Re: supporting larger number of iser sessions/targets

2011-03-29 Thread Степан Фёдоров
29 марта 2011 г. 16:24 пользователь Or Gerlitz ogerl...@mellanox.com написал: Sounds interesting, so you are using also GPFS from the client side and have GPFS work in its SAN mode? No - GPFS is used at iSER target side - not on client (XEN virtualization node). It's not the best solution,

Re: supporting larger number of iser sessions/targets

2011-03-29 Thread Степан Фёдоров
Hello! About redundancy: we have distributed filesystem (IBM GPFS), on several nodes. Each node have it's own disks directly attachet to it - there is no shared storage. So we use GPFS replication to store two replicas of all data. Disks of virtual machines is actually a files on GPFS. So, to

Re: supporting larger number of iser sessions/targets

2011-03-29 Thread Or Gerlitz
Степан Фёдоров wrote: upfront, there's max_fmrs but its zero...). Is that 123 targets for specific initiator a realistic requirement for your environment? No. Realistic requirement is at least 256 targets per node. Each target represents virtual machine in VDS hosting environment, so we need

Re: supporting larger number of iser sessions/targets

2011-03-29 Thread Or Gerlitz
Stepan Fedorov wrote: About redundancy: we have distributed filesystem (IBM GPFS), on several nodes. Each node have it's own disks directly attachet to it - there is no shared storage. So we use GPFS replication to store two replicas of all data. Disks of virtual machines is actually a files

[PATCH RFC] ib/iser: use actual maximal number of scsi commands instead of default

2011-03-29 Thread Or Gerlitz
Align the iser code to use the actual maximal number of scsi commands set for that session when allocating IB FMR resources instead of the default max Signed-off-by: Or Gerlitz ogerl...@mellanox.com --- done against Linus tree of commit 036a98263a30930a329e7bb184d5e77f27358e40 compile tested

Re: [PATCH RFC] ib/iser: use actual maximal number of scsi commands instead of default

2011-03-29 Thread Or Gerlitz
On Tue, 29 Mar 2011, Or Gerlitz wrote: Align the iser code to use the actual maximal number of scsi commands set for that session when allocating IB FMR resources instead of the default max If this patch doesn't work out of the box and you want something simpler just to make sure you can

Re: Kernel NULL pointer dereference [when using iser]

2011-03-29 Thread Mike Christie
On 03/28/2011 04:11 AM, Or Gerlitz wrote: Hi Mike, I don't see this message in the open-iscsi archive, I also It might have shown up late. I had to manually ok messages. didn't get it to a subscription I have in my gmail email account. I'm suspecting this is b/c my sender address is now

proposal to move mailing list to vger.kernel.org

2011-03-29 Thread Mike Christie
Hi list, Googlegroups just does not work well. To handle the spam problem I made it so posting the list required that I manually ok a new users message. This has resulted in people getting banned accidentally and mails getting delayed by a couple days sometimes. I would like to see if