similarity index 74%
rename from docs/man/xl-numa-placement.markdown.7
rename to docs/man/xl-numa-placement.pod.7
@@ -1,6 +1,12 @@
-# Guest Automatic NUMA Placement in libxl and xl #
+=encoding utf8
-## Rationale ##
+=head1 NAME
+
+Guest Automatic NUMA Placement in libxl and xl
+
+=head1 DESCRIPTION
+
+=head2 Rationale
NUMA (which stands for Non-Uniform Memory Access) means that the memory
accessing times of a program running on a CPU depends on the relative
@@ -17,13 +23,14 @@ running memory-intensive workloads on a shared host. In fact, the cost
of accessing non node-local memory locations is very high, and the
performance degradation is likely to be noticeable.
-For more information, have a look at the [Xen NUMA Introduction][numa_intro]
+For more information, have a look at the L<Xen NUMA Introduction|http://wiki.xen.org/wiki/Xen_NUMA_Introduction>
page on the Wiki.
-## Xen and NUMA machines: the concept of _node-affinity_ ##
+
+=head2 Xen and NUMA machines: the concept of I<node-affinity>
The Xen hypervisor deals with NUMA machines throughout the concept of
-_node-affinity_. The node-affinity of a domain is the set of NUMA nodes
+I<node-affinity>. The node-affinity of a domain is the set of NUMA nodes
of the host where the memory for the domain is being allocated (mostly,
at domain creation time). This is, at least in principle, different and
unrelated with the vCPU (hard and soft, see below) scheduling affinity,
@@ -42,15 +49,16 @@ it is very important to "place" the domain correctly when it is fist
created, as the most of its memory is allocated at that time and can
not (for now) be moved easily.
-### Placing via pinning and cpupools ###
+
+=head2 Placing via pinning and cpupools
The simplest way of placing a domain on a NUMA node is setting the hard
scheduling affinity of the domain's vCPUs to the pCPUs of the node. This
also goes under the name of vCPU pinning, and can be done through the
"cpus=" option in the config file (more about this below). Another option
is to pool together the pCPUs spanning the node and put the domain in
-such a _cpupool_ with the "pool=" config option (as documented in our
-[Wiki][cpupools_howto]).
+such a I<cpupool> with the "pool=" config option (as documented in our
+L<Wiki|http://wiki.xen.org/wiki/Cpupools_Howto>).
In both the above cases, the domain will not be able to execute outside
the specified set of pCPUs for any reasons, even if all those pCPUs are
@@ -59,7 +67,8 @@ busy doing something else while there are others, idle, pCPUs.
So, when doing this, local memory accesses are 100% guaranteed, but that
may come at he cost of some load imbalances.
-### NUMA aware scheduling ###
+
+=head2 NUMA aware scheduling
If using the credit1 scheduler, and starting from Xen 4.3, the scheduler
itself always tries to run the domain's vCPUs on one of the nodes in
@@ -87,21 +96,37 @@ workload.
Notice that, for each vCPU, the following three scenarios are possbile:
- * a vCPU *is pinned* to some pCPUs and *does not have* any soft affinity
- In this case, the vCPU is always scheduled on one of the pCPUs to which
- it is pinned, without any specific peference among them.
- * a vCPU *has* its own soft affinity and *is not* pinned to any particular
- pCPU. In this case, the vCPU can run on every pCPU. Nevertheless, the
- scheduler will try to have it running on one of the pCPUs in its soft
- affinity;
- * a vCPU *has* its own vCPU soft affinity and *is also* pinned to some
- pCPUs. In this case, the vCPU is always scheduled on one of the pCPUs
- onto which it is pinned, with, among them, a preference for the ones
- that also forms its soft affinity. In case pinning and soft affinity
- form two disjoint sets of pCPUs, pinning "wins", and the soft affinity
- is just ignored.
-
-## Guest placement in xl ##
+=over
+
+=item *
+
+a vCPU I<is pinned> to some pCPUs and I<does not have> any soft affinity
+In this case, the vCPU is always scheduled on one of the pCPUs to which
+it is pinned, without any specific peference among them.
