Mainstream NUMA and the TCP/IP stack: Final Thoughts(blogs.msdn.com)

submitted by wisemxwisemx(8074) 3 years, 8 months ago

Note that a final version of a white paper tying this series of five blog entries together (and a Powerpoint presentation on the subject) are attached. For many years, the effort to improve network performance on Windows and other platforms focused on reducing the host processing requirements associated with the need to service frequent interrupts from the NIC. In the many-core era where the clock speeds of processors are constrained by power considerations, this strategy is inadequate to the growing host processing requirements that accompany high-speed networking. It is necessary to augment technologies like interrupt moderation and TCP Offload Engine that improve the efficiency of network I/O with an approach that allows TCP/IP Receive packets to be processed in parallel across multiple CPUs. Together, MSI-X and RSS are technologies that enable host processing of TCP/IP packets to scale in the many-core world, albeit not without some compromises with the prevailing model of networking using isolated, layered components.

add a comment |category: |Views: 1

tags: another

new Add a live kick counter to your blog >> liveImage

You can even customize the image by choosing your own colors, and then clicking the button below to update the preview and the html code:

  • "Kick It" text
  • "Kick It" background
  • kick count text
  • kick count background
  • border

Simply copy and paste this HTML into your blog post.


Users who kicked this story:
Comments:

No comments so far

information Login or create an account to comment on this story