00:14:52 <Smithx10> lol.... this is fun.....  https://github.com/influxdata/go-syslog/blob/develop/rfc5424/machine.go#L129
00:33:37 <jbk> i can only hope that's generated code from some other input (ala yacc/lex)
02:32:42 <Smithx10> jbk:  I think its generated by something called "ragel"
03:34:45 <rennj> you mean using computers to autom8 repetitive tasks...i dont believe it!
03:34:59 <rennj> 614 case statements
03:36:15 <rennj> testof big deal...
03:50:42 <Smithx10> rennj:  lol
03:51:03 <Smithx10> I'm confused at why when we move messages into /var/log/messages those fields are cut out lol 
03:52:09 <Smithx10> or maybe illumos no follow the rfc
03:52:31 <Smithx10> Didn't think I'd be playing with ragel today :)
04:03:39 <Smithx10> : ixgbe3: Could not allocate rbd dma memory: ffffffff  ixgbe3: Failed to allocate DMA resource..... this doesn't seem good
04:51:06 <jbk> if you have VMs you're not using, try shutting them down
04:52:14 <jbk> hmm.. i actually have ixgbe nics...
04:52:48 <jbk> so if no one else gets to it in the next few months, i'll probably try to fix that after i've moved and have a 10gb switch to use w/ it
04:57:22 <rennj> the switch being the important part
04:57:37 <rennj> 1 ended is useless
04:59:02 <rennj> AGI and starving artist!
05:01:25 <rennj> so vmware HA/vmotion between dc's takes minutes to failover...lame
05:01:44 <rennj> not seconds but minutes
05:07:03 <rennj> the computer industry/rent seeking has left me jaded
05:10:42 <rennj> its all SaaS
05:13:36 <arekinath> my personal fav is when vmware VMs just sometimes... stop being able to vmotion at all
05:13:49 <arekinath> I have like 3 of them where vmotion just errors out with weird error codes that google doesn't know
05:15:03 <arekinath> there's a reason people say you should never rely on hypervisor-layer stuff for actual HA in a failure scenario (vs. planned outage failover), heh
05:15:19 <jbk> i love when if for whatever reason your NFS datastore times out.. you have to reboot the ESX host
05:15:28 <rennj> you are only as good as your backups
05:15:34 <jbk> you can't just reset the VMs or anything once the NFS mount is back
05:16:03 <rennj> 52weeks level 0, 5,4,3,2,1-->0... weekly per server...you need 57tapes
05:16:40 <rennj> just to do yearly backups before the ransom ware encrypts your data
05:17:14 <rennj> 52 tapes for just level 0, rotate the other 5 tapes till failure
05:18:40 <rennj> my storagetek/adic is screwed in end
05:19:20 <rennj> robot library is not going to fix the data issue...
05:20:34 <rennj> bitcoin worse then mining actual gold..for env
05:26:37 <rennj> yeah well lameness rules at this point
05:27:40 <rennj> Roko's basilisk suffer...
05:28:09 <rennj> its all dependency hell
05:31:40 <rennj> draw me mona lisa in DaVinci style...
05:35:32 <rennj> and dell/emc will sell vmware to broadcom for what $61 billion
13:47:39 <neuroserve> https://dl.gi.de/bitstream/handle/20.500.12116/38504/Paper01.pdf <- Operating System Name Options exhausted?
14:18:34 <jlevon> you think they'd google
14:32:06 <andyf> There's an OmniOS too, somewhere... I don't think they bother checking!
15:15:01 <Smithx10> Would only having 14gb free of memory on a machine make an interface flap?
15:16:49 <Smithx10> or I guess running low on memory could do this?
15:19:27 <Smithx10>  0 0 687 753157100 4724428 2211 34702 1 0 0 0 0 150 185 185 149 139862 153507 191941 2 17 81  I have a machine with 4gb  of memory free and the interfaces is up/downing like crazy
15:35:06 <Smithx10> I freed up some memory and got it to 24GB in vmstat,  the up/down is still going strong,  not sure if its related at all
15:48:34 <danmcd> I'm imagining fragmentation for some reason.
15:49:33 <jbk> I don't think it'd make it flap (link up/down).. IIRC that's normally just an indication from the HW
15:50:10 <jbk> the big issue with fragmentation is usually with jumbo frames -- since that means trying to find potentially lots of chunks of physically contiguous memory
15:50:27 <danmcd> Oh wait this is ixgbe not i40e as well. (i40e is a pig whenever you bring up a new vnic.)
15:52:23 <danmcd> Okay, more likely a HW issue then.
15:56:57 <Smithx10> We do have  the underlay using 9k but im not sure if that wuld cause it.... going to have DC folks go replace cables and audit more *
16:11:35 <Smithx10> interesting
16:11:46 <Smithx10> I removed the interface from the aggregation and the up/downs stopped
16:13:18 <jbk> do you see anything on the switch side?
16:14:31 <Smithx10> I dont have access :(
16:14:34 <Smithx10> this is the problem
16:27:27 <danmcd> Oh yeah, you have one of those "traditional" network vs. machines splits.  :barf:
16:30:18 <jbk> and of course the network is never the problem.. the network is flawless... perfection manifest... all who gaze upon it despair...
16:37:32 <jbk> also.. thank god for the various unix shell utilities