DPDK Interfaces Configuration [Документация VAS Experts]
Документация VAS Experts Документация VAS Experts-mobile
in

Settings

  • Show page
  • Old revisions
  • Export to PDF
  • Fold/unfold all
  • Backlinks
  • Show page
  • Old revisions
  • Export to PDF
  • Fold/unfold all
  • Backlinks

    • Differences

    This shows you the differences between two versions of the page.

    Link to this comparison view

    Both sides previous revisionPrevious revision
    Next revision    		Previous revision
    en:dpi:dpi_components:platform:dpi_config [2024/09/26 15:29] – external edit 127.0.0.1en:dpi:dpi_components:platform:dpi_config [2025/07/24 11:30] (current) – [dpdk_engine=6: RSS dispatchers per bridge] elena.krasnobryzh
    Line 180: Line 180:
       * cluster with bridge 41-00.0 ←→ 41-00.1   * cluster with bridge 41-00.0 ←→ 41-00.1
       * cluster with bridges  01-00.0 ←→ 01-00.1 and 05-00.0 ←→ 05-00.1   * cluster with bridges  01-00.0 ←→ 01-00.1 and 05-00.0 ←→ 05-00.1
    -Clusters are a kind of a legacy of the Stingray SG pf_ring-version: in pf_ring, cluster is the basic concept of "one dispatcher thread + RSS handler threads" and is almost the only way to scale. The disadvantage of the cluster approach is that the clusters are physically isolated from each other: it is impossible to forward a packet from the X-interface of cluster #1 to the Y-interface of cluster #2. This can be a significant obstacle in the SKAT L2 BRAS mode.+Clusters are a kind of a legacy of the Stingray SG pf_ring-version: in pf_ring, cluster is the basic concept of "one dispatcher thread + RSS handler threads" and is almost the only way to scale. The disadvantage of the cluster approach is that the clusters are physically isolated from each other: it is impossible to forward a packet from the X-interface of cluster #1 to the Y-interface of cluster #2. This can be a significant obstacle in the SSG L2 BRAS mode.
      
     In DPDK, clusters are also isolated from each other, but unlike pf_ring, here a cluster is a more logical concept inherited from pf_ring. DPDK is much more flexible than pf_ring and allows you to build complex multi-bridge configurations with many dispatchers without using clusters. In fact, the only "pro" argument for clustering in the Stingray-DPDK version is the case when you have two independent networks A and B connected to the Stingray SG, which should not interact with each other in any way. In DPDK, clusters are also isolated from each other, but unlike pf_ring, here a cluster is a more logical concept inherited from pf_ring. DPDK is much more flexible than pf_ring and allows you to build complex multi-bridge configurations with many dispatchers without using clusters. In fact, the only "pro" argument for clustering in the Stingray-DPDK version is the case when you have two independent networks A and B connected to the Stingray SG, which should not interact with each other in any way.
    Line 357: Line 357:
       * RX queue count = 1   * RX queue count = 1
       * TX queue count = The processing threads write directly each to its own TX queue card.   * TX queue count = The processing threads write directly each to its own TX queue card.
     +
     +==== dpdk_engine=6: RSS dispatchers per bridge ====
     +<note important>This ''dpdk_engine'' is available starting from version 14.0!</note>
     +This engine is intended for configurations with multiple bridges (dev1:dev2:dev3:...) for 100G+ cards.
     +
     +<code>
     +in_dev=41-00.0:02-00.0:c3-00.0:c1-00.0:04-00.0:04-00.1
     +out_dev=41-00.1:41-00.1:02-00.1:02-00.1:c3-00.1:c3-00.1
     +
     +dpdk_engine=6
     +dpdk_rss=4
     +num_threads=64
     +
     +dpdk_mempool_size=256000
     +mem_tracking_flow=40000000
     +mem_tracking_ip=40000000
     +dpdk_emit_mempool_size=256000
     +mem_ssl_parsers=18000000
     +mem_http_parsers=512000
     +</code>
     +This example creates 24 dispatcher threads — 4 dispatchers per bridge.
     +
     +<note tip>Total number of dispatchers = ''dpdk_rss'' * number of bridges. Starting with version 14.0, the maximum number of dispatchers is 32.</note>
     +
     +On-stick devices are supported.\\
     +SSG configures the cards as follows:
     +  * RX queue count = ''dpdk_rss''
     +  * TX queue count = number of processing threads. Processing threads write directly to their own TX queue on the card.
     +