How to verify a mirror raid using atacontrol?
I have a mirror raid on Promise controller supported by atacontrol. How can i verify it? Thank you in advance -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: How to verify a mirror raid using atacontrol?
Steve Bertrand wrote: Artem Kuchin wrote: I have a mirror raid on Promise controller supported by atacontrol. How can i verify it? [snip] No, no. i meant completelly verify raid data, that is that bother drive match and no bad blocks on any of them. There is a special VERIFY raid command on 3ware and HPT and other, but i don't see it on atacontrol. -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Question about 'top' values on memory usage
William LeFebvre wrote: Artem Kuchin wrote: Hello! Maybe someone with deeper knowledge of the internals of FreeBSD can clean up something for me (any for many others)^ Here are lines from my top: PID USERNAMETHR PRI NICE SIZERES STATE C TIME WCPU COMMAND 9258 hordelo_ru1 40 40992K 4260K accept 0 0:00 0.00% httpd 9257 hordelo_ru1 440 40992K 4296K select 1 0:00 0.00% httpd 9259 hordelo_ru1 40 40992K 4292K select 1 0:00 0.00% httpd As you see, 'size' is the same for all processes, while RES varies. As i understand, the real memory taken by a process is RES and SIZE include a bunch of shares .so libs, so, if more httpd's started each will take only about 4300K more, so, 100 https will take 43K to run, right? Another question is that is httpd uses threads (as provided by FreeBSD) starting a new thread will or will not copy executable copy and data? Basically, will a new thread eat another 4300K or just a little bit for its data? SIZE is the total amount of virtual memory that a process has allocated. This includes text, data, and stack. It also includes all the stuff that's shared with other processes (mostly through the use of shared libraries). RES is the amount of physical memory in use by the process and will only include that part of a process's virtual memory space which is currently allocated in physical memory. Unfortunately, freebsd does not appear to track the amount of shared virtual memory for each process. It could be obtained by walking through all the pages in a process's vm map, but that would really slow top down. I don't know of any freebsd utility that would give that information for an individual process. But hey, if it's out there somewhere where it is easy to grab, I would be very happy to add it to top. My knowledge of VM system of FReebSD is so low, that even though i can write in C i don't know where to start here. I haven't found anything ready for this. make search in port on 'memory' and 'ram' does not return much. All this i need to calculate maximum possible number of https i can run on a box with certain amount of memory and select proper MPM for Apache. Somehow, i could not find any practical info on this regarding FreeBSD. limits how many of them can be active at a given time. You're not just going to be able to sit down and plug numbers in to a formula and say voila!. You will have to observe how httpd performs in your particular environment to see how many page faults per second it generates and decide for yourself the point at which X pf/s is too much. Of course, but i need to start with something instead of just pure guess out of the blue. Personally, based on my experience, I would be more concerned with the amount of available cpu cycles than memory. CPU is more than just enough in my case. There will a a lot https sitting there but load, i am sure, will be low. Swapping is simply unacceptable, so i am counting only real physical ram. However, noone mentioned anything about threads. DO they give any memory advantage on freebsd? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Question about 'top' values on memory usage, now threads
William LeFebvre wrote: Artem Kuchin wrote: CPU is more than just enough in my case. There will a a lot https sitting there but load, i am sure, will be low. If the load is low then you may not need very many processes. They belong to different sites ;) so they need to be run constantly and for security reasons each site has its own http. Swapping is simply unacceptable, so i am counting only real physical ram. Whether there is actual swapping going on or not, processes will still [SNIP] However, noone mentioned anything about threads. DO they give any memory advantage on freebsd? Yes, threading within httpd should provide a big advantage. The top [SNIP] Thank you very much for the answers. You were very helpful! -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Question about 'top' values on memory usage
Hello! Maybe someone with deeper knowledge of the internals of FreeBSD can clean up something for me (any for many others)^ Here are lines from my top: PID USERNAMETHR PRI NICE SIZERES STATE C TIME WCPU COMMAND 9258 hordelo_ru1 40 40992K 4260K accept 0 0:00 0.00% httpd 9257 hordelo_ru1 440 40992K 4296K select 1 0:00 0.00% httpd 9259 hordelo_ru1 40 40992K 4292K select 1 0:00 0.00% httpd As you see, 'size' is the same for all processes, while RES varies. As i understand, the real memory taken by a process is RES and SIZE include a bunch of shares .so libs, so, if more httpd's started each will take only about 4300K more, so, 100 https will take 43K to run, right? Another question is that is httpd uses threads (as provided by FreeBSD) starting a new thread will or will not copy executable copy and data? Basically, will a new thread eat another 4300K or just a little bit for its data? All this i need to calculate maximum possible number of https i can run on a box with certain amount of memory and select proper MPM for Apache. Somehow, i could not find any practical info on this regarding FreeBSD. Thank you in advance! -- Regards, Artem Kuchin ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
how to compiel kernel and world to maxium optimization
Hello! Somehow, i cannot find info now how to build kernel and world very optimized to a particular machine. Maybe i am not looking hard enough? The point is that if i have Xeon HT cpus (not very new, but definitelly not Pentium PRO :) i can build kernel and world using insttructions for this CPU and optimization for it, so i would get myself a speedy system and less memory hungry, right? The only option known to me which is related to the isee is cpu setting in kernel config file. Anything else? Thank you very much in advance -- Regards, Artem Kuchin ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Heads UP - MFC for em coming shortly
Jack Vogel wrote: I am preparing to update the em driver to the equivalent of my 6.6.6 driver. Just doing some last minute sanity checking, I hope to the checkin before end of day. This will provide support for devices up to our latest, the next stage I'm planning will incorporate multiqueue and multiple locks that are already in my Oplin driver (ixgbe) but this will take a bit longer. This driver has the support for TSO in it but its not on by default, as soon as Andre is able to get that MFC'd it can be enabled via a compile option. Hello, Jack! Remember, i wrote about problems with TSO (dropping send perfomace). I just posted news about it. Switching to SCHED_ULE solved to problem or.. i could be switching from HZ 1000 to HZ 100. I need to check into it. I hope it helps in some way. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Quation about HZ kernel option
Oliver Fromme wrote: Artem Kuchin wrote: What value of HZ option would you recommend for a hosting (web) server with a lot of processes (about 900) and polling off (as decided from previous discussion polling is useless in this situation). In that case, I would recommend not to override the default at all (which is 1000). Umm.. default is 100 (one hundred), i think. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Panic with RELENG_6_2 on DELL PE 4600 with PAE
Claus Guttesen wrote: Why would there be no space when I have 24GB of memory? 1. Any process, including the kernel can only allocate up to 4 GB of memory on a 32-bit system (since a 32-bit integer can only hold that many values) 2. The kernel is further constrained so the user programs can get enough memory 3. Kernel structures for tracking and using memory are also stored in kernel memory. 24 GB of memory with PAE probably eats up a lot of those. I think you'll need to increase kmem_size (see http://wiki.freebsd.org/ZFSTuningGuide for an example - ignore ZFS-specific things). It made no difference. Still the same error. Is anyone actually using PAE with FreeBSD 6.2? I have found practically no information using google. We are using it on very heavy loaded production web server. 8GB of ram, dual xeon with HT. FreebSD 6-STABLE. about 900 process running constantly in about 20 jails. No problems detected :) Planning to migrate to 7-CURRENT AMD64 within a month. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Quation about HZ kernel option
Craig Boston wrote: On Thu, Oct 04, 2007 at 02:32:39PM +0200, Oliver Fromme wrote: In that case, I would recommend not to override the default at all (which is 1000). ISTM that it would be better to use kern.hz=100 in this case. My reasoning is that a web server shouldn't be terribly sensitive to latency, so it's better to have longer quantums to get more work done without context switching overhead. If you're not using polling, you'll be getting interrupts for network traffic anyway. That what i personally thought. However 100 seems to be too rough. I just feel so, no reasoning behind this ;) Maybe 200-300 is better than 100 and better than 1000? I wonder how to build a test case for this to find best settings for web server, so others will not stuggle with this on the future. With polling on however, a high HZ value makes sense. polling does not make sense in case of webhosting though ;) -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Panic with RELENG_6_2 on DELL PE 4600 with PAE
Stephen Clark wrote: Artem Kuchin wrote: Claus Guttesen wrote: Why would there be no space when I have 24GB of memory? 1. Any process, including the kernel can only allocate up to 4 GB of memory on a 32-bit system (since a 32-bit integer can only hold that many values) 2. The kernel is further constrained so the user programs can get enough memory 3. Kernel structures for tracking and using memory are also stored in kernel memory. 24 GB of memory with PAE probably eats up a lot of those. I think you'll need to increase kmem_size (see http://wiki.freebsd.org/ZFSTuningGuide for an example - ignore ZFS-specific things). It made no difference. Still the same error. Is anyone actually using PAE with FreeBSD 6.2? I have found practically no information using google. We are using it on very heavy loaded production web server. 8GB of ram, dual xeon with HT. FreebSD 6-STABLE. about 900 process running constantly in about 20 jails. No problems detected :) Planning to migrate to 7-CURRENT AMD64 within a month. Hi Artem, Could you send me your kernel config file? I have tried the standard PAE config file with no luck. I'd be glad to do so, but when i send email to you i get [EMAIL PROTECTED]: 64.202.166.12 does not like recipient. Remote host said: 553 Dynamic pool 84.21.226.46. http://unblock.secureserver.net/?ip=84.21.226.* Giving up on 64.202.166.12. I have visited the link and made a request to unblock our smtp server but it hasn;t been done yet. So, i send it to stable list with attachments :) -- Artem OMNI2-PAE Description: Binary data OMNI2 Description: Binary data ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Quation about HZ kernel option
effect. I would not go under 100, though. I personally believe that a default of 1000 is ridiculously high, especially on a SMP system. Nuts! Everybody has his own opinion on this matter. Any idea how to actually build syntetic but close to real benchmark for this? For example: Usual web server does: 1) forks 2) reads a bunch of small files from disk for some time 3) forks some cgi scripts 4) dies If i write a test in C doing somthing like this and run very many of then is parallel for, say, 1 hour and then count how many interation have been done with HZ=100 and with HZ=1000 will it be a good test for this? -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Quation about HZ kernel option
Hello! What value of HZ option would you recommend for a hosting (web) server with a lot of processes (about 900) and polling off (as decided from previous discussion polling is useless in this situation). What parts of kernel does this option affect? What depends on it? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: device polling and weird timer interrupt count from vmstat
