free blog   apache   shopping directory   php powered
lokoShould you be using overlap for x86 or not?
axisysprevious topic: compression on or off
axisysnew topic: hw raid cntrl or zfs raid ?
axisysi have a t5410 (i think)
axisysi prefer zfs raid w/ ssd for cache and log devices ..
axisysi think it will perform better if i have enough memory .. since hw raid control do not have as much mem
axisyssorry t5140
MilkmanDanIf your hardware "raid control" has any memory in it at all it'd damned well better be battery backed, or you ought to disable it immediately.
MilkmanDanI can't understand how proper Unix shops that have years of institutional knowledge in SVM or VxVM root mirroring can suddenly decide that "hardware RAID" for OS disks is a good idea.
peerceyeah, the main performance gain of hardware raid is write performance if you have battery backed write-back cache
MilkmanDanIf you're only paying for VxVM for OS mirroring, yeah, ok, I can see a justification for saving the money.
MilkmanDanBut nobody in their right mind has done that this century.
axisyspeerce: so with ssh for log and cace wont outperform the hw raid write-cache ?
peerceeven SSD has write performance issues.  a write cache means the host can treat hte data as committed as soon as its sent to the controller
axisyspeerce: but with cache zfs can do the writing asynchronous .. to should not introduce any delay either.. no ?
axisysi am just trying to understand.. not arguing w/ anyone
peerceaxisys; cache in main memory is toast if there is a power event, or system crash
axisyspeerce: no i meant if i have ssd cache device ..
peercebut that takes longer to write to tahn a raid controller BBU write-cache
Stric(l2arc read) cache device, or zil/slog?
axisysStric: zil/slog
gothospeerce: I fixed my DSEE7 problem, more or less, I set cert-pwd-prompt to off and can now start the DSEE7 just fine
axisyspeerce: is that right? btw, whats BBU ?
Stricbattery backup unit
axisysStric: thanks..
Stricor backed
axisyspeerce: hmm.. did not know it takes longer to write slog on ssd than on raid controller w/ bbu
Stricdram is fast at writing, disk and flash isn't
Stricflash units usually "fix" this by having some dram where your writes end up
Stricso if you rely on that to be written, then you can be toast
axisysStric: oh yeah.. raid controller has real memory.. but if the total mem is slow it has to buffer somewhere else in slower location
axisysbut if the toal mem is full..
StricI don't follow
Strica raid controller with battery backed write cache memory, it puts writes into dram and then tells the host "ok".. and starts writing that to the slower disks in the background
axisysif i have  big chunk of data to write commit .. raid controller memory wont have enough of it to hold .. so it has to keep those cached in slower disk or ssd anyways.. no?
Stricraid controller memory is usually 128MB, 512MB or similar
Stricnothing is "cached in slower disk".. either it's cached in fast ram, or stored permanently on slower disk
axisysStric: ok.. so performance wise raid controller seems a better choice ..
Striccould be
Stricunless that raid controller sucks
Stricand that set of controllers is not empty
axisysStric: well can you elaborate? i am going to be using t5140
Stricseparate raid controller or something built-in? if the built-in, then it doesn't have a battery backed write cache, so this whole disscussion is moot
axisysIntegrated hard drive controller supports RAID 0 and RAID 1.
Stricand no battery backed write cache, so no write cache
Stricso all it does is raid1 with less protection than zfs
axisysit has option to buy pci raid controller to expand
axisysthe site will not have power outage.. has generator
Stricthe OS can panic
Stricsomeone can trip on the power cord
Stricwith proper stuff, neither of those matter
axisysStric: gotcha
axisysLithium Ion Battery Module, 8-Port SAS Adaptec RAID HBA, RoHS:Y , SGXPCIESAS-R-INT-Z
axisysthat is a pci card to buy as optional to expand
axisysinternal i think
axisysthis one shows zfs raid gave more iops that hardware raid
axisysmay be v440 raid controller sucks
Stricit's an lsi-1030
axisysStric: is it any good?
