x86,sched: allow topologies where NUMA nodes share an LLC
PATCH v5 1/1 x86,sched: allow topologies where NUMA nodes share an LLC
From: Alison Schofield <[email protected]>
Intel's Skylake Server CPUs have a different LLC topology than previous generations. When in Sub-NUMA-Clustering (SNC) mode, the package is divided into two "slices", each containing half the cores, half the LLC, and one memory controller and each slice is enumerated to Linux as a NUMA node. This is similar to how the cores and LLC were arranged for the Cluster-On-Die (CoD) feature.
CoD allowed the same cache line to be present in each half of the LLC. But, with SNC, each line is only ever present in *one* slice. This means that the portion of the LLC *available* to a CPU depends on the data being accessed:
Remote socket: entire package LLC is shared
Local socket->local slice: data goes into local slice LLC Local socket->remote slice: data goes into remote-slice LLC. Slightly
higher latency than local slice LLC.
The biggest implication from this is that a process accessing all NUMA-local memory only sees half the LLC capacity.
The CPU describes its cache hierarchy with the CPUID instruction. One of the CPUID leaves enumerates the "logical processors sharing this cache". This information is used for scheduling decisions so that tasks move more freely between CPUs sharing the cache.
But, the CPUID for the SNC configuration discussed above enumerates the LLC as being shared by the entire package. This is not 100% precise because the entire cache is not usable by all accesses. But, it *is* the way the hardware enumerates itself, and this is not likely to change.
The userspace visible impact of all the above is that the sysfs info reports the entire LLC as being available to the entire package. As noted above, this is not true for local socket accesses. This patch does not correct the sysfs info. It is the same, pre and post patch.
This patch continues to allow this SNC topology and it does so without complaint. It eliminates a warning that looks like this:
sched: CPU #3's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency.
The warning is coming from the sane_topology check() in smpboot.c. To fix this, add a vendor and model specific check to never call topology_sane() for these systems. Also, just like "Cluster-on-Die" we throw out the "coregroup" sched_domain_topology_level and use NUMA information from the SRAT alone.
This is OK at least on the hardware we are immediately concerned about because the LLC sharing happens at both the slice and at the package level, which are also NUMA boundaries.
---
Changes in v5:
* Removed the redundant setting of boolean x86_has_numa_in_package. Related comments were put back in their pre-patch locations.
Changes in v4:
* Added this to the patch description above:
The userspace visible impact of all the above is that the sysfs info reports the entire LLC as being available to the entire package. As noted above, this is not true for local socket accesses. This patch does not correct the sysfs info. It is the same, pre and post patch.
This patch continues to allow this SNC topology and it does so without complaint. It eliminates a warning that looks like this:
* Changed the code comment per PeterZ/DaveH discussion wrt bypassing that topology_sane() check in match_llc()
/*
* false means 'c' does not share the LLC of 'o'.
* Note: this decision gets reflected all the way
* out to userspace
*/
This message hopes to clarify what happens when we return false. Note that returning false is *not* new to this patch. Without this patch we always returned false - with a warning. This avoids that warning and returns false directly.
* Remove __initconst from snc_cpu[] declaration that I had added in v3. This is not an init time only path.
* Do not deal with the wrong sysfs info. It was wrong before this patch and it will be the exact same 'wrongness' after this patch.
We can address the sysfs reporting separately. Here are some options:
1) Change the way the LLC-size is reported. Enumerate two separate, half-sized LLCs shared only by the slice when SNC mode is on.
2) Do not export the sysfs info that is wrong. Prevents userspace from making bad decisions based on inaccurate info.
Changes in v3:
* Use x86_match_cpu() for vendor & model check and moved related comments to the array define. (Still just one system model)
* Updated the comments surrounding the topology_sane() check.
Changes in v2:
* Add vendor check (Intel) where we only had a model check (Skylake_X). Considered the suggestion of adding a new flag here but thought that to be overkill for this usage.