Nikos Vassiliadis wrote: On Monday 24 September 2007 20:58, Artem Kuchin wrote: What i don't understand is why timer rate on each cpu is 1995? I have set it to 1000, not 1995 or 2000. I have seen it showing 2000 on another box. So 1) why not 1000? DOUBLING I can only make assumptions about the doubling, and I don't want to. FreeBSD is not a RTOS and some milliseconds variation is understandable. 2) if it is supposed to be doubled (why?) when why not 2000? I can only make assumptions about the doubling, and I don't want to. FreeBSD is not a RTOS and some milliseconds variation is understandable. /DOUBLING 3) Is timer int really generated on each cpu? Apparently, why do you doubt it? Am i really wasting cpu time on ~4000 ints per second? You can lower it you know, if you feel that you are waisting that much resources. Ofcourse you'll break your traffic flow that way, since latency will increase. You seem very upset about it, are you sure you want to use polling(4)? it uses much more resources than interrupts. I am not upset about all this. But i want to understand why is it doubled. Because when i turn on polling i think that timer freq supposed to be just like i set HZ. However, actually, i am now thinking about another issue. I have dual CPU with HT. If i turn on HT (and it does help in my case) it shoud 2000 int x4 = 8000 ints per second. SO, i have saved 200 int/second from NIC and got myself 8000 ints/second from timer. Did i really win anything? I wish there were some good explanation on this. 4) does twe driver use polling? whay about twa? how to check it in the sources? Polling is only used on some network interface drivers. Polling(4) does not offer generic device-polling facilities. By the way, you know your post has an aggressive sense, don't you? Please don't do this when asking questions and want replies. Hmm.. Really? I didn't mean it, i was just trying to me as short and as technical as possible. Alright, i'll give a though on how to be more.. polite, i guess. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: device polling and weird timer interrupt count from vmstat
Nikos Vassiliadis wrote: On Tuesday 25 September 2007 12:13, Artem Kuchin wrote: I have dual CPU with HT. If i turn on HT (and it does help in my case) it shoud 2000 int x4 = 8000 ints per second. SO, i have saved 200 int/second from NIC and got myself 8000 ints/second from timer. This kind of load(200intrs/s) earns nothing from polling. Did i really win anything? I wish there were some good explanation on this. It would make a difference for let's say 8000 - 1 interrupts/sec. You should read polling(4). It explains a lot:) Yes, i have read the man for polling. However, it does not contain info on when it worth enabling. From this point of view it seems like if i have 8CPU server an a NIC with 8000 ints/sec when i enable polling with HZ=1000 i get about 30 ints/sec from NIC about 16000 ints from NIC So, we were at 8000 ints a second and now we are at 16000 ints/second. Is it worth in this case? It seems like enabling polling on really multi cpu computers never worth it. I think there is a mistake in my logic here. It just canot be like this. any thoughts? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: device polling and weird timer interrupt count from vmstat
3) Is timer int really generated on each cpu? Am i really wasting cpu time on ~4000 ints per second? 4000 ints per second is rather nothing on any modern CPU. Have a look at the top(1) display of an otherwise idle system. The %interrupt column should be zero, even if it's processing 4000 timer interrupts per second. As far as I know, the cpu timer interrupt handler is very light- weight. Thank you for the answer. My convern is that with 4 CPUs i get 8000 ints/second. While em generates only about 200 ints/second. As i undertand not all int handlers are the same. Some are heavy and some are light on CPU. So, the question is what is better (better=less CPU time): 8000 ints/sec from timer or 200 ints/sec from NIC? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: device polling and weird timer interrupt count from vmstat
Oliver Fromme wrote: Artem Kuchin wrote: Oliver Fromme wrote: Artem Kuchin wrote: 3) Is timer int really generated on each cpu? Am i really wasting cpu time on ~4000 ints per second? 4000 ints per second is rather nothing on any modern CPU. Have a look at the top(1) display of an otherwise idle system. The %interrupt column should be zero, even if it's processing 4000 timer interrupts per second. As far as I know, the cpu timer interrupt handler is very light- weight. Thank you for the answer. My convern is that with 4 CPUs i get 8000 ints/second. While em generates only about 200 ints/second. As i undertand not all int handlers are the same. Some are heavy and some are light on CPU. So, the question is what is better (better=less CPU time): 8000 ints/sec from timer or 200 ints/sec from NIC? There's no simple answer to the question. The best way is to just try it. As I wrote, run top(1) while the system is idle, so only the cpu timer interrupts are active. If the %interrupt column is zero most of the time, then there is nothing to worry about at all. However, if you have a constant non-zero %interrupt value, you might consider lowering HZ, and you might reconsider whether polling really has advantages in your situation. Do you have reasons to believe so? Remember that the main purpose of polling is to improve interactivity under very high network load. If you're not in such a situation, then polling probably doesn't buy you much. Well, problem with top is that on dual 3GHZ box it alsway s shows 0% load when not loaded with real traffic (web traffic) no matter if it is polling of int handling. And when loaded with real traffic web server eat a lot more cpu power then traffic handling, so, no separate measurement of traffic cpu load is possible. But i think it is possible to simulate this kind of load, need to think about it. Also, when it comes to public web server i can never be secure enough and crazy load of traffic can come any time from DDOS attack which can bring down any box. So, for public web server it is a matter of security and managebility to have server interactive even on high traffic load. So, even from this poing of view polling can be usefull. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
device polling and weird timer interrupt count from vmstat
Anyone any clue on this issue: Artem Kuchin wrote: I enabled device polling in the kernel, in nics and set HZ=1000. How, when i do omni2# vmstat -i i see interrupt total rate irq14: ata0 47 0 irq15: ata1 41 0 irq28: em0 2268 4 irq72: twe058380120 cpu0: timer 965994 1995 cpu3: timer1 0 cpu1: timer1 0 cpu2: timer 965857 1995 Total1992589 4116 (it is dual xeon with HT, HT disabled, that why cpu3 and cpu1 are zero). What i don't understand is why timer rate on each cpu is 1995? I have set it to 1000, not 1995 or 2000. I have seen it showing 2000 on another box. So 1) why not 1000? 2) if it is supposed to be doubled (why?) when why not 2000? 3) Is timer int really generated on each cpu? Am i really wasting cpu time on ~4000 ints per second? 4) does twe driver use polling? whay about twa? how to check it in the sources? ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
device polling and weird timer interrupt count from vmstat
I enabled device polling in the kernel, in nics and set HZ=1000. How, when i do omni2# vmstat -i i see interrupt total rate irq14: ata0 47 0 irq15: ata1 41 0 irq28: em0 2268 4 irq72: twe058380120 cpu0: timer 965994 1995 cpu3: timer1 0 cpu1: timer1 0 cpu2: timer 965857 1995 Total1992589 4116 (it is dual xeon with HT, HT disabled, that why cpu3 and cpu1 are zero). What i don't understand is why timer rate on each cpu is 1995? I have set it to 1000, not 1995 or 2000. I have seen it showing 2000 on another box. So 1) why not 1000? 2) if it is supposed to be doubled (why?) when why not 2000? 3) Is timer int really generated on each cpu? Am i really wasting cpu time on ~4000 ints per second? 4) does twe driver use polling? whay about twa? how to check it in the sources? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: A little story of failed raid5 (3ware 8000 series)
Martin Nilsson wrote: Artem Kuchin wrote: But i don't understand how and why it happened. ONly 6 hours ago (a night before) all those files were backed up fine w/o any read error. And now, right after replacing the driver and starting rebuild it said that there are bad sectors all over those file. How come? That is what patrol read is intended to detect before it is a problem. In a RAID5 array the checksums are only used when reconstructing data, if you have a bad block in a checksum sector it will not be detected until a drive have failed and you try to rebuild the array, unfortunately at that time it is too late... Beware that OS software solutions like diskcheckd will not find this as it only reads the data, not the checksums, it must be done on the controller. That exactly was i was talking about. I don't acess to individual disks behind raid unit, so, i cannot doit. I don't know it controller VERIFY command does it right. If it doesm then i shoudl put it into a cron job and do it on weekly basis. Also, it would halpfull it i could get access to number of left reserved sector for remapping. Any idea about these two for 3ware controllers? Also, someone should mention, that while using raid MUST do verifies often. -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: A little story of failed raid5 (3ware 8000 series)
Darren Pilgrim wrote: Artem Kuchin wrote: That exactly was i was talking about. I don't acess to individual disks behind raid unit, so, i cannot doit. I don't know it controller VERIFY command does it right. If it doesm then i shoudl put it into a cron job and do it on weekly basis. Also, it would halpfull it i could get access to number of left reserved sector for remapping. Any idea about these two for 3ware controllers? Also, someone should mention, that while using raid MUST do verifies often. The 3dm2 software (sysutils/3dm port) can dump the SMART data from individual disks. It can also schedule verify and self-test tasks and identify individual drives by blinking the activity light for the drive. ___ Problems are: 1) how to parse this dump of data? 2) No scheduling is available on 7000,8000 on 4 port models -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: A little story of failed raid5 (3ware 8000 series)
You can run smartmontools on disks behind 3ware controllers, eg /dev/twe0 -d 3ware,0 -a -o on -S on -m [EMAIL PROTECTED] /dev/twe0 -d 3ware,1 -a -o on -S on -m [EMAIL PROTECTED] did this: smartctl /dev/twe0 -d 3ware,1 -a for each driver on another server. Two driver are pretty old, the driver on port 2 is less than a month old. However, ALL of the drives have the same values for this 5 Reallocated_Sector_Ct 0x0033 100 100 036Pre-fail Always - 0 How come the number are the same? Even more, what does this 100 mean? 100% of backup sector space is free or just 100 sectors are available? How many total of them in there. Why does it say Pre-fail if it is WAY above the threshold? This data seems to be useless. Now, i did the same for the raid which failed and got me into so many trobles and has bad sectors now (some files are unredable): smartctl /dev/twe0 -d 3ware,0 -A 5 Reallocated_Sector_Ct 0x0033 100 100 036Pre-fail Always - 0 smartctl /dev/twe0 -d 3ware,1 -A 5 Reallocated_Sector_Ct 0x0033 100 100 036Pre-fail Always - 39 smartctl /dev/twe0 -d 3ware,2 -A 5 Reallocated_Sector_Ct 0x0033 100 100 036Pre-fail Always - 9 Now this is BS!!! Agaim accroding to SMART i shoud lookup at VALUE (100) and see if it is below THRES (36). If it is then i am in trouble. No, it does no work this way. Now, if we look at raw number we see 39 for disk1 and 9 for disk 2 For 39 disk1 also 198 Offline_Uncorrectable 0x0010 100 100 000Old_age Offline - 22 1 Raw_Read_Error_Rate 0x000f 058 055 006Pre-fail Always - 170185544 195 Hardware_ECC_Recovered 0x001a 058 055 000Old_age Always - 170185544 7 Seek_Error_Rate 0x000f 087 060 030Pre-fail Always - 524461066 Even for the newly inserted ( 24 hours ago, absulutelly new) driver: 7 Seek_Error_Rate 0x000f 069 060 030Pre-fail Always - 8525167 195 Hardware_ECC_Recovered 0x001a 069 066 000Old_age Always - 8433725 Now, as i undertand the main indication is Offline_Uncorrectable is raw value of it any more than 0 - REPLACE DRIVER ASAP (or maybe it is too late and it is replace driver asap as soon as Reallocated_Sector_Ct 0 ?) Now, what i don't understand is why Hardware_ECC_Recovered and Seek_Error_Rate are so hight. The first one is maybe relate to cabling problem. The driver are all in hot swap baskets of supermicro 2u case. Maybe backpanel is no so good? Seek_Error_Rate is a mistety for me. Any idea? -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