+
+
+=item *
+
+a vCPU I<has> its own soft affinity and I<is not> pinned to any particular
+pCPU. In this case, the vCPU can run on every pCPU. Nevertheless, the
+scheduler will try to have it running on one of the pCPUs in its soft
+affinity;
+
+
+=item *
+
+a vCPU I<has> its own vCPU soft affinity and I<is also> pinned to some
+pCPUs. In this case, the vCPU is always scheduled on one of the pCPUs
+onto which it is pinned, with, among them, a preference for the ones
+that also forms its soft affinity. In case pinning and soft affinity
+form two disjoint sets of pCPUs, pinning "wins", and the soft affinity
+is just ignored.
+
+
+=back
+
+
+=head2 Guest placement in xl
If using xl for creating and managing guests, it is very easy to ask for
both manual or automatic placement of them across the host's NUMA nodes.
@@ -111,7 +136,8 @@ the details of the heuristics adopted for automatic placement (see below),
and the lack of support (in both xm/xend and the Xen versions where that
was the default toolstack) for NUMA aware scheduling.
-### Placing the guest manually ###
+
+=head2 Placing the guest manually
Thanks to the "cpus=" option, it is possible to specify where a domain
should be created and scheduled on, directly in its config file. This
@@ -126,19 +152,31 @@ or Xen won't be able to guarantee the locality for their memory accesses.
That, of course, also mean the vCPUs of the domain will only be able to
execute on those same pCPUs.
-It is is also possible to have a "cpus\_soft=" option in the xl config file,
+It is is also possible to have a "cpus_soft=" option in the xl config file,
to specify the soft affinity for all the vCPUs of the domain. This affects
the NUMA placement in the following way:
- * if only "cpus\_soft=" is present, the VM's node-affinity will be equal
- to the nodes to which the pCPUs in the soft affinity mask belong;
- * if both "cpus\_soft=" and "cpus=" are present, the VM's node-affinity
- will be equal to the nodes to which the pCPUs present both in hard and
- soft affinity belong.
+=over
+
+=item *
+
+if only "cpus_soft=" is present, the VM's node-affinity will be equal
+to the nodes to which the pCPUs in the soft affinity mask belong;
-### Placing the guest automatically ###
-If neither "cpus=" nor "cpus\_soft=" are present in the config file, libxl
+=item *
+
+if both "cpus_soft=" and "cpus=" are present, the VM's node-affinity
+will be equal to the nodes to which the pCPUs present both in hard and
+soft affinity belong.
+
+
+=back
+
+
+=head2 Placing the guest automatically
+
+If neither "cpus=" nor "cpus_soft=" are present in the config file, libxl
tries to figure out on its own on which node(s) the domain could fit best.
If it finds one (some), the domain's node affinity get set to there,
and both memory allocations and NUMA aware scheduling (for the credit
@@ -160,14 +198,29 @@ to have, and as much pCPUs as it has vCPUs. After that, the actual
decision on which candidate to pick happens accordingly to the following
heuristics:
- * candidates involving fewer nodes are considered better. In case
- two (or more) candidates span the same number of nodes,
- * candidates with a smaller number of vCPUs runnable on them (due
- to previous placement and/or plain vCPU pinning) are considered
- better. In case the same number of vCPUs can run on two (or more)
- candidates,
- * the candidate with with the greatest amount of free memory is
- considered to be the best one.
+=over
+
+=item *
+
+candidates involving fewer nodes are considered better. In case
+two (or more) candidates span the same number of nodes,
+
+
+=item *
+
+candidates with a smaller number of vCPUs runnable on them (due
+to previous placement and/or plain vCPU pinning) are considered
+better. In case the same number of vCPUs can run on two (or more)
+candidates,
+
+
+=item *
+
+the candidate with with the greatest amount of free memory is
+considered to be the best one.
