From: "Burakov, Anatoly" <anatoly.burakov@intel.com>
To: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>,
"dev@dpdk.org" <dev@dpdk.org>,
"Richardson, Bruce" <bruce.richardson@intel.com>
Cc: "Loftus, Ciara" <ciara.loftus@intel.com>,
"Hunt, David" <david.hunt@intel.com>
Subject: Re: [dpdk-dev] [PATCH v1 1/7] power_intrinsics: allow monitor checks inversion
Date: Thu, 24 Jun 2021 16:54:03 +0100 [thread overview]
Message-ID: <a5ae8069-4868-392c-06d8-39cd5f41033c@intel.com> (raw)
In-Reply-To: <DM6PR11MB4491070E7DF0CA90B7692AD49A079@DM6PR11MB4491.namprd11.prod.outlook.com>
On 24-Jun-21 4:25 PM, Ananyev, Konstantin wrote:
>
>>>>>>>> I did a quick prototype for this, and i don't think it is going to work.
>>>>>>>>
>>>>>>>> Callbacks with just "current value" as argument will be pretty limited
>>>>>>>> and will only really work for cases where we know what we are expecting.
>>>>>>>> However, for cases like event/dlb or net/mlx5, the expected value is (or
>>>>>>>> appears to be) dependent upon some internal device data, and is not
>>>>>>>> constant like in case of net/ixgbe for example.
>>>>>>>>
>>>>>>>> This can be fixed by passing an opaque pointer, either by storing it in
>>>>>>>> the monitor condition, or by passing it directly to rte_power_monitor at
>>>>>>>> invocation time.
>>>>>>>>
>>>>>>>> The latter doesn't work well because when we call rte_power_monitor from
>>>>>>>> inside the rte_power library, we lack the context necessary to get said
>>>>>>>> opaque pointer.
>>>>>>>>
>>>>>>>> The former doesn't work either, because the only place where we can get
>>>>>>>> this argument is inside get_monitor_addr, but the opaque pointer must
>>>>>>>> persist after we exit that function in order to avoid use-after-free -
>>>>>>>> which means that it either has to be statically allocated (which means
>>>>>>>> it's not thread-safe for a non-trivial case), or dynamically allocated
>>>>>>>> (which a big no-no on a hotpath).
>>>>>>>
>>>>>>> If I get you right, expected_value (and probably mask) can be variable ones.
>>>>>>> So for callback approach to work we need to pass all this as parameters
>>>>>>> to PMD comparison callback:
>>>>>>> int pmc_callback(uint64_t real_val, uint64_t expected_val, uint64_t mask)
>>>>>>> Correct?
>>>>>>
>>>>>> If we have both expected value, mask, and current value, then what's the
>>>>>> point of the callback? The point of the callback would be to pass just
>>>>>> the current value, and let the callback decide what's the expected value
>>>>>> and how to compare it.
>>>>>
>>>>> For me the main point of callback is to hide PMD specific comparison semantics.
>>>>> Basically they provide us with some values in struct rte_power_monitor_cond,
>>>>> and then it is up to them how to interpret them in their comparison function.
>>>>> All we'll do for them: will read the value at address provided.
>>>>> I understand that it looks like an overkill, as majority of these comparison functions
>>>>> will be like:
>>>>> int cmp_callback(uint64_t real_val, uint64_t expected_val, uint64_t mask)
>>>>> {
>>>>> return ((real_val & mask) == expected_val);
>>>>> }
>>>>> Though qsort() and bsearch() work in a similar manner, and everyone seems ok with it.
>>>>>
>>>>>>
>>>>>> So, we can either let callback handle expected values itself by having
>>>>>> an opaque callback-specific argument (which means it has to persist
>>>>>> between .get_monitor_addr() and rte_power_monitor() calls),
>>>>>
>>>>> But that's what we doing already - PMD fills rte_power_monitor_cond values
>>>>> for us, we store them somewhere and then use them to decide should we go to sleep or not.
