Re: Failed sending data to the peer in 7.72.0

I've been running 7.72.0 with that patch cherry-picked for over a day and the issue has not recurred. There's definitely something spooky going on. Does extract_if_dead have any other side effects? On Wed, Sep 16, 2020 at 1:22 AM Daniel Stenberg wrote: > On Mon, 14 Sep 2020, James Brown via

Re: Failed sending data to the peer in 7.72.0

On Mon, 14 Sep 2020, James Brown via curl-library wrote: Thanks for digging deep into this issue! I went through commits on master that aren't in 7.72.0 and came across 728f8d3bd , which looks promising. It says it

Re: Failed sending data to the peer in 7.72.0

I went through commits on master that aren't in 7.72.0 and came across 728f8d3bd , which looks promising. It says it partially reverts a change from 7.65.2, which is kind of weird because this problem does *not *occur

Re: Failed sending data to the peer in 7.72.0

Unfortunately, it takes rather several hours of running to identify this failure; building a new package and bisecting is going to be quite difficult with that long of a turnaround. I however was able to get a tcpdump of one of the affected sessions. This session spans several requests to the

Re: Failed sending data to the peer in 7.72.0

On 9/11/2020 2:03 PM, James Brown via curl-library wrote: After upgrading a test cluster from 7.71.1 to 7.72.0, we're now seeing around 0.1% of POSTs from one (and only one) of our applications fail with "Failed sending data to the peer" (CURLE_SEND_ERROR) and no other error. Based on logs,

Failed sending data to the peer in 7.72.0

After upgrading a test cluster from 7.71.1 to 7.72.0, we're now seeing around 0.1% of POSTs from one (and only one) of our applications fail with "Failed sending data to the peer" (CURLE_SEND_ERROR) and no other error. Based on logs, the request actually succeeds, but libcurl is returning this