Re: [dpdk-dev] [PATCH] app: fix redundant comparison

2021-04-19 Thread David Hunt
Hi Connor, On 19/4/2021 1:29 PM, Min Hu (Connor) wrote: The return value of 'rte_eal_cleanup' is always zero, so comparison with zero is redundant. This patch fixed it by deleting the redundant comparison. Fixes: 67684d1e87b6 ("app/procinfo: call EAL cleanup before exit") Fixes: b68a82425da4 (

Re: [dpdk-dev] [PATCH v5 1/2] test/power: add delay before checking cpuinfo cur freq

2021-04-20 Thread David Hunt
On 15/4/2021 6:59 AM, Richael Zhuang wrote: For some platforms the newly-set frequency may not be effective immediately. If we didn't get the right value from cpuinfo_cur_freq immediately, add 10ms delay each time before rechecking until timeout. From our test, for some arm platforms, it requ

Re: [dpdk-dev] [PATCH v5 1/2] test/power: add delay before checking cpuinfo cur freq

2021-04-20 Thread David Hunt
On 20/4/2021 1:38 PM, David Hunt wrote: On 15/4/2021 6:59 AM, Richael Zhuang wrote: For some platforms the newly-set frequency may not be effective immediately. If we didn't get the right value from cpuinfo_cur_freq immediately, add 10ms delay each time before rechecking until ti

Re: [dpdk-dev] [PATCH v5 2/2] test/power: round cpuinfo cur freq value in cpufreq autotest

2021-04-20 Thread David Hunt
his, rounds nicely. I found an unrelated issue around turbo mode that I need to look at but this patch looks fine. Reviewed-by: David Hunt

[dpdk-dev] [PATCH v1 1/4] test/power: fix check for cpu frequency

2021-04-22 Thread David Hunt
power manager unit tests") Cc: sta...@dpdk.org Signed-off-by: David Hunt --- app/test/test_power_cpufreq.c | 15 --- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/app/test/test_power_cpufreq.c b/app/test/test_power_cpufreq.c index f753d24ac5..52f58ef8b2 100644 ---

[dpdk-dev] [PATCH v1 3/4] test/power: fix low freq test when turbo enabled

2021-04-22 Thread David Hunt
With the intel_pstate driver and turbo enabled, indexing is slightly different to normal, so to get the test to work properly, enable turbo at the start. Fixes: ed7c51a6a680 ("app/test: vm power management") Cc: sta...@dpdk.org Signed-off-by: David Hunt --- app/test/test_power_cpu

[dpdk-dev] [PATCH v1 2/4] test/power: add turbo mode to freq check function

2021-04-22 Thread David Hunt
expected (turbo mode), in which case the check should be successful. Fixes: aeaeaf5f2d62 ("test/power: add cases for turbo feature") Cc: sta...@dpdk.org Signed-off-by: David Hunt --- app/test/test_power_cpufreq.c | 27 +++ 1 file changed, 15 insertions(+), 12

[dpdk-dev] [PATCH v1 4/4] test/power: fix turbo test

2021-04-22 Thread David Hunt
when turbo is enabled or disabled, the frequency is set to a low non-turbo frequency, so we need to set to the frequency expected by the test before checking. Fixes: aeaeaf5f2d62 ("test/power: add cases for turbo feature") Cc: sta...@dpdk.org Signed-off-by: David Hunt ---

Re: [dpdk-dev] [PATCH] examples/vm_power_manager: remove vm channel number check

2021-04-23 Thread David Hunt
RTE_LOG(INFO, CHANNEL_MANAGER, "Channel(%u) is out of range " "0...%d\n", channel_list[i], Thanks, Reshma. The rte_lcore_index() call was incorrectly comparing virtual core_id against the list of physical core_ids. Reviewed-by: David Hunt

Re: [dpdk-dev] [PATCH v1 1/2] net/ixgbe: allow get_monitor_addr for VF driver

2021-04-26 Thread David Hunt
h resolves the issue. Reviewed-by: David Hunt

Re: [dpdk-dev] [PATCH v1 2/2] net/i40e: allow get_monitor_addr for VF driver

2021-04-26 Thread David Hunt
e issue as the ixgbe, get_monitor_addr op missing for the vf portion of the driver. Thanks. Reviewed-by: David Hunt

Re: [dpdk-dev] [RFC PATCH] test/distributor: fix burst flush on worker quit

2021-04-28 Thread David Hunt
rte_eal_mp_wait_lcore(); quit = 0; worker_idx = 0;     Tested-by: Lukasz Wojciechowski     Reviewed-by: Lukasz Wojciechowski Thanks, Stanislaw, Lukasz. Acked-by: David Hunt

Re: [dpdk-dev] [RFC PATCH] test/distributor: fix burst flush on worker quit

2021-04-28 Thread David Hunt
On 28/4/2021 1:53 PM, Stanisław Kardach wrote: On Wed, Apr 28, 2021 at 2:51 PM David Hunt <mailto:david.h...@intel.com>> wrote: Thanks, Stanislaw, Lukasz. Acked-by: David Hunt mailto:david.h...@intel.com>> Just to be sure, may I send the non-RFC patch without the qu