* Return false, instead of true, from match_llc() per reviewer suggestion. That also cleaned up a topology broken bug message in sched_domain().
* Updated the comments around the match_llc() return value, continuing to note that the return value doesn't actually matter because we are throwing away coregroups for scheduling.
* Changed submitter. I'm following up on this patch originally submitted by Dave Hansen.
arch/x86/kernel/smpboot.c | 45 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 40 insertions(+), 5 deletions(-)
arch/x86/kernel/smpboot.c +40 -5
@@ -77,6 +77,8 @@#include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> /* Number of siblings per CPU package */ int smp_num_siblings =1 ;
@@ -390,15 +392,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)return false; } +/* +* Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs. +* +* These are Intel CPUs that enumerate an LLC that is shared by +* multiple NUMA nodes. The LLC on these systems is shared for +* off-package data access but private to the NUMA node (half +* of the package) for on-package access. +* +* CPUID (the source of the information about the LLC) can only +* enumerate the cache as being shared *or* unshared, but not +* this particular configuration. The CPU in this case enumerates +* the cache to be shared across the entire package (spanning both +* NUMA nodes). +*/ + +static const struct x86_cpu_id snc_cpu[] = { + {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_SKYLAKE_X }, + {} +}; +static bool match_llc (struct cpuinfo_x86 *c,struct cpuinfo_x86 *o) {int cpu1 = c->cpu_index, cpu2 = o->cpu_index; -if (per_cpu (cpu_llc_id, cpu1) !=BAD_APICID && -per_cpu (cpu_llc_id, cpu1) ==per_cpu (cpu_llc_id, cpu2)) -return topology_sane (c, o,"llc" ); +/* Do not match if we do not have a valid APICID for cpu: */ +if (per_cpu (cpu_llc_id, cpu1) ==BAD_APICID ) +return false; -return false; +/* Do not match if LLC id does not match: */ +if (per_cpu (cpu_llc_id, cpu1) !=per_cpu (cpu_llc_id, cpu2)) +return false; + +/* +* Allow the SNC topology without warning. Return of false +* means 'c' does not share the LLC of 'o'. This will be +* reflected to userspace. +*/ +if (!topology_same_node (c, o) &&x86_match_cpu (snc_cpu)) +return false; + +return topology_sane (c, o,"llc" ); }/*
@@ -456,7 +490,8 @@ static struct sched_domain_topology_level x86_topology[] = {/* * Set if a package/die has multiple NUMA nodes inside. -* AMD Magny-Cours and Intel Cluster-on-Die have this. +* AMD Magny-Cours, Intel Cluster-on-Die, and Intel +* Sub-NUMA Clustering have this. */ static bool x86_has_numa_in_package;
Signature · 1 line
2.7.4
Quoted 38 lines · Alison Schofield
From: Alison Schofield <[email protected]>
Intel's Skylake Server CPUs have a different LLC topology than previous generations. When in Sub-NUMA-Clustering (SNC) mode, the package is divided into two "slices", each containing half the cores, half the LLC, and one memory controller and each slice is enumerated to Linux as a NUMA node. This is similar to how the cores and LLC were arranged for the Cluster-On-Die (CoD) feature.
CoD allowed the same cache line to be present in each half of the LLC. But, with SNC, each line is only ever present in *one* slice. This means that the portion of the LLC *available* to a CPU depends on the data being accessed:
Remote socket: entire package LLC is shared
Localsocket->localslice: data goes into local slice LLC Localsocket->remoteslice: data goes into remote-slice LLC. Slightly
higher latency than local slice LLC.The biggest implication from this is that a process accessing all NUMA-local memory only sees half the LLC capacity.
The CPU describes its cache hierarchy with the CPUID instruction. One of the CPUID leaves enumerates the "logical processors sharing this cache". This information is used for scheduling decisions so that tasks move more freely between CPUs sharing the cache.