Stric4 connections, of which it can do raid1 on 2 of them
Stricso pretty basic
peercethe 1030 is a good SAS controller but a lame raid controller, has rather limited cache, and no battery by default, although SOME cards add
Stricumm.. v440 is not sas.. it's u320 scsi, sca..
peercei didn't think the v440 even had a raid controller, just scsi jbod ?
peerceat least for its internal drives
Stricas I said, it can do 1..4 disk jbod or 2 disk raid1 + 2 jbod
peercewe've gotten rather mixed results from our database benchmarking on zfs.   if we're running oracle hard, we tend to use 80% of CPU while doing an almost pure write load on a large number of SAN volumes.   ZFS takes a fair amount of CPU away from oracle
jamesd2peerce, do you have compression enabled? did you set recordsize to 8k? did oracle performance dispote its excessive cpu usage?
peercewe did all the recommended sun and oracle zfs tuning
peerceour CPU usage in oracle is because we have a ton of business logic in pl/sql
peerceits the nature of our backend app
axisysStric: here is a t5140/5240 with lsi 1068E
axisysStric: is that a good raid controller ?
jamesd2peerce, it may be wise to add a cpu to the box, but not allow oracle to use it.. could give you a performance boost without the oracle tax.
Stric1068e in t5120 as well.. haven't used it for anything but jbod
axisysStric: jbod? w/ software raid ?
Stricall 2 disks
axisysStric: heh
MilkmanDanjamesd2: The problem is, Oracle doesn't like you doing that.  They say they'll accept Containerization of the database for the purposes of determining CPU/core count, but then they say "oh!  Not running in the global Zone!  UNSUPPORTED!"
MilkmanDanThey're being greedy, just like they always have.
MilkmanDanOtherwise, yeah, it'd make perfect sense to dedicate a few cores to the OS so ZFS could stay well fed, and shave that off the DB cost of the box.
AJC_Z0This puts Google in the position of not supporting their product running on their hardware in the way it's designed to be used
MilkmanDanAnd yes, now that they own Solaris, that's precisely correct.
MilkmanDanBut since they've never been a company to allow loopholes for customers to eke out more performance than they were paying for, expect everything to change once you finally get a handle on it.
MilkmanDanRepeat, ad nauseum.
Action: AJC_Z0 was dealing with the liars, thieves and charlatans at Google
zetanany know ce.conf configuration details?
zetani'm trying to enable jumbo frames on my 4 ceX devices and the settings dont 'take'
peercethat reminds me, I have to figure that out myself :D
zetanname="pci100b,35" parent="/pci@8,700000" unit-address=0 accept-jumbo=1;
zetanreboot, and ifconfig ce0 mtu 9194 fails
peerceno idea
jamesd2does it support mtu's that high i thought the most commonly supported jump packet was 9000
kop_it isn't about morals it's about not buying a car with the hood welded shut
kop_ it's about being independent of the mindless addiction and irrational upgrade path of a monolithic ,monotheist monopoly  
kop_it's about reasoning for ones self even if it includes M$hit products
kop_choice      now where were we
kop_Oh yeah  w7 sux dawg bawlls
zetan9194 was the value from the gigaswift manual (which is ripe with typos and spelling errors)
peercekop; so you have the source to your car's EFI processor ?
jamesd2i would try 9000 and perhaps even 8000-8500 just to be sure that you aren't exceeding some internal limit
peercemight as well be welded shut, there's nothing a regular person can do under there other than check the oil and water
zetanwhich is why I stick with mechanically controlled vehicles
Action: zetan points to throttle cable and hydraulic brake actuators
zetanno computer at all
peercezetan; so nothing built since the 70s ?
zetannot true
zetan1984 GMC 6.2L diesel G-van
kop_peerce, actually yes but that's a bad example in my case
zetanand my 1995 Chevy 6.5L diesel G-van
peercemechnical diesel injection on those?
zetanthe 'computer' does very little in these cases. mostly dash lights, trouble codes, and transmission stuff
jamesd2kop is not normal has has more 8 and 16bit bit microcontrollers in his house and garage than can be found anywhere on earth ;-)
zetanyeah both
peercethat must be efficient.
zetan20mpg freeway with a big load
peercenice big cloud of black smoke when you step on it?
kop_peerce, my own aftermarket closed loop
peercekop; so not street legal?