[dpdk-dev] [PATCH v2 1/2] power: don't use rte prefix in internal code

2021-06-22 Thread David Hunt
From: Anatoly Burakov Currently, ACPI code uses rte_power_info as the struct name, which gives the appearance that this is an externally visible API. Fix to use internal namespace. Signed-off-by: Anatoly Burakov Acked-by: David Hunt --- lib/power/power_acpi_cpufreq.c | 34

[dpdk-dev] [PATCH v2 2/2] power: refactor pstate and acpi code

2021-06-22 Thread David Hunt
-off-by: Anatoly Burakov Signed-off-by: David Hunt --- changes in v2 * fixed bugs raised by Richael Zhuang in review - open file rw+, etc. * removed FOPS* and FOPEN* macros, which contained control statements. * fixed some checkpatch warnings. --- lib/power/meson.build| 7 + lib

[dpdk-dev] [PATCH v5 1/2] power: don't use rte prefix in internal code

2021-06-22 Thread David Hunt
From: Anatoly Burakov Currently, ACPI code uses rte_power_info as the struct name, which gives the appearance that this is an externally visible API. Fix to use internal namespace. Signed-off-by: Anatoly Burakov Acked-by: David Hunt --- lib/power/power_acpi_cpufreq.c | 34

[dpdk-dev] [PATCH v5 2/2] power: refactor pstate and acpi code

2021-06-22 Thread David Hunt
-off-by: Anatoly Burakov Signed-off-by: David Hunt --- changes in v2 * fixed bugs raised by Richael Zhuang in review - open file rw+, etc. * removed FOPS* and FOPEN* macros, which contained control statements. * fixed some checkpatch warnings. --- lib/power/meson.build| 7 + lib

Re: [dpdk-dev] [PATCH v2 1/2] power: don't use rte prefix in internal code

2021-06-22 Thread David Hunt
On 22/6/2021 1:43 PM, David Hunt wrote: From: Anatoly Burakov Currently, ACPI code uses rte_power_info as the struct name, which gives the appearance that this is an externally visible API. Fix to use internal namespace. Signed-off-by: Anatoly Burakov Acked-by: David Hunt --- lib/power

Re: [dpdk-dev] [PATCH v2 2/2] power: refactor pstate and acpi code

2021-06-22 Thread David Hunt
On 22/6/2021 1:43 PM, David Hunt wrote: From: Anatoly Burakov Currently, ACPI and PSTATE modes have lots of code duplication, confusing logic, and a bunch of other issues that can, and have, led to various bugs and resource leaks. This commit factors out the common parts of sysfs reading

Re: [dpdk-dev] [PATCH v5 2/2] power: refactor pstate and acpi code

2021-06-22 Thread David Hunt
Adding people to the CC list that were on v4 of this patch set, and Richael who raised some issues in v4. On 22/6/2021 1:58 PM, David Hunt wrote: From: Anatoly Burakov Currently, ACPI and PSTATE modes have lots of code duplication, confusing logic, and a bunch of other issues that can, and

[dpdk-dev] [PATCH v2] examples/power: add baseline mode to PMD power

2021-06-22 Thread David Hunt
--pmg-mgmt=baseline. Signed-off-by: David Hunt --- changes in v2 * added a bool for baseline mode rather than abusing enums --- examples/l3fwd-power/main.c | 14 -- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/ma

Re: [dpdk-dev] [PATCH v5 2/2] power: refactor pstate and acpi code

2021-06-23 Thread David Hunt
fflush(f); + if (ret != 0) + return -1; + + return 0; +} Best regards, Richael -Original Message- From: David Hunt Sent: Tuesday, June 22, 2021 9:28 PM To: dev@dpdk.org Cc: anatoly.bura...@intel.com; step...@networkplumber.org; Richael Zhuang ; Reshma Pattan ; nd Sub

[dpdk-dev] [PATCH v6 1/2] power: don't use rte prefix in internal code

2021-06-23 Thread David Hunt
From: Anatoly Burakov Currently, ACPI code uses rte_power_info as the struct name, which gives the appearance that this is an externally visible API. Fix to use internal namespace. Signed-off-by: Anatoly Burakov Acked-by: David Hunt --- lib/power/power_acpi_cpufreq.c | 34

[dpdk-dev] [PATCH v6 2/2] power: refactor pstate and acpi code

2021-06-23 Thread David Hunt
-off-by: Anatoly Burakov Signed-off-by: David Hunt --- changes in v5 * fixed bugs raised by Richael Zhuang in review - open file rw+, etc. * removed FOPS* and FOPEN* macros, which contained control statements. * fixed some checkpatch warnings. changes in v6 * fixed check of fputs return, negative

