Messages in this thread | | | Date | Wed, 02 Sep 2015 18:18:06 +0300 | From | Boaz Harrosh <> | Subject | Re: [PATCH] dax, pmem: add support for msync |
| |
On 09/02/2015 05:23 PM, Dave Hansen wrote: <> > I'd be curious what the cost is in practice. Do you have any actual > numbers of the cost of doing it this way? > > Even if the instruction is a "noop", I'd really expect the overhead to > really add up for a tens-of-gigabytes mapping, no matter how much the > CPU optimizes it.
What tens-of-gigabytes mapping? I have yet to encounter an application that does that. Our tests show that usually the mmaps are small.
I can send you a micro benchmark results of an mmap vs direct-io random write. Our code will jump over holes in the file BTW, but I'll ask to also run it with falloc that will make all blocks allocated.
Give me a few days to collect this.
I guess one optimization we should do is jump over holes and zero-extents. This will save the case of a mostly sparse very big file.
Thanks Boaz
| |