xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Drivers: hv: Introduce a policy for controlling channel affinity

Browse Source 
Introduce a mechanism to control how channels will be affinitized. We will
support two policies:

1. HV_BALANCED: All performance critical channels will be dstributed
evenly amongst all the available NUMA nodes. Once the Node is assigned,
we will assign the CPU based on a simple round robin scheme.

2. HV_LOCALIZED: Only the primary channels are distributed across all
NUMA nodes. Sub-channels will be in the same NUMA node as the primary
channel. This is the current behaviour.

The default policy will be the HV_BALANCED as it can minimize the remote
memory access on NUMA machines with applications that span NUMA nodes.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
K. Y. Srinivasan
2016-09-02 05:58:23 -07:00
committed by Greg Kroah-Hartman
parent bb08d431a9
commit 509879bdb3
2 changed files with 62 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
include/linux/hyperv.h
View File

@@ -674,6 +674,11 @@ enum hv_signal_policy {
HV_SIGNAL_POLICY_EXPLICIT,
};
enum hv_numa_policy {
HV_BALANCED = 0,
HV_LOCALIZED,
};
enum vmbus_device_type {
HV_IDE = 0,
HV_SCSI,
@@ -876,6 +881,18 @@ struct vmbus_channel {
*/
bool low_latency;
/*
* NUMA distribution policy:
* We support teo policies:
* 1) Balanced: Here all performance critical channels are
* distributed evenly amongst all the NUMA nodes.
* This policy will be the default policy.
* 2) Localized: All channels of a given instance of a
* performance critical service will be assigned CPUs
* within a selected NUMA node.
*/
enum hv_numa_policy affinity_policy;
};
static inline void set_channel_lock_state(struct vmbus_channel *c, bool state)
@@ -895,6 +912,12 @@ static inline void set_channel_signal_state(struct vmbus_channel *c,
c->signal_policy = policy;
}
static inline void set_channel_affinity_state(struct vmbus_channel *c,
enum hv_numa_policy policy)
{
c->affinity_policy = policy;
}
static inline void set_channel_read_state(struct vmbus_channel *c, bool state)
{
c->batched_reading = state;