Re: [dpdk-dev] [PATCH v2] examples/power: add baseline mode to PMD power

2021-06-23 Thread David Hunt
On 23/6/2021 11:14 AM, Burakov, Anatoly wrote: On 22-Jun-21 3:07 PM, David Hunt wrote: The PMD Power Management scheme currently has 3 modes, scale, monitor and pause. However, it would be nice to have a baseline mode for easy comparison of power savings with and without these modes. This

Re: [dpdk-dev] [PATCH v4 1/2] power: add support for cppc cpufreq

2021-06-23 Thread David Hunt
macros need to be removed to bring in line with the latest (v6) patch for the cleanup work, a few people have been wanting to remove those macros for a while now :) Once that's done, this patch looks good to me, although I can't give it a run as I don't have access to a sui

Re: [dpdk-dev] [PATCH v4 2/2] test/power: round cpuinfo cur freq only when using CPPC cpufreq

2021-06-23 Thread David Hunt
uang --- app/test/test_power_cpufreq.c | 23 ++- 1 file changed, 14 insertions(+), 9 deletions(-) --snip-- Makes sense. Reviewed-by: David Hunt

Re: [dpdk-dev] [PATCH v5 5/7] power: support callbacks for multiple Rx queues

2021-06-30 Thread David Hunt
Hi Anatoly, On 29/6/2021 4:48 PM, Anatoly Burakov wrote: Currently, there is a hard limitation on the PMD power management support that only allows it to support a single queue per lcore. This is not ideal as most DPDK use cases will poll multiple queues per core. The PMD power management mecha

Re: [dpdk-dev] [PATCH v5 5/7] power: support callbacks for multiple Rx queues

2021-07-01 Thread David Hunt
On 30/6/2021 10:52 AM, David Hunt wrote: Hi Anatoly, On 29/6/2021 4:48 PM, Anatoly Burakov wrote: Currently, there is a hard limitation on the PMD power management support that only allows it to support a single queue per lcore. This is not ideal as most DPDK use cases will poll multiple

Re: [dpdk-dev] [PATCH v6 5/7] power: support callbacks for multiple Rx queues

2021-07-07 Thread David Hunt
On 5/7/2021 4:22 PM, Anatoly Burakov wrote: Currently, there is a hard limitation on the PMD power management support that only allows it to support a single queue per lcore. This is not ideal as most DPDK use cases will poll multiple queues per core. The PMD power management mechanism relies

Re: [dpdk-dev] [PATCH v7 5/7] power: support callbacks for multiple Rx queues

2021-07-07 Thread David Hunt
wer savings are back as expected when low traffic in both monitor and pause modes. All previous issues seem now to be resolved. Patch set LGTM. Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v7 1/7] power_intrinsics: use callbacks for comparison

2021-07-07 Thread David Hunt
v2: - Use callback mechanism for more flexibility - Address feedback from Konstantin Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v7 3/7] eal: add power monitor for multiple events

2021-07-07 Thread David Hunt
en available to use. Once this was done, I was then able to successfully see power saving when a core was configuired with multiple queues. Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v7 4/7] power: remove thread safety from PMD power API's

2021-07-07 Thread David Hunt
d, and document this limitation. This greatly simplifies the `rte_power_monitor`-related code. Signed-off-by: Anatoly Burakov --- Notes: v2: - Add check for stopped queue - Clarified doc message - Added release notes Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v7 6/7] power: support monitoring multiple Rx queues

2021-07-07 Thread David Hunt
is not supported by the hardware. Signed-off-by: Anatoly Burakov --- Notes: v6: - Fix the missed feedback from v5 v4: - Fix possible out of bounds access - Added missing index increment --snip-- Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v7 7/7] l3fwd-power: support multiqueue in PMD pmgmt modes

2021-07-07 Thread David Hunt
wer management mode, only one queue per lcore is allowed\n"); - } - /* init RX queues */ for(queue = 0; queue < qconf->n_rx_queue; ++queue) { struct rte_eth_rxconf rxq_conf; Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v5 1/2] power: add support for cppc cpufreq

2021-07-07 Thread David Hunt
Hi Richael, On 25/6/2021 3:02 AM, Richael Zhuang wrote: Currently in DPDK only acpi_cpufreq and pstate_cpufreq drivers are supported, which are both not available on arm64 platforms. Add support for cppc_cpufreq driver which works on most arm64 platforms. Signed-off-by: Richael Zhuang --- H

Re: [dpdk-dev] [PATCH v6 1/2] power: add support for cppc cpufreq

2021-07-08 Thread David Hunt
on't have access to a suitable machine. LGTM. Acked-by: David Hunt

Re: [dpdk-dev] [PATCH v6 2/2] test/power: round cpuinfo cur freq only in CPPC cpufreq

2021-07-08 Thread David Hunt
test_power_cpufreq.c | 23 ++- 1 file changed, 14 insertions(+), 9 deletions(-) Acked-by: David Hunt

Re: [dpdk-dev] [PATCH] power: fix use-after-free in pstate code

2021-04-07 Thread David Hunt
val is fine. Acked-by: David Hunt

Re: [PATCH v5 44/50] distributor: remove unneeded header includes

2022-01-25 Thread David Hunt
/rte_distributor_single.c| 2 -- 3 files changed, 6 deletions(-) Acked-by: David Hunt