A little story of failed raid5 (3ware 8000 series)
Hello! Here is the newest story of mine about how one should never use raid5. Controller is 8xxx-4LP. I have a simple 360GB raid5 with 4 drives since 2004. Only about a year ago i realized how much speed i have wasted be saving lousy 120GB. I should have choosen bigger driver and setup two mirrors instead. But that's no the point. A week ago one driver just totally failed. It fell out of the unit and when i tried to rebuild the unit it failed. It seemed like the driver electronis failed. ANyhow, i have found newest 160gb seagate driver for replacement (twice as thin, very nicely done electornics on it). A day ago at 11 am i have turn off the server, pull out the old driver, installed a new one, turned of the server and started rebuild in an hour from remote location via web interface. After about 5 minuted the machine became unresponsive. Tried rebooting - nothing. I went to the machine and fingure out, that rebuild failed (0%) and some data cannot be read because of bad sectors. Well, hell, i thoght. Maybe i could tell teh controller to ignore all the errors and just some rebuilding and the figure out which driver failed, replace it, rebuild again and restore corrupted data from backup. Noway, controller said. - i cannot make it ignore read errors - i cannot figure out which driver has bad sectors (maybe someone know it?) But i don't understand how and why it happened. ONly 6 hours ago (a night before) all those files were backed up fine w/o any read error. And now, right after replacing the driver and starting rebuild it said that there are bad sectors all over those file. How come? Well. Since we have a buch of full and inceremnetal paraoid backups no data was lost and we are in process of recovering. However, i simply imaged what would happed if one more driver completelly failed. That would mean that we have lost all data, since any of the disk which left do not contain any readable copy of one data (unlink mirror, for example). So, we are migrating to mirror config with huge disks. I am thinking about raid10 for more perfomance. It seems a lot more safe, since if any pair of disks failed the data is still readable and even if all disks have bad block the data can be easily recovered by fairly simply script from the couterpart. But the problem, however, So, no raid5 or even raid 6 for me any more. Never! -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: A little story of failed raid5 (3ware 8000 series)
David Schwartz wrote: A day ago at 11 am i have turn off the server, pull out the old driver, installed a new one, turned of the server and started rebuild in an hour from remote location via web interface. After about 5 minuted the machine became unresponsive. Tried rebooting - nothing. I went to the machine and fingure out, that rebuild failed (0%) and some data cannot be read because of bad sectors. Why would you power cycle a RAID 5 array with a failed drive? That's like the biggest no-no that there is. When you lose a drive on a RAID 5 array, you are vulnerable until a replacement drive is configured and the array is rebuilt. Any high risk operations during that time would be foolhardy. Um.. it is because i did not have a map of hot swap baskets to conroller ports and i needed to check every driver basket to understand which port it sits on. I have no choise, i think. So, no raid5 or even raid 6 for me any more. Never! Since RAID6 would have saved you from what presumably was a drive failure before a rebuild could be done, it's hard to understand why you would say this is a reason to avoid RAID 6. Perhaps you would do better to understand your failure and avoid the causes of the failure rather than avoiding the things you happened to be using at the time of the failure. If you get food poisoning while wearing a blue shirt, the solution is not to avoid blue shirts in the future. Read the post before. I still don't known which driver has the bad sectors. And it is very posible that EACH driver has them. RAID6 would not help then. -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
panic after removing usb flash disk
Hello! I don't know if it really belongs to this list, since i have only tested on 7-CURRENT, but on the other hand 7-CURRENT is soon going to be stable. So here it goes: 1) insert usb flash disk 2) usbd detected it 3) mount it (mount -t msdosfs /dev/da1s1 /mnt) 4) simply pull the pen drive off the usb slot 5) /mnt mount pount is left 6) try to unmount it (umount /dev) I don't know to get all those kernel bright white messages in to a file, so i just attached a screenshot ;) -- Regards Artem___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
How stable is 7 now? How to cvs it?
Hello! I have heard that 7 is very stable since november and much better (perfomance wise since GIANT lock have been deleted completely) since that time. Is it true? Also, how to cvsup the sources? I tried RELENG_7 and HEAD tags and no sources and docs fetched at all. Which is the correct tag? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
twa is giant locked in 7-Current or everywhere?
Hi! When i installed twas driver on 6.2-STABLE it said [FAST] i presumed that it measn that twa is giant-lock free. Now, after installing 7-CURRENT i see Aug 15 17:00:02 omni3 kernel: 3ware device driver for 9000 series storage controllers, version: 3.70.03.007 Aug 15 17:00:02 omni3 kernel: twa0: 3ware 9000 series Storage Controller port 0x3000-0x30ff mem 0x8800-0x89ff,0x8a20-0x8a200fff irq 16 at devic Aug 15 17:00:02 omni3 kernel: twa0: [GIANT-LOCKED] Aug 15 17:00:02 omni3 kernel: twa0: [ITHREAD] So, it says GIANT-LOCKED and then ITHREAD. Apparently, i have no real understaning what those words mean. COuld anyone explain the meaning of FAST ITHREAD Giant-locked is self explanatory and.. bad. Thank you. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: When inode change time changes?
Oliver Fromme wrote: Artem Kuchin [EMAIL PROTECTED] wrote: I use gtar (gtar because it has incremental backups, and tar does not) You _can_ use BSD tar for incremental backups. I do that every day. Yes, but that's not real incremental backup because if you restore data you'll get a bunch of files that were deleted along the way. gtar stores full file list and actually deleted the deleted files when restoring. And i have excessively many of such created and deleted files and i need only current ones. So tar is of no use for me. Also, i use inode time because i only need files which really have been changed. For example, i you restore a file from a month ago it will have a date which is a month ago. Then that backup is destroyed but this file would not be backed up because the date is too much in the past. So, we loose the file. If i used inode change time the file will be backup in any case. However, some stupid programs like mysql or qmail seem to touch files so, for example, all mail message and databases are backed up every time. And this sucks. So, when backing up these files i need to use file modification time and it is suitable here, since these file are never managed by human, only by daemon and old file eather go away (like in email) or change its mod time (like in mysql). What is still do not understand is what time gtar uses for --newer option. Man page says: --newer dateOnly store files with creation time newer than date. This is simply not true. NOT creation time defenetly. It is either modification time or inode change time. Which one? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
When inode change time changes?
I am having tough time with backup system. I use gtar (gtar because it has incremental backups, and tar does not) I use inode change time in order to backup all changed files. I have notices that some files are always backed up even if they did not change. For example all mysql database. I checked their file change time and it is not changed, howeever, inode change time changes on every mysql restart. Maybe someone can englighten me when inode change time changes? What must be done with file to change it (except writing to it)? I tried chmoding - it does not affect inode time. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
question about gtar and --newer
man gtar states: --newer dateOnly store files with creation time newer than date. Is it totally wrong and gtar really uses inode change time (like tar) or gtar does no take inode change time into account at all? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Broken locale after upgrade to 6-STABEL from 5-STABLE
Stanislaw Halik wrote: On Thu, May 24, 2007, Artem Kuchin wrote: What i don't understand, is how the appropriate 'so' is selected? How freebsd known which so to load this libc.so.5 or this libc.so.6 ? Did you recompile Perl after the last installworld? If not, do so. No i did not do it explicitelly. However, i think buildworl should do it, or it is not a part of the world anymore? Also, why C code does not work anyway? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Broken locale after upgrade to 6-STABEL from 5-STABLE
KAYVEN RIESE wrote: On Thu, 24 May 2007, Artem Kuchin wrote: /lib/libc.so.5 I chflaged it, deleted it and made a link to libc.so.6 this guy sounds familiar. i am really hosed right now, i can't run a browser simultaneously, maybe i am being really stupid, but what do you mean when you say you chflaged it? an explicit unix command line dingy is the sort of thing that makes me happy. well, this is is system imutable and cannoy be deleted so chflag nosunlnk libc.so.5 chflag noschg libc.so.5 do the trick and after that file can be deleted -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Broken locale after upgrade to 6-STABEL from 5-STABLE
Karol Kwiatkowski wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA256 Artem Kuchin wrote: Stanislaw Halik wrote: On Thu, May 24, 2007, Artem Kuchin wrote: What i don't understand, is how the appropriate 'so' is selected? How freebsd known which so to load this libc.so.5 or this libc.so.6 ? Did you recompile Perl after the last installworld? If not, do so. No i did not do it explicitelly. However, i think buildworl should do it, or it is not a part of the world anymore? It's not, for quite some time now: http://lists.freebsd.org/pipermail/freebsd-announce/2002-May/000823.html Ahh, well, i just forgot. Of course it is not for a long time now. But anyhow, why locale in C does not work? And how 'so' lib is selected for an executable? How OS selected so.5 or so.6 for a executable file? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Broken locale after upgrade to 6-STABEL from 5-STABLE
Karol Kwiatkowski wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA256 Artem Kuchin wrote: Karol Kwiatkowski wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA256 Artem Kuchin wrote: Stanislaw Halik wrote: On Thu, May 24, 2007, Artem Kuchin wrote: What i don't understand, is how the appropriate 'so' is selected? How freebsd known which so to load this libc.so.5 or this libc.so.6 [...snip...] But anyhow, why locale in C does not work? And how 'so' lib is selected for an executable? How OS selected so.5 or so.6 for a executable file? My understanding is, it is hardcoded into the executable during compilation/linking time. You can check linked libraries with ldd(1) command: $ ldd `which perl` /usr/bin/perl: libperl.so = /usr/local/lib/perl5/5.8.8/mach/CORE/libperl.so (0x2807c000) libm.so.5 = /lib/libm.so.5 (0x28192000) libcrypt.so.4 = /lib/libcrypt.so.4 (0x281a7000) libutil.so.7 = /lib/libutil.so.7 (0x281c) libc.so.7 = /lib/libc.so.7 (0x281cd000) Oh, hell... I just realized that i need to rebuild EVERYTHING in EVERY jail after this upgrade from 5 to 6. Even if something seem to work it does not mean it will not fail in some rare case. Still, does not explain why freshly compile locale test in C does not work. Weird. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
How to test locale in C? All my tests fail.
