search.noResults

search.searching

saml.title
dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
Column: Embedded design


Aſt er launching Tracealyzer, select


“File->Open Folder” and select the “lttng-traces” directory. Tracealyzer will analyse the directory for the captured trace session and load all included fi les (an LTTng trace consists of multiple fi les). Choose the appropriate view to analyse the driver’s performance. Whilst Tracealyzer has views to provide


Figure 5: “Actor Instances” window


useful insights into the userspace-kernel interaction, my focus is on the kernel space and, thus, the “Trace View”, “Actor Instances”, “CPU Load Graph” and “Context Switch Intensity” views, which can be selected by clicking on the appropriate icons in the main Tracealyzer window. Upon opening the Trace View, there will be


a graph; see Figure 3. T e leſt most column is for “Actor


Names”, which are the userspace and kernel processes/threads executing at any given time. T e leſt most column (in grey) is the kernel “swapper”, which is the idle task in the Linux kernel. Farther on the right is a blue line, which is a kernel thread (“kworker”). As we implement the driver and monitor, we’re going to use the Trace View to verify that my kernel thread is given enough execution resources to manage the DMA transfer. Even farther right are a green line, the


lttng userspace process, and a yellow line, the rcu_sched userspace process. Right-clicking in the window, select “Zoom


Figure 6: If we select another kernel thread, we see anomalies in the graph


Out – Show Full Traces”, which will show a concise view of all the threads and processes executed during the entire duration of the capture; see Figure 4. It can be seen that the swapper occupies


the most execution resources here, which makes sense, since no substantial tasks are being done. When the driver is running and


transferring data from my device to the Phytec development board, we can see sections of the Trace View that are consumed by blue fragments. T is would indicate that my specifi c kernel thread has been given a greater chunk of the execution resources on the platform to perform the transfer. The next important view is the “Actor


Figure 7: Different actors using the CPU


Instances”, where we have selected the “Execution Time” in the drop down box at the top left; see Figure 5.


12 February 2021 www.electronicsworld.co.uk


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44