Hi Peter, On 2/26/25 5:27 AM, Peter Newman wrote: > Hi Babu, > > On Tue, Feb 25, 2025 at 10:31 PM Moger, Babu <babu.moger@xxxxxxx> wrote: >> >> Hi Peter, >> >> On 2/25/25 11:11, Peter Newman wrote: >>> Hi Reinette, >>> >>> On Fri, Feb 21, 2025 at 11:43 PM Reinette Chatre >>> <reinette.chatre@xxxxxxxxx> wrote: >>>> >>>> Hi Peter, >>>> >>>> On 2/21/25 5:12 AM, Peter Newman wrote: >>>>> On Thu, Feb 20, 2025 at 7:36 PM Reinette Chatre >>>>> <reinette.chatre@xxxxxxxxx> wrote: >>>>>> On 2/20/25 6:53 AM, Peter Newman wrote: >>>>>>> On Wed, Feb 19, 2025 at 7:21 PM Reinette Chatre >>>>>>> <reinette.chatre@xxxxxxxxx> wrote: >>>>>>>> On 2/19/25 3:28 AM, Peter Newman wrote: >>>>>>>>> On Tue, Feb 18, 2025 at 6:50 PM Reinette Chatre >>>>>>>>> <reinette.chatre@xxxxxxxxx> wrote: >>>>>>>>>> On 2/17/25 2:26 AM, Peter Newman wrote: >>>>>>>>>>> On Fri, Feb 14, 2025 at 8:18 PM Reinette Chatre >>>>>>>>>>> <reinette.chatre@xxxxxxxxx> wrote: >>>>>>>>>>>> On 2/14/25 10:31 AM, Moger, Babu wrote: >>>>>>>>>>>>> On 2/14/2025 12:26 AM, Reinette Chatre wrote: >>>>>>>>>>>>>> On 2/13/25 9:37 AM, Dave Martin wrote: >>>>>>>>>>>>>>> On Wed, Feb 12, 2025 at 03:33:31PM -0800, Reinette Chatre wrote: >>>>>>>>>>>>>>>> On 2/12/25 9:46 AM, Dave Martin wrote: >>>>>>>>>>>>>>>>> On Wed, Jan 22, 2025 at 02:20:08PM -0600, Babu Moger wrote: >>>>>>>>>>>> >>>>>>>>>>>> (quoting relevant parts with goal to focus discussion on new possible syntax) >>>>>>>>>>>> >>>>>>>>>>>>>>>> I see the support for MPAM events distinct from the support of assignable counters. >>>>>>>>>>>>>>>> Once the MPAM events are sorted, I think that they can be assigned with existing interface. >>>>>>>>>>>>>>>> Please help me understand if you see it differently. >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>> Doing so would need to come up with alphabetical letters for these events, >>>>>>>>>>>>>>>> which seems to be needed for your proposal also? If we use possible flags of: >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>> mbm_local_read_bytes a >>>>>>>>>>>>>>>> mbm_local_write_bytes b >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>> Then mbm_assign_control can be used as: >>>>>>>>>>>>>>>> # echo '//0=ab;1=b' >/sys/fs/resctrl/info/L3_MON/mbm_assign_control >>>>>>>>>>>>>>>> # cat /sys/fs/resctrl/mon_data/mon_L3_00/mbm_local_read_bytes >>>>>>>>>>>>>>>> <value> >>>>>>>>>>>>>>>> # cat /sys/fs/resctrl/mon_data/mon_L3_00/mbm_local_bytes >>>>>>>>>>>>>>>> <sum of mbm_local_read_bytes and mbm_local_write_bytes> >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>> One issue would be when resctrl needs to support more than 26 events (no more flags available), >>>>>>>>>>>>>>>> assuming that upper case would be used for "shared" counters (unless this interface is defined >>>>>>>>>>>>>>>> differently and only few uppercase letters used for it). Would this be too low of a limit? >>>>>>>>>>>> >>>>>>>>>>>> As mentioned above, one possible issue with existing interface is that >>>>>>>>>>>> it is limited to 26 events (assuming only lower case letters are used). The limit >>>>>>>>>>>> is low enough to be of concern. >>>>>>>>>>> >>>>>>>>>>> The events which can be monitored by a single counter on ABMC and MPAM >>>>>>>>>>> so far are combinable, so 26 counters per group today means it limits >>>>>>>>>>> breaking down MBM traffic for each group 26 ways. If a user complained >>>>>>>>>>> that a 26-way breakdown of a group's MBM traffic was limiting their >>>>>>>>>>> investigation, I would question whether they know what they're looking >>>>>>>>>>> for. >>>>>>>>>> >>>>>>>>>> The key here is "so far" as well as the focus on MBM only. >>>>>>>>>> >>>>>>>>>> It is impossible for me to predict what we will see in a couple of years >>>>>>>>>> from