[Bloat] Progress with latency-under-load tool

Dave Täht d at taht.net
Sun Mar 20 18:47:16 EDT 2011


d at taht.net (Dave Täht) writes:

> The interesting outlier thus far is 8... I'm tempted to stop the test
> now and recompile for testing 3 u/l 3 d/l first....

Scenario 12: 2 uploads, 2 downloads... 4725 KiB/s up, 3645 KiB/s down, 0.81 Hz smoothness

... Still running tests ...

> Txqueuelen = 1000 = ~1.5Mbyte (and I'm struggling with using consistent
> decimal or base 2 units this month) Mibibyte?
>
> Normal dma tx ring size ranges from 64 to 512, can be seen sometimes
> with ethtool -g device

With wireless you also have TX_RETRIES = 13 for these (ath9) devices
drivers under test. (Reduced to 4 in the less bloated version I can't
test right now)

You also have contention from other devices, and the occasional complete
retrain from a base figure of 1Mbit/sec up, while devices struggle to
regain sync.

There are (presumably helpful) effects of packet aggregation.

You also have modulo issues against the size of the tx queues, an
interaction with the network flow scheduler (what triggers filling the
tx queue?), SACK/DSACK and lost ACK retransmits, and probably more
issues than I've been able to come up with offhand.

-- 
Dave Taht
http://nex-6.taht.net



More information about the Bloat-devel mailing list