput and resource utilization. Each I/O operation is sent to the
54
+
next path in sequence.
55
+
56
+
When to use the round-robin policy:
57
+
1. Balanced Workloads: Effective for balanced and predictable workloads with
58
+
similar I/O size and type.
59
+
2. Homogeneous Path Performance: Utilizes all paths efficiently when
60
+
performance characteristics (e.g., latency, bandwidth) are similar.
61
+
62
+
63
+
Queue-Depth
64
+
-----------
65
+
66
+
The queue-depth policy manages I/O requests based on the current queue depth
67
+
of each path, selecting the path with the least number of in-flight I/Os.
68
+
69
+
When to use the queue-depth policy:
70
+
1. High load with small I/Os: Effectively balances load across paths when
71
+
the load is high, and I/O operations consist of small, relatively
72
+
fixed-sized requests.