On Fri, Feb 11, 2022 at 11:52:41PM -0800, Abhinav Kumar wrote: > Hi Greg > > On 2/11/2022 11:04 PM, Greg KH wrote: > > On Fri, Feb 11, 2022 at 10:59:39AM -0800, Abhinav Kumar wrote: > > > Hi Greg > > > > > > Thanks for the response. > > > > > > On 2/11/2022 3:09 AM, Greg KH wrote: > > > > On Tue, Feb 08, 2022 at 11:44:32AM -0800, Abhinav Kumar wrote: > > > > > There are cases where depending on the size of the devcoredump and the speed > > > > > at which the usermode reads the dump, it can take longer than the current 5 mins > > > > > timeout. > > > > > > > > > > This can lead to incomplete dumps as the device is deleted once the timeout expires. > > > > > > > > > > One example is below where it took 6 mins for the devcoredump to be completely read. > > > > > > > > > > 04:22:24.668 23916 23994 I HWDeviceDRM::DumpDebugData: Opening /sys/class/devcoredump/devcd6/data > > > > > 04:28:35.377 23916 23994 W HWDeviceDRM::DumpDebugData: Freeing devcoredump node > > > > > > > > What makes this so slow? Reading from the kernel shouldn't be the > > > > limit, is it where the data is being sent to? > > > > > > We are still checking this. We are seeing better read times when we bump up > > > the thread priority of the thread which was reading this. > > > > Where is the thread sending the data to? > > The thread is writing the data to a file in local storage. From our > profiling, the read is the one taking the time not the write. The read is coming directly from memory, there should not be any slowdown at all here. How can that be the delay? Have a trace somewhere? thanks, greg k-h
