Add JSON string handling to vm_power_manager for JSON strings received
through the fifo. The format of the JSON strings are detailed in the
next patch, the vm_power_manager user guide documentation updates.
This patch introduces a new dependency on Jansson, a C library for
encoding, decoding and manipulating JSON data. To compile the sample app
you now need to have installed libjansson4 and libjansson-dev (these may
be named slightly differently depending on your Operating System)
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Now that we're handling host policies, containers and virtual machines,
we'll rename MAX_VMS to MAX_CLIENTS, and increase from 4 to 64
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
This patch adds a fifo channel to the vm_power_manager app through which
we can send commands and polices. Intended for sending JSON strings.
The fifo is at /tmp/powermonitor/fifo
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
The changes here are minimal, as the guest app functionality is not
changing at all, but there is a new element in the channel_packet
struct that needs to have a default set (channel_packet->core_type).
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
This patch does a couple of things:
* Adds a new message type for removing policies (PKT_POLICY_REMOVE)
Used when we want to remove a previously created policy.
* Adds a core_type bool to the channel packet struct to specify whether
the type of core we want to control is virtual or physical.
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Previously the vm_power_manager app required to have some vms defined, so
the call to get_all_vm() always set the noVms variable. Now we're accepting
policies from the host OS (without any VMs defined), so it is now valid to
have zero VMs. This patch initialises the relevant variables to zero just
in case the call to get_all_vms() does not find any, so could return with
the variables uninitialised.
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Allow vm_power_manager to run without requiring qemu to be present
on the machine. This will be required for instances where the JSON
interface is used for commands and polices, without any VMs present.
A use case for this is a container enviromnent.
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Add the support for new traffic pattern aware power control
power management API.
Example:
./l3fwd-power -l xxx -n 4 -w 0000:xx:00.0 -w 0000:xx:00.1 -- -p 0x3
-P --config="(0,0,xx),(1,0,xx)" --empty-poll="0,0,0" -l 14 -m 9 -h 1
Please Reference l3fwd-power document for full parameter usage
The option "l", "m", "h" are used to set the power index for
LOW, MED, HIGH power state. Only is useful after enable empty-poll
--empty-poll="training_flag, med_threshold, high_threshold"
The option training_flag is used to enable/disable training mode.
The option med_threshold is used to indicate the empty poll threshold
of modest state which is customized by user.
The option high_threshold is used to indicate the empty poll threshold
of busy state which is customized by user.
Above three option default value is all 0.
Once enable empty-poll. System will apply the default parameter if no
other command line options are provided.
If training mode is enabled, the user should ensure that no traffic
is allowed to pass through the system. When training phase complete,
the application transfer to normal operation
System will start running with the modest power mode.
If the traffic goes above 70%, then system will move to High power state.
If the traffic drops below 30%, the system will fallback to the modest
power state.
Example code use master thread to monitoring worker thread busyness.
The default timer resolution is 10ms.
Signed-off-by: Liang Ma <liang.j.ma@intel.com>
Reviewed-by: Lei Yao <lei.a.yao@intel.com>
Acked-by: David Hunt <david.hunt@intel.com>
1. Abstract
For packet processing workloads such as DPDK polling is continuous.
This means CPU cores always show 100% busy independent of how much work
those cores are doing. It is critical to accurately determine how busy
a core is hugely important for the following reasons:
* No indication of overload conditions.
* User does not know how much real load is on a system, resulting
in wasted energy as no power management is utilized.
Compared to the original l3fwd-power design, instead of going to sleep
after detecting an empty poll, the new mechanism just lowers the core
frequency. As a result, the application does not stop polling the device,
which leads to improved handling of bursts of traffic.
When the system become busy, the empty poll mechanism can also increase the
core frequency (including turbo) to do best effort for intensive traffic.
This gives us more flexible and balanced traffic awareness over the
standard l3fwd-power application.
2. Proposed solution
The proposed solution focuses on how many times empty polls are executed.
The less the number of empty polls, means current core is busy with
processing workload, therefore, the higher frequency is needed. The high
empty poll number indicates the current core not doing any real work
therefore, we can lower the frequency to safe power.
In the current implementation, each core has 1 empty-poll counter which
assume 1 core is dedicated to 1 queue. This will need to be expanded in the
future to support multiple queues per core.
2.1 Power state definition:
LOW: Not currently used, reserved for future use.
MED: the frequency is used to process modest traffic workload.
HIGH: the frequency is used to process busy traffic workload.
2.2 There are two phases to establish the power management system:
a.Initialization/Training phase. The training phase is necessary
in order to figure out the system polling baseline numbers from
idle to busy. The highest poll count will be during idle, where
all polls are empty. These poll counts will be different between
systems due to the many possible processor micro-arch, cache
and device configurations, hence the training phase.
In the training phase, traffic is blocked so the training
algorithm can average the empty-poll numbers for the LOW, MED and
HIGH power states in order to create a baseline.
