Hi all, First, there are some rather trivial ones (up to [TCP]: Cleanup local variables of clean _rtx_queue)...
They're followed by my current efforts to improve SACK processing latencies with large windows, including RB-tree for fast searching, problem space split to provide tight bounds that relate to the amount of new information discovered through the received SACK block, per skb fack_count to provide access to fack_count at search provided entry point. There's still need for additional changes after these to really provide such good bounds without loop-holes but this is a big step in the right direction already. Cost to store all this, seems tremendous, however, the new structures enable also dropping of many existing caches, making the end result much nicer (these are not yet done). Potential kill list includes at least: most _hints drop, recv_sack_cache drop, highest_sack skb->seqno restore... Also the linked-list for SACKed part is probably unnecessary but having it makes things simpler, it can be killed later on rather than adding complexity to this patch. ...I would like to still take some time to make the last patch cleaner by extracting at least the DSACK separation from it. Though, the amount of necessary changes remains still relatively huge in the core patch. ...Minor FIXMEs todo, only the DSACK one is really preventive one. Comments welcome, especially about the last patch. -- i. -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
