1 / 6

Netgames Plugin Issues

Netgames Plugin Issues. John DeHart. 512W. 512W. 512W. 512W. 512W. ONL NP Router. Large SRAM Ring. xScale. Assoc. Data ZBT-SRAM. xScale (3 Rings?). Small SRAM Ring. Scratch Ring. SRAM. LD. TCAM. SRAM. Errors. Except. NN Ring. NN. 64KW. Parse, Lookup, Copy (3 MEs).

crwys
Download Presentation

Netgames Plugin Issues

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Netgames Plugin Issues John DeHart

  2. 512W 512W 512W 512W 512W ONL NP Router Large SRAM Ring xScale Assoc. Data ZBT-SRAM xScale (3 Rings?) Small SRAM Ring Scratch Ring SRAM LD TCAM SRAM Errors Except NN Ring NN 64KW Parse, Lookup, Copy (3 MEs) Rx (2 ME) Mux (1 ME) QM (1 ME) HdrFmt (1 ME) Tx (1 ME) NN Mostly Unchanged xScale 64KW 64KW 64KW 64KW 64KW 64KW Plugin to XScale Ctrl,Update & RLI Msgs 512W 512W 512W 512W 512W New NN NN NN NN Plugin3 Plugin4 Plugin0 Plugin1 Plugin2 SRAM Needs A Lot Of Mod. Rx Mux HF Copy Plugins Tx Needs Some Mod. Tx, QM Parse Plugin XScale Stats (1 ME) FreeList Mgr (1 ME) SRAM

  3. Netgames Plugin Issues SCR 256W SCR 256W SCR 256W SRAM 64KW Parse, Lookup, Copy (3 MEs) Rx (2 ME) Mux (1 ME) QM (1 ME) HdrFmt (1 ME) Tx (1 ME) NN SRAM 64KW SRAM 64KW NN NN NN NN Plugin3 Plugin4 Plugin0 Plugin1 Plugin2 SRAM SCR 512W SCR 256W Rx Mux HF Copy Plugins Tx Tx, QM Parse Plugin XScale Stats (1 ME) FreeList Mgr (1 ME) SRAM

  4. Netgames Plugin Issues • Just Under Overload • Rcv Rate: 2.025 Mpkts/sec • Measured by MUX counting packets it reads from the Rx input Ring • Rcv Drop Rate: 0 pkts/sec • Counted by Rx when it finds a full ring to MUX • Total Pkt Rate arriving at Rx: 2.025 + 0 = 2.025 Mpkts/sec • Plugin to Mux Rate: 3.235 Mpkts/sec • Counted by Plugin when it is putting a pkt into the Plugin to Mux Ring • PLC to Plugin Drop Rate: 0 pkts/sec • Counted by PLC when it finds a full Plugin Ring • QM Drop Rate: 2.3 Mpkts/sec • Queues default to 32KB • Tx Rate: 1 Mpkts/sec (0.500 Mpkts/sec per port, 840 Mb/s per port) • Tx Drop Rate: 0 pkts/sec • Just into Overload: • Rcv Rate: 1.07 Mpkts/sec • Measured by MUX counting packets it reads from the Rx input Ring • Rcv Drop Rate: 0.985 Mpkts/sec • Counted by Rx when it finds a full ring to MUX • Total Pkt Rate arriving at Rx: 1.07 + 0.985 = 2.055 Mpkts/sec • Plugin to Mux Rate: 0.535 Mpkts/sec • Counted by Plugin when it is putting a pkt into the Plugin to Mux Ring • PLC to Plugin Drop Rate: 0.733 Mpkts/sec • Counted by PLC when it finds a full Plugin Ring • QM Drop Rate: 0 pkts/sec • Queues default to 32KB • Tx Rate: 0.535 Mpkts/sec • Tx Drop Rate: 0.020 Mpkts/sec

  5. Netgames Plugin Issues • Notes: • Using 5 ME’s for plugin • Each Plugin ME is reading from Plugin Input Ring 0 • Making copies going to just ports 0 and 1 (fanout = 2) for this experiment • Packet from port x will not have a copy going back to port x so we are multiplying Rx packets by 8/5. • Each Port is using just 1 Queue • Ethernet Frame Size: 248 B • UDP Payload 182 B • Application Payload 150 B • Application Header 32 B • UDP/IP Header: 28 B • Ethernet Header: 14 B • Ethernet CRC: 4 B • Ethernet IFS: 12 B • Ethernet Preamble: 8B • Link Rate is set to 846 Mb/s (measured on IP Pkt size) • 846 Mb/s * (248 B / 210 B) = 999.085 Mb/s • With Workbench attached in Overload condition Mux to PLC Ring seems to fill up first • This tends to agree with our results from the ONL SIGCOM Paper in which PLC was the bottleneck under heavy load • Once we are in overload and rates have “collapsed” I have to drop the input rate below the Rx rate that MUX reports for things to recover. But it does recover. • Occasionally there is another type of failure mode, PLC starts dropping lots of packets because the Xscale ring is full. PLC should NOT be sending anything to the Xscale once the test is running for a while. • This failure mode is not one we can recover from. We have to reboot. • Good News: • Plugin and rest of system keeps up with an input rate that is enough to fill output links • Also true for fanout of 4. • Question(s): • Why does the rate processed drop so drastically in overload?

More Related