zetanyeah I can make a smoke show on demand, but usually it's clean
kop_but I do own a 94 exploder
kop_and I supose in that case it's valid
zetanI'm hoping to add hydroxy injection (HHO) soon to solve the smoke issue
peercehho, you mean, water.
kop_peerce, meets emissions so who phuckin cares
peercei guess you don't have smog inspections where you live
zetanwell, splitting water into 2 H and an O and injecting that gas into the air intake
zetanit's well documented it proves milage and reduces emissions
zetannot a fuel replacement, mind you
kop_peerce, they don't inspect , yet, alll they do is sniff
peerceand how do you do this split?
peerceelectrolysis ?
zetanusing about 10amps off the alternator
zetanPWM controlled
zetanKOH as a catalyst
zetanand a bubble to filer the KOH vapor
zetani have a proof of concept device working
kop_Ever heard of Stanlel Meyer ?
zetani hesitate to say "search youtube for HHO" because of all the redneck versions of this tech
kop_Ever heard of Stanley Meyer ?
peerceyah, lotta snakeoil out there and BS claims  (K&N Filters <cough>)
kop_look on youtube for "it runs on water"
zetani'm on the hydroxy yahoo group. lots of good research flying around
zetanyeah you spend more energy splitting that you get in return
peerceI'd rather read an engineering article that had been peer rewviewed, frankly.
zetani know ,it's a bunch of numb nuts doing it
zetanbut there is some validity in the work
kop_peerce, many people have looked into Meyer's snake oil
peercei just hate watching 'talking heads' videos
kop_peerce, I'll do some editing and drop it on ya
kop_you're a bright guy , you don't need to crawl before you run
kop_it's in a down'd box atm
kop_peerce, save you the trouble of trolling rexweb and patents online to sift through all the mysticism and smoke show salesmen
kop_the basic principal is interesting
peercei don't have audio right where i am atm anyways, on a laptop, using remote control
peerceand video over remote is wretched
gwshow do I find otu if solaris 10 is seeing my emulex fiber card?  a hitchi guy can see it in the SAN, but I must now learn how the os sees the space....
kop_peerce, it won't be any time soon but I'll remember
peercegws: otu ?
g4lt-mordantpeerce, typoese...
peercegws; assuming everything is setup, to see new LUNs that are mapped to your host, use `devfsadm -v`
gwsdevfsadm -v returns nothing, I think the Luns have yet to be assigned...
gwsI am so weak at SAN
zetananything show up in 'format' ?
zetani'm using qlogic cards, and those tools show you the SAN network, can browse luns, do diags, etc. i dont know the emulex variety
gwsformat shows only disk 0
gwstime to call the party people at sun support!
gwsI have to whip people here to make em use raid 0+1
gwsthey want performance
gwsour dba a joker
WOUniversityHello all, I was hoping someone here could help me.
WOUniversityI am trying to integrate some Solaris machines into my Active Directory hosted by a Windows 2008 Server.
WOUniversityThey are running Solaris 10, I need to somehow enable Kerberos and am currently at a loss for what to do.
WOUniversityHas anybody here seen or done anything like that?
peerceare the windows servers using the Microsoft Unix extensions?
peerceoh, he left.
zetansome of our customers use libVas for AD integration
zetanbut sadly libvas is not thread safe
doubletwistI dunno, but I suspect we will be looking into authenticating against the AD servers soon. Within a year perhaps.
peerceas I understand it, and I've not set this up, if you use Microsoft's Unix extensions, its pretty straight forward, you configure unix for LDAP
peerceyou have to populate the unix user's AD records with the unix UID/GID you want them to use
doubletwistI'm not looking forward to it. I've tried on my own playing around at home to get my linux boxes to authenticate against an openldap server. I came to the conclusion that I'm too stupid to understand ldap :)
ChubbzDoes someone know of a good resource on Solaris hard drive notation?
peerceum, cXtYdZsW, where X is the channel, Y is the target, Z is the device or lun# on that target, and W is the slice, 0-9
Popular searches: iso 2 usb   use mlocate with apache   ubuntu setup pgpool   perl utf-8 tis-620   

Generated by 2.1mg by Jeff Waugh - return