On Wed, 2014-12-03 at 14:39 +0800, Pi-Cheng Chen wrote:
On 2 December 2014 at 19:02, Ivan T. Ivanov iivanov@mm-sol.com wrote:
On Tue, 2014-12-02 at 15:21 +0800, pi-cheng.chen wrote:
Add 2 new kind of event for running a memory or a io bounded load. "mem" name for a load is memory bounded, and "iorun" name for a load is io bounded. The default file to be written to create the load is /dev/null and the device/file could be specified with "io_device" key in "global" section.
E.g. "tasks" : { "thread0" : { "sleep" : 1000, "run" : 100, "mem" : 1000, "sleep" 10000, "iorun" : 1000 } }, "global" : { "io_device" : "/dev/ttyS0" }
Wouldn't be better if we can specify size of the accessed memory region, instead of iteration count? We can use phases to create arbitrary number of iterations for memory access.
Thanks, Ivan
Hi Ivan,
I think the value of "mem" key we specify here is taken as the size of the memory to be memcpy() in the patch, not as iteration count. Did I misunderstand what you mean?
No. I have missed that count is used to specify memory chunk size, sorry.
Thank you. Ivan