But, the CPUID for the SNC configuration discussed above enumerates the LLC as being shared by the entire package. This is not 100% precise because the entire cache is not usable by all accesses. But, it *is* the way the hardware enumerates itself, and this is not likely to change.
The userspace visible impact of all the above is that the sysfs info reports the entire LLC as being available to the entire package. As noted above, this is not true for local socket accesses. This patch does not correct the sysfs info. It is the same, pre and post patch.
Quoted 6 lines
This patch continues to allow this SNC topology and it does so without complaint. It eliminates a warning that looks like this:
sched: CPU #3's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency.The warning is coming from the
sane_topologycheck()insmpboot.c.
s/sane_topology check()/topology_sane() check/
Quoted 8 lines
To fix this, add a vendor and model specific check to never call
topology_sane()for these systems. Also, just like "Cluster-on-Die" we throw out the "coregroup"sched_domain_topology_leveland use NUMA information from the SRAT alone.This is OK at least on the hardware we are immediately concerned about because the LLC sharing happens at both the slice and at the package level, which are also NUMA boundaries.
I wish everyone would write commit messages like this. Very good and nicely written explanation!
Quoted 12 lines
Signed-off-by Alison Schofield <[email protected]>Cc Dave Hansen <[email protected]>Cc Tony Luck <[email protected]>Cc Tim Chen <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc Borislav Petkov <[email protected]>Cc Peter Zijlstra (Intel) <[email protected]>Cc David Rientjes <[email protected]>Cc Igor Mammedov <[email protected]>Cc Prarit Bhargava <[email protected]>Cc Ingo Molnar <[email protected]>
Quoted 1 line
---
Signature · 4 lines
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.tip-bot for Alison Schofield
merge bot[tip:x86/urgent] x86,sched: Allow topologies where NUMA nodes share an LLC
In reply to Alison Schofieldx86,sched: Allow topologies where NUMA nodes share an LLC
Commit-ID: 1340ccfa9a9afefdbab90d7935d4ed19817e37c2 Gitweb: https://git.kernel.org/tip/1340ccfa9a9afefdbab90d7935d4ed19817e37c2 Author: Alison Schofield <[email protected]> AuthorDate: Fri, 6 Apr 2018 17:21:30 -0700 Committer: Thomas Gleixner <[email protected]> CommitDate: Tue, 17 Apr 2018 15:39:55 +0200
x86,sched: Allow topologies where NUMA nodes share an LLC
Intel's Skylake Server CPUs have a different LLC topology than previous generations. When in Sub-NUMA-Clustering (SNC) mode, the package is divided into two "slices", each containing half the cores, half the LLC, and one memory controller and each slice is enumerated to Linux as a NUMA node. This is similar to how the cores and LLC were arranged for the Cluster-On-Die (CoD) feature.
CoD allowed the same cache line to be present in each half of the LLC. But, with SNC, each line is only ever present in *one* slice. This means that the portion of the LLC *available* to a CPU depends on the data being accessed:
Remote socket: entire package LLC is shared
Local socket->local slice: data goes into local slice LLC Local socket->remote slice: data goes into remote-slice LLC. Slightly
higher latency than local slice LLC.
The biggest implication from this is that a process accessing all NUMA-local memory only sees half the LLC capacity.
The CPU describes its cache hierarchy with the CPUID instruction. One of the CPUID leaves enumerates the "logical processors sharing this cache". This information is used for scheduling decisions so that tasks move more freely between CPUs sharing the cache.
But, the CPUID for the SNC configuration discussed above enumerates the LLC as being shared by the entire package. This is not 100% precise because the entire cache is not usable by all accesses. But, it *is* the way the hardware enumerates itself, and this is not likely to change.
The userspace visible impact of all the above is that the sysfs info reports the entire LLC as being available to the entire package. As noted above, this is not true for local socket accesses. This patch does not correct the sysfs info. It is the same, pre and post patch.