The core's counter are collected every 10ms, and the Training
phase will take 2 seconds.
Training is disabled as default configuration. The default
parameter is applied. Sample App still can trigger training
if that's needed. Once the training phase has been executed once on
a system, the application can then be started with the relevant
thresholds provided on the command line, allowing the application
to start passing start traffic immediately
b.Normal phase. Traffic starts immediately based on the default
thresholds, or based on the user supplied thresholds via the
command line parameters. The run-time poll counts are compared with
the baseline and the decision will be taken to move to MED power
state or HIGH power state. The counters are calculated every 10ms.
3. Proposed API
1. rte_power_empty_poll_stat_init(struct ep_params **eptr,
uint8_t *freq_tlb, struct ep_policy *policy);
which is used to initialize the power management system.
2. rte_power_empty_poll_stat_free(void);
which is used to free the resource hold by power management system.
3. rte_power_empty_poll_stat_update(unsigned int lcore_id);
which is used to update specific core empty poll counter, not thread safe
4. rte_power_poll_stat_update(unsigned int lcore_id, uint8_t nb_pkt);
which is used to update specific core valid poll counter, not thread safe
5. rte_power_empty_poll_stat_fetch(unsigned int lcore_id);
which is used to get specific core empty poll counter.
6. rte_power_poll_stat_fetch(unsigned int lcore_id);
which is used to get specific core valid poll counter.
7. rte_empty_poll_detection(struct rte_timer *tim, void *arg);
which is used to detect empty poll state changes then take action.
Signed-off-by: Liang Ma <liang.j.ma@intel.com>
Reviewed-by: Lei Yao <lei.a.yao@intel.com>
Acked-by: David Hunt <david.hunt@intel.com>
This commit changes the hashing mechanism to "partial-key
hashing" to calculate bucket index and signature of key.
This is proposed in Bin Fan, et al's paper
"MemC3: Compact and Concurrent MemCache with Dumber Caching
and Smarter Hashing". Basically the idea is to use "xor" to
derive alternative bucket from current bucket index and
signature.
With "partial-key hashing", it reduces the bucket memory
requirement from two cache lines to one cache line, which
improves the memory efficiency and thus the lookup speed.
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
This commit changes the current rte_hash unit test to
test the extendable table feature and performance.
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
In use cases that hash table capacity needs to be guaranteed,
the extendable bucket feature can be used to contain extra
keys in linked lists when conflict happens. This is similar
concept to the extendable bucket hash table in packet
framework.
This commit adds the extendable bucket feature. User can turn
it on or off through the extra flag field during table
creation time.
Extendable bucket table composes of buckets that can be
linked list to current main table. When extendable bucket
is enabled, the hash table load can always achieve 100%.
In other words, the table can always accommodate the same
number of keys as the specified table size. This provides
100% table capacity guarantee.
Although keys ending up in the ext buckets may have longer
look up time, they should be rare due to the cuckoo
algorithm.
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
In rte_hash_iterate, the reader lock did not protect the
while loop which checks empty entry. This created a race
condition that the entry may become empty when enters
the lock, then a wrong key data value would be read out.
This commit reads out the position in the while condition,
which makes sure that the position will not be changed
to empty before entering the lock.
Fixes: f2e3001b53ec ("hash: support read/write concurrency")
Cc: stable@dpdk.org
Reported-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Since the depth-first search of cuckoo path is removed, we do not
need the macro anymore which specifies the depth of the cuckoo
search.
Fixes: f2e3001b53ec ("hash: support read/write concurrency")
Cc: stable@dpdk.org
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
The test_hash_readwrite.c was not in the meson.build file. This
commit adds the missing test into the file.
Fixes: 0eb3726ebcf1 ("test/hash: add test for read/write concurrency")
Cc: stable@dpdk.org
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
the multi-reader and multi-writer rte_hash unit test does not
work correctly with non-consecutive core ids. This commit
fixes the issue.
Fixes: 0eb3726ebcf1 ("test/hash: add test for read/write concurrency")
Cc: stable@dpdk.org
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Tested-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Edit the printf information when error happens to be more
accurate and informative.
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
The bucket size was changed from 4 to 8 but the corresponding
perf test was not changed accordingly.
In the test, the bucket size and number of buckets are used
to map to the underneath rte_hash structure. They are used
to test performance of two conditions: keys in primary
buckets only and keys in both primary and secondary buckets.
Although there is no functional issue with bucket size set
to 4, it mismatches the underneath rte_hash structure,
which may affect code readability and future extension.
Fixes: 58017c98ed53 ("hash: add vectorized comparison")
Cc: stable@dpdk.org
Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
The 'TX' in OCTEON TX would cause a warning.
Adding an exception for that.
OCTEON TX is a registered product under Cavium
Signed-off-by: Anoob Joseph <anoob.joseph@caviumnetworks.com>
Really minor issue:
There were extra spaces making the alignment wrong.
Fixes: e95faac15110 ("crypto/mrvl: rename PMD to mvsam")
Fixes: 4ccc8d770d3b ("net/mvneta: add PMD skeleton")
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
The option GENERATE_DEPRECATEDLIST will create a page
"Deprecated List" in "Related Pages" menu.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
The internal shared libraries shouldn't be part of release notes shared
library version section.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Latency calculation logic is not correct for the case where
packets gets dropped before TX. As for the dropped packets,
the timestamp is not cleared, and such packets still gets
counted for latency calculation in next runs, that will result
in inaccurate latency measurement.
So fix this issue as below,
Before setting timestamp in mbuf, check mbuf don't have
any prior valid time stamp flag set and after marking
the timestamp, set mbuf flags to indicate timestamp is
valid.
Before calculating timestamp check mbuf flags are set to
indicate timestamp is valid.
With the above logic it is guaranteed that correct timestamps
have been used.
Fixes: 5cd3cac9ed ("latency: added new library for latency stats")
Cc: stable@dpdk.org
Reported-by: Bao-Long Tran <longtb5@viettel.com.vn>
Signed-off-by: Reshma Pattan <reshma.pattan@intel.com>
Tested-by: Bao-Long Tran <longtb5@viettel.com.vn>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
This patch fixes an issue caught with ASAN where a vdev_scan()
to a secondary bus was failing to free some memory.
The doxygen comment in EAL is fixed at the same time.
Fixes: cdb068f031c6 ("bus/vdev: scan by multi-process channel")
Fixes: 783b6e54971d ("eal: add synchronous multi-process communication")
Cc: stable@dpdk.org
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
rte_devargs_parsef will leak memory each time it is called.
The device string must be freed.
Fixes: a23bc2c4e01b ("devargs: add non-variadic parsing function")
Cc: stable@dpdk.org
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com>
eal: add shorthand __rte_weak macro
qat: update code to use __rte_weak macro
avf: update code to use __rte_weak macro
fm10k: update code to use __rte_weak macro
i40e: update code to use __rte_weak macro
ixgbe: update code to use __rte_weak macro
mlx5: update code to use __rte_weak macro
virtio: update code to use __rte_weak macro
acl: update code to use __rte_weak macro
bpf: update code to use __rte_weak macro
Signed-off-by: Keith Wiles <keith.wiles@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The cast of hpet_msb_inc is causing a warning in some compilations.
Yet the cast is unnecessary, the function is used only one place
just use the correct signature.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
rte_init_alert already adds a newline, don't do it twice.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Shreyansh Jain <shreyansh.jain@nxp.com>
When a device is hot-unplugged, pci_remove will be invoked unexpectedly
before pci_release, it will caused kernel hung issue which will throw the
error info of "Trying to free already-free IRQ XXX". And on the other hand,
if pci_remove before pci_release, the interrupt will not got chance to be
disabled. So this patch aim to fix this issue by adding pci_release call
in pci_remove, it will gurranty that all pci clean up will be done before
pci removal.
Signed-off-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
In skeleton_rawdev unit tests, a malloc'd memory was leaking in case
the next sequential test fails. This fix moves the free of the
malloc'd memory above the failing test.
Coverity issue: 260402
Fixes: 55ca1b0f2151 ("raw/skeleton: add test cases")
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
In case the link is down during initial link state check, messages for
link state check flood the console. Reducing the log level for these.
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Presence of PA-VA Table is transparent to the drivers. Ignoring the
return values from table update call.
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
DPAAX is a library used by various NXP drivers. In case of non-NXP
environment, this start spewing message about unavailability of
necessary environment.
This patch reduces the log level for certain messages as well as
reduces overall log-level. As a library, these message are not
necessarily relevant at higher log level, either.
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Tested-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
In case the memory for nodes cannot be allocated, there is no need
to check for the length. Also, `node_count` is an unsigned value
and cannot be less than 0.
Coverity issue: 323521
Fixes: 2f3d633aa593 ("common/dpaax: add library for PA/VA translation table")
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
There is a possibility that either because of missing device tree entry
or lack of memory, the PA-VA table might not be available. But, the
table being transparent, the callers don't necessary check for its
initialization state. This is explicitly done during update and
translation call.
Fixes: 2f3d633aa593 ("common/dpaax: add library for PA/VA translation table")
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Currently not able to pass EXTRA_CFLAGS while building *.pmd.c file,
adding it.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
PDCP session configuration for lookaside protocol offload
and data path is added.
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Signed-off-by: Akhil Goyal <akhil.goyal@nxp.com>
DPAA2 SEC platform can support look aside protocol
offload for PDCP protocol.
The relevant APIs for configuring the hardware for PDCP
is added for various modes and crypto algorithms.
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Signed-off-by: Horia Geanta Neag <horia.geanta@nxp.com>
Signed-off-by: Alex Porosanu <alexandru.porosanu@nxp.com>
Signed-off-by: Akhil Goyal <akhil.goyal@nxp.com>