Re: [PATCH v5 17/50] power: remove unneeded header includes

2022-01-25 Thread David Hunt
/rte_power.h | 2 -- lib/power/rte_power_empty_poll.c | 2 -- 14 files changed, 1 insertion(+), 40 deletions(-) Acked-by: David Hunt

Re: [PATCH v2 82/83] power: remove unnecessary NULL checks

2022-01-25 Thread David Hunt
(ep_params != NULL) - rte_free(ep_params); + rte_free(ep_params); } int Acked-by: David Hunt

Re: [PATCH v4 4/4] examples/l3fwd_power: add cli for configurable options

2022-05-24 Thread David Hunt
-by: David Hunt

Re: [PATCH v4 3/4] lib/power: add get and set API for scaling freq min and max with pstate mode

2022-05-24 Thread David Hunt
anged, 181 insertions(+), 5 deletions(-) Tested-by: David Hunt

Re: [PATCH v4 2/4] lib/power: add get and set API for pause duration

2022-05-24 Thread David Hunt
lib/power/rte_power_pmd_mgmt.c | 25 +++-- lib/power/rte_power_pmd_mgmt.h | 31 +++ lib/power/version.map | 2 ++ 3 files changed, 56 insertions(+), 2 deletions(-) Tested-by: David Hunt

Re: [PATCH v4 1/4] lib/power: add get and set API for emptypoll max

2022-05-24 Thread David Hunt
/rte_power_pmd_mgmt.h | 27 +++ lib/power/version.map | 4 3 files changed, 49 insertions(+), 3 deletions(-) Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v7 5/5] examples/l3fwd-power: support virtio/vhost

2021-10-22 Thread David Hunt
ret = rte_eth_dev_configure(portid, nb_rx_queue, (uint16_t)n_tx_queue, &local_port_conf); if (ret < 0) -- 2.25.1 Reviewed-by: Chenbo Xia LGTM. Acked-by: David Hunt

Re: [dpdk-dev] [PATCH v7 4/5] power: modify return of queue_stopped

2021-10-22 Thread David Hunt
On 21/10/2021 5:48 PM, Ferruh Yigit wrote: On 10/18/2021 3:16 PM, Miao Li wrote: Since some vdevs like virtio and vhost do not support rxq_info_get and queue state inquiry, the error return value -ENOTSUP need to be ignored when queue_stopped cannot get rx queue information and rx queue state.

Re: [dpdk-dev] [PATCH v7 3/5] net/vhost: implement rte_power_monitor API

2021-10-22 Thread David Hunt
tats_get_names, .rx_queue_intr_enable = eth_rxq_intr_enable, .rx_queue_intr_disable = eth_rxq_intr_disable, + .get_monitor_addr = vhost_get_monitor_addr, }; static int -- 2.25.1 Reviewed-by: Chenbo Xia Acked-by: David Hunt

Re: [dpdk-dev] [PATCH v7 2/5] vhost: implement rte_power_monitor API

2021-10-22 Thread David Hunt
RTE_LOG_REGISTER_SUFFIX(vhost_config_log_level, config, INFO); RTE_LOG_REGISTER_SUFFIX(vhost_data_log_level, data, WARNING); -- 2.25.1 Reviewed-by: Chenbo Xia Acked-by: David Hunt

Re: [dpdk-dev] [PATCH v7 1/5] net/virtio: implement rte_power_monitor API

2021-10-22 Thread David Hunt
pmc->opaque[CLB_MSK_IDX] = vq->vq_nentries - 1; + pmc->opaque[CLB_MATCH_IDX] = 0; + pmc->size = sizeof(vq->vq_split.ring.used->idx); + } + pmc->fn = virtio_monitor_callback; + + return 0; +} + static int virtio_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on) { LGTM. Acked-by: David Hunt

Re: [dpdk-dev] [PATCH v8 5/5] lib/distributor: use wait event scheme

2021-11-01 Thread David Hunt
be fixed in merge time. Acked-by: Jerin Jacob Acked-by David Hunt --- lib/distributor/rte_distributor_single.c | 10 -- 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/lib/distributor/rte_distributor_single.c b/lib/distributor/rte_distributor_single.c index

Re: [dpdk-dev] [PATCH v5 2/2] eal: add additional info if core mask too long

2021-11-03 Thread David Hunt
Hi David, On 2/11/2021 5:45 PM, David Marchand wrote: On Thu, Sep 23, 2021 at 1:03 PM David Hunt wrote: If the user requests to use an lcore above 128 using -c, the eal will exit with "EAL: invalid coremask syntax" and very little else useful information. This patch adds

Re: [dpdk-dev] [PATCH v5 2/2] eal: add additional info if core mask too long

2021-11-03 Thread David Hunt
On 3/11/2021 10:27 AM, David Hunt wrote: Hi David, On 2/11/2021 5:45 PM, David Marchand wrote: On Thu, Sep 23, 2021 at 1:03 PM David Hunt wrote: If the user requests to use an lcore above 128 using -c, the eal will exit with "EAL: invalid coremask syntax" and very little e