>>>>> All callback does - moves actual values interpretation back to PMD:
>>>>> Right now:
>>>>> PMD: provide PMC values
>>>>> POWER: store PMC values somewhere
>>>>> read the value at address provided in PMC
>>>>> interpret PMC values and newly read value and make the decision
>>>>>
>>>>> With callback:
>>>>> PMD: provide PMC values
>>>>> POWER: store PMC values somewhere
>>>>> read the value at address provided in PMC
>>>>> PMD: interpret PMC values and newly read value and make the decision
>>>>>
>>>>> Or did you mean something different here?
>>>>>
>>>>>> or we do the
>>>>>> comparisons inside rte_power_monitor(), and store the expected/mask
>>>>>> values in the monitor condition, and *don't* have any callbacks at all.
>>>>>> Are you suggesting an alternative to the above two options?
>>>>>
>>>>> As I said in my first mail - we can just replace 'inverse' with 'op'.
>>>>> That at least will make this API extendable, if someone will need
>>>>> something different in future.
>>>>>
>>>>> Another option is
>>>>
>>>> Right, so the idea is store the PMD-specific data in the monitor
>>>> condition, and leave it to the callback to interpret it.
>>>>
>>>> The obvious question then is, how many values is enough? Two? Three?
>>>> Four? This option doesn't really solve the basic issue, it just kicks
>>>> the can down the road. I guess three values should be enough for
>>>> everyone (tm) ? :D
>>>>
>>>> I don't like the 'op' thing because if the goal is to be flexible, it's
>>>> unnecessarily limiting *and* makes the API even more complex to use. I
>>>> would rather have a number of PMD-specific values and leave it up to the
>>>> callback to interpret them, because at least that way we're not limited
>>>> to predefined operations on the monitor condition data.
>>>
>>> Just to make sure we are talking about the same, does what you propose
>>> looks like that:
>>>
>>> struct rte_power_monitor_cond {
>>> volatile void *addr; /**< Address to monitor for changes */
>>> uint8_t size; /**< Data size (in bytes) that will be used to compare
>>> * expected value (`val`) with data read from the
>>> * monitored memory location (`addr`). Can be 1, 2,
>>> * 4, or 8. Supplying any other value will result in
>>> * an error.
>>> */
>>> int (*cmp)(uint64_t real_value, const uint64_t opaque[4]);
>>> uint64_t opaque[4]; /*PMD specific data, used by comparison call-back below */
>>> };
>>>
>>> And then in rte_power_monitor():
>>> ...
>>> uint64_t cur_value = __get_umwait_val(pmc->addr, pmc->size);
>>> if (pmc->cmp(cur_value, pmc->opaque) != 0) {
>>> /* goto sleep */
>>> }
>>>
>>> ?
>>>
>>
>> Something like that, yes.
>>
>
> Seems reasonable to me.
> Thanks
> Konstantin
>
OK, i'll implement this in v2. Thanks for your input!
--
Thanks,
Anatoly
next prev parent reply other threads:[~2021-06-24 15:56 UTC|newest]
Thread overview: 165+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-01 12:00 [dpdk-dev] [PATCH v1 0/7] Enhancements for PMD power management Anatoly Burakov
2021-06-01 12:00 ` [dpdk-dev] [PATCH v1 1/7] power_intrinsics: allow monitor checks inversion Anatoly Burakov
2021-06-21 12:56 ` Ananyev, Konstantin
2021-06-23 9:43 ` Burakov, Anatoly
2021-06-23 9:55 ` Ananyev, Konstantin
2021-06-23 10:00 ` Burakov, Anatoly
2021-06-23 11:00 ` Ananyev, Konstantin
2021-06-23 12:12 ` Burakov, Anatoly
2021-06-23 13:27 ` Ananyev, Konstantin
2021-06-23 14:13 ` Burakov, Anatoly
2021-06-24 9:47 ` Ananyev, Konstantin
2021-06-24 14:34 ` Burakov, Anatoly
2021-06-24 14:57 ` Ananyev, Konstantin
2021-06-24 15:04 ` Burakov, Anatoly
2021-06-24 15:25 ` Ananyev, Konstantin
2021-06-24 15:54 ` Burakov, Anatoly [this message]
2021-07-09 15:03 ` David Marchand
2021-06-01 12:00 ` [dpdk-dev] [PATCH v1 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-06-02 12:59 ` Loftus, Ciara
2021-06-01 12:00 ` [dpdk-dev] [PATCH v1 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-06-01 12:00 ` [dpdk-dev] [PATCH v1 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-06-22 9:13 ` Ananyev, Konstantin
2021-06-23 9:46 ` Burakov, Anatoly
2021-06-23 9:52 ` Ananyev, Konstantin
2021-06-25 11:52 ` Burakov, Anatoly
2021-06-25 14:42 ` Ananyev, Konstantin
