I've discovered that the issue is related to the proxywrap module https://github.com/findhit/proxywrap/issues/15
El viernes, 8 de enero de 2016, 18:49:11 (UTC+1), Pedro Narciso García Revington escribió: > > I have a (connect) web application that, under certain strees, > accumulates connections in the CLOSE_WAIT state. > At some point, I need to reboot the application. > I have reproduced the behavior in my local machine by running stress tests > with wrk (https://github.com/wg/wrk). > > Everytime I run the test —no matter if the application is running in > cluster mode or not— the first connection remains in CLOSE_WAIT state > > ----- > $ ss -e | grep 3000 | grep CLOSE > tcp CLOSE-WAIT 0 0 ::ffff:127.0.0.1:3000 ::ffff: > 127.0.0.1:41818 uid:1000 ino:332823 sk:ffff8803265e5d00 --> > ----- > > I have tried to stress the application with ab or vegeta, but the issue > only arises with wrk. As I said, I'm facing this issue in production with > normal browsers when there is a peak. > I run wrk with -4 -c400 -d30s params. > > Any hint or tip? I have no idea how to debug this issue. > > Thanks, > > Pedro > -- Job board: http://jobs.nodejs.org/ New group rules: https://gist.github.com/othiym23/9886289#file-moderation-policy-md Old group rules: https://github.com/joyent/node/wiki/Mailing-List-Posting-Guidelines --- You received this message because you are subscribed to the Google Groups "nodejs" group. To unsubscribe from this group and stop receiving emails from it, send an email to nodejs+unsubscr...@googlegroups.com. To post to this group, send email to nodejs@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/nodejs/a294016c-d9c5-4dc2-a26a-dc417a83e52d%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.