Maybe it is the wrong list, but maybe someone can quickly help me out. I have a very stupid problem. I cannot convert to upper or lower case using manually set locale (setlocale(..)). A very simple program: #include locale.h #include errno.h #include ctype.h main(){ char *b=setlocale(LC_CTYPE, ru_RU.CP1251); if (!b){ printf(FAILED! %d\n,errno); } else { printf(OK: %s %d\n,b,errno); printf(IS UPPER й: %d\n,isupper('й')); printf(IS UPPER Й: %d\n,isupper('Й')); printf(IS LOWER й: %d\n,islower('й')); printf(IS LOWER Й: %d\n,islower('Й')); printf(LOCALE %s\n,setlocale(LC_CTYPE,NULL)); printf(1: TO UPPER %c TO LOWER %c\n,toupper('ж'),tolower('Ж')); printf(1-0: TO UPPER %c TO LOWER %c\n,toupper('Я'),tolower('я')); printf(2: TO UPPER %c TO LOWER %c\n,toupper('r'),tolower('R')); } } Output is always: OK: ru_RU.CP1251 0 IS UPPER й: 0 IS UPPER Й: 0 IS LOWER й: 0 IS LOWER Й: 0 LOCALE ru_RU.CP1251 1: TO UPPER ж TO LOWER Ж 1-0: TO UPPER Я TO LOWER я 2: TO UPPER R TO LOWER r й,ж,я - is lower case leters and Й,Ж,Я - is upper case As you see, it simply does not work at all. It seems like the locale is C but as you see setlocale returned ru_RU.CP1251 tested on 6.2, 5.4 and 4.10 - all the same. What am i doing wrong? (except posting in the wrong list ;) -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: How to test locale in C? All my tests fail.
Massimo Fusaro wrote: From the setlocale(3) manual page: ... A locale argument of NULL causes setlocale() to return the current locale. ... Right. that why i first call setlocale(LC_CTYPE, ru_RU.CP1251); to set locale and the call setlocale(LC_CTYPE,NULL); to check what locale is currently set. I tried without call setlocale(LC_CTYPE,NULL); - no difference. -- Regards, Artem -- -max 2007/5/24, Artem Kuchin [EMAIL PROTECTED]: Maybe it is the wrong list, but maybe someone can quickly help me out. I have a very stupid problem. I cannot convert to upper or lower case using manually set locale (setlocale(..)). A very simple program: #include locale.h #include errno.h #include ctype.h main(){ char *b=setlocale(LC_CTYPE, ru_RU.CP1251); if (!b){ printf(FAILED! %d\n,errno); } else { printf(OK: %s %d\n,b,errno); printf(IS UPPER й: %d\n,isupper('й')); printf(IS UPPER Й: %d\n,isupper('Й')); printf(IS LOWER й: %d\n,islower('й')); printf(IS LOWER Й: %d\n,islower('Й')); printf(LOCALE %s\n,setlocale(LC_CTYPE,NULL)); printf(1: TO UPPER %c TO LOWER %c\n,toupper('ж'),tolower('Ж')); printf(1-0: TO UPPER %c TO LOWER %c\n,toupper('Я'),tolower('я')); printf(2: TO UPPER %c TO LOWER %c\n,toupper('r'),tolower('R')); } } Output is always: OK: ru_RU.CP1251 0 IS UPPER й: 0 IS UPPER Й: 0 IS LOWER й: 0 IS LOWER Й: 0 LOCALE ru_RU.CP1251 1: TO UPPER ж TO LOWER Ж 1-0: TO UPPER Я TO LOWER я 2: TO UPPER R TO LOWER r й,ж,я - is lower case leters and Й,Ж,Я - is upper case As you see, it simply does not work at all. It seems like the locale is C but as you see setlocale returned ru_RU.CP1251 tested on 6.2, 5.4 and 4.10 - all the same. What am i doing wrong? (except posting in the wrong list ;) -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED] ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED] ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: How to test locale in C? All my tests fail.
Oliver Fromme wrote: Artem Kuchin wrote: I have a very stupid problem. I cannot convert to upper or lower case using manually set locale (setlocale(..)). A very simple program: [...] printf(IS UPPER ?: %d\n,isupper('?')); printf(IS UPPER ?: %d\n,isupper('?')); printf(IS LOWER ?: %d\n,islower('?')); That's a common pitfall. Chars are signed by default on FreeBSD, and the isupper() etc. function take an int type argument. That means that characters = 128 end up as negative numbers, so they fail all isupper() and islower() checks, and toupper()/tolower() don't touch them at all. The solution is to typecast the constants to unsigned char explicitly, like this: isupper((unsigned char) '?') etc. Your program will work fine then. My stupid. I should've noticed that. Thank you very much! Issue closed. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Broken locale after upgrade to 6-STABEL from 5-STABLE
Recently i figured out that all locales stopped working properly on some of my 6-STABLE servers and in all jails on them. These server diffeer from others (on which locale work) in that they were upgraded to 6-STABLE directly from 5.3-STABLE. Test was easy: #!/usr/bin/perl use POSIX qw(locale_h); use locale; setlocale(LC_ALL, 'ru_RU.CP1251') || warn LOCALE: $!\n; print lc(РУЧКАручкаABCabc\n).\n; (the string is partially in RUssia, so you might not be able to see correctly, but that is not the point). After an hour of figuring out why it does not work i figureed that it was because of /lib/libc.so.5 I chflaged it, deleted it and made a link to libc.so.6 After that setlocale in perl worked fine. However, on another server, where setlocale worked and works fine this libc.so.5 also present and causes no problems. What i don't understand, is how the appropriate 'so' is selected? How freebsd known which so to load this libc.so.5 or this libc.so.6 ? where it is specified? Another question, is why setlocale in C says that locale is set fine. A simple proggie: #include locale.h #include errno.h #include ctype.h main(){ char *b=setlocale(LC_ALL, ru_RU.CP1251); if (!b){ printf(FAILED! %d\n,errno); } else { printf(OK: %s %d\n,b,errno); printf(LOCALE %s\n,setlocale(LC_CTYPE,NULL)); printf(1: TO UPPER %c TO LOWER %c\n,toupper('я'),tolower('Я')); printf(1-0: TO UPPER %c TO LOWER %c\n,toupper('Я'),tolower('я')); printf(2: TO UPPER %c TO LOWER %c\n,toupper('r'),tolower('R')); } } Does not work even when locales work on perl (toupper does not return an upper letter for russia, but works with latin r, same with tolower). Am i missing something? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Top not showing 4 cpus on 2 xeons with HT
I am just wondering if it is normal. I have two xeon processors with HT on each of them. When loading kernel says that 4 cpu's are found, but when i do top i can see only 0 or 2 in the C column. never 1 or 3. Is it normal? FreeBSD 6.2-STABLE (cvsed 1 day ago) -- Regards. Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
GIANT LOCKED raid driver
We use 3ware cards (twe driver) on most of our server. While it is a very good raid controller it's driver is still GIANT LOCKED and i think this reduces perfomance of the server (they do a lot of disk io). Does anyone know a good raid controller (raid-5 not really needed, mirror is enough) whose driver is not giant locked? Or maybe i worry for nothing and this giant locked issue is not really affecting perfomance (we are talking 2 real CPUs configuration and sometimes 2 real + 2 logical (HT)). -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Top not showing 4 cpus on 2 xeons with HT
Richard Tector wrote: Artem Kuchin wrote: I am just wondering if it is normal. I have two xeon processors with HT on each of them. When loading kernel says that 4 cpu's are found, but when i do top i can see only 0 or 2 in the C column. never 1 or 3. Is it normal? FreeBSD 6.2-STABLE (cvsed 1 day ago) If I remember correctly, HT is disabled by default for security reasons but there should be a sysctl to enable it. I believe there is also a paper by Colin Percival on the issue. ahh, heck, i'll take my chances. I've read the paper and the attack seem to me almost unreal. Also, everybody is in the jail on the server. Note that in a lot of common loads, the use of HT with the standard scheduler does not yield any real benefits. Hmm. I just turned it on and already see that hosts are running generally faster (it is a hosting server, 100+ site). No numbers though. It just *SEEMS* faster. Anyway, it cannot make thing slower for sure, or can it? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 6.2-RELEASE does not use second CPU on pentium D
John Baldwin wrote: On Wednesday 25 April 2007 04:47:48 am Alex Povolotsky wrote: Hello! I have a Pentium D box, running 6.2-RELEASE. In dmesg, I see CPU#1 launched, but I never see any process running on it, and mptable shows Hmm. I am running PentiumD 3.0 Ghz on Asus p5p800-vm motherboard. Needed to update BIOS to make CPU work correctly. Also, i am not running RELEASE. I run 6.2-STABLE cvsupped regulary. I have no problem like that, top shows 0 and 1 in C column for different processes. So,I'd simply recomment to cvs and rebuild the kernel and update your MB BIOS to the latest. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: PAE does not give any ram increase, why?
the number do not change with or without PAE Maybe i look in the wrong place? I'm not going to waste my time explaining for the hundredth time how the x86 memory layout works. If you want to recover the missing 256MB, go look in your BIOS for an option about memory hole remapping. No need, i know this stuff. Problem is that asus p5p800-vm bios does not have such option (no memory remapping support in chipset) , so, and simply assumed that in PAE mode this simply does not matter and it will give me whole 4GB. Isn't it so? Is it true for 64bit mode (amd64)? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
PAE does not give any ram increase, why?
Hello! I've upgraded one of my servers today. Now it is Asus P5p800-VM Pentium D 3.0Ghz 4GB RAM (4x1 GB) 3WARE raid5 FreebSD 6.2 cvsed today compiled from sources. after that i decided to try PAE. It runs just fine but when i compare available memory with and without pae i do not see any difference. At kernel boot with PAE it says: pr 21 18:01:30 osiris kernel: ACPI APIC Table: A M I OEMAPIC Apr 21 18:01:30 osiris kernel: Timecounter i8254 frequency 1193182 Hz quality 0 Apr 21 18:01:30 osiris kernel: CPU: Intel(R) Pentium(R) D CPU 3.00GHz (3000.33-MHz 686-class CPU) Apr 21 18:01:30 osiris kernel: Origin = GenuineIntel Id = 0xf64 Stepping = 4 Apr 21 18:01:30 osiris kernel: Features=0xbfebfbffFPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2 Apr 21 18:01:30 osiris kernel: Features2=0xe49dSSE3,RSVD2,MON,DS_CPL,EST,CNTX-ID,CX16,b14,b15 Apr 21 18:01:30 osiris kernel: AMD Features=0x2000LM Apr 21 18:01:30 osiris kernel: AMD Features2=0x1LAHF Apr 21 18:01:30 osiris kernel: Cores per package: 2 Apr 21 18:01:30 osiris kernel: real memory = 4017881088 (3831 MB) Apr 21 18:01:30 osiris kernel: avail memory = 3933429760 (3751 MB) The real and avail memory sizes are the same w/o PAE. Then i do sysctl -a | grep hw | grep mem and i always see hw.physmem: 4012244992 hw.usermem: 3861307392 hw.realmem: 4017881088 hw.pci.host_mem_start: 2147483648 the number do not change with or without PAE Maybe i look in the wrong place? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: PAE does not give any ram increase, why?