The current code emits the following warning:
sched: CPU #3's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency.
The warning is coming from the topology_sane() check in smpboot.c because the topology is not matching the expectations of the model for obvious reasons.
To fix this, add a vendor and model specific check to never call topology_sane() for these systems. Also, just like "Cluster-on-Die" disable the "coregroup" sched_domain_topology_level and use NUMA information from the SRAT alone.
This is OK at least on the hardware we are immediately concerned about because the LLC sharing happens at both the slice and at the package level, which are also NUMA boundaries.
--- arch/x86/kernel/smpboot.c | 45 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 40 insertions(+), 5 deletions(-)
arch/x86/kernel/smpboot.c +40 -5
@@ -77,6 +77,8 @@#include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> /* Number of siblings per CPU package */ int smp_num_siblings =1 ;
@@ -390,15 +392,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)return false; } +/* +* Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs. +* +* These are Intel CPUs that enumerate an LLC that is shared by +* multiple NUMA nodes. The LLC on these systems is shared for +* off-package data access but private to the NUMA node (half +* of the package) for on-package access. +* +* CPUID (the source of the information about the LLC) can only +* enumerate the cache as being shared *or* unshared, but not +* this particular configuration. The CPU in this case enumerates +* the cache to be shared across the entire package (spanning both +* NUMA nodes). +*/ + +static const struct x86_cpu_id snc_cpu[] = { + {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_SKYLAKE_X }, + {} +}; +static bool match_llc (struct cpuinfo_x86 *c,struct cpuinfo_x86 *o) {int cpu1 = c->cpu_index, cpu2 = o->cpu_index; -if (per_cpu (cpu_llc_id, cpu1) !=BAD_APICID && -per_cpu (cpu_llc_id, cpu1) ==per_cpu (cpu_llc_id, cpu2)) -return topology_sane (c, o,"llc" ); +/* Do not match if we do not have a valid APICID for cpu: */ +if (per_cpu (cpu_llc_id, cpu1) ==BAD_APICID ) +return false; -return false; +/* Do not match if LLC id does not match: */ +if (per_cpu (cpu_llc_id, cpu1) !=per_cpu (cpu_llc_id, cpu2)) +return false; + +/* +* Allow the SNC topology without warning. Return of false +* means 'c' does not share the LLC of 'o'. This will be +* reflected to userspace. +*/ +if (!topology_same_node (c, o) &&x86_match_cpu (snc_cpu)) +return false; + +return topology_sane (c, o,"llc" ); }/*
@@ -456,7 +490,8 @@ static struct sched_domain_topology_level x86_topology[] = {/* * Set if a package/die has multiple NUMA nodes inside. -* AMD Magny-Cours and Intel Cluster-on-Die have this. +* AMD Magny-Cours, Intel Cluster-on-Die, and Intel +* Sub-NUMA Clustering have this. */ static bool x86_has_numa_in_package;
Fwd: [tip:x86/urgent] x86, sched: Allow topologies where NUMA nodes share an LLC
Is this something we should be aware of in Xen, too?
Juergen
-------- Forwarded Message --------
Subject: [tip:x86/urgent] x86,sched: Allow topologies where NUMA nodes share an LLC
Date: Tue, 17 Apr 2018 06:46:12 -0700
From: tip-bot for Alison Schofield <[email protected]>
Reply-To: [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected]
To: [email protected]
CC: [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected]
Commit-ID: 1340ccfa9a9afefdbab90d7935d4ed19817e37c2 Gitweb:
https://git.kernel.org/tip/1340ccfa9a9afefdbab90d7935d4ed19817e37c2
Author: Alison Schofield <[email protected]> AuthorDate: Fri, 6 Apr 2018 17:21:30 -0700 Committer: Thomas Gleixner <[email protected]> CommitDate: Tue, 17 Apr 2018 15:39:55 +0200
x86,sched: Allow topologies where NUMA nodes share an LLC
Intel's Skylake Server CPUs have a different LLC topology than previous generations. When in Sub-NUMA-Clustering (SNC) mode, the package is divided into two "slices", each containing half the cores, half the LLC, and one memory controller and each slice is enumerated to Linux as a NUMA node. This is similar to how the cores and LLC were arranged for the Cluster-On-Die (CoD) feature.
