Update the documentation for the new features: 1. Slow Memory Bandwidth allocation (SMBA). With this feature, the QOS enforcement policies can be applied to the external slow memory connected to the host. QOS enforcement is accomplished by assigning a Class Of Service (COS) to a processor and specifying allocations or limits for that COS for each resource to be allocated. 2. Bandwidth Monitoring Event Configuration (BMEC). The bandwidth monitoring events mbm_total_bytes and mbm_local_bytes are set to count all the total and local reads/writes respectively. With the introduction of slow memory, the two counters are not enough to count all the different types of memory events. With the feature BMEC, the users have the option to configure mbm_total_bytes and mbm_local_bytes to count the specific type of events. Also add configuration instructions with examples. Signed-off-by: Babu Moger <babu.moger@xxxxxxx> --- Documentation/x86/resctrl.rst | 136 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 134 insertions(+), 2 deletions(-) diff --git a/Documentation/x86/resctrl.rst b/Documentation/x86/resctrl.rst index 71a531061e4e..e2a59249d183 100644 --- a/Documentation/x86/resctrl.rst +++ b/Documentation/x86/resctrl.rst @@ -17,14 +17,16 @@ AMD refers to this feature as AMD Platform Quality of Service(AMD QoS). This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo flag bits: -============================================= ================================ +=============================================== ================================ RDT (Resource Director Technology) Allocation "rdt_a" CAT (Cache Allocation Technology) "cat_l3", "cat_l2" CDP (Code and Data Prioritization) "cdp_l3", "cdp_l2" CQM (Cache QoS Monitoring) "cqm_llc", "cqm_occup_llc" MBM (Memory Bandwidth Monitoring) "cqm_mbm_total", "cqm_mbm_local" MBA (Memory Bandwidth Allocation) "mba" -============================================= ================================ +SMBA (Slow Memory Bandwidth Allocation) "smba" +BMEC (Bandwidth Monitoring Event Configuration) "bmec" +=============================================== ================================ To use the feature mount the file system:: @@ -161,6 +163,79 @@ with the following files: "mon_features": Lists the monitoring events if monitoring is enabled for the resource. + Example:: + + # cat /sys/fs/resctrl/info/L3_MON/mon_features + llc_occupancy + mbm_total_bytes + mbm_local_bytes + + If the system supports Bandwidth Monitoring Event + Configuration (BMEC), then the bandwidth events will + be configurable. The output will be:: + + # cat /sys/fs/resctrl/info/L3_MON/mon_features + llc_occupancy + mbm_total_bytes + mbm_total_config + mbm_local_bytes + mbm_local_config + +"mbm_total_config", "mbm_local_config": + These files contain the current event configuration for the events + mbm_total_bytes and mbm_local_bytes, respectively, when the + Bandwidth Monitoring Event Configuration (BMEC) feature is supported. + The event configuration settings are domain specific and will affect + all the CPUs in the domain. + + Following are the types of events supported: + + ==== ======================================================== + Bits Description + ==== ======================================================== + 6 Dirty Victims from the QOS domain to all types of memory + 5 Reads to slow memory in the non-local NUMA domain + 4 Reads to slow memory in the local NUMA domain + 3 Non-temporal writes to non-local NUMA domain + 2 Non-temporal writes to local NUMA domain + 1 Reads to memory in the non-local NUMA domain + 0 Reads to memory in the local NUMA domain + ==== ======================================================== + + By default, the mbm_total_bytes configuration is set to 0x7f to count + all the event types and the mbm_local_bytes configuration is set to + 0x15 to count all the local memory events. + + Examples: + + * To view the current configuration:: + :: + + # cat /sys/fs/resctrl/info/L3_MON/mbm_total_config + 0=0x7f;1=0x7f;2=0x7f;3=0x7f + + # cat /sys/fs/resctrl/info/L3_MON/mbm_local_config + 0=0x15;1=0x15;3=0x15;4=0x15 + + * To change the mbm_total_bytes to count only reads on domain 0. + To achieve this, the bits 0, 1, 4 and 5 needs to be set which is + 110011b (in hex 0x33). + :: + + # echo "0=0x33" > /sys/fs/resctrl/info/L3_MON/mbm_total_config + + # cat /sys/fs/resctrl/info/L3_MON/mbm_total_config + 0=0x33;1=0x7f;2=0x7f;3=0x7f + + * To change the mbm_local_bytes to count all the slow memory reads + on domain 1. To achieve this, the bits 4 and 5 needs to be set + which is 110000b (in hex 0x30). + :: + + # echo "1=0x30" > /sys/fs/resctrl/info/L3_MON/mbm_local_config + + # cat /sys/fs/resctrl/info/L3_MON/mbm_local_config + 0=0x15;1=0x30;3=0x15;4=0x15 "max_threshold_occupancy": Read/write file provides the largest value (in @@ -464,6 +539,25 @@ Memory bandwidth domain is L3 cache. MB:<cache_id0>=bw_MBps0;<cache_id1>=bw_MBps1;... +Slow Memory bandwidth Allocation (SMBA) +------------------------------------------------- +AMD hardware can support slow Memory bandwidth Allocation feature. +Currently, CXL.memory is the only supported "slow" memory device. +With the support of SMBA feature the hardware enables bandwidth +allocation on the slow memory devices. If there are multiple slow +memory devices in the system, then the throttling logic groups all +the slow sources together and applies the limit on them as a whole. + +The presence of the SMBA feature(with CXL.memory) is independent +of whether slow memory device is actually present in the system. +If there is no slow memory in the system, then setting a SMBA limit +will have no impact on the performance of the system. + +Slow Memory bandwidth domain is L3 cache. +:: + + SMBA:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;... + Reading/writing the schemata file --------------------------------- Reading the schemata file will show the state of all resources @@ -479,6 +573,44 @@ which you wish to change. E.g. L3DATA:0=fffff;1=fffff;2=3c0;3=fffff L3CODE:0=fffff;1=fffff;2=fffff;3=fffff +Reading/writing the schemata file (on AMD systems) +-------------------------------------------------- +Reading the schemata file will show the state of all resources +on all domains. When writing the memory bandwidth allocation you +only need to specify those values in an absolute number expressed +in 1/8 GB/s increments. To allocate bandwidth limit of 2GB, you +need to specify the value 16 (16 * 1/8 = 2). For example: +:: + + # cat schemata + MB:0=2048;1=2048;2=2048;3=2048 + L3:0=ffff;1=ffff;2=ffff;3=ffff + + # echo "MB:1=16" > schemata + # cat schemata + MB:0=2048;1= 16;2=2048;3=2048 + L3:0=ffff;1=ffff;2=ffff;3=ffff + +Reading/writing the schemata file (on AMD systems) with SMBA feature +------------------------------------------------------------------- +Reading the schemata file will show the state of all resources +on all domains. When writing the memory bandwidth allocation you +only need to specify those values in an absolute number expressed +in 1/8 GB/s increments. To allocate bandwidth limit of 8GB, you +need to specify the value 64 (64 * 1/8 = 8). E.g. +:: + + # cat schemata + SMBA:0=2048;1=2048;2=2048;3=2048 + MB:0=2048;1=2048;2=2048;3=2048 + L3:0=ffff;1=ffff;2=ffff;3=ffff + + # echo "SMBA:1=64" > schemata + # cat schemata + SMBA:0=2048;1= 64;2=2048;3=2048 + MB:0=2048;1=2048;2=2048;3=2048 + L3:0=ffff;1=ffff;2=ffff;3=ffff + Cache Pseudo-Locking ==================== CAT enables a user to specify the amount of cache space that an
