Re: [PATCH 4/4] RDMA/cxgb4: Add timeouts when waiting for FW responses.

2010-08-02 Thread Roland Dreier
thanks, applied all 4 -- Roland Dreier || For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/index.html -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majord...@vger.kernel.org More majordomo info at

[PATCH 2/2] IB/qib: fix race between qib_error_qp() and receive packet processing

2010-08-02 Thread Ralph Campbell
When transitioning a QP to the error state, in progress RWQEs need to be marked complete. This also involves releasing the reference count to the memory regions referenced in the SGEs. The locking in the receive packet processing wasn't sufficient to prevent qib_error_qp() from modifying the r_sge

[PATCH 1/2] IB/qib: limit the number of packets processed per interrupt

2010-08-02 Thread Ralph Campbell
Don't processes too many packets without allowing other IRQ functions a chance to run. Otherwise, there is a chance of getting "soft lockup" messages and poor application response times. Signed-off-by: Ralph Campbell --- 0 files changed, 0 insertions(+), 0 deletions(-) diff --git a/drivers/inf

Re: [PATCH 4/4] IB/srp: export req_lim via sysfs

2010-08-02 Thread David Dillow
On Mon, 2010-08-02 at 17:32 +0200, Bart Van Assche wrote: > Exports req_lim via sysfs, which is convenient for debugging purposes. > > Signed-off-by: Bart Van Assche > Cc: Roland Dreier > Cc: David Dillow Acked-by: David Dillow -- To unsubscribe from this list: send the line "unsubscribe linu

Re: [PATCH 3/4] IB/srp: adjust can_queue

2010-08-02 Thread David Dillow
On Mon, 2010-08-02 at 17:32 +0200, Bart Van Assche wrote: > Makes sure that the SCSI mid-layer never tries to queue more than > (SRP request limit) - 1 SCSI commands. Improves performance for targets whose > request limit is less than or equal to SRP_SQ_REQ_SIZE (63) by reducing the > number of BUS

Re: [PATCH 2/4] IB/srp: implement SRP_CRED_REQ

2010-08-02 Thread David Dillow
On Mon, 2010-08-02 at 17:32 +0200, Bart Van Assche wrote: > This patch enables allocation of request and response information units on the > send queue instead of only requests, and implements processing of SRP_CRED_REQ > information units. Also, declarations have been added to include/scsi/srp.h >

Re: [PATCH 1/4] IB/srp: rename some symbolic constants

2010-08-02 Thread David Dillow
On Mon, 2010-08-02 at 17:32 +0200, Bart Van Assche wrote: > The patch below realizes the following transformations on the symbolic > constants defined in ib_srp.h and used in ib_srp.h and ib_srp.c: > * Added the constants SRP_RQ_MASK and SRP_SQ_MASK. > * Renamed SRP_SQ_SIZE into SRP_REQ_SQ_SIZE. >

Re: [PATCH] IB/srp: use multiple CPU cores more effectively

2010-08-02 Thread Vladislav Bolkhovitin
Bart Van Assche, on 08/02/2010 10:40 PM wrote: On Mon, Aug 2, 2010 at 8:36 PM, David Dillow wrote: On Mon, 2010-08-02 at 22:16 +0400, Vladislav Bolkhovitin wrote: Bart Van Assche, on 08/02/2010 07:57 PM wrote: block size number ofIOPSIOPS IOPS in bytesthreads wi

Re: [PATCH] IB/srp: use multiple CPU cores more effectively

2010-08-02 Thread David Dillow
On Mon, 2010-08-02 at 22:16 +0400, Vladislav Bolkhovitin wrote: > Bart Van Assche, on 08/02/2010 07:57 PM wrote: > >>> > >>> block size number ofIOPSIOPS IOPS > >>> in bytesthreads without with with > >>>($bs) ($numjobs) this patch thread=n thread=y >

Re: [PATCH] IB/srp: use multiple CPU cores more effectively

2010-08-02 Thread Bart Van Assche
On Mon, Aug 2, 2010 at 8:36 PM, David Dillow wrote: > > On Mon, 2010-08-02 at 22:16 +0400, Vladislav Bolkhovitin wrote: > > Bart Van Assche, on 08/02/2010 07:57 PM wrote: > > >>> > > >>> block size  number of    IOPS        IOPS      IOPS > > >>>   in bytes    threads     without     with      wit

[PATCH] dapl-2.0 - common: cleanup CR linkings after DTO error on EP

2010-08-02 Thread Davis, Arlin R
Add cleanup to remove CR from SP and EP during DTO errors in dapli_evd_cqe_to_event. dapl_sp_remove_ep needs to remove cr_ptr reference from EP before freeing cr object. Signed-off-by: Arlin Davis --- dapl/common/dapl_evd_util.c |1 + dapl/common/dapl_sp_util.c |2 ++ 2 files changed

[PATCH] dapl-2.0 - ucm: cleanup CM debug warning messages

2010-08-02 Thread Davis, Arlin R
Signed-off-by: Arlin Davis --- dapl/openib_ucm/cm.c | 20 +++- 1 files changed, 11 insertions(+), 9 deletions(-) diff --git a/dapl/openib_ucm/cm.c b/dapl/openib_ucm/cm.c index b874c8b..05b5af5 100644 --- a/dapl/openib_ucm/cm.c +++ b/dapl/openib_ucm/cm.c @@ -165,9 +165,9 @@ sta

[PATCH] dapl-2.0 - scm, ucm: improperly handles pkey check/query in host order

2010-08-02 Thread Davis, Arlin R
Convert consumer input to network order before verbs query pkey check. Change appropriate debug messages, increase level of bad key message. Signed-off-by: Arlin Davis --- dapl/openib_common/util.c | 14 +++--- 1 files changed, 7 insertions(+), 7 deletions(-) diff --git a/dapl/openib

Re: [PATCH] IB/srp: use multiple CPU cores more effectively

2010-08-02 Thread Vladislav Bolkhovitin
Bart Van Assche, on 08/02/2010 07:57 PM wrote: SRP I/O with small block sizes causes a high CPU load. Processing IB completions on the context of a kernel thread instead of in interrupt context allows to process up to 25% more I/O operations per second. This patch does add a kernel parameter 'thr

Re: [RFC PATCH] libmthca: Add support for the reg_io_mr verb.

2010-08-02 Thread Tom Tucker
Tziporet Koren wrote: Hi Tom, What is the purpose of this? Is there a reason you did it only for mthca and not mlx4? Tziporet Hi Tziporet, I just picked mthca arbitrarily to demonstrate how to do it. If people like the verb, then I'll do it for all the devices, but I didn't want to do all

Re: [PATCH] IB/srp: use multiple CPU cores more effectively

2010-08-02 Thread Bart Van Assche
On Mon, Aug 2, 2010 at 3:08 PM, Vladislav Bolkhovitin wrote: > > Bart Van Assche, on 08/02/2010 12:15 PM wrote: >> >> SRP I/O with small block sizes causes a high CPU load. Processing IB >> completions on the context of a kernel thread instead of in interrupt context >> allows to process up to 25%

[PATCH 4/4] IB/srp: export req_lim via sysfs

2010-08-02 Thread Bart Van Assche
Exports req_lim via sysfs, which is convenient for debugging purposes. Signed-off-by: Bart Van Assche Cc: Roland Dreier Cc: David Dillow --- drivers/infiniband/ulp/srp/ib_srp.c | 14 ++ 1 files changed, 14 insertions(+), 0 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib

[PATCH 3/4] IB/srp: adjust can_queue

2010-08-02 Thread Bart Van Assche
Makes sure that the SCSI mid-layer never tries to queue more than (SRP request limit) - 1 SCSI commands. Improves performance for targets whose request limit is less than or equal to SRP_SQ_REQ_SIZE (63) by reducing the number of BUSY responses. Signed-off-by: Bart Van Assche Cc: Roland Dreier C

[PATCH 2/4] IB/srp: implement SRP_CRED_REQ

2010-08-02 Thread Bart Van Assche
This patch enables allocation of request and response information units on the send queue instead of only requests, and implements processing of SRP_CRED_REQ information units. Also, declarations have been added to include/scsi/srp.h for the SRP_CRED_REQ and SRP_CRED_RSP information units. Signed-

[PATCH 1/4] IB/srp: rename some symbolic constants

2010-08-02 Thread Bart Van Assche
The patch below realizes the following transformations on the symbolic constants defined in ib_srp.h and used in ib_srp.h and ib_srp.c: * Added the constants SRP_RQ_MASK and SRP_SQ_MASK. * Renamed SRP_SQ_SIZE into SRP_REQ_SQ_SIZE. * Changed the value of SRP_SQ_SIZE from 63 to 64. Note: this patch

[PATCH 0/4] IB/srp: add SRP_CRED_REQ support

2010-08-02 Thread Bart Van Assche
This series of four patches adds SRP_CRED_REQ support in ib_srp, which is a feature defined by the SRP (draft) standard. Compared to an earlier patch for implementing this functionality that I posted a few months ago I have done my best to address all comments that were posted to this mailing list,

Re: [PATCH] IB/srp: use multiple CPU cores more effectively

2010-08-02 Thread Vladislav Bolkhovitin
Bart Van Assche, on 08/02/2010 12:15 PM wrote: SRP I/O with small block sizes causes a high CPU load. Processing IB completions on the context of a kernel thread instead of in interrupt context allows to process up to 25% more I/O operations per second. This patch does add a kernel parameter 'thr

RE: [RFC PATCH] libmthca: Add support for the reg_io_mr verb.

2010-08-02 Thread Tziporet Koren
Hi Tom, What is the purpose of this? Is there a reason you did it only for mthca and not mlx4? Tziporet

[PATCH] IB/srp: use multiple CPU cores more effectively

2010-08-02 Thread Bart Van Assche
SRP I/O with small block sizes causes a high CPU load. Processing IB completions on the context of a kernel thread instead of in interrupt context allows to process up to 25% more I/O operations per second. This patch does add a kernel parameter 'thread' that allows to specify whether to process IB

Re: [PATCH v4] libibverbs: ibv_fork_init() and huge pages

2010-08-02 Thread Alexander Schmidt
On Mon, 19 Jul 2010 13:34:29 +0200 Alexander Schmidt wrote: > Hi Roland, > > this is the fourth version of the huge pages support, please see below for > change log + description, we appreciate your comments. Hi Roland, did you have a chance to take a look at the code? We would like to get thi