CoD allowed the same cache line to be present in each half of the LLC. But, with SNC, each line is only ever present in *one* slice. This means that the portion of the LLC *available* to a CPU depends on the data being accessed:
Remote socket: entire package LLC is shared
Local socket->local slice: data goes into local slice LLC Local socket->remote slice: data goes into remote-slice LLC. Slightly
higher latency than local slice LLC.
The biggest implication from this is that a process accessing all NUMA-local memory only sees half the LLC capacity.
The CPU describes its cache hierarchy with the CPUID instruction. One of the CPUID leaves enumerates the "logical processors sharing this cache". This information is used for scheduling decisions so that tasks move more freely between CPUs sharing the cache.
But, the CPUID for the SNC configuration discussed above enumerates the LLC as being shared by the entire package. This is not 100% precise because the entire cache is not usable by all accesses. But, it *is* the way the hardware enumerates itself, and this is not likely to change.
The userspace visible impact of all the above is that the sysfs info reports the entire LLC as being available to the entire package. As noted above, this is not true for local socket accesses. This patch does not correct the sysfs info. It is the same, pre and post patch.
The current code emits the following warning:
sched: CPU #3's llc-sibling CPU #0 is not on the same node! [node: 1 !=
0]. Ignoring dependency.
The warning is coming from the topology_sane() check in smpboot.c because the topology is not matching the expectations of the model for obvious reasons.
To fix this, add a vendor and model specific check to never call topology_sane() for these systems. Also, just like "Cluster-on-Die" disable the "coregroup" sched_domain_topology_level and use NUMA information from the SRAT alone.
This is OK at least on the hardware we are immediately concerned about because the LLC sharing happens at both the slice and at the package level, which are also NUMA boundaries.
Link:
https://lkml.kernel.org/r/[email protected]
--- arch/x86/kernel/smpboot.c | 45 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 40 insertions(+), 5 deletions(-)
arch/x86/kernel/smpboot.c +2 -0
@@ -77,6 +77,8 @@#include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> /* Number of siblings per CPU package */ int smp_num_siblings =1 ;
@@ -390,15 +392,47 @@ static bool match_smt(struct cpuinfo_x86 *c,
struct cpuinfo_x86 *o)
return false;
}
+/*
+ * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs.
+ *
+ * These are Intel CPUs that enumerate an LLC that is shared by
+ * multiple NUMA nodes. The LLC on these systems is shared for
+ * off-package data access but private to the NUMA node (half
+ * of the package) for on-package access.
+ *
+ * CPUID (the source of the information about the LLC) can only
+ * enumerate the cache as being shared *or* unshared, but not
+ * this particular configuration. The CPU in this case enumerates
+ * the cache to be shared across the entire package (spanning both
+ * NUMA nodes).
+ */
+
+static const struct x86_cpu_id snc_cpu[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X },
+ {}
+};
+
static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) {
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
- if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
- per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
- return topology_sane(c, o, "llc");
+ /* Do not match if we do not have a valid APICID for cpu: */
+ if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
+ return false;
- return false;
+ /* Do not match if LLC id does not match: */
+ if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
+ return false;
+
+ /*
+ * Allow the SNC topology without warning. Return of false
+ * means 'c' does not share the LLC of 'o'. This will be
+ * reflected to userspace.
+ */
+ if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu))
+ return false;
+
+ return topology_sane(c, o, "llc");
}
/*
@@ -456,7 +490,8 @@ static struct sched_domain_topology_level x86_topology[] = {
/*
* Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours and Intel Cluster-on-Die have this.
+ * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
+ * Sub-NUMA Clustering have this.