[dpdk-dev] [PATCH v6 1/2] eal: add additional info if core list too long

2021-11-03 Thread David Hunt
AX_LCORE (128) EAL: to use high physical core ids , please use --lcores to map them to lcore ids below RTE_MAX_LCORE, EAL: e.g. --lcores 0@12,1@13,2@14,3@15,4@16,5@132,6@133 Signed-off-by: David Hunt Acked-by: Bruce Richardson --- changes in v6 * none changes in v5 * removed un-neede

[dpdk-dev] [PATCH v6 2/2] eal: add additional info if core mask too long

2021-11-03 Thread David Hunt
RE (128) EAL: lcore 129 >= RTE_MAX_LCORE (128) EAL: to use high physical core ids , please use --lcores to map them to lcore ids below RTE_MAX_LCORE, EAL: e.g. --lcores 0@128,1@129 Signed-off-by: David Hunt Acked-by: Bruce Richardson --- changes in v6 * Fixed typo (gto -> got). * Removed dead cod

[dpdk-dev] [PATCH v1 4/6] lib/power: reduce memory footprint of cppc lib

2021-09-09 Thread David Hunt
nging max_lcores default from 128 to 512. Signed-off-by: David Hunt --- lib/power/power_cppc_cpufreq.c | 111 +++-- 1 file changed, 93 insertions(+), 18 deletions(-) diff --git a/lib/power/power_cppc_cpufreq.c b/lib/power/power_cppc_cpufreq.c index 6afd310e4e..952daf312e 1

[dpdk-dev] [PATCH v1 5/6] lib/power: reduce memory footprint of channels

2021-09-09 Thread David Hunt
27;re changing max_lcores default from 128 to 512. Signed-off-by: David Hunt --- lib/power/power_kvm_vm.c | 36 +++- 1 file changed, 31 insertions(+), 5 deletions(-) diff --git a/lib/power/power_kvm_vm.c b/lib/power/power_kvm_vm.c index ab7d4b8cee..c60e7acf16 100644 ---

[dpdk-dev] [PATCH v1 6/6] lib/power: switch empty poll to max cores config

2021-09-09 Thread David Hunt
empty poll algorithm uses NUM_NODES as 256, but should really use RTE_MAX_LCORE, which is configurable. Signed-off-by: David Hunt --- lib/power/rte_power_empty_poll.c | 12 ++-- lib/power/rte_power_empty_poll.h | 4 +--- 2 files changed, 7 insertions(+), 9 deletions(-) diff --git a

[dpdk-dev] [PATCH v1] usertools/telemetry: add non-interactive mode

2021-09-09 Thread David Hunt
Add non-interactive mode to dpdk-telemetry.py so that a query string can be supplied on the command line, and script dumps out data and exits. Handing for calling from scripts. Signed-off-by: David Hunt --- usertools/dpdk-telemetry.py | 22 ++ 1 file changed, 14 insertions

Re: [dpdk-dev] [PATCH v1 1/6] build: increase default of max lcores to 512

2021-09-14 Thread David Hunt
+0100, David Hunt wrote: Modern processors are coming with an ever increasing number of cores, and 128 does not seem like a sensible max limit any more, especially when you consider multi-socket systems with Hyper-Threading enabled. This patch increases max_lcores default from 128 to 512. Signed

Re: [dpdk-dev] [PATCH v1 1/6] build: increase default of max lcores to 512

2021-09-14 Thread David Hunt
On 14/9/2021 11:00 AM, David Marchand wrote: On Tue, Sep 14, 2021 at 11:34 AM David Hunt wrote: On 10/9/2021 9:24 AM, Thomas Monjalon wrote: 10/09/2021 10:06, David Marchand: On Fri, Sep 10, 2021 at 9:54 AM Bruce Richardson wrote: On Fri, Sep 10, 2021 at 08:51:04AM +0200, David Marchand

Re: [dpdk-dev] [PATCH v1] usertools/telemetry: add non-interactive mode

2021-09-15 Thread David Hunt
at 11:43:25AM +0100, Bruce Richardson wrote: On Thu, Sep 09, 2021 at 04:56:25PM +0100, David Hunt wrote: Add non-interactive mode to dpdk-telemetry.py so that a query string can be supplied on the command line, and script dumps out data and exits. Handing for calling from scripts. Signed-off-by

[dpdk-dev] [PATCH v2] eal: add additional info if lcore exceeds max cores

2021-09-15 Thread David Hunt
-14,130,132" is used, we see the following additional output on the command line: EAL: Error = One of the 5 cores provided exceeds RTE_MAX_LCORE (128) EAL: Please use --lcores instead, e.g. --lcores 0@12,1@13,2@14,3@130,4@132 Signed-off-by: David Hunt --- changes in v2 * Rather than increa