2021-06-01 12:00 ` [dpdk-dev] [PATCH v1 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-06-22 9:41 ` Ananyev, Konstantin
2021-06-23 9:36 ` Burakov, Anatoly
2021-06-23 9:49 ` Ananyev, Konstantin
2021-06-23 9:56 ` Burakov, Anatoly
2021-06-01 12:00 ` [dpdk-dev] [PATCH v1 6/7] power: support monitoring " Anatoly Burakov
2021-06-01 12:00 ` [dpdk-dev] [PATCH v1 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 0/7] Enhancements for PMD power management Anatoly Burakov
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 1/7] power_intrinsics: use callbacks for comparison Anatoly Burakov
2021-06-28 12:19 ` Ananyev, Konstantin
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-06-28 12:37 ` Ananyev, Konstantin
2021-06-28 12:43 ` Burakov, Anatoly
2021-06-28 12:58 ` Ananyev, Konstantin
2021-06-28 13:29 ` Burakov, Anatoly
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-06-28 7:10 ` David Marchand
2021-06-28 9:25 ` Burakov, Anatoly
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 6/7] power: support monitoring " Anatoly Burakov
2021-06-25 14:00 ` [dpdk-dev] [PATCH v2 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 0/7] Enhancements for PMD power management Anatoly Burakov
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 1/7] power_intrinsics: use callbacks for comparison Anatoly Burakov
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 6/7] power: support monitoring " Anatoly Burakov
2021-06-28 13:29 ` Ananyev, Konstantin
2021-06-28 14:09 ` Burakov, Anatoly
2021-06-29 0:07 ` Ananyev, Konstantin
2021-06-29 11:05 ` Burakov, Anatoly
2021-06-29 11:39 ` Burakov, Anatoly
2021-06-29 12:14 ` Ananyev, Konstantin
2021-06-29 13:23 ` Burakov, Anatoly
2021-06-28 12:41 ` [dpdk-dev] [PATCH v3 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 0/7] Enhancements for PMD power management Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 1/7] power_intrinsics: use callbacks for comparison Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 6/7] power: support monitoring " Anatoly Burakov
2021-06-28 15:54 ` [dpdk-dev] [PATCH v4 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 0/7] Enhancements for PMD power management Anatoly Burakov
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 1/7] power_intrinsics: use callbacks for comparison Anatoly Burakov
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-06-30 9:52 ` David Hunt
2021-07-01 9:01 ` David Hunt
2021-07-05 10:24 ` Burakov, Anatoly
2021-06-30 11:04 ` Ananyev, Konstantin
2021-07-05 10:23 ` Burakov, Anatoly
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 6/7] power: support monitoring " Anatoly Burakov
2021-06-30 10:29 ` Ananyev, Konstantin
2021-07-05 10:08 ` Burakov, Anatoly
2021-06-29 15:48 ` [dpdk-dev] [PATCH v5 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-07-05 15:21 ` [dpdk-dev] [PATCH v6 0/7] Enhancements for PMD power management Anatoly Burakov
2021-07-05 15:21 ` [dpdk-dev] [PATCH v6 1/7] power_intrinsics: use callbacks for comparison Anatoly Burakov
2021-07-05 15:21 ` [dpdk-dev] [PATCH v6 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-07-05 15:21 ` [dpdk-dev] [PATCH v6 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-08-04 9:52 ` Kinsella, Ray
2021-07-05 15:21 ` [dpdk-dev] [PATCH v6 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-07-07 10:14 ` Ananyev, Konstantin
2021-07-05 15:22 ` [dpdk-dev] [PATCH v6 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-07-06 18:50 ` Ananyev, Konstantin
2021-07-07 10:06 ` Burakov, Anatoly
2021-07-07 10:11 ` Ananyev, Konstantin
2021-07-07 11:54 ` Burakov, Anatoly
2021-07-07 12:51 ` Ananyev, Konstantin
2021-07-07 14:35 ` Burakov, Anatoly
2021-07-07 17:09 ` Ananyev, Konstantin
2021-07-07 10:04 ` David Hunt
2021-07-07 10:28 ` Burakov, Anatoly
2021-07-05 15:22 ` [dpdk-dev] [PATCH v6 6/7] power: support monitoring " Anatoly Burakov
2021-07-07 10:16 ` Ananyev, Konstantin
2021-07-05 15:22 ` [dpdk-dev] [PATCH v6 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 0/7] Enhancements for PMD power management Anatoly Burakov
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 1/7] power_intrinsics: use callbacks for comparison Anatoly Burakov
2021-07-07 11:56 ` David Hunt
