- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I've got a question about pipeline usage.
In the example PacketProcessing in chapter 11, why is forwarding the only filter that runs in parallel? Cant' the others (aside the first and the last one) run in parallel as well?
Thanks for your time!
I've got a question about pipeline usage.
In the example PacketProcessing in chapter 11, why is forwarding the only filter that runs in parallel? Cant' the others (aside the first and the last one) run in parallel as well?
Thanks for your time!
Link Copied
2 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
From a quick look, it appears that the Network Address Translator and Gateway stages could be a parallel stages too. Indeed translator::spare_port is declared as a tbb::atomic, which suggests the author was planning to turn Network Address Translator into a parallel filter. I'll check with the original author. There may be a subtle semantic issue with respect to IP address processing that I'm missing.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Agreed. The example is simplistic and somewhat limited, but the concept of concurrency here can (and should) be extended in a real router.

Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page