+
+
+=back
Giving preference to candidates with fewer nodes ensures better
performance for the guest, as it avoid spreading its memory among
@@ -178,35 +231,37 @@ largest amounts of free memory helps keeping the memory fragmentation
small, and maximizes the probability of being able to put more domains
there.
-## Guest placement in libxl ##
+
+=head2 Guest placement in libxl
xl achieves automatic NUMA placement because that is what libxl does
by default. No API is provided (yet) for modifying the behaviour of
the placement algorithm. However, if your program is calling libxl,
-it is possible to set the `numa_placement` build info key to `false`
-(it is `true` by default) with something like the below, to prevent
+it is possible to set the C<numa_placement> build info key to C<false>
+(it is C<true> by default) with something like the below, to prevent
any placement from happening:
libxl_defbool_set(&domain_build_info->numa_placement, false);
-Also, if `numa_placement` is set to `true`, the domain's vCPUs must
-not be pinned (i.e., `domain_build_info->cpumap` must have all its
+Also, if C<numa_placement> is set to C<true>, the domain's vCPUs must
+not be pinned (i.e., C<<< domain_build_info->cpumap >>> must have all its
bits set, as it is by default), or domain creation will fail with
-`ERROR_INVAL`.
+C<ERROR_INVAL>.
Starting from Xen 4.3, in case automatic placement happens (and is
-successful), it will affect the domain's node-affinity and _not_ its
+successful), it will affect the domain's node-affinity and I<not> its
vCPU pinning. Namely, the domain's vCPUs will not be pinned to any
pCPU on the host, but the memory from the domain will come from the
selected node(s) and the NUMA aware scheduling (if the credit scheduler
is in use) will try to keep the domain's vCPUs there as much as possible.
Besides than that, looking and/or tweaking the placement algorithm
-search "Automatic NUMA placement" in libxl\_internal.h.
+search "Automatic NUMA placement" in libxl_internal.h.
Note this may change in future versions of Xen/libxl.
-## Xen < 4.5 ##
+
+=head2 Xen < 4.5
The concept of vCPU soft affinity has been introduced for the first time
in Xen 4.5. In 4.3, it is the domain's node-affinity that drives the
@@ -215,25 +270,24 @@ and so each vCPU can have its own mask of pCPUs, while node-affinity is
per-domain, that is the equivalent of having all the vCPUs with the same
soft affinity.
-## Xen < 4.3 ##
+
+=head2 Xen < 4.3
As NUMA aware scheduling is a new feature of Xen 4.3, things are a little
bit different for earlier version of Xen. If no "cpus=" option is specified
and Xen 4.2 is in use, the automatic placement algorithm still runs, but
-the results is used to _pin_ the vCPUs of the domain to the output node(s).
+the results is used to I<pin> the vCPUs of the domain to the output node(s).
This is consistent with what was happening with xm/xend.
On a version of Xen earlier than 4.2, there is not automatic placement at
all in xl or libxl, and hence no node-affinity, vCPU affinity or pinning
being introduced/modified.
-## Limitations ##
+
+=head2 Limitations
Analyzing various possible placement solutions is what makes the
algorithm flexible and quite effective. However, that also means
it won't scale well to systems with arbitrary number of nodes.
For this reason, automatic placement is disabled (with a warning)
if it is requested on a host with more than 16 NUMA nodes.
-
-[numa_intro]: http://wiki.xen.org/wiki/Xen_NUMA_Introduction
-[cpupools_howto]: http://wiki.xen.org/wiki/Cpupools_Howto
Convert source for xl-numa-placement.7 from markdown to pod. This removes the buildtime requirement for pandoc, and subsequently the need for ghc, in the chain for BuildRequires of xen.rpm. Signed-off-by: Olaf Hering <olaf@aepfle.de> --- ...lacement.markdown.7 => xl-numa-placement.pod.7} | 166 ++++++++++++++------- 1 file changed, 110 insertions(+), 56 deletions(-) rename docs/man/{xl-numa-placement.markdown.7 => xl-numa-placement.pod.7} (74%)