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-07-07 12:01 ` David Hunt
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-07-07 12:02 ` David Hunt
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-07-07 11:54 ` David Hunt
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 6/7] power: support monitoring " Anatoly Burakov
2021-07-07 12:03 ` David Hunt
2021-07-07 10:48 ` [dpdk-dev] [PATCH v7 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-07-07 12:03 ` David Hunt
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 0/7] Enhancements for PMD power management Anatoly Burakov
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 1/7] power_intrinsics: use callbacks for comparison Anatoly Burakov
2021-07-08 16:56 ` McDaniel, Timothy
2021-07-09 13:46 ` Thomas Monjalon
2021-07-09 14:41 ` Burakov, Anatoly
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 2/7] net/af_xdp: add power monitor support Anatoly Burakov
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 3/7] eal: add power monitor for multiple events Anatoly Burakov
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 4/7] power: remove thread safety from PMD power API's Anatoly Burakov
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 5/7] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-07-09 14:24 ` David Marchand
2021-07-09 14:42 ` Burakov, Anatoly
2021-07-09 14:46 ` David Marchand
2021-07-09 14:53 ` Burakov, Anatoly
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 6/7] power: support monitoring " Anatoly Burakov
2021-07-08 14:13 ` [dpdk-dev] [PATCH v8 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes Anatoly Burakov
2021-07-09 14:50 ` David Marchand
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 0/8] Enhancements for PMD power management Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 1/8] eal: use callbacks for power monitoring comparison Anatoly Burakov
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 2/8] net/af_xdp: add power monitor support Anatoly Burakov
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 3/8] doc: add PMD power management NIC feature Anatoly Burakov
2021-07-09 15:57 ` Burakov, Anatoly
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 4/8] eal: add power monitor for multiple events Anatoly Burakov
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 5/8] power: remove thread safety from PMD power API's Anatoly Burakov
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 6/8] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 7/8] power: support monitoring " Anatoly Burakov
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 15:53 ` [dpdk-dev] [PATCH v9 8/8] examples/l3fwd-power: support multiq in PMD modes Anatoly Burakov
2021-07-09 16:00 ` Anatoly Burakov
2021-07-09 16:00 ` [dpdk-dev] [PATCH v9 0/8] Enhancements for PMD power management Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 " Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 1/8] eal: use callbacks for power monitoring comparison Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 2/8] net/af_xdp: add power monitor support Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 3/8] doc: add PMD power management NIC feature Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 4/8] eal: add power monitor for multiple events Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 5/8] power: remove thread safety from PMD power API's Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 6/8] power: support callbacks for multiple Rx queues Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 7/8] power: support monitoring " Anatoly Burakov
2021-07-09 16:08 ` [dpdk-dev] [PATCH v10 8/8] examples/l3fwd-power: support multiq in PMD modes Anatoly Burakov
2021-07-09 19:24 ` [dpdk-dev] [PATCH v10 0/8] Enhancements for PMD power management David Marchand
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=a5ae8069-4868-392c-06d8-39cd5f41033c@intel.com \
--to=anatoly.burakov@intel.com \
--cc=bruce.richardson@intel.com \
--cc=ciara.loftus@intel.com \
--cc=david.hunt@intel.com \
--cc=dev@dpdk.org \
--cc=konstantin.ananyev@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).