Re: [PATCH 1/3] rdma_cm: Add support for a new RDMA_PS_LUSTRE Lustre port space

2010-01-19 Thread sebastien dugue
Hi Roland, On Tue, 19 Jan 2010 17:12:43 -0800 Roland Dreier wrote: > > > Well, without a specific port space, the default for Lustre is to use the > > TCP port space so you cannot distinguish Lustre traffic from other traffic > using > > that same port space. > > I'm still a bit confu

Re: [PATCH 1/3] rdma_cm: Add support for a new RDMA_PS_LUSTRE Lustre port space

2010-01-19 Thread Roland Dreier
> Well, without a specific port space, the default for Lustre is to use the > TCP port space so you cannot distinguish Lustre traffic from other traffic > using > that same port space. I'm still a bit confused. The problem as I understand it is that Lustre always uses the same TCP port, s

Re: mode connected infiniband

2010-01-19 Thread Roland Dreier
> > IPoIB CM is very stable now and has a better performance > > The last time I tried to use it the kernel began reporting lots of > OOM events (2.6.30 stock). I thought this was well known because CM > mode uses high order allocations?? And in any case changing the kernel config option de

Re: mode connected infiniband

2010-01-19 Thread Roland Dreier
> The last time I tried to use it the kernel began reporting lots of > OOM events (2.6.30 stock). I thought this was well known because CM > mode uses high order allocations?? That's not well-known to me. What's the backtrace for those high-order allocations? I thought the CM code was carefu

Re: [PATCH] IB/mlx4: fix post_recv wq overflow check

2010-01-19 Thread Roland Dreier
> mmm, why is that common? typically there's a higher layer to which the > IB ULP advertises some sort of maximal number of credits (e.g in the > SCSI case, iser and srp specify the maximal number of commands in the > scsi host template) or the ULP informs a higher layer that no more > sends

Re: [PATCH] IB/mlx4: fix post_recv wq overflow check

2010-01-19 Thread Or Gerlitz
Roland Dreier wrote: I do think it is quite common to see this WQ overflow check trigger, even for kernel code mmm, why is that common? typically there's a higher layer to which the IB ULP advertises some sort of maximal number of credits (e.g in the SCSI case, iser and srp specify the maximal

Re: clarification on the mlx4 CQE structure

2010-01-19 Thread Or Gerlitz
Yevgeny Petrilin wrote: > This commit has an endianess bug, that was fixed in commit f781a22f. > The cqe->sl_vid field is a be16, so we needed to convert the sl value to > host order. Before the commit this field was two u8 fields, so no conversion > was needed okay, got it, thanks Or. -- To un

Re: [infiniband-diags] [UPDATED PATCH] [3/3] support --load-cache in iblinkinfo and ibqueryerrors

2010-01-19 Thread Sasha Khapyorsky
On 21:35 Mon 18 Jan , Al Chu wrote: > Hey Sasha, > > Here's an updated patch with the cleanup changes as we discussed. Applied. Thanks. Sasha -- 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

RE: clarification on the mlx4 CQE structure

2010-01-19 Thread Yevgeny Petrilin
> @@ -692,14 +692,13 @@ repoll: > - wc->sl = cqe->sl >> 4; > + wc->sl = be16_to_cpu(cqe->sl_vid >> 12); > > I wasn't sure if/why a conversion from network order to host order is neeed here, can you clarify that? This commit has an endianess bug, tha

clarification on the mlx4 CQE structure

2010-01-19 Thread Or Gerlitz
Hi Yevgeny, looking on commit f780a9f "mlx4_core: Add ethernet fields to CQE struct" I see the following two changes: @@ -692,14 +692,13 @@ repoll: - wc->sl = cqe->sl >> 4; + wc->sl = be16_to_cpu(cqe->sl_vid >> 12); I wasn't sure if/why a conver