Add a new option --enable_pci_id to Prometheus plugin, which will map
the GPU index to the PCI Device Identifier.
Change-Id: I38a2a7e4841975da095391002397d4515ffb8e0d
grpc v1.44.0 needs to link to library absl_synchronization. The
CMakeLists.txt is changed to link to that library if available.
Change-Id: I92f7247473a70e7a83416b9744e788e45d104565
Include the upgrade operation check in the prerm and postun scripts
in package.
Signed-off-by: Saravanan Solaiyappan <saravanan.solaiyappan@amd.com>
Change-Id: Ide29b84e59eea6154276f790e353a25506dd3bdb
When compile grpc on SLES, the libprotobuf is created under lib64
folder, install it to lib folder as well.
Change-Id: I9ccf2133c3b1b71e623d9009a86cf580a19e76cf
A new diagnostic module librdc_rocr.so is created. The
module uses Rocr to test the memory allocation, memory access
and compute queue ready status.
Change-Id: I9098f4fc3209bf381b7cb3658a4e94c2e22f2fe9
Needed to work around a debian packaging bug if debug information is
being produced in a separate package.
Signed-off-by: Icarus Sparry <icarus.sparry@amd.com>
Change-Id: Ieab3cc3515eeeb952159acea3dc1effd14613eeb
The RDC override the LD_LIBRARY_PATH to force to use the current grpc
path. The change will also add original LD_LIBRARY_PATH to it.
Change-Id: I48da84c3135c6ede129c3cb9148dbb1896b652c3
Provides a RdcSmiDiagnostic module, which will call rocm_smi_lib.
It will support following diagnostics: Get GPU Topology, Check GPU
parameters and check processes running on the GPUs.
The grpc client and server side diagnostics function is added.
The diag module is added to the rdci.
Change-Id: I10a0cf3c20556a61373ab686f82cae75acaa40dd
The rdcd uses another thread to listen the GPU events. That thread
runs in a tight loop which consume 100% CPU.
The fix will add a sleep to yield CPU.
Bug: SWDEV-291576
Change-Id: I7996720aab4a80346d79b1c73ee532d2abcd93cc
RDC can optimize by bulk fetching multiple metrics using a single
rocm_smi call. However, currently this is not completely supported in
all ASIC generations. By default disable this for now.
Set environment variable RDC_BULK_FETCH_ENABLED=TRUE to enable
RDC bulk fetch.
BUG: SWDEV-289316
Change-Id: Ibb55514f198356dccf5f47bb0fd2d53c17acb251
The API interface defines how the caller will use the API. An
example also shows how the API can be used.
It also defines the RdcDiagnostic module which can load the
library dynamically and then dispatch diagnostic test to run.
Change-Id: I1e041aab86f7e19338860f5ba65262977f4ea9cb
RDC is trying to bulk fetch power usage from gpu_metrics. If the
gpu_metrics is 0, it will fallback to rsmi_dev_power_ave_get().
Change-Id: I57d165d6af0c91b39798c89eef317d4e5df2d0f6
Create a folder for prebuild raslib which contains the RAS binary
and configure files. The CMakeLists.txt is changed to include
those files.
Change-Id: I530198cff5686a19e58096c87457ab8b7c52d5f3
When above option is used, the plugin returns errors:
result = rdc.rdc_group_gpu_add(rdc_handle, gpu_group_id, gpu)
ctypes.ArgumentError: argument 3: <type 'exceptions.TypeError'>: wrong type
The rdc_prometheus.py is changed to convert string to integer.
The RdcUtil.py is also changed to raise Exception properly.
Change-Id: I9535091ff1fc8882cccd32e5f2810da5241768c3
Write access is required for some RSMI services. This change
temporarily permits write access so configuration can be done,
and then turns it off.
To help with this, the ScopedCapability struct is introduced to
provide scope limited access, helping to ensure a process is not
left with extra capability, should an exception occur.
Change-Id: I4978a1a688db935b8bfc27b3b537a0dd07959d3f
RDC_EVNT_XGMI_[2-5]_THRPUT were missing from RDC. Additionally,
these were handled as "pseudo" events, but this is not
necessary.
Change-Id: I3478365ac0d78f60a7b63235bea484f3edb8bd16
The rdc may install third party library in its local folder. We
need to disable the Autoprov to prevent the rpm add provides
for them.
Change-Id: I18d008c2ca2ecb6bba64467d78b1f8c3a6585aea
Install the grpc lib to rdc/grpc/lib and add miss libraries.
Add “--no-as-needed” and all extra grpc libraries in rdci/rdcd as
RUNPATH will only search direct dependencies.
Change-Id: I596acb2eb3a7228d703e79db64699bc20d0e7c09
The RDC provides a wrapper to bulk fetch metrics from rocm_smi_lib.
If the video card does not support bulk fetch or the metrics cannot be
bulk fetched, it will fallback to fetch them one by one.
Change-Id: I8852ba1ed67e0fabc805c93b1080f74c233516e1
The name of rocm-smi-lib64 has been changed to rocm-smi-lib
Hence updating the requisite name here for resolving installation dependency
Depends-On: Ib37d29aedc20b610619f6921f4147b41c0eaf134
Change-Id: I4efd778b72d43ad8f0842410a94ac1e3d3b9192a
Installing files to standard path across each version and using
ldconfig has issues with side-by-side install.
Usage of RUNPATH/RPATH for ROCm to ensure all ROCm libraries are
picked without the need for ldconfig.
For RDC server to be picked up by systemctl, service config file
shall be a symlink from /lib/systemctl/system/rdc.service to
corresponding RDC file path in a given version of ROCm
For side-by-side install packages of RDC post install scripts
will be removed. Hence Use will have to set the symlink explicitly
for now.
Change-Id: I916da7cf132f0f9c667e2470fac2b0875e3db9d0
The new raslib fields are added to RDC for dmon.
* The rdc_field.data, rdc.h and rdc_bootstrap.py are changed
for new fields.
* The RDC_FI_ECC_CORRECT_TOTAL and RDC_FI_ECC_UNCORRECT_TOTAL are
removed from RdcSmiLib.cc, and will be gotten from raslib.
Change-Id: I4ee016e3d52e9d38b54406ca129da511f741c6d6
Also:
* print header line every 50 line on output
* print events that are being listened for with header
* cpplint clean-up
Change-Id: Ic049eb79156a9528b556e56f0fa43e1344f898cc
When RDC are only used as the libraries, the user can choose not to build
the rdci and rdcd, which will remove the dependencies to the gRPC and protoc.
The -DBUILD_STANDALONE=off should be pass to the cmake.
* Change README.md for the instructions.
* Move the python_binding installation from client/CMakeLists.txt to CMakeLists.txt
so that the RDC library only build will also install the folder.
* Change CMakeLists.txt and rdc_libs/CMakeLists.txt to build with gRPC only if
the BUILD_STANDALONE is enabled.
Change-Id: If9cfe9fc298a83636d85fe352a311fe2fe041661
Two files are added to the python_binding folder:
* The rdc_collectd.py is a collectd plugin to store the RDC
metrics to the collectd round robin database.
* The rdc_collectd.conf is a configure file which can control
which fields to collect, how frequently the fields can be collected
and run the plugin in embedded mode.
Change-Id: Ief44d004376ca8a82ed0d8ad36805243acb47080
Having grpc installed outside of ROCm dir is problematic
for multiple, simultaneous ROCm installations.
Change-Id: I5ad458ad01a76786339607d708b48534f15b137b
A new Grafana dashboard file rdc_grafana_dashboard_example.json
has been added to the folder python_binding. User can import
this dashboard to monitor multiple compute nodes.
To display the host name only in the dashboard, the
rdc_prometheus_example.yml is also changed to create a new label
short_instance which will not have the port number.
Change-Id: I9ab91838006d59c8dcb5fea01decb8c799484e1d
The framework now supports watch() and unwatch(), which can be used
by the telemetry library to init events or pre-fetch fields when recording
starts.
* A new header file RdcTelemetryLibInterface.h is defined for library to
include it.
* The RdcWatchTable will not talk to RdcMetricFetcher directly anymore.
It will call the framework watch/unwatch to dispatch it to the libraries.
* Make the python binding consistent with the current code.
Change-Id: Ie5731d920ed5928f901369d60c23bd450807a562
Ranjith Ramakrishnan
Bill(Shuzhou) Liu
Saravanan Solaiyappan
Icarus Sparry
Chris Freehill
Ashutosh Mishra
Freddy Paul
Cole Nelson