Re: [dpdk-dev] [PATCH v1 1/6] build: increase default of max lcores to 512

2021-09-15 Thread David Hunt
On 14/9/2021 12:29 PM, David Marchand wrote: On Tue, Sep 14, 2021 at 1:07 PM David Hunt wrote: “ERROR: logical core 212 is above the maximum lcore number permitted. Please use the --lcores option to map lcores onto physical cores, e.g. --lcores="(0-3)@(212-215).” If you could dir

Re: [dpdk-dev] [PATCH v2] eal: add additional info if lcore exceeds max cores

2021-09-20 Thread David Hunt
Hi David, On 16/9/2021 1:34 PM, David Marchand wrote: On Wed, Sep 15, 2021 at 2:11 PM David Hunt wrote: If the user requests to use an lcore above 128 using -l or -c, the eal will exit with "EAL: invalid core list syntax" and very little other useful information. This patch adds

[dpdk-dev] [PATCH v3 1/2] eal: add additional info if core list too long

2021-09-21 Thread David Hunt
uot; is used, we see the following additional output on the command line: EAL: Error = One of the 7 cores provided exceeds RTE_MAX_LCORE (128) EAL: Please use --lcores instead, e.g. --lcores 0@12,1@13,2@14,3@15,4@16,5@130,6@132 Signed-off-by: David Hunt --- changes in v2 * Rather than in

[dpdk-dev] [PATCH v3 2/2] eal: add additional info if core mask too long

2021-09-21 Thread David Hunt
le, if "-c 0xf" is used, we see the following additional output on the command line: EAL: Error = One of the 4 cores provided exceeds RTE_MAX_LCORE (128) EAL: Please use --lcores instead, e.g. --lcores 0@128,1@129,2@130,3@131 Signed-off-by: David Hunt --- changes in v3 * added t

Re: [dpdk-dev] [PATCH v3 1/2] eal: add additional info if core list too long

2021-09-21 Thread David Hunt
On 21/9/2021 12:57 PM, Bruce Richardson wrote: On Tue, Sep 21, 2021 at 12:50:14PM +0100, David Hunt wrote: If the user requests to use an lcore above 128 using -l, the eal will exit with "EAL: invalid core list syntax" and very little else useful information. THis patch adds

Re: [dpdk-dev] [PATCH v3 1/2] eal: add additional info if core list too long

2021-09-21 Thread David Hunt
On 21/9/2021 1:04 PM, David Hunt wrote: On 21/9/2021 12:57 PM, Bruce Richardson wrote: On Tue, Sep 21, 2021 at 12:50:14PM +0100, David Hunt wrote: If the user requests to use an lcore above 128 using -l, the eal will exit with "EAL: invalid core list syntax" and very little e

Re: [dpdk-dev] [PATCH v3 1/2] eal: add additional info if core list too long

2021-09-21 Thread David Hunt
On 21/9/2021 2:51 PM, David Marchand wrote: On Tue, Sep 21, 2021 at 1:50 PM David Hunt wrote: static int eal_parse_coremask(const char *coremask, int *cores) { @@ -839,54 +880,89 @@ eal_parse_service_corelist(const char *corelist) static int eal_parse_corelist(const char *corelist

[dpdk-dev] [PATCH v4 2/2] eal: add additional info if core mask too long

2021-09-22 Thread David Hunt
RE (128) EAL: lcore 129 >= RTE_MAX_LCORE (128) EAL: to use high physical core ids , please use --lcores to map them to lcore ids below RTE_MAX_LCORE, EAL: e.g. --lcores 0@128,1@129 Signed-off-by: David Hunt Acked-by: Bruce Richardson --- changes in v3 * added this patch to the set. Addresses the chan

[dpdk-dev] [PATCH v4 1/2] eal: add additional info if core list too long

2021-09-22 Thread David Hunt
AX_LCORE (128) EAL: to use high physical core ids , please use --lcores to map them to lcore ids below RTE_MAX_LCORE, EAL: e.g. --lcores 0@12,1@13,2@14,3@15,4@16,5@132,6@133 Signed-off-by: David Hunt Acked-by: Bruce Richardson --- changes in v2 * Rather than increasing the default max lcor

Re: [dpdk-dev] [PATCH v4 1/2] eal: add additional info if core list too long

2021-09-23 Thread David Hunt
On 23/9/2021 9:11 AM, David Marchand wrote: On Wed, Sep 22, 2021 at 2:29 PM David Hunt wrote: If the user requests to use an lcore above 128 using -l, the eal will exit with "EAL: invalid core list syntax" and very little else useful information. This patch adds some extra i

Re: [dpdk-dev] [PATCH v4 2/2] eal: add additional info if core mask too long

2021-09-23 Thread David Hunt
On 23/9/2021 9:12 AM, David Marchand wrote: On Wed, Sep 22, 2021 at 2:29 PM David Hunt wrote: int i, j, idx; int val; char c; + int lcores[RTE_MAX_LCORE]; + char *coremask_copy = NULL; Contrary to patch 1, coremask_copy is used. But, coremask is const

