> -Original Message-
> From: Chuck Lever [mailto:chuck.le...@oracle.com]
> Sent: Thursday, July 03, 2014 1:30 AM
> To: Devesh Sharma
> Cc: Steve Wise; linux-rdma@vger.kernel.org; Linux NFS Mailing List
> Subject: Re: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disconnect
>
On 7/2/2014 6:46 PM, sean.he...@intel.com wrote:
> rclose will call shutdown only if we're connected. However, if the
> keepalive failed, the socket will be in an error state. So,
> no call to rshutdown, which will leave the freed rsocket on
> the keepalive thread's list.
>
> The fix is to to
On Jul 2, 2014, at 10:45 AM, Chuck Lever wrote:
> Hi Jack-
>
>
> On Jul 2, 2014, at 3:19 AM, Jack Morgenstein wrote:
>
>> On Tue, 1 Jul 2014 18:17:27 -0400
>> Chuck Lever wrote:
>>
>>> Hi-
>>>
>>> This happens during boot, and means that lockdep and lock_stat are
>>> completely disabled d
From: Sean Hefty
The following crash was reported by Hal Rosenstock,
, with keepalive enabled. The crash
occurs in the keepalive thread attempting to send a
keepalive message.
report:
Program received signal SIGSEGV, Segmentation fault.
[Switching to Thread 0x7fffecf08700 (LWP 6013)]
rs_post_wr
> > > > diff --git a/src/acm.c b/src/acm.c index 8f147ef..fae9d0b 100644
> > > > --- a/src/acm.c
> > > > +++ b/src/acm.c
> > > > @@ -193,7 +193,7 @@ static int log_level = 0; static char
> > > > lock_file[128] = "/var/run/ibacm.pid"; static short server_port =
> > > > 6125; static int support_ip
> > > diff --git a/src/acm.c b/src/acm.c
> > > index 8f147ef..fae9d0b 100644
> > > --- a/src/acm.c
> > > +++ b/src/acm.c
> > > @@ -193,7 +193,7 @@ static int log_level = 0; static char
> > > lock_file[128] = "/var/run/ibacm.pid"; static short server_port =
> > > 6125; static int support_ips_in_a
> >
> > diff --git a/src/acm.c b/src/acm.c
> > index 8f147ef..fae9d0b 100644
> > --- a/src/acm.c
> > +++ b/src/acm.c
> > @@ -193,7 +193,7 @@ static int log_level = 0; static char
> > lock_file[128] = "/var/run/ibacm.pid"; static short server_port =
> > 6125; static int support_ips_in_addr_cfg =
>
> diff --git a/src/acm.c b/src/acm.c
> index 8f147ef..fae9d0b 100644
> --- a/src/acm.c
> +++ b/src/acm.c
> @@ -193,7 +193,7 @@ static int log_level = 0; static char lock_file[128] =
> "/var/run/ibacm.pid"; static short server_port = 6125; static int
> support_ips_in_addr_cfg = 0; -static char
On Jul 2, 2014, at 3:48 PM, Devesh Sharma wrote:
>
>
>> -Original Message-
>> From: Steve Wise [mailto:sw...@opengridcomputing.com]
>> Sent: Thursday, July 03, 2014 1:16 AM
>> To: 'Chuck Lever'; Devesh Sharma
>> Cc: linux-rdma@vger.kernel.org; 'Linux NFS Mailing List'
>> Subject: RE: [
> -Original Message-
> From: Steve Wise [mailto:sw...@opengridcomputing.com]
> Sent: Thursday, July 03, 2014 1:27 AM
> To: Devesh Sharma; 'Chuck Lever'; linux-rdma@vger.kernel.org; linux-
> n...@vger.kernel.org
> Subject: RE: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disco
> -Original Message-
> From: Steve Wise [mailto:sw...@opengridcomputing.com]
> Sent: Thursday, July 03, 2014 1:21 AM
> To: Devesh Sharma; 'Chuck Lever'; linux-rdma@vger.kernel.org; linux-
> n...@vger.kernel.org
> Subject: RE: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disco
> -Original Message-
> From: Devesh Sharma [mailto:devesh.sha...@emulex.com]
> Sent: Wednesday, July 02, 2014 2:54 PM
> To: Steve Wise; 'Chuck Lever'; linux-rdma@vger.kernel.org;
> linux-...@vger.kernel.org
> Subject: RE: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disconn
> -Original Message-
> From: Steve Wise [mailto:sw...@opengridcomputing.com]
> Sent: Thursday, July 03, 2014 1:21 AM
> To: Devesh Sharma; 'Chuck Lever'; linux-rdma@vger.kernel.org; linux-
> n...@vger.kernel.org
> Subject: RE: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disco
> -Original Message-
> From: Devesh Sharma [mailto:devesh.sha...@emulex.com]
> Sent: Wednesday, July 02, 2014 2:43 PM
> To: Steve Wise; Chuck Lever; linux-rdma@vger.kernel.org;
> linux-...@vger.kernel.org
> Subject: RE: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disconnec
> -Original Message-
> From: Steve Wise [mailto:sw...@opengridcomputing.com]
> Sent: Thursday, July 03, 2014 1:16 AM
> To: 'Chuck Lever'; Devesh Sharma
> Cc: linux-rdma@vger.kernel.org; 'Linux NFS Mailing List'
> Subject: RE: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disco
> -Original Message-
> From: Chuck Lever [mailto:chuck.le...@oracle.com]
> Sent: Wednesday, July 02, 2014 2:40 PM
> To: Steve Wise; Devesh Sharma
> Cc: linux-rdma@vger.kernel.org; Linux NFS Mailing List
> Subject: Re: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disconnect
>
> -Original Message-
> From: Steve Wise [mailto:sw...@opengridcomputing.com]
> Sent: Thursday, July 03, 2014 12:59 AM
> To: Devesh Sharma; Chuck Lever; linux-rdma@vger.kernel.org; linux-
> n...@vger.kernel.org
> Subject: Re: [PATCH v1 05/13] xprtrdma: Don't drain CQs on transport
> disconne
On Jul 2, 2014, at 3:28 PM, Steve Wise wrote:
> On 7/2/2014 2:06 PM, Devesh Sharma wrote:
>> This change is very much prone to generate poll_cq errors because of
>> un-cleaned completions which still
>> point to the non-existent QPs. On the new connection when these completions
>> are polled,
Yes, thanks for the correction.
Shirley
On 07/02/2014 12:18 PM, Chuck Lever wrote:
>
> On Jul 2, 2014, at 12:11 PM, Shirley Ma wrote:
>
>> 7. Mike reported that NFSoRDMA doesn't show same performance as SMB for fio
>> test.
>
> Shirley, did you mean Mark Lehrer ?
>
> http://marc.info/?l=lin
On 7/2/2014 2:06 PM, Devesh Sharma wrote:
This change is very much prone to generate poll_cq errors because of un-cleaned
completions which still
point to the non-existent QPs. On the new connection when these completions are
polled, the poll_cq will
fail because old QP pointer is already NULL.
On Jul 2, 2014, at 12:11 PM, Shirley Ma wrote:
> 7. Mike reported that NFSoRDMA doesn't show same performance as SMB for fio
> test.
Shirley, did you mean Mark Lehrer ?
http://marc.info/?l=linux-rdma&m=140260285527831&w=2
> Shirley is able to reproduce it, Steve will ask Chelsio engineer to
This change is very much prone to generate poll_cq errors because of un-cleaned
completions which still
point to the non-existent QPs. On the new connection when these completions are
polled, the poll_cq will
fail because old QP pointer is already NULL.
Did anyone hit this situation during their
From: Kaike Wan
This patch fixes a segfault error when the option file defines the provider
lib path. The variable prov_lib_path should be a buffer (char array) instead
of a char pointer. This allows a string to be copied into it during option
parsing.
Signed-off-by: Kaike Wan
---
src/acm.c |
Sorry for being late, I just found this email wasn't out. Please add what's
missing.
Attendees:
Rupert Dance (Soft Forge)
Chuck Lever (Oracle)
Doug Ledford (RedHat)
Shirley Ma (Oracle)
Anna Schumaker (Net App)
Steve Wise (OpenGridComputing, Chelsio)
Steve Dickson (RedHat)
Jeff is busy on OFED s
Hi Jack-
On Jul 2, 2014, at 3:19 AM, Jack Morgenstein wrote:
> On Tue, 1 Jul 2014 18:17:27 -0400
> Chuck Lever wrote:
>
>> Hi-
>>
>> This happens during boot, and means that lockdep and lock_stat are
>> completely disabled during any testing I do.
>>
>> Does this splat have a known fix, or
Hi Erez,
Yep, I haven't cleanup pkey_index before p_key lookup and compare,
so child won't flush/get back up on p_key reappearance event
if index stays the same.
Thanks,
Alex.
> Still there is an issue here, please try the following:
>
> 1. pkey table contains the pkey 8001
> 2. echo 0x8001 >
On Wed, Jul 2, 2014 at 10:18 AM, Erez Shitrit wrote:
> Still there is an issue here, please try the following:
> 1. pkey table contains the pkey 8001
> 2. echo 0x8001 > /sys/class/net/ib0/create_child ; ifconfig ib0.8001 1.1.1.1
> up - till now all good.
> 3. change the sm partiotion file, take ou
On Tue, 1 Jul 2014 18:17:27 -0400
Chuck Lever wrote:
> Hi-
>
> This happens during boot, and means that lockdep and lock_stat are
> completely disabled during any testing I do.
>
> Does this splat have a known fix, or should I file an upstream
> bugzilla?
>
>
> Jul 1 15:50:22 manet kernel: =
Hi Alex,
Still there is an issue here, please try the following:
1. pkey table contains the pkey 8001
2. echo 0x8001 > /sys/class/net/ib0/create_child ; ifconfig ib0.8001
1.1.1.1 up - till now all good.
3. change the sm partiotion file, take out the pkey value 8001
4. force the sm to send the
29 matches
Mail list logo