Martin Nilsson wrote: Artem Kuchin wrote: Apr 21 18:01:30 osiris kernel: CPU: Intel(R) Pentium(R) D CPU 3.00GHz (3000.33-MHz 686-class CPU) Why bother with PAE on a CPU that is 64-bit capable and can run the amd64 version of FreeBSD 6.2? Do you know a RELIABLE way to migrade a production server with a bunch of jails and a dozen of webserver from x86 to amd64 without going into full system reinstall from scratch? If yes, then, please, give the procedure and will do it. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: PAE does not give any ram increase, why?
Andrew Pantyukhin wrote: On 4/21/07, Artem Kuchin [EMAIL PROTECTED] wrote: Hello! I've upgraded one of my servers today. Now it is Asus P5p800-VM Pentium D 3.0Ghz 4GB RAM (4x1 GB) 3WARE raid5 FreebSD 6.2 cvsed today compiled from sources. after that i decided to try PAE. It runs just fine but when i compare available memory with and without pae i do not see any difference. At kernel boot with PAE it says: pr 21 18:01:30 osiris kernel: ACPI APIC Table: A M I OEMAPIC Apr 21 18:01:30 osiris kernel: Timecounter i8254 frequency 1193182 Hz quality 0 Apr 21 18:01:30 osiris kernel: CPU: Intel(R) Pentium(R) D CPU 3.00GHz (3000.33-MHz 686-class CPU) Apr 21 18:01:30 osiris kernel: Origin = GenuineIntel Id = 0xf64 Stepping = 4 Apr 21 18:01:30 osiris kernel: Features=0xbfebfbffFPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2 Apr 21 18:01:30 osiris kernel: Features2=0xe49dSSE3,RSVD2,MON,DS_CPL,EST,CNTX-ID,CX16,b14,b15 Apr 21 18:01:30 osiris kernel: AMD Features=0x2000LM Apr 21 18:01:30 osiris kernel: AMD Features2=0x1LAHF Apr 21 18:01:30 osiris kernel: Cores per package: 2 Apr 21 18:01:30 osiris kernel: real memory = 4017881088 (3831 MB) Apr 21 18:01:30 osiris kernel: avail memory = 3933429760 (3751 MB) The real and avail memory sizes are the same w/o PAE. Then i do sysctl -a | grep hw | grep mem and i always see hw.physmem: 4012244992 hw.usermem: 3861307392 hw.realmem: 4017881088 hw.pci.host_mem_start: 2147483648 the number do not change with or without PAE Maybe i look in the wrong place? What number do you expect to see? 8Gb? I expect to see DIFFERENCE (in particular INCREASE) in amount of memory with PAE comparing to kernel w/o PAE. And 4 GB = 1024*4 MB = 1024*1024*4 KB = = 1024*1024*1024*4=4294967296 So, where is my 277086208 bytes? (ieven is built-in video eats 128MB for AGP aperture then still whene is my another almost 120MB?) -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Migrating from x86 (32) to amd64
About one year ago, I was able to do the regular procedure after enabling i386 compat. It was just another make world for me. options COMPAT_IA32 This is interesting. I have setup and amd64 box with this option enabled. And i am sure i have to leave foreve, since some client have their binaries w/o sources and they need to run anyway. The quesiton, does this option have any perfomance impact? -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Migrating from x86 (32) to amd64
Maybe someone could help me. I have a machine with 4GB of RAM 128MB of which is wasted and i really need 2 gigs more. This is a heavy duty production server with a lot of jails and custom scripts, etc.. and i am afraid i cannot reinstall all from scratch. Furthermore it is located in the data center away from the office and i simply cannot spend whoel day there, but 2-4 hours would be ok. Currentlyt it is 5.4-STABLE (i386, 32bit architecture) Is there way to more or less sefely migrade to AMD64 arhitecture via csup and source build? Any recomendations? -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Canonical 4.x to 6.x upgrade docs?
Has anyone succeeded in doing a 4.x - 6.x upgrade from source without upgrading first to 5.x as an intermediate step? tried twice - did not work, but going to 5 and then to 6 was not a problem. But i suspect than going from older 4.x to newer 5.x (like 5.4) might not work and it might need another round of upgrade lile 4.x - 5.1 - 5.4 - 6.2 I don't kwow for sure. -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Canonical 4.x to 6.x upgrade docs?
What's the basis for your suspicion? My memory might play tricks on me, but i think I remember that i tried to upgrade from 4.1 to 5.3 longtime ago and it did not work. I had to up to 5.0 and the to 5.3. But that might be just some weird client install (i did not install freebsd on that box originally). The world just did not compile. I canot provide any more detail on that, sorry. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Migrating from x86 (32) to amd64
Is there way to more or less sefely migrade to AMD64 arhitecture via csup and source build? AFAIK nobody has lived to tell the tale (or at least I didn't see any followups from people who claimed they'd try it). In any case it would be better to migrate it via binary reinstall (the same as installing from scratch, using the boot CD...). Damn it. Then i guess i need to do some experimenting myself. Theoretically, what would be the procedure? Any recomendations? Try using PAE, but read up on possible problems. No, just not PAE. Tried it on 6.2, felt all the pain, cried outloud and went back to simple plain 32 bit. As it has been told - PAE IS AN UGLY HACK. -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Migrating from x86 (32) to amd64
Is there way to more or less sefely migrade to AMD64 arhitecture via csup and source build? ... Damn it. Then i guess i need to do some experimenting myself. Definitely. Theoretically, what would be the procedure? 1) Backup system. 2) Download amd64 install ISO and burn to CD 3) Boot from CD 4) Follow instructions for fresh install 5) Restore/merge configuration from backups. If you have a spare amd64 system and most of the content is static, you could reduce downtime by doing steps 4 thru 5 on the second system and either swapping the disk(s) or the entire system. no, that's no what i ment. I mean the procedure to source build/install amd64 on x86 and make it work. Just theoretically, -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
Yep. It should look something like this output, from my dual-core Opteron running Linux 2.6.19-ck2: BYTE UNIX Benchmarks (Version 4.1-wht.1) System -- Linux daydream 2.6.19-ck2 #5 SMP PREEMPT Sat Jan 20 12:23:54 EST 2007 i686 athlon-4 i386 GNU/Linux /dev/mapper/vg-u2 10321208 6610764 3710444 65% /u2 Start Benchmark Run: Wed Mar 7 01:34:36 EST 2007 01:34:36 up 53 min, 3 users, load average: 0.24, 0.18, 0.14 End Benchmark Run: Wed Mar 7 01:45:33 EST 2007 01:45:33 up 1:04, 3 users, load average: 12.80, 5.64, 2.63 = FINAL SCORE 254.1 Here is mine retested and patched to work on AMD64 (Pentium D 3.4Ghz) BYTE UNIX Benchmarks (Version 4.1.0) System -- aaa.itlegion.ru Start Benchmark Run: Wed Mar 7 14:03:27 MSK 2007 1 interactive users. 2:03PM up 6 mins, 1 user, load averages: 0.00, 0.09, 0.06 -r-xr-xr-x 1 root wheel 131328 Mar 5 23:55 /bin/sh /bin/sh: ELF 64-bit LSB executable, AMD x86-64, version 1 (FreeBSD), dynamically linked (uses shared libs), stripped /dev/ar0s1e 289385582 2746558 263488178 1%/usr Dhrystone 2 using register variables 10486183.3 lps (10.1 secs, 10 samples) Double-Precision Whetstone 1289.1 MWIPS (10.7 secs, 10 samples) System Call Overhead 494962.3 lps (10.1 secs, 10 samples) Pipe Throughput 603048.3 lps (10.1 secs, 10 samples) Pipe-based Context Switching 34302.9 lps (12.8 secs, 10 samples) Process Creation 3011.8 lps (38.6 secs, 3 samples) Execl Throughput 1229.4 lps (30.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks467804.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 109705.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks109313.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 126505.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 86216.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 50229.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks1399150.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks67555.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 64288.0 KBps (30.0 secs, 3 samples) Shell Scripts (1 concurrent) 3222.7 lpm (62.7 secs, 3 samples) Shell Scripts (8 concurrent)579.8 lpm (60.2 secs, 3 samples) Shell Scripts (16 concurrent) 293.5 lpm (60.1 secs, 3 samples) Arithmetic Test (type = short) 891421.9 lps (10.1 secs, 3 samples) Arithmetic Test (type = int) 951512.1 lps (10.1 secs, 3 samples) Arithmetic Test (type = long)298204.3 lps (10.2 secs, 3 samples) Arithmetic Test (type = float) 1033235.9 lps (10.1 secs, 3 samples) Arithmetic Test (type = double) 516114.2 lps (10.1 secs, 3 samples) Arithoh 17357328.1 lps (10.2 secs, 3 samples) C Compiler Throughput 1801.4 lpm (61.4 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 73671.7 lpm (37.9 secs, 3 samples) Recursion Test--Tower of Hanoi 142907.4 lps (20.3 secs, 3 samples) INDEX VALUES TESTBASELINE RESULT INDEX Dhrystone 2 using register variables116700.0 10486183.3 898.6 Double-Precision Whetstone 55.0 1289.1 234.4 Execl Throughput43.0 1229.4 285.9 File Copy 1024 bufsize 2000 maxblocks 3960.0 109313.0 276.0 File Copy 256 bufsize 500 maxblocks 1655.050229.0 303.5 File Copy 4096 bufsize 8000 maxblocks 5800.064288.0 110.8 Pipe Throughput 12440.0 603048.3 484.8 Pipe-based Context Switching 4000.034302.9 85.8 Process Creation 126.0 3011.8 239.0 Shell Scripts (8 concurrent) 6.0 579.8 966.3 System Call Overhead 15000.0 494962.3 330.0 = FINAL SCORE 300.0 As you see, baselines a TOTALLY diffrent, this sucks. I trying to install Debian today w no luck. CD=ROM just will not boot. I'll try to install CentOS x32-AMD64 on friday and try to compile the source code of unixbench from freebsd port to get the same baselines. -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
Hmm. what kind of HDD, RAID or whatever are you using? My raid pretty much sucks. It is build it on the intel motherboard LSI Megaraid. But i still get 81Mb/sec when doing dd if=/dev/ar0 of=/dev/null bs=1M How much do you get on this? -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
Artem Kuchin wrote: Hmm. what kind of HDD, RAID or whatever are you using? My raid pretty much sucks. It is build it on the intel motherboard LSI Megaraid. But i still get 81Mb/sec when doing dd if=/dev/ar0 of=/dev/null bs=1M How much do you get on this? geom_mirror on 2 desktop SATA drives, but the results of dd are pretty low: # dd if=/dev/mirror/data of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 17.817686 secs (58850290 bytes/sec) As you can see, results with a single drive are better: # dd if=/dev/ad4 of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 16.219518 secs (64649023 bytes/sec) Now i am lost. i get 81MB/sec on dd but still you get File Copy 1024 bufsize 2000 maxblocks 3960.0 159513.0 402.8 and i get File Copy 1024 bufsize 2000 maxblocks 3960.0 109313.0 276.0 The drives i use are Seagate 7200.10 (320Gb, SATA II, 16MB cache with perpendicular heads) How is it possible that you get 2x file copy perfomance ? What's the matter?! -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
