OK, i just replace "ISCSI_DEF_XMIT_CMDS_MAX * 2" by 128, "ISCSI_DEF_XMIT_CMDS_MAX" by 64, and remove null pointer dereference from your patch, and i report about successful overcommiting "123 sessions" boundary.
Next, i will try to create as many sessions as possible at this configuration, and report results. And now, after resolving this problem, tgt memory usage becomes our main problem that prevent us from adopting iSER as storage solution in VDS hosting environment. But this is a subject for another mailing list. Thank you! 2011/3/30 Or Gerlitz <[email protected]>: > Mike Christie wrote: >> >> Hey Or, was the problem that you wanted the session->*cmds*max info at >> ep_connect time or create_conn time? > > let me look on that, I hope to be able to get away with deferring these > resource allocations to a point where I have the session at hand, e.g post > bind. Looking on the good old ladder diagram chart @ > http://www.open-iscsi.org/docs/open-iscsi-1.jpg > I see that the session is created only after we connect, so I can't actually > get a session object beforehand, isn't it? > > Or. > > -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