*/
static bool x86_has_numa_in_package;
_______________________________________________
Xen-devel mailing list
[email protected]
https://lists.xenproject.org/mailman/listinfo/xen-devel
Re: Fwd: [tip:x86/urgent] x86, sched: Allow topologies where NUMA nodes share an LLC
Quoted 1 line · Juergen Gross
Is this something we should be aware of in Xen, too?
If we had something close to a working topology representation, probably.
As things stand, I don't really know, but I doubt it will cause problems in the default case, due to us being fairly NUMA-inefficient to begin with.
I haven't had the time to turn SNC on see what happens.
~Andrew
_______________________________________________
Xen-devel mailing list
[email protected]
https://lists.xenproject.org/mailman/listinfo/xen-devel
Re: Fwd: [tip:x86/urgent] x86, sched: Allow topologies where NUMA nodes share an LLC
Quoted 6 lines · Andrew Cooper
Quoted 1 line · Juergen Gross
Is this something we should be aware of in Xen, too?
If we had something close to a working topology representation, probably.
True, as far as letting the guest know about these details (in appropriate circumnstaces) goes.
About using it _within_ Xen, well:
"Intel's Skylake Server CPUs have a different LLC topology than previous
generations. When in Sub-NUMA-Clustering (SNC) mode, the package is divided
into two "slices", each containing half the cores, half the LLC, and one
memory controller and each slice is enumerated to Linux as a NUMA node. This is similar to how the cores and LLC were arranged for the Cluster-On-Die (CoD) feature."
This looks similar (but not identical) to, e.g., AMD EPYC. If Xen also sees each slice as a NUMA node as well, we already are doing something (although, of course, we can always improve).
If not, I see ways of taking advantage of the information that not all the cores in the socket equally share the LLC, e.g., in Credit2, by providing a per-LLC runqueue option and/or by taking that into account in the 'migration resistance' mechanisms (there is already work in that direction).
Regards,
Dario
Signature · 4 lines
<<This happens because I choose it to happen!>> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Software Engineer @ SUSE https://www.suse.com/
_______________________________________________
Xen-devel mailing list
[email protected]
https://lists.xenproject.org/mailman/listinfo/xen-devel
Re: Fwd: [tip:x86/urgent] x86, sched: Allow topologies where NUMA nodes share an LLC
Quoted 25 lines · Dario Faggioli
Quoted 5 lines · Andrew Cooper
Quoted 1 line · Juergen Gross
Is this something we should be aware of in Xen, too?
If we had something close to a working topology representation, probably.
True, as far as letting the guest know about these details (in appropriate circumnstaces) goes.
About using it _within_ Xen, well:
"Intel's Skylake Server CPUs have a different LLC topology than previous
generations. When in Sub-NUMA-Clustering (SNC) mode, the package is divided
into two "slices", each containing half the cores, half the LLC, and one
memory controller and each slice is enumerated to Linux as a NUMA node. This is similar to how the cores and LLC were arranged for the Cluster-On-Die (CoD) feature."This looks similar (but not identical) to, e.g., AMD EPYC. If Xen also sees each slice as a NUMA node as well, we already are doing something (although, of course, we can always improve).
Quoted 5 lines
If not, I see ways of taking advantage of the information that not all the cores in the socket equally share the LLC, e.g., in Credit2, by providing a per-LLC runqueue option and/or by taking that into account in the 'migration resistance' mechanisms (there is already work in that direction).
Yeah, per-LLC runqueue option sounds like a good option. We can look into that.
Yes, I am working on dynamically definining migration resistance as a factor of cache and cpu topology ie. instead of having a constant value of migration resistance it will consider the placement of cpus, cache and sharing of cache among cpus.
Quoted 3 lines
Regards,
Dario
Anshul
_______________________________________________
Xen-devel mailing list
[email protected]
https://lists.xenproject.org/mailman/listinfo/xen-devel