- Original Message - From: Charles Shannon Hendrix [EMAIL PROTECTED] To: freebsd-stable@freebsd.org Sent: Wednesday, March 07, 2007 9:49 PM Subject: Re: Some Unix benchmarks for those who are interesed On Wed, 07 Mar 2007 17:30:12 +0100 Ivan Voras [EMAIL PROTECTED] wrote: Charles Shannon Hendrix wrote: On Wed, 07 Mar 2007 17:11:24 +0100 Ivan Voras [EMAIL PROTECTED] wrote: Charles Shannon Hendrix wrote: BYTE UNIX Benchmarks (Version 4.1-wht.1) Off-topic: Who or what is the origin of the wht version? One of the nice things about unixbench is that it hadn't changed from 1997, but now most Linux variants use the -wht version that has completely different baselines and results from the normal version? It's a version created for the website: webhostingtalk.com. It was created to have a stable and standard benchmark. Beautiful - they fiddled with the baselines but still managed not to see the obvious problem in execl() call in the execl benchmark for 64-bit platform. Or maybe they just don't care? It seems to me they use the software a lot and it serves their purposes. It's just a standardized version and run script that they use to evaluate web servers. Hmm. if the whole world uses wht version of unixbench maybe someone should update freebsd ports version to this wht version, because otherwise we cannot compare anything else than freebsd. Not good. -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
- Original Message - From: Torfinn Ingolfsen [EMAIL PROTECTED] To: freebsd-stable@freebsd.org Sent: Wednesday, March 07, 2007 10:57 PM Subject: Re: Some Unix benchmarks for those who are interesed On Wed, 07 Mar 2007 22:32:36 +0300 Artem Kuchin [EMAIL PROTECTED] wrote: Hmm. if the whole world uses wht version of unixbench maybe someone should update freebsd ports version to this wht version, because otherwise we cannot compare anything else than freebsd. Not good. Does it really matter? Benchmarks are like statistics; if you don't find one that fits your purpose, you just tweak / change an existing one until you get the results you want. Not agreed. Benchmarks is a mean of comparing thing for figure out what is best for you or where is area with problems. If baselines are different then you cannot compare and then you cannot choose or determine problematic area and cannon improve what you already have. just my 0.02 russian federation roubles :) -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
- Original Message - From: Fluffles [EMAIL PROTECTED] To: Artem Kuchin [EMAIL PROTECTED] Sent: Wednesday, March 07, 2007 11:35 PM Subject: Re: Some Unix benchmarks for those who are interesed Artem Kuchin wrote: Artem Kuchin wrote: Hmm. what kind of HDD, RAID or whatever are you using? My raid pretty much sucks. It is build it on the intel motherboard LSI Megaraid. But i still get 81Mb/sec when doing dd if=/dev/ar0 of=/dev/null bs=1M How much do you get on this? geom_mirror on 2 desktop SATA drives, but the results of dd are pretty low: # dd if=/dev/mirror/data of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 17.817686 secs (58850290 bytes/sec) As you can see, results with a single drive are better: # dd if=/dev/ad4 of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 16.219518 secs (64649023 bytes/sec) How is it possible that you get 2x file copy perfomance ? What's the matter?! If you use dd on the raw device (meaning no UFS/VFS) there is no read-ahead. This means that the following DD-command will give lower STR read than the second: no read-ahead: dd if=/dev/mirror/data of=/dev/null bs=1m count=1000 read-ahead and multiple I/O queue depth: dd if=/mounted/mirror/volume of=/dev/null bs=1m count=1000 You can test read STR best with bonnie (see /usr/ports/benchmarks/bonnie); or just with DD on a mounted volume. You should mount with -o noatime to avoid useless writes during reading, or use soft updates to prevent meta data from taking it's toll on I/O performance. Totall disagree. On the following reasons: 1) Read ahead is simply useless when stream-reading (sequential) 1GB of data 2) atime is NOT updated when using dd on any device, atime is related to file/inode operations which are not performed by dd 3) soft update are also useless (no bad, no good) for long sequential read basically, long sequatial reads/write ignore anything but real drive speed (plate on the spindle) if they are performed long enough. I think that 2 times differences is reallty related to seek times. But on the other hand i am sure my HDD have very good seek times. I'll have a chance to check it all on friday. -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Some Unix benchmarks for those who are interesed
I used unixbenchmark for measure overall perfomance of three machines of different generations and with different OS versions. See for your self and compare results with machine cost. Hope this will be usefull for someone. BENCHMARKS: OMNI3 (current cost 2400$): Intel entry server mainboard, intel 1U case, 20 2HDD MIRROR, 2GB ECC 533Mhz, Pentium D 3.4Ghz Built-in LSI MegaRAID RAID controller on the mainbopard. FreeBSD 6.2-STABLE /bin/sh: ELF 64-bit LSB executable, AMD x86-64, version 1 (FreeBSD), dynamically linked (uses shared libs), stripped /dev/ar0s1e 289385582 2514874 263719862 1%/usr Dhrystone 2 using register variables 10588607.7 lps (10.0 secs, 10 samples) Double-Precision Whetstone 1293.5 MWIPS (10.6 secs, 10 samples) System Call Overhead 494540.4 lps (10.0 secs, 10 samples) Pipe Throughput 597906.5 lps (10.0 secs, 10 samples) Pipe-based Context Switching 34342.0 lps (12.3 secs, 10 samples) Process Creation 3009.9 lps (38.8 secs, 3 samples) Execl Throughput no measured results File Read 1024 bufsize 2000 maxblocks464078.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 110822.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks110268.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 124661.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 86272.0 KBps ( File Copy 256 bufsize 500 maxblocks 50327.0 KBps ( File Read 4096 bufsize 8000 maxblocks1394205.0 KBps File Write 4096 bufsize 8000 maxblocks67200.0 KBps ( File Copy 4096 bufsize 8000 maxblocks 64455.0 KBps ( Shell Scripts (1 concurrent) 3212.6 lpm ( Shell Scripts (8 concurrent)579.2 lpm ( Shell Scripts (16 concurrent) 293.2 lpm ( Arithmetic Test (type = short) 892425.3 lps ( Arithmetic Test (type = int) 954128.2 lps ( Arithmetic Test (type = long)298186.4 lps ( Arithmetic Test (type = float) 1035063.3 lps Arithmetic Test (type = double) 516773.0 lps ( Arithoh 17328248.7 lps C Compiler Throughput 1815.1 lpm ( Dc: sqrt(2) to 99 decimal places 73558.8 lpm ( Recursion Test--Tower of Hanoi 141070.4 lps ( INDEX VALUES TESTBASELINE Dhrystone 2 using register variables116700.0 1058 Double-Precision Whetstone 55.0 Execl Throughput43.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 11 File Copy 256 bufsize 500 maxblocks 1655.05 File Copy 4096 bufsize 8000 maxblocks 5800.06 Pipe Throughput 12440.0 59 Pipe-based Context Switching 4000.03 Process Creation 126.0 Shell Scripts (8 concurrent) 6.0 System Call Overhead 15000.0 49 OMNI2 (current cost approx 4000$): Supermicro mainboard, supermicro case. 360 3HDD RAID-5, 4GB ECC 400Mhz, DUal Xeon 2.67Ghz 3WARE 8 with 4 PORTS FreeBSD 5.4-STABLE /bin/sh: ELF 32-bit LSB executable, Intel 80386, version 1 (FreeBSD), for FreeBSD 5.4-CURRENT (rev 2), dynamically linked ( uses shared libs), stripped /dev/twed0s1e 10154158 5684520 365730661%/usr Dhrystone 2 using register variables 3979893.5 lps (10.0 secs, 10 samples) Double-Precision Whetstone 837.4 MWIPS (10.3 secs, 10 samples) System Call Overhead 218348.2 lps (10.0 secs, 10 samples) Pipe Throughput 236742.1 lps (10.1 secs, 10 samples) Pipe-based Context Switching 56205.9 lps (10.0 secs, 10 samples) Process Creation 2662.7 lps (30.0 secs, 3 samples) Execl Throughput719.6 lps (29.6 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks250541.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks11986.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 12850.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 71142.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 10535.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 10247.0 KBps ( File Read 4096 bufsize 8000 maxblocks617670.0 KBps ( File Write 4096 bufsize 8000 maxblocks26746.0 KBps ( File Copy 4096 bufsize 8000 maxblocks 21936.0 KBps ( Shell Scripts (1 concurrent) 1285.4 lpm ( Shell Scripts (8 concurrent)163.4 lpm ( Shell Scripts (16 concurrent) 133.2 lpm ( Arithmetic Test (type = short) 630290.8 lps ( Arithmetic Test (type = int)
Re: Boot prompt for Intel AMT
I hope some people will understand what i am talking about, because the technology, i think, is not very popular, but can come VERY handy. Intel AMT Serial over LAN (SOL, why is it called 'over LAN' if it is really 'OVER IP'?) allows to boot into BIOS of a remote machine and even, as seen in their demo, can be used to control MS DOS prompt. well because it isnt using IP, besides SOIP is uninspiring :) Wait.. how so? I was sure that the whose SOL (IPMI) protocal is running over IP and i can REMOTELY (e.g. from anoth planet with IP connection) access the machine in the data center. If i can do such thing, then it DOES run over IP eventually. Isn't it? Anyway, nobody said anothing about getting freebsd boot prompt over SOL. My guess, that this is THE MOST usefull usage of SOL for remote upgrades. I understand that this is not as simple as sending data to UART. THis is must be done explicitely in the boot loader, i thinks. But why no do it? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Boot prompt for Intel AMT
Artem Kuchin wrote: I hope some people will understand what i am talking about, because the technology, i think, is not very popular, but can come VERY handy. Intel AMT Serial over LAN (SOL, why is it called 'over LAN' if it is really 'OVER IP'?) allows to boot into BIOS of a remote machine and even, as seen in their demo, can be used to control MS DOS prompt. well because it isnt using IP, besides SOIP is uninspiring :) Wait.. how so? I was sure that the whose SOL (IPMI) protocal is running over IP and i can REMOTELY (e.g. from anoth planet with IP connection) access the machine in the data center. If i can do such thing, then it DOES run over IP eventually. Isn't it? Anyway, nobody said anothing about getting freebsd boot prompt over SOL. My guess, that this is THE MOST usefull usage of SOL for remote upgrades. I understand that this is not as simple as sending data to UART. THis is must be done explicitely in the boot loader, i thinks. But why no do it? We have a number of Dell PowerEdge 2950's that we boot using the built in SOL, which does run over IP as we use it across a routed VPN backbone (server in the data center, console in the office). We have found that the IPMI serial port is connected to the system as COM2, which we select in the bios configuration. We then set device.hints so that the freebsd console is set to use the same port. We use the open source ipmitool to access the ipmi controller, and serial port, on the system. Aha! This is something already. When our system boot it says: Mar 5 23:59:04 aaa kernel: sio0: configured irq 4 not in bitmap of probed irqs 0 Mar 5 23:59:04 aaa kernel: sio0: port may not be enabled Mar 5 23:59:04 aaa kernel: sio0: 16550A-compatible COM port port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 Mar 5 23:59:04 aaa kernel: sio0: type 16550A Mar 5 23:59:04 aaa kernel: sio1: configured irq 3 not in bitmap of probed irqs 0 Mar 5 23:59:04 aaa kernel: sio1: port may not be enabled My guess is that sio0 is the real port and sio1 is the IPMI port of Intel AMT. But what does this message really say? What must i do to enable the port? The other question, do i need to include device ipmi in the kernel config? And how do i tell the boot loader to redirect its output to serial port? Sorry, working with freebsd for 10 years now but never touched this issue. -- Regads, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Is SATA II supported in 6.2-stable?
Hi! I just setup a new machine and while it is supposed to be full SATA II i still see these lines in at kernel init: Mar 6 14:00:09 aaa kernel: ad8: 305245MB Seagate ST3320620AS 3.AAE at ata4-master SATA150 Mar 6 14:00:09 aaa kernel: ad10: 305245MB Seagate ST3320620AS 3.AAE at ata5-master SATA150 As you see, it says SATA150 , while the drives are SATA II (which is, as i understand, SATA 300). Both drives are connected to RAID controller and form a mirror raid: Mar 6 14:00:09 aaa kernel: ar0: 305108MB LSILogic v3 MegaRAID RAID1 status: READY Mar 6 14:00:09 aaa kernel: ar0: disk0 READY (master) using ad8 at ata4-master Mar 6 14:00:09 aaa kernel: ar0: disk1 READY (mirror) using ad10 at ata5-master Any idea how to make it work as SATA II? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Boot prompt for Intel AMT (serial port redirection on Intel AMT)
- Original Message - From: Tom Judge [EMAIL PROTECTED] To: Artem Kuchin [EMAIL PROTECTED] Cc: [EMAIL PROTECTED]; Jack Vogel [EMAIL PROTECTED] Sent: Tuesday, March 06, 2007 2:04 PM Subject: Re: Boot prompt for Intel AMT Artem Kuchin wrote: Artem Kuchin wrote: snip/ We have a number of Dell PowerEdge 2950's that we boot using the built in SOL, which does run over IP as we use it across a routed VPN backbone (server in the data center, console in the office). We have found that the IPMI serial port is connected to the system as COM2, which we select in the bios configuration. We then set device.hints so that the freebsd console is set to use the same port. We use the open source ipmitool to access the ipmi controller, and serial port, on the system. Aha! This is something already. When our system boot it says: Mar 5 23:59:04 aaa kernel: sio0: configured irq 4 not in bitmap of probed irqs 0 Mar 5 23:59:04 aaa kernel: sio0: port may not be enabled Mar 5 23:59:04 aaa kernel: sio0: 16550A-compatible COM port port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 Mar 5 23:59:04 aaa kernel: sio0: type 16550A Mar 5 23:59:04 aaa kernel: sio1: configured irq 3 not in bitmap of probed irqs 0 Mar 5 23:59:04 aaa kernel: sio1: port may not be enabled My guess is that sio0 is the real port and sio1 is the IPMI port of Intel AMT. But what does this message really say? What must i do to enable the port? The other question, do i need to include device ipmi in the kernel config? And how do i tell the boot loader to redirect its output to serial port? Sorry, working with freebsd for 10 years now but never touched this issue. This is the dmesg from our servers (sio1 is the ipmi SOL port): sio0: 16550A-compatible COM port port 0x3f8-0x3ff irq 4 on acpi0 sio0: type 16550A sio1: 16550A-compatible COM port port 0x2f8-0x2ff irq 3 flags 0x10 on acpi0 sio1: type 16550A, console As far as I know it is not required to have ipmi in the kernel (we dont have it in our kernels) to use the SOL port. This page should help you setup the serial console: http://www.freebsd.org/doc/en_US.ISO8859-1/books/handbook/serialconsole-setup.html Hmm. i am stuck now. I have setup everything as described but still see nothing in SOL terminal when system boots (still can see BIOS). I can turn on video redirection to serial port COM1 in the BIOS and then i can see boot prompt and boot menu, but i cannot do anything there because keyboard is not working at all. Now i have the floowing questions: 1) What port is redirected over SOL in intel ? It is not COM1. 2) Can it do serial redirection at all? 3) Did anybody ever managed to set this thing up on Intel Server with AMT? My server is ENtry level SE7230ONH1-E -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
Artem Kuchin wrote: I used unixbenchmark for measure overall perfomance of three machines of different generations and with different OS versions. See for your self and compare results with machine cost. Hope this will be usefull for someone. Several things: a) It looks like your message was weirdly truncated - whole rectangles of text are missing from the results on the right-hand-side. Maybe you copied it through Excel? Ummm... hmmm.. i checked the message in the list, nothimng is missing. Just like it was in the putty terminal from where i copied it. b) I submitted a patch for unixbench than enables execl benchmark on amd64, it should be in the ports tree by now. oh! that's good. will retest. c) It would be interesting for the general discussion if you could install a recent server-like version of Linux (e.g. CentOS, SuSE, Debian) on one of the machines you did your benchmarks on to compare results :) I am not good at linux, but this is an interesting idea. I'll try it. Which one is easier to install? -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Some Unix benchmarks for those who are interesed
See here: http://lists.freebsd.org/pipermail/freebsd-stable/2007-March/033494.html Yes, that what i've got in the list and this how it was in the putty terminal originally. Nothing is missing. I don't know why open left parentesis are there. -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Boot prompt for Intel AMT
Hello! I hope some people will understand what i am talking about, because the technology, i think, is not very popular, but can come VERY handy. Intel AMT Serial over LAN (SOL, why is it called 'over LAN' if it is really 'OVER IP'?) allows to boot into BIOS of a remote machine and even, as seen in their demo, can be used to control MS DOS prompt. However, i tried it and did not see any boot prompt over SOL connection. As i understand it does not use bios for input/output and therefore data is not sent/received over SOL connection. Thisis a pitty because of boot prompt would work over SOL then remote source upgrade would be much plainless and less risky than now. For example, i could just book old kernel if something goes wrong. Is there a way to make boot prompt work over SOL? The othe question, is there such technology for Supermicro mainboards? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: What is a good choice of sata-ii raid controller for freebsd?
On 2007-Feb-12 16:07:03 +1030, Daniel O'Connor [EMAIL PROTECTED] wrote: I regularly ship systems overseas where the power fails frequently. The inability to boot because one disk got hosed is Bad News (tm). A decent UPS can help here. No, i can't. I have seen UPS (even APC) fail in some cases. Computers got frozen. Also, i've seen many cases when power failes for more than 4 hours and nobody want to buy UPS which hold 4 hours of power for a dual xeon with 5 hdds. It depends on your exact situation, I was just pointing out that SW RAID doesn't cover all the bases HW RAID does. If the disk is dead then the BIOS will skip it and the system should boot normally (I've tested this by pulling a disk since I didn't have a suitable dead disk to hand). A hard error in the 2nd stage boot loader, ficl or the kernel is definitely the worst case - I agree that this is very difficult for software raid to recover from. No, BIOS does not always do it. If HDD REALLY fails (chips fried or something is really messy) the BIOS often just become frozen and never boots. I have seen it too. I've seen many things, you know :)) Note that even with hardware raid, there are still lots of failure points. The least reliable parts of a current computer are the CPU and PSU fans, not the disks. That is why RAID controller MUST be w/o fans and there must be MANY fans inside server case and there MUST constant temperature monitoring with SMS, EMAIL, ICQ messages on alarams. -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: What is a good choice of sata-ii raid controller for freebsd?
hi! I am the original poster of this thread. I have read many interesting reply during these two days. However, as i said in the original message due to certification issues i am pretty limited to INTEL controllers and i have not seen a single relevant reply about them. This is interesting. Nobody uses Intel controllers on FreeBSD or they just suck that much? -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
What is a good choice of sata-ii raid controller for freebsd?
