1. 18 6月, 2012 1 次提交
  2. 08 6月, 2012 1 次提交
  3. 19 5月, 2012 1 次提交
  4. 09 5月, 2012 1 次提交
  5. 26 4月, 2012 4 次提交
  6. 24 4月, 2012 1 次提交
  7. 20 3月, 2012 2 次提交
  8. 24 2月, 2012 1 次提交
  9. 13 2月, 2012 1 次提交
    • S
      be2net: event queue re-design · 10ef9ab4
      Sathya Perla 提交于
      v2: Fixed up the bad typecasting pointed out by David...
      
      In the current design 8 TXQs are serviced by 1 EQ, while each RSS queue
      is serviced by a separate EQ. This is being changed as follows:
      
      - Upto 8 EQs will be used (based on the availabilty of msix vectors).
      Each EQ will handle 1 RSS and 1 TX ring. The default non-RSS RX queue and
      MCC queue are handled by the last EQ.
      
      - On cards which provide support, upto 8 RSS rings will be used, instead
      of the current limit of 4.
      
      The new design allows spreading the TX multi-queue completion processing
      across multiple CPUs unlike the previous design.
      Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
      Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      10ef9ab4
  10. 05 2月, 2012 2 次提交
  11. 31 12月, 2011 1 次提交
  12. 27 11月, 2011 2 次提交
  13. 17 11月, 2011 3 次提交
  14. 13 11月, 2011 3 次提交
  15. 04 11月, 2011 3 次提交
  16. 28 10月, 2011 2 次提交
  17. 25 10月, 2011 1 次提交
  18. 04 10月, 2011 3 次提交
  19. 28 9月, 2011 2 次提交
  20. 25 8月, 2011 1 次提交
  21. 19 8月, 2011 1 次提交
  22. 11 8月, 2011 1 次提交
  23. 03 8月, 2011 2 次提交