[dpdk-dev] [PATCH v5 1/2] eal: add additional info if core list too long

2021-09-23 Thread David Hunt
AX_LCORE (128) EAL: to use high physical core ids , please use --lcores to map them to lcore ids below RTE_MAX_LCORE, EAL: e.g. --lcores 0@12,1@13,2@14,3@15,4@16,5@132,6@133 Signed-off-by: David Hunt Acked-by: Bruce Richardson --- changes in v2 * Rather than increasing the default max lcor

[dpdk-dev] [PATCH v5 2/2] eal: add additional info if core mask too long

2021-09-23 Thread David Hunt
RE (128) EAL: lcore 129 >= RTE_MAX_LCORE (128) EAL: to use high physical core ids , please use --lcores to map them to lcore ids below RTE_MAX_LCORE, EAL: e.g. --lcores 0@128,1@129 Signed-off-by: David Hunt Acked-by: Bruce Richardson --- changes in v3 * added this patch to the set. Addresses the chan

Re: [dpdk-dev] [PATCH v6 2/2] power: refactor pstate and acpi code

2021-07-08 Thread David Hunt
On 8/7/2021 1:49 PM, David Marchand wrote: On Wed, Jun 23, 2021 at 2:04 PM David Hunt wrote: From: Anatoly Burakov Currently, ACPI and PSTATE modes have lots of code duplication, confusing logic, and a bunch of other issues that can, and have, led to various bugs and resource leaks. This

[dpdk-dev] [PATCH v7 2/2] power: refactor pstate and acpi code

2021-07-08 Thread David Hunt
-off-by: Anatoly Burakov Signed-off-by: David Hunt --- changes in v5 * fixed bugs raised by Richael Zhuang in review - open file rw+, etc. * removed FOPS* and FOPEN* macros, which contained control statements. * fixed some checkpatch warnings. changes in v6 * fixed check of fputs return, negative

[dpdk-dev] [PATCH v7 1/2] power: don't use rte prefix in internal code

2021-07-08 Thread David Hunt
From: Anatoly Burakov Currently, ACPI code uses rte_power_info as the struct name, which gives the appearance that this is an externally visible API. Fix to use internal namespace. Signed-off-by: Anatoly Burakov Acked-by: David Hunt --- lib/power/power_acpi_cpufreq.c | 34

Re: [dpdk-dev] [PATCH v7 1/2] power: add support for cppc cpufreq

2021-07-09 Thread David Hunt
On 9/7/2021 4:34 AM, Richael Zhuang wrote: Currently in DPDK only acpi_cpufreq and pstate_cpufreq drivers are supported, which are both not available on arm64 platforms. Add support for cppc_cpufreq driver which works on most arm64 platforms. Signed-off-by: Richael Zhuang --- --snip-- Hi

Re: [dpdk-dev] [PATCH v1 1/1] power: fix potential null dereferences

2021-07-09 Thread David Hunt
On 9/7/2021 4:09 PM, David Marchand wrote: On Fri, Jul 9, 2021 at 5:02 PM Anatoly Burakov wrote: Currently, the error paths can lead to attempts at dereferencing NULL pointers. Add the check to avoid attempts at dereferencing NULL pointers. Coverity issue: 371895 This patch also fixes C

Re: [dpdk-dev] [PATCH v1 1/1] test/power: check cpuinfo cur freq before scaling cur freq

2021-07-14 Thread David Hunt
On 14/7/2021 9:44 AM, Richael Zhuang wrote: For acpi_cpufreq and cppc_cpufreq, both cpuinfo_cur_freq and scaling_cur_freq exist. For pstate, only scaling_cur_freq exists. And value in scaling_cur_freq and cpuinfo_cur_freq may not be the same. For acpi_cpufreq and cppc_cpufreq, we should check c

Re: [dpdk-dev] [PATCH v1 1/1] test/power: check cpuinfo cur freq before scaling cur freq

2021-07-14 Thread David Hunt
On 14/7/2021 10:23 AM, Richael Zhuang wrote: -Original Message- From: David Hunt Sent: Wednesday, July 14, 2021 5:15 PM To: Richael Zhuang ; dev@dpdk.org Cc: zhiminx.hu...@intel.com; sta...@dpdk.org Subject: Re: [PATCH v1 1/1] test/power: check cpuinfo cur freq before scaling cur

Re: [dpdk-dev] [PATCH v2 1/1] test/power: fix CPU frequency check

2021-07-14 Thread David Hunt
then freq_conv=80 Looks good now. I ran the power_cpufreq_autotest test on both the acpi-cpufreq and pstate drivers, and both passed. Acked-by: David Hunt

[dpdk-dev] [PATCH v1] lib/distributor: fix unaligned 128-bit write

2021-07-16 Thread David Hunt
("distributor: add new burst-capable library") Cc: sta...@dpdk.org Signed-off-by: David Hunt --- lib/distributor/rte_distributor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/distributor/rte_distributor.c b/lib/distributor/rte_distributor.c index 07e385a259..c210cf8

Re: [dpdk-dev] [PATCH v1 1/1] power: fix multi-queue scale mode for pmd mgmt

2021-07-21 Thread David Hunt
a core, now with this patch, succeeds. Tested-by: David Hunt

Re: [dpdk-dev] [PATCH v3 1/1] power: check freq count before filling the freqs array

2021-07-23 Thread David Hunt
| 5 + lib/power/power_pstate_cpufreq.c | 5 + 2 files changed, 10 insertions(+) ---snip--- LGTM to fix the coverity issue. Acked-by: David Hunt

Re: [PATCH v1] examples/l3fwd-power: add wakeup log

2021-11-16 Thread David Hunt
Hi Li, On 16/11/2021 1:00 PM, Miao Li wrote: This patch adds a log in main telemetry loop to show the thread is waked up and begins to send and receive packets. Signed-off-by: Miao Li --- examples/l3fwd-power/main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/examples/l3fwd-power

Re: [PATCH v2] examples/l3fwd-power: add wakeup log

2021-11-17 Thread David Hunt
nb_rx == 0)) continue; Acked-by: David Hunt

Re: [dpdk-dev] [PATCH v1 1/6] build: increase default of max lcores to 512

2021-11-17 Thread David Hunt
suggested. @David Hunt, do you have idea about the memory cost of increasing from 128 to 512? This seems to be the primary objection. -Morten Hi Morten, I seem to recall that a simple increase from 128 to 512 cores would result in an increased static memory footprint of 2.5MBs per application, but

[PATCH] examples/power: revert "add wakeup log"

2021-11-23 Thread David Hunt
: 931e3a994597 ("examples/l3fwd-power: add wakeup log") Signed-off-by: David Hunt --- examples/l3fwd-power/main.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c index 5c5825166d..b8b3be2b8a 100644 --- a/examples/l3fwd-power/ma

[PATCH] doc/power: add info on scale mode reaction time

2021-11-24 Thread David Hunt
When using PMD Power Management, scale mode reacts slower than monitor mode and pause mode. Add note in user guide to this effect. Signed-off-by: David Hunt --- doc/guides/prog_guide/power_man.rst | 4 +++- doc/guides/sample_app_ug/l3_forward_power_man.rst | 5 +++-- 2 files

Re: [dpdk-dev] [PATCH v3 5/6] power: add new header file to export list

2021-01-20 Thread David Hunt
On 20/1/2021 2:28 PM, Burakov, Anatoly wrote: On 20-Jan-21 1:55 PM, David Hunt wrote: From: Bruce Richardson Adjust meson.build so that 'ninja install' copies the new header file into the installation directory. Fixes: 210c383e247b ("power: packet format for vm power man

Re: [dpdk-dev] [PATCH v3 3/6] power: rename public structs

2021-01-20 Thread David Hunt
On 20/1/2021 2:27 PM, Burakov, Anatoly wrote: On 20-Jan-21 1:55 PM, David Hunt wrote: From: Bruce Richardson rename the public structs to have an rte_power_ prefix. Fixes: 210c383e247b ("power: packet format for vm power management") Fixes: cd0d5547e873 ("power: vm communi

Re: [dpdk-dev] [PATCH v3 2/6] power: make channel msg functions public

2021-01-20 Thread David Hunt
On 20/1/2021 2:26 PM, Burakov, Anatoly wrote: On 20-Jan-21 1:55 PM, David Hunt wrote: From: Bruce Richardson Move the 2 public functions into rte_power_guest_channel.h Fixes: 210c383e247b ("power: packet format for vm power management") Fixes: cd0d5547e873 ("power: v

Re: [dpdk-dev] [PATCH v3 1/6] power: create guest channel public header file

2021-01-20 Thread David Hunt
On 20/1/2021 3:09 PM, Burakov, Anatoly wrote: On 20-Jan-21 1:55 PM, David Hunt wrote: From: Bruce Richardson In preparation for making the header file public, we first rename channel_commands.h as rte_power_guest_channel.h. Fixes: 210c383e247b ("power: packet format for vm power manag

Re: [dpdk-dev] [PATCH v3 5/6] power: add new header file to export list

2021-01-20 Thread David Hunt
On 20/1/2021 3:18 PM, Burakov, Anatoly wrote: On 20-Jan-21 3:08 PM, Bruce Richardson wrote: On Wed, Jan 20, 2021 at 02:28:59PM +, Burakov, Anatoly wrote: On 20-Jan-21 1:55 PM, David Hunt wrote: From: Bruce Richardson Adjust meson.build so that 'ninja install' copies the

[dpdk-dev] [PATCH v4 0/6] power: fix make build for power apps

2021-01-21 Thread David Hunt
The guest channel message definitions and functions in guest_channel.h are needed by applications and need to be made public. This worked pre-20.11, but now with all the meson/ninja changes, making these apps externally no longer works. To fix, we need to move the header file with the API definiti

  1   2   3   4   5   6   7   8   9   >