Hello! I need a raid controller for FBSD 6.2 which has the following options 1) Full SATA-II support 2) Good rperfomance (over 50MB read, over 30 write) in mirror mode 3) No weird problems with freebSD (like with SRCS16) 4) Utility to monitor status of raids (command line or web) 5) Utility to rebuild, repair, manager arrays in OS 6) Preferably Intel I know, 3ware has such good stuff, but those controller are not certified for internet services in here (russia). So, i am pretty much limited to Intel controllers. Is there intel controller which satisfied all the 1-6 conditions? I only need mirroring. -- С уважением, Артем Кучин ООО Ай Ти Легион www.itlegion.ru +7 (495) 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Filesystem corruption and bad perfomance with SRCS16 and PAE (raid 5 2TB)
Boris Samorodov wrote: On Wed, 7 Feb 2007 03:04:05 +0300 Artem Kuchin wrote: Andras Gót wrote: Can you try the AMD64 version on that server? Um.. i have never tried anything AMD in my life. I thought AMD64 is only for AMD CPUs and this is Intel Xeon. Are you really suggesting installing FreeBSD for AMD64 on this Xeon server? Why? Should it help? You may be interested at reading: http://www.freebsd.org/releases/6.2R/hardware-amd64.html#PROC Actually i have read it many time before, but i guess, never paed attention ;) anyhow, this: There may be some issues with 64-bit cleanliness in some (particularly older) drivers. Generally, drivers that already function correctly on other 64-bit platforms should work. FreeBSD/amd64 is a very young platform on FreeBSD. While the core FreeBSD kernel and base system components are generally fairly robust, there are likely to still be rough edges, particularly with third party packages. scares me. Do you really think it is better than PAE? -- Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Filesystem corruption and bad perfomance with SRCS16 and PAE (raid 5 2TB)
Hello! I've got an Intel 2400A server to install FBSD. It has 4GB RAM, SRCS16 raid controller, configured 2TB (actually a little less, about 1.9TB) RAID-5 array, Xeon 3.2Ghz Recently i have installed 6.2-R, cvsupped it to 6.2-STABLE (today, thanks to included csup utility, very convinient) and decided to turn on PAE so i can utilize all 4GB of RAM (w/o PAE i am loosing 512MB, too bad). I did that and then tried to run perl. Got segmantaion fault. Ignored that and tried to copy port tree and then i found out that some files are damanged and connot be read. Also, directoried could not be deleted because it is not empty, but when i do ls in that dir it IS empty. weird. Booted single user, did fsck - found a buch of errors, many softupdate inconsistencies. Fixed them. Rebooted (still in PAE). Run buildworld and copy ports tree at the same time. AFter 10 minutes again the same errors. Built a kernel without PAE, installed, rebooted in single user, fixed all filesystems, booted multiuser, run buildworld and copy of ports tree. Everything is okay. Did it many times. Still everything is ok. Is it something bad about amr driver working under PAE? Also, with and after running in PAE (i mean, run PAE kernel, then install normal kernel and run it) the kernel compains like this _vfs_done(): amrd0 [WRITE(offset=8192, length=1536)] error = 5 (no other message before or aftrer this, disks are fully okay becuase dd works like a charm) Also, i did a simple thing dd if=/dev/amrd0 of=/dev/null bs=1M (tried 2m, 5m, 512k) The throughoutput is about 29MB/sec w/o PAE and 27MB/sec with PAE Did the same on a very old DUal Pentium III with 3Ware 7 with RAID-5 array and older harddrives. Got over 50Mb/sec. unixbench show terrible number for file perfomance. Why the heck amr is so slow? -- Regards, Artem Kuchin ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Filesystem corruption and bad perfomance with SRCS16 and PAE (raid 5 2TB)
Andras Gót wrote: Hi, Can you try the AMD64 version on that server? Um.. i have never tried anything AMD in my life. I thought AMD64 is only for AMD CPUs and this is Intel Xeon. Are you really suggesting installing FreeBSD for AMD64 on this Xeon server? Why? Should it help? -- Artem Artem Kuchin wrote: Hello! I've got an Intel 2400A server to install FBSD. It has 4GB RAM, SRCS16 raid controller, configured 2TB (actually a little less, about 1.9TB) RAID-5 array, Xeon 3.2Ghz Recently i have installed 6.2-R, cvsupped it to 6.2-STABLE (today, thanks to included csup utility, very convinient) and decided to turn on PAE so i can utilize all 4GB of RAM (w/o PAE i am loosing 512MB, too bad). I did that and then tried to run perl. Got segmantaion fault. Ignored that and tried to copy port tree and then i found out that some files are damanged and connot be read. Also, directoried could not be deleted because it is not empty, but when i do ls in that dir it IS empty. weird. Booted single user, did fsck - found a buch of errors, many softupdate inconsistencies. Fixed them. Rebooted (still in PAE). Run buildworld and copy ports tree at the same time. AFter 10 minutes again the same errors. Built a kernel without PAE, installed, rebooted in single user, fixed all filesystems, booted multiuser, run buildworld and copy of ports tree. Everything is okay. Did it many times. Still everything is ok. Is it something bad about amr driver working under PAE? Also, with and after running in PAE (i mean, run PAE kernel, then install normal kernel and run it) the kernel compains like this _vfs_done(): amrd0 [WRITE(offset=8192, length=1536)] error = 5 (no other message before or aftrer this, disks are fully okay becuase dd works like a charm) Also, i did a simple thing dd if=/dev/amrd0 of=/dev/null bs=1M (tried 2m, 5m, 512k) The throughoutput is about 29MB/sec w/o PAE and 27MB/sec with PAE Did the same on a very old DUal Pentium III with 3Ware 7 with RAID-5 array and older harddrives. Got over 50Mb/sec. unixbench show terrible number for file perfomance. Why the heck amr is so slow? -- Regards, Artem Kuchin ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED] ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED] ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Cannot start install cd of 6.2-R at all
Mark Kirkwood wrote: Artem Kuchin wrote: Hello! I am having a VERY weird problem. The pc config is: 1) Celeron 1+ GHZ 2) Intel PCI ethernet nic 3) Fasttrak TX2000 raid + 2 mirrored disks (seagate 80gb) 4) teac dvd driver 5) 512 MB ram 6) Chaintech montherboard (old one) also tried on gigabyte motherboard I insert boot cd and when it starts loading a get a dump of cpu register scrolling crazy on the screen. If i delete TX2000 the installer loads fine. Any idea what is happening and how to SOLVE it? I have seen this with a Tyan PIII board + TX2000. In my case re-trying the boot from cd several times would *eventually* get a working installer session. (If you search the archives you'll see several cases of folks encountering this). Unfortunately I don't know of any solution. A (tedious) workaround (in case repeated attempts always fail for you), is to install a minimal system off an earlier version of FreeBSD and run the installer off the installed system - or just src upgrade to the version you want. I found that the 4.x, 5.0, 5.1 and 5.2 cd's all worked fine - but 5.3 onwards and 6.x would register dump. There is a better workaround which i used. A simple start of installer from 4 floppies. Then install the whole system from CD-ROM. It does work but insolved copying of floppy images onto the disks. However is it a very annoying problem which i have been encountering since 5.0-RELEASE. The bootloader failed when trying to load installed from CD-ROM on pretty much every PIII and old Celeron pc which i tried. (it is about 6 machines by now). Very weird and i have no idea to how help to solve the problem. -- Regards Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Cannot start install cd of 6.2-R at all
Hello! I am having a VERY weird problem. The pc config is: 1) Celeron 1+ GHZ 2) Intel PCI ethernet nic 3) Fasttrak TX2000 raid + 2 mirrored disks (seagate 80gb) 4) teac dvd driver 5) 512 MB ram 6) Chaintech montherboard (old one) also tried on gigabyte motherboard I insert boot cd and when it starts loading a get a dump of cpu register scrolling crazy on the screen. If i delete TX2000 the installer loads fine. Any idea what is happening and how to SOLVE it? -- Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Quotas inside jails
Sometime ago and have setup 5.3-STABLE box with quotas for jailed users. At that time quotas did not work inside jails, so i just created some group on host machine and group with the same ID inside jail and then put a quota upon that group on the host box. That was quotas are observed. However, user iside jail cannot check their quota this way. Do quotas work now (as of 6.1-STABLE) inside jails correctly? Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
What's done and what's not done in 6.1?
see: http://www.freebsd.org/releases/6.1R/todo.html Is it the final status of things when went into 6.1R? I am particulary interested in status of the following problems: devfs locking problem unmount pending error swap_pager warnings pty leak calcru: runtime went backwards problem for threaded program update sysinstall disk labeling Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Disappointed
Alexey Karagodov wrote: needs, make a mirror, make a test server/workstation/notebook/PDA etc. i'm not an freebsd developer. i'm just admin and a user. your system is most greatest i ever seen. another wonderful system is SOLARIS. but your's is so unstable ... I never could really undertand this. How come i have run over 40 freebsd servers since 1997 and never had ANY stability problem. Even with 5.1 and hier (i skipped 5.0). The only stability problem i had is on dual Xeon with HT on. Well, i truned off HT and lived happily ever after. I this people must be more careful when selecting hardware for server and be VERY VERY careful and picky when selecting hardware to run on FREEBSD. If you do so, you will not have any problems. And if you want ot experiment then do it on your test server or workstation. Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Strange number of mbufs
Gleb Smirnoff wrote: On Fri, Feb 03, 2006 at 12:52:09AM +0300, Artem Kuchin wrote: Running 5.4-CURRENT. Web server. About 150 virtual servers. %netstat -m 4294481198 mbufs in use What does this mean? Do i really have 4294481198 mbufs in use? How is this possible? This is fixed in 6.0-RELEASE. In 5.x the true values can be obtained via 'vmstat -z'. Which number from output of vmstat -z indicates mbufs? I don't see it there. Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Does fxp works with PAE in 6-STABLE? Is TWE stable in PAE?
I have read that in 5.x fxp driver did not work with PAE, but, as i see, fxp is not in 'nodevice' section of PAE kernel config anymore. Is it okay now to use fpx in PAE kernel? Also, is twe driver very stable in PAE? I have a web server with 6 gigs of RAM and would like to use them all. Thanks, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Strange number of mbufs
Running 5.4-CURRENT. Web server. About 150 virtual servers. %netstat -m 4294481198 mbufs in use 4294662679/25600 mbuf clusters in use (current/max) 0/694/6656 sfbufs in use (current/peak/max) 3463545 KBytes allocated to network 0 requests for sfbufs denied 0 requests for sfbufs delayed 1681997 requests for I/O initiated by sendfile 75325 calls to protocol drain routines What does this mean? Do i really have 4294481198 mbufs in use? How is this possible? kern.ipc.nmbclusters is set to 25600 Regards, Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: SATA vs SCSI ...
Marc G. Fournier [EMAIL PROTECTED] wrote: looking at the specs between two cards, the SATA card(s) seem to rate ~100-150MB/s on each channel (if I'm reading right), with both the 3Ware and ICP cards having 4 individual channels ... looking at the SCSI cards, they are rated at 320MB/s, but that is total for the SCSI bus itself, right? So, if I have three drives on a SCSI bus, each 'maxing out evenly', I'd be cap'd at about the same 100MB/s per drive, no? In fact, looking at the SATA 2.x specs, each chanell there is rated at 300MB/s, which, again, if I could 'max out evenly', could seriously blow away the SCSI bus itself ... *If* I'm reading this right ... ? For the last 6 month i really think that if you don't need something high-end scsi then you should go for SATA. There are test on sites such as Tom's hardware guide and ixbt.com. They show then on sequrncial read there is no difference between scsi and sata. Acatuallty, modern hdds use the same mechanics for sata and scsi versions of them. The brains (electronics) on the hdds are different of course. However, when it comes to random read/writes scsi wins because of command queueing. This was an issue until recently, Recently SATA with NCQ became widly available. Test show that some of those SATA disks with NCW ***WIN*** over scsi 320. The test envolve artificialy random read/write tests as well as real application benchmarking. I din't rememeber where excatly i saw the tests on those site, but you could search. So, my opinion, workstation never needs SCSI and every server MUST be on mirror or RