All of lore.kernel.org
 help / color / mirror / Atom feed
From: Potnuri Bharat Teja <bharat@chelsio.com>
To: Jason Gunthorpe <jgg@ziepe.ca>
Cc: "nab@linux-iscsi.org" <nab@linux-iscsi.org>,
	"sagi@grimberg.me" <sagi@grimberg.me>,
	"target-devel@vger.kernel.org" <target-devel@vger.kernel.org>,
	"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>
Subject: Re: [RFC] iser-target: avoid reinitializing rdma contexts for isert commands
Date: Thu, 14 Dec 2017 00:18:49 +0530	[thread overview]
Message-ID: <20171213184848.GA9181@chelsio.com> (raw)
In-Reply-To: <20171213175104.GA14143@ziepe.ca>

On Wednesday, December 12/13/17, 2017 at 23:21:04 +0530, Jason Gunthorpe wrote:
> On Tue, Nov 28, 2017 at 11:58:07PM +0530, Bharat Potnuri wrote:
> > isert commands that failed during isert_rdma_rw_ctx_post() are queued to
> > Queue-Full(QF) queue and are scheduled to be reposted during queue-full
> > queue processing. During this reposting, the rdma contexts are initialised
> > again in isert_rdma_rw_ctx_post(), which is leaking significant memory.
> > 
> > unreferenced object 0xffff8830201d9640 (size 64):
> >   comm "kworker/0:2", pid 195, jiffies 4295374851 (age 4528.436s)
> >   hex dump (first 32 bytes):
> >     00 60 8b cb 2e 00 00 00 00 10 00 00 00 00 00 00  .`..............
> >     00 90 e3 cb 2e 00 00 00 00 10 00 00 00 00 00 00  ................
> >   backtrace:
> >     [<ffffffff8170711e>] kmemleak_alloc+0x4e/0xb0
> >     [<ffffffff811f8ba5>] __kmalloc+0x125/0x2b0
> >     [<ffffffffa046b24f>] rdma_rw_ctx_init+0x15f/0x6f0 [ib_core]
> >     [<ffffffffa07ab644>] isert_rdma_rw_ctx_post+0xc4/0x3c0 [ib_isert]
> >     [<ffffffffa07ad972>] isert_put_datain+0x112/0x1c0 [ib_isert]
> >     [<ffffffffa07dddce>] lio_queue_data_in+0x2e/0x30 [iscsi_target_mod]
> >     [<ffffffffa076c322>] target_qf_do_work+0x2b2/0x4b0 [target_core_mod]
> >     [<ffffffff81080c3b>] process_one_work+0x1db/0x5d0
> >     [<ffffffff8108107d>] worker_thread+0x4d/0x3e0
> >     [<ffffffff81088667>] kthread+0x117/0x150
> >     [<ffffffff81713fa7>] ret_from_fork+0x27/0x40
> >     [<ffffffffffffffff>] 0xffffffffffffffff
> > 
> > Here is patch to use the older rdma contexts while reposting
> > the isert commands intead of reinitialising them.
> > 
> > Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
> > Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
> >  drivers/infiniband/ulp/isert/ib_isert.c | 7 +++++++
> >  drivers/infiniband/ulp/isert/ib_isert.h | 1 +
> >  2 files changed, 8 insertions(+)
> >
> 
> So this RFC got Reviewed-by Sagi, is it to be applied now or something
> else??
> 
> If yes, what tree does it want to go through? I see Nicholas and Doug
> have both been historically taking isert patches.

Hi Jason,
Yes, this needs to be applied now, to the target-pending tree.
This fixes the "Queue-full handling" change that is already part of stable trees:
https://www.spinics.net/lists/target-devel/msg13574.html
This also needs to be tagged to stable trees.
As the Queue-full handling changes are already in linux, I think this can go 
through rdma tree aswell.

Thanks,
Bharat
> 
> Thanks,
> Jason
> --
> To unsubscribe from this list: send the line "unsubscribe target-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

WARNING: multiple messages have this Message-ID (diff)
From: Potnuri Bharat Teja <bharat@chelsio.com>
To: Jason Gunthorpe <jgg@ziepe.ca>
Cc: "nab@linux-iscsi.org" <nab@linux-iscsi.org>,
	"sagi@grimberg.me" <sagi@grimberg.me>,
	"target-devel@vger.kernel.org" <target-devel@vger.kernel.org>,
	"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>
Subject: Re: [RFC] iser-target: avoid reinitializing rdma contexts for isert commands
Date: Wed, 13 Dec 2017 18:49:02 +0000	[thread overview]
Message-ID: <20171213184848.GA9181@chelsio.com> (raw)
In-Reply-To: <20171213175104.GA14143@ziepe.ca>

On Wednesday, December 12/13/17, 2017 at 23:21:04 +0530, Jason Gunthorpe wrote:
> On Tue, Nov 28, 2017 at 11:58:07PM +0530, Bharat Potnuri wrote:
> > isert commands that failed during isert_rdma_rw_ctx_post() are queued to
> > Queue-Full(QF) queue and are scheduled to be reposted during queue-full
> > queue processing. During this reposting, the rdma contexts are initialised
> > again in isert_rdma_rw_ctx_post(), which is leaking significant memory.
> > 
> > unreferenced object 0xffff8830201d9640 (size 64):
> >   comm "kworker/0:2", pid 195, jiffies 4295374851 (age 4528.436s)
> >   hex dump (first 32 bytes):
> >     00 60 8b cb 2e 00 00 00 00 10 00 00 00 00 00 00  .`..............
> >     00 90 e3 cb 2e 00 00 00 00 10 00 00 00 00 00 00  ................
> >   backtrace:
> >     [<ffffffff8170711e>] kmemleak_alloc+0x4e/0xb0
> >     [<ffffffff811f8ba5>] __kmalloc+0x125/0x2b0
> >     [<ffffffffa046b24f>] rdma_rw_ctx_init+0x15f/0x6f0 [ib_core]
> >     [<ffffffffa07ab644>] isert_rdma_rw_ctx_post+0xc4/0x3c0 [ib_isert]
> >     [<ffffffffa07ad972>] isert_put_datain+0x112/0x1c0 [ib_isert]
> >     [<ffffffffa07dddce>] lio_queue_data_in+0x2e/0x30 [iscsi_target_mod]
> >     [<ffffffffa076c322>] target_qf_do_work+0x2b2/0x4b0 [target_core_mod]
> >     [<ffffffff81080c3b>] process_one_work+0x1db/0x5d0
> >     [<ffffffff8108107d>] worker_thread+0x4d/0x3e0
> >     [<ffffffff81088667>] kthread+0x117/0x150
> >     [<ffffffff81713fa7>] ret_from_fork+0x27/0x40
> >     [<ffffffffffffffff>] 0xffffffffffffffff
> > 
> > Here is patch to use the older rdma contexts while reposting
> > the isert commands intead of reinitialising them.
> > 
> > Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
> > Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
> >  drivers/infiniband/ulp/isert/ib_isert.c | 7 +++++++
> >  drivers/infiniband/ulp/isert/ib_isert.h | 1 +
> >  2 files changed, 8 insertions(+)
> >
> 
> So this RFC got Reviewed-by Sagi, is it to be applied now or something
> else??
> 
> If yes, what tree does it want to go through? I see Nicholas and Doug
> have both been historically taking isert patches.

Hi Jason,
Yes, this needs to be applied now, to the target-pending tree.
This fixes the "Queue-full handling" change that is already part of stable trees:
https://www.spinics.net/lists/target-devel/msg13574.html
This also needs to be tagged to stable trees.
As the Queue-full handling changes are already in linux, I think this can go 
through rdma tree aswell.

Thanks,
Bharat
> 
> Thanks,
> Jason
> --
> To unsubscribe from this list: send the line "unsubscribe target-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

  reply	other threads:[~2017-12-13 18:48 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-28 18:28 [PATCH RFC] iser-target: avoid reinitializing rdma contexts for isert commands Potnuri Bharat Teja
2017-11-28 18:40 ` Potnuri Bharat Teja
2017-11-29 22:50 ` Sagi Grimberg
2017-11-29 22:50   ` Sagi Grimberg
2017-11-30 10:34   ` Potnuri Bharat Teja
2017-11-30 10:46     ` Potnuri Bharat Teja
2017-12-04 18:31     ` Sagi Grimberg
2017-12-04 18:31       ` Sagi Grimberg
2017-12-13 17:51 ` [RFC] " Jason Gunthorpe
2017-12-13 17:51   ` Jason Gunthorpe
2017-12-13 18:48   ` Potnuri Bharat Teja [this message]
2017-12-13 18:49     ` Potnuri Bharat Teja
2017-12-18 23:14 ` Jason Gunthorpe
2017-12-18 23:14   ` Jason Gunthorpe
     [not found]   ` <20171218231439.GA31621-uk2M96/98Pc@public.gmane.org>
2018-01-13  6:20     ` Nicholas A. Bellinger
2018-01-13  6:20       ` Nicholas A. Bellinger
     [not found]       ` <1515824443.24576.108.camel-XoQW25Eq2zs8TOCF0fvnoXxStJ4P+DSV@public.gmane.org>
2018-01-13 18:04         ` Jason Gunthorpe
2018-01-13 18:04           ` Jason Gunthorpe
2018-01-14  9:26           ` Sagi Grimberg
2018-01-14  9:26             ` Sagi Grimberg
     [not found]             ` <143bd378-193e-0bbd-1ee3-25299af61aa8-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2018-01-14 18:23               ` Jason Gunthorpe
2018-01-14 18:23                 ` Jason Gunthorpe
     [not found]                 ` <20180114182344.GB9088-uk2M96/98Pc@public.gmane.org>
2018-01-15  4:39                   ` Nicholas A. Bellinger
2018-01-15  4:39                     ` Nicholas A. Bellinger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20171213184848.GA9181@chelsio.com \
    --to=bharat@chelsio.com \
    --cc=jgg@ziepe.ca \
    --cc=linux-rdma@vger.kernel.org \
    --cc=nab@linux-iscsi.org \
    --cc=sagi@grimberg.me \
    --cc=target-devel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.