On 12.08.2019 11:59, Holger Hoffstätte wrote: > On 8/9/19 10:52 AM, Holger Hoffstätte wrote: >> On 8/9/19 10:25 AM, Eric Dumazet wrote: >> (snip) >>>> >>>> So that didn't take long - got another timeout this morning during some >>>> random light usage, despite sg/tso being disabled this time. >>>> Again the only common element is the xmit_more patch. :( >>>> Not sure whether you want to revert this right away or wait for 5.4-rc1 >>>> feedback. Maybe this too is chipset-specific? >>>> >>>>> Thanks a lot for the analysis and testing. Then I'll submit the disabling >>>>> of SG on RTL8168evl (on your behalf), independent of whether it fixes >>>>> the timeout issue. >>>> >>>> Got it, thanks! >>>> >>>> Holger >>> >>> I would try this fix maybe ? >>> >>> diff --git a/drivers/net/ethernet/realtek/r8169_main.c >>> b/drivers/net/ethernet/realtek/r8169_main.c >>> index >>> b2a275d8504cf099cff738f2f7554efa9658fe32..e77628813daba493ad50dab9ac1e3703e38b560c >>> 100644 >>> --- a/drivers/net/ethernet/realtek/r8169_main.c >>> +++ b/drivers/net/ethernet/realtek/r8169_main.c >>> @@ -5691,6 +5691,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff >>> *skb, >>> */ >>> smp_wmb(); >>> netif_stop_queue(dev); >>> + door_bell = true; >>> } >>> >>> if (door_bell) >>> >> >> Thanks Eric, I'll give that a try and see how it fares over the next few >> days. >> It suspiciously looks like it could help.. > > Good news everyone! > > After three days non-stop action between two machines and hundreds of GBs > pushed back and forth: not a single timeout or hiccup. Nice! \o/ > Eric, please send this as a proper patch for -next. Feel free to add my > Tested-by. > Thanks for the feedback! I can submit the fix with Eric's "Suggested-by".
> cheers > Holger > Heiner
