[00:02:03] *** Quits: Shuhei (caf6fc61@gateway/web/freenode/ip.202.246.252.97) (Ping timeout: 252 seconds) [02:41:36] *** Quits: gila (~gila@5ED74129.cm-7-8b.dynamic.ziggo.nl) (Ping timeout: 260 seconds) [02:49:52] *** Joins: gila (~gila@5ED74129.cm-7-8b.dynamic.ziggo.nl) [06:01:43] *** Joins: vmysak (~vmysak@134.134.139.76) [09:43:49] *** Joins: travis-ci (~travis-ci@ec2-54-234-5-40.compute-1.amazonaws.com) [09:43:50] (spdk/master) nvmf/rdma: Don't release qpair resources when messages pending (Ben Walker) [09:43:50] Diff URL: https://github.com/spdk/spdk/compare/f10a91ed0df8...9b47c7e7cfb9 [09:43:50] *** Parts: travis-ci (~travis-ci@ec2-54-234-5-40.compute-1.amazonaws.com) () [10:48:19] *** Joins: bluebird (~bluebird@p5DE9547E.dip0.t-ipconnect.de) [11:23:54] *** Quits: vmysak (~vmysak@134.134.139.76) (Ping timeout: 252 seconds) [12:04:32] *** Joins: travis-ci (~travis-ci@ec2-54-80-158-82.compute-1.amazonaws.com) [12:04:33] (spdk/master) bdev/raid: Update the comment of raid_bdev_add_base_bdevs() (Shuhei Matsumoto) [12:04:33] Diff URL: https://github.com/spdk/spdk/compare/9b47c7e7cfb9...6bc4a314aeac [12:04:33] *** Parts: travis-ci (~travis-ci@ec2-54-80-158-82.compute-1.amazonaws.com) () [14:20:35] *** Joins: travis-ci (~travis-ci@ec2-54-163-191-60.compute-1.amazonaws.com) [14:20:36] (spdk/master) ioat: change return type of spdk_ioat_detach() to be void (Rami Rosen) [14:20:36] Diff URL: https://github.com/spdk/spdk/compare/55014ddf5352...412d89cd6fef [14:20:36] *** Parts: travis-ci (~travis-ci@ec2-54-163-191-60.compute-1.amazonaws.com) () [14:23:46] *** Joins: travis-ci (~travis-ci@ec2-54-198-134-35.compute-1.amazonaws.com) [14:23:47] (spdk/master) blobstore: Add support for bdev_blob_queue_io in blobstore (Piotr Pelplinski) [14:23:48] Diff URL: https://github.com/spdk/spdk/compare/412d89cd6fef...89762b29ef55 [14:23:48] *** Parts: travis-ci (~travis-ci@ec2-54-198-134-35.compute-1.amazonaws.com) () [14:37:57] *** Joins: travis-ci (~travis-ci@ec2-54-197-142-194.compute-1.amazonaws.com) [14:37:58] (spdk/master) nvmf: get qp_context only on QP related event (Maciej Szwed) [14:37:58] Diff URL: https://github.com/spdk/spdk/compare/89762b29ef55...44ab0033ba8b [14:37:58] *** Parts: travis-ci (~travis-ci@ec2-54-197-142-194.compute-1.amazonaws.com) () [14:48:15] *** Quits: lhodev (~lhodev@66-90-218-190.dyn.grandenetworks.net) (Read error: Connection reset by peer) [15:03:27] *** Joins: travis-ci (~travis-ci@ec2-54-234-5-40.compute-1.amazonaws.com) [15:03:28] (spdk/master) iscsi: Fix the bug that mutual chap is not enabled by .ini config file (Shuhei Matsumoto) [15:03:28] Diff URL: https://github.com/spdk/spdk/compare/44ab0033ba8b...0bb86d1cf3b7 [15:03:28] *** Parts: travis-ci (~travis-ci@ec2-54-234-5-40.compute-1.amazonaws.com) () [15:09:26] bwalker: does this assert mean anything to you? https://ci.spdk.io/spdk/builds/review/df999cfc877c3665fad0a7d57d53552b0cafa4fa.1536702036/fedora-06/build.log [15:09:32] in the shutdown test [15:10:33] this is the primary failure we're seeing now [15:10:42] it doesn't always hit that assert - sometimes ASAN booms it [15:10:48] but it's the same problem - the pointer is junk [15:10:54] ah [15:12:27] the problem, as far as I can tell, is that we did an ibv_poll_cq and received work completions related to a queue pair that no longer exists [15:12:51] and it's not the case that we got a batch of completions and in the course of processing them destroyed the qpair [15:13:02] and one of the later ones in the batch crashed it - that's not what happens [15:13:32] the first completion pulled out of ibv_poll_cq blows up because it's reference (an rdma_req) is invalid [15:13:43] klateck's patches to collect nvmf trace logs will help once those are ready and merged [15:13:49] yeah [15:14:08] I've seen it happen where the wc succeeded or fail, and I've seen it where the wc is for a send or a recv [15:14:14] *** Quits: bluebird (~bluebird@p5DE9547E.dip0.t-ipconnect.de) (Quit: Leaving) [15:15:17] we need some mechanism, either from RDMA or from our own code, to wait for all completion queue entries for a given queue pair to be posted, consume them, and kill the queue pair [15:50:29] *** Joins: Shuhei (caf6fc61@gateway/web/freenode/ip.202.246.252.97) [16:19:23] *** Joins: travis-ci (~travis-ci@ec2-54-225-45-90.compute-1.amazonaws.com) [16:19:24] (spdk/master) nvmf/host: Add incapsule data support to nvmef host. (Potnuri Bharat Teja) [16:19:24] Diff URL: https://github.com/spdk/spdk/compare/cf1366ef662b...94f87a2dbb94 [16:19:24] *** Parts: travis-ci (~travis-ci@ec2-54-225-45-90.compute-1.amazonaws.com) () [16:59:30] *** Joins: travis-ci (~travis-ci@ec2-54-157-25-36.compute-1.amazonaws.com) [16:59:31] (spdk/master) nvmf: Add IP based load balancing (Avinash M N) [16:59:31] Diff URL: https://github.com/spdk/spdk/compare/94f87a2dbb94...1f3f16058139 [16:59:31] *** Parts: travis-ci (~travis-ci@ec2-54-157-25-36.compute-1.amazonaws.com) () [19:01:39] *** Quits: Shuhei (caf6fc61@gateway/web/freenode/ip.202.246.252.97) (Ping timeout: 252 seconds) [21:22:52] *** Joins: travis-ci (~travis-ci@ec2-54-226-183-222.compute-1.amazonaws.com) [21:22:53] (spdk/master) vhost: show failed taks status (Pawel Wodkowski) [21:22:53] Diff URL: https://github.com/spdk/spdk/compare/1f3f16058139...43ab58b61337 [21:22:53] *** Parts: travis-ci (~travis-ci@ec2-54-226-183-222.compute-1.amazonaws.com) () [21:35:22] *** Quits: guerby (~guerby@april/board/guerby) (Read error: Connection reset by peer) [21:37:20] *** Joins: guerby (~guerby@april/board/guerby)