RDMA/addr: create addr_wq with WQ_MEM_RECLAIM flag
A message that is not in the archive (sent off-list or not yet received): 5f5a1e4e90f3625cea57ffa79fc0e5bcb7efe09d.1548963371.git.swise@opengridcomputing.com
A message that is not in the archive (sent off-list or not yet received): [email protected]
A message that is not in the archive (sent off-list or not yet received): [email protected]
A message that is not in the archive (sent off-list or not yet received): [email protected]
PATCH 1/1 RDMA/addr: create addr_wq with WQ_MEM_RECLAIM flag
Quoted 27 lines · Steve Wise
Quoted 25 lines · Steve Wise
Quoted 13 lines · Jason Gunthorpe
Quoted 12 lines · Steve Wise
While running NVMe/oF wire unplug tests, we hit this warning in kernel/workqueue.c:check_flush_dependency():
WARN_ONCE(worker && ((
worker->current_pwq->wq->flags&(WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func);Which I think means we're flushing a workq that doesn't have
WQ_MEM_RECLAIMset, from workqueue context that does have it set.Quoted 7 lines
Quoted 4 lines
Looking at
rdma_addr_cancel()which is doing the flushing, it flushes theaddr_wqwhich doesn't haveMEM_RECLAIMset. Yetrdma_addr_cancel()is being called by the nvme host connection timeout/reconnect workqueue thread that does haveWQ_MEM_RECLAIMset.Since we haven't learned anything more, I think you should look to remove either the
WQ_MEM_RECLAIMor therdma_addr_cancel()from the nvme side.The nvme code is just calling
rdma_destroy_id(), which in turn callsrdma_addr_cancel(),? so I'll have to removeWQ_MEM_RECLAIMfrom the workqueue.
Quoted 8 lines
Quoted 1 line
I'll post this patch then.
What a mess.? If I remove RECLAIM for
nvme_wq, then I'll regress this change, I think:
c669ccdc50c2("nvme: queue ns scanning and async request fromnvme_wq")
Hi All,
I see this issue with some basic tests. Looks like the discussion ended here. Please suggest where this ideally needs to be fixed so that I can try fixing it.
Thanks,
Bharat