Hi Tony,
On 8/29/2023 4:44 PM, Tony Luck wrote:
> With Sub-NUMA Cluster mode enabled the scope of monitoring resources is
> per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in
> their name refer to Sub-NUMA nodes instead of L3 cache ids.
>
> Users should be aware that SNC mode also affects the amount of L3 cache
> available for allocation within each SNC node.
>
> Signed-off-by: Tony Luck <[email protected]>
> ---
> Documentation/arch/x86/resctrl.rst | 25 ++++++++++++++++++++++---
> 1 file changed, 22 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
> index cb05d90111b4..407764f43f25 100644
> --- a/Documentation/arch/x86/resctrl.rst
> +++ b/Documentation/arch/x86/resctrl.rst
> @@ -345,9 +345,15 @@ When control is enabled all CTRL_MON groups will also contain:
> When monitoring is enabled all MON groups will also contain:
>
> "mon_data":
> - This contains a set of files organized by L3 domain and by
> - RDT event. E.g. on a system with two L3 domains there will
> - be subdirectories "mon_L3_00" and "mon_L3_01". Each of these
> + This contains a set of files organized by L3 domain or by NUMA
> + node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
> + or enabled respectively) and by RDT event. E.g. on a system with
> + SNC mode disabled with two L3 domains there will be subdirectories
> + "mon_L3_00" and "mon_L3_01". The numerical suffix refers to the
> + L3 cache id. With SNC enabled the directory names are the same,
> + but the numerical suffix refers to the node id.
> + Mappings from node ids to CPUs are available in the
> + /sys/devices/system/node/node*/cpulist files. Each of these
Please be consistent with tabs vs spaces.
> directories have one file per event (e.g. "llc_occupancy",
> "mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
> files provide a read out of the current value of the event for
> @@ -452,6 +458,19 @@ and 0xA are not. On a system with a 20-bit mask each bit represents 5%
> of the capacity of the cache. You could partition the cache into four
> equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
>
> +Notes on Sub-NUMA Cluster mode
> +==============================
> +When SNC mode is enabled the "llc_occupancy", "mbm_total_bytes", and
> +"mbm_local_bytes" will only give accurate results for well behaved NUMA
> +applications. I.e. those that perform the majority of memory accesses
> +to memory on the local NUMA node to the CPU where the task is executing.
> +
Following our discussion of the cover letter I believe this will change to
be specific about what user space can expect and what is actually "accurate".
> +The cache allocation feature still provides the same number of
> +bits in a mask to control allocation into the L3 cache. But each
> +of those ways has its capacity reduced because the cache is divided
> +between the SNC nodes. The values reported in the resctrl
> +"size" files are adjusted accordingly.
> +
> Memory bandwidth Allocation and monitoring
> ==========================================
>
Reinette
On Mon, Sep 25, 2023 at 04:30:22PM -0700, Reinette Chatre wrote:
> Hi Tony,
>
> On 8/29/2023 4:44 PM, Tony Luck wrote:
> > With Sub-NUMA Cluster mode enabled the scope of monitoring resources is
> > per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in
> > their name refer to Sub-NUMA nodes instead of L3 cache ids.
> >
> > Users should be aware that SNC mode also affects the amount of L3 cache
> > available for allocation within each SNC node.
> >
> > Signed-off-by: Tony Luck <[email protected]>
> > ---
> > Documentation/arch/x86/resctrl.rst | 25 ++++++++++++++++++++++---
> > 1 file changed, 22 insertions(+), 3 deletions(-)
> >
> > diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
> > index cb05d90111b4..407764f43f25 100644
> > --- a/Documentation/arch/x86/resctrl.rst
> > +++ b/Documentation/arch/x86/resctrl.rst
> > @@ -345,9 +345,15 @@ When control is enabled all CTRL_MON groups will also contain:
> > When monitoring is enabled all MON groups will also contain:
> >
> > "mon_data":
> > - This contains a set of files organized by L3 domain and by
> > - RDT event. E.g. on a system with two L3 domains there will
> > - be subdirectories "mon_L3_00" and "mon_L3_01". Each of these
> > + This contains a set of files organized by L3 domain or by NUMA
> > + node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
> > + or enabled respectively) and by RDT event. E.g. on a system with
> > + SNC mode disabled with two L3 domains there will be subdirectories
> > + "mon_L3_00" and "mon_L3_01". The numerical suffix refers to the
> > + L3 cache id. With SNC enabled the directory names are the same,
> > + but the numerical suffix refers to the node id.
> > + Mappings from node ids to CPUs are available in the
> > + /sys/devices/system/node/node*/cpulist files. Each of these
>
> Please be consistent with tabs vs spaces.
I blame "vim" for this one. Typing <TAB> while working on a .rst file
throws in 8 spaces. Maybe there's a vim setting to stop this annoying
behaviour (set syntax=off didn't help). Had to use CTRL(V)<TAB> to make
it work.
>
> > directories have one file per event (e.g. "llc_occupancy",
> > "mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
> > files provide a read out of the current value of the event for
> > @@ -452,6 +458,19 @@ and 0xA are not. On a system with a 20-bit mask each bit represents 5%
> > of the capacity of the cache. You could partition the cache into four
> > equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
> >
> > +Notes on Sub-NUMA Cluster mode
> > +==============================
> > +When SNC mode is enabled the "llc_occupancy", "mbm_total_bytes", and
> > +"mbm_local_bytes" will only give accurate results for well behaved NUMA
> > +applications. I.e. those that perform the majority of memory accesses
> > +to memory on the local NUMA node to the CPU where the task is executing.
> > +
>
> Following our discussion of the cover letter I believe this will change to
> be specific about what user space can expect and what is actually "accurate".
I added more text about the importance of binding tasks to SNC nodes.
>
> > +The cache allocation feature still provides the same number of
> > +bits in a mask to control allocation into the L3 cache. But each
> > +of those ways has its capacity reduced because the cache is divided
> > +between the SNC nodes. The values reported in the resctrl
> > +"size" files are adjusted accordingly.
> > +
> > Memory bandwidth Allocation and monitoring
> > ==========================================
> >
>
> Reinette