Intel RDT, AMD PQoS, and Arm MPAM that now all rely on resctrl interface >>>>>>>>>> to support their users. Just looking at the Intel RDT spec the event register >>>>>>>>>> has space for 32 events for each "CPU agent" resource. That does not take into >>>>>>>>>> account the "non-CPU agents" that are enumerated via ACPI. Tony already mentioned >>>>>>>>>> that he is working on patches [1] that will add new events and shared the idea >>>>>>>>>> that we may be trending to support "perf" like events associated with RMID. I >>>>>>>>>> expect AMD PQoS and Arm MPAM to provide related enhancements to support their >>>>>>>>>> customers. >>>>>>>>>> This all makes me think that resctrl should be ready to support more events than 26. >>>>>>>>> >>>>>>>>> I was thinking of the letters as representing a reusable, user-defined >>>>>>>>> event-set for applying to a single counter rather than as individual >>>>>>>>> events, since MPAM and ABMC allow us to choose the set of events each >>>>>>>>> one counts. Wherever we define the letters, we could use more symbolic >>>>>>>>> event names. >>>>>>>> >>>>>>>> Thank you for clarifying. >>>>>>>> >>>>>>>>> >>>>>>>>> In the letters as events model, choosing the events assigned to a >>>>>>>>> group wouldn't be enough information, since we would want to control >>>>>>>>> which events should share a counter and which should be counted by >>>>>>>>> separate counters. I think the amount of information that would need >>>>>>>>> to be encoded into mbm_assign_control to represent the level of >>>>>>>>> configurability supported by hardware would quickly get out of hand. >>>>>>>>> >>>>>>>>> Maybe as an example, one counter for all reads, one counter for all >>>>>>>>> writes in ABMC would look like... >>>>>>>>> >>>>>>>>> (L3_QOS_ABMC_CFG.BwType field names below) >>>>>>>>> >>>>>>>>> (per domain) >>>>>>>>> group 0: >>>>>>>>> counter 0: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>>>>> counter 1: VictimBW,LclNTWr,RmtNTWr >>>>>>>>> group 1: >>>>>>>>> counter 2: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>>>>> counter 3: VictimBW,LclNTWr,RmtNTWr >>>>>>>>> ... >>>>>>>>> >>>>>>>> >>>>>>>> I think this may also be what Dave was heading towards in [2] but in that >>>>>>>> example and above the counter configuration appears to be global. You do mention >>>>>>>> "configurability supported by hardware" so I wonder if per-domain counter >>>>>>>> configuration is a requirement? >>>>>>> >>>>>>> If it's global and we want a particular group to be watched by more >>>>>>> counters, I wouldn't want this to result in allocating more counters >>>>>>> for that group in all domains, or allocating counters in domains where >>>>>>> they're not needed. I want to encourage my users to avoid allocating >>>>>>> monitoring resources in domains where a job is not allowed to run so >>>>>>> there's less pressure on the counters. >>>>>>> >>>>>>> In Dave's proposal it looks like global configuration means >>>>>>> globally-defined "named counter configurations", which works because >>>>>>> it's really per-domain assignment of the configurations to however >>>>>>> many counters the group needs in each domain. >>>>>> >>>>>> I think I am becoming lost. Would a global configuration not break your >>>>>> view of "event-set applied to a single counter"? If a counter is configured >>>>>> globally then it would not make it possible to support the full configurability >>>>>> of the hardware. >>>>>> Before I add more confusion, let me try with an example that builds on your >>>>>> earlier example copied below: >>>>>> >>>>>>>>> (per domain) >>>>>>>>> group 0: >>>>>>>>> counter 0: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>>>>> counter 1: VictimBW,LclNTWr,RmtNTWr >>>>>>>>> group 1: >>>>>>>>> counter 2: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>>>>> counter 3: VictimBW,LclNTWr,RmtNTWr >>>>>>>>> ... >>>>>> >>>>>> Since the above states "per domain" I rewrite the example to highlight that as >>>>>> I understand it: >>>>>> >>>>>> group 0: >>>>>> domain 0: >>>>>> counter 0: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 1: VictimBW,LclNTWr,RmtNTWr >>>>>> domain 1: >>>>>> counter 0: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 1: VictimBW,LclNTWr,RmtNTWr >>>>>> group 1: >>>>>> domain 0: >>>>>> counter 2: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 3: VictimBW,LclNTWr,RmtNTWr >>>>>> domain 1: >>>>>> counter 2: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 3: VictimBW,LclNTWr,RmtNTWr >>>>>> >>>>>> You mention that you do not want counters to be allocated in domains that they >>>>>> are not needed in. So, let's say group 0 does not need counter 0 and counter 1 >>>>>> in domain 1, resulting in: >>>>>> >>>>>> group 0: >>>>>> domain 0: >>>>>> counter 0: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 1: VictimBW,LclNTWr,RmtNTWr >>>>>> group 1: >>>>>> domain 0: >>>>>> counter 2: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 3: VictimBW,LclNTWr,RmtNTWr >>>>>> domain 1: >>>>>> counter 2: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 3: VictimBW,LclNTWr,RmtNTWr >>>>>> >>>>>> With counter 0 and counter 1 available in domain 1, these counters could >>>>>> theoretically be configured to give group 1 more data in domain 1: >>>>>> >>>>>> group 0: >>>>>> domain 0: >>>>>> counter 0: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 1: VictimBW,LclNTWr,RmtNTWr >>>>>> group 1: >>>>>> domain 0: >>>>>> counter 2: LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>>> counter 3: VictimBW,LclNTWr,RmtNTWr >>>>>> domain 1: >>>>>> counter 0: LclFill,RmtFill >>>>>> counter 1: LclNTWr,RmtNTWr >>>>>> counter 2: LclSlowFill,RmtSlowFill >>>>>> counter 3: VictimBW >>>>>> >>>>>> The counters are shown with different per-domain configurations that seems to >>>>>> match with earlier goals of (a) choose events counted by each counter and >>>>>> (b) do not allocate counters in domains where they are not needed. As I >>>>>> understand the above does contradict global counter configuration though. >>>>>> Or do you mean that only the *name* of the counter is global and then >>>>>> that it is reconfigured as part of every assignment? >>>>> >>>>> Yes, I meant only the *name* is global. I assume based on a particular >>>>> system configuration, the user will settle on a handful of useful >>>>> groupings to count. >>>>> >>>>> Perhaps mbm_assign_control syntax is the clearest way to express an example... >>>>> >>>>> # define global configurations (in ABMC terms), not necessarily in this >>>>> # syntax and probably not in the mbm_assign_control file. >>>>> >>>>> r=LclFill,RmtFill,LclSlowFill,RmtSlowFill >>>>> w=VictimBW,LclNTWr,RmtNTWr >>>>> >>>>> # legacy "total" configuration, effectively r+w >>>>> t=LclFill,RmtFill,LclSlowFill,RmtSlowFill,VictimBW,LclNTWr,RmtNTWr >>>>> >>>>> /group0/0=t;1=t >>>>> /group1/0=t;1=t >>>>> /group2/0=_;1=t >>>>> /group3/0=rw;1=_ >>>>> >>>>> - group2 is restricted to domain 0 >>>>> - group3 is restricted to domain 1 >>>>> - the rest are unrestricted >>>>> - In group3, we decided we need to separate read and write traffic >>>>> >>>>> This consumes 4 counters in domain 0 and 3 counters in domain 1. >>>>> >>>> >>>> I see. Thank you for the example. >>>> >>>> resctrl supports per-domain configurations with the following possible when >>>> using mbm_total_bytes_config and mbm_local_bytes_config: >>>> >>>> t(domain 0)=LclFill,RmtFill,LclSlowFill,RmtSlowFill,VictimBW,LclNTWr,RmtNTWr >>>> t(domain 1)=LclFill,RmtFill,VictimBW,LclNTWr,RmtNTWr >>>> >>>> /group0/0=t;1=t >>>> /group1/0=t;1=t >>>> >>>> Even though the flags are identical in all domains, the assigned counters will >>>> be configured differently in each domain. >>>> >>>> With this supported by hardware and currently also supported by resctrl it seems >>>> reasonable to carry this forward to what will be supported next. >>> >>> The hardware supports both a per-domain mode, where all groups in a >>> domain use the same configurations and are limited to two events per >>> group and a per-group mode where every group can be configured and >>> assigned freely. This series is using the legacy counter access mode >>> where only counters whose BwType matches an instance of QOS_EVT_CFG_n >>> in the domain can be read. If we chose to read the assigned counter >>> directly (QM_EVTSEL[ExtendedEvtID]=1, QM_EVTSEL[EvtID]=L3CacheABMC) >>> rather than asking the hardware to find the counter by RMID, we would >>> not be limited to 2 counters per group/domain and the hardware would >>> have the same flexibility as on MPAM. >> >> In extended mode, the contents of a specific counter can be read by >> setting the following fields in QM_EVTSEL: [ExtendedEvtID]=1, >> [EvtID]=L3CacheABMC and setting [RMID] to the desired counter ID. Reading >> QM_CTR will then return the contents of the specified counter. >> >> It is documented below. >> https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24593.pdf >> Section: 19.3.3.3 Assignable Bandwidth Monitoring (ABMC) >> >> We previously discussed this with you (off the public list) and I >> initially proposed the extended assignment mode. >> >> Yes, the extended mode allows greater flexibility by enabling multiple >> counters to be assigned to the same group, rather than being limited to >> just two. >> >> However, the challenge is that we currently lack the necessary interfaces >> to configure multiple events per group. Without these interfaces, the >> extended mode is not practical at this time. >> >> Therefore, we ultimately agreed to use the legacy mode, as it does not >> require modifications to the existing interface, allowing us to continue >> using it as is. >> >>> >>> (I might have said something confusing in my last messages because I >>> had forgotten that I switched to the extended assignment mode when >>> prototyping with soft-ABMC and MPAM.) >>> >>> Forcing all groups on a domain to share the same 2 counter >>> configurations would not be acceptable for us, as the example I gave >>> earlier is one I've already been asked about. >> >> I don’t see this as a blocker. It should be considered an extension to the >> current ABMC series. We can easily build on top of this series once we >> finalize how to configure the multiple event interface for each group. > > I don't think it is, either. Only being able to use ABMC to assign > counters is fine for our use as an incremental step. My longer-term > concern is the domain-scoped mbm_total_bytes_config and > mbm_local_bytes_config files, but they were introduced with BMEC, so > there's already an expectation that the files are present when BMEC is > supported. > > On ABMC hardware that also supports BMEC, I'm concerned about enabling > ABMC when only the BMEC-style event configuration interface exists. ABMC currently depends on BMEC making the current implementation the one you are concerned about? https://lore.kernel.org/lkml/e4111779ebb0e7004dbedc258eeae2677f578ab1.1737577229.git.babu.moger@xxxxxxx/ > The scope of my issue is just whether enabling "full" ABMC support > will require an additional opt-in, since that could remove the BMEC > interface. If it does, it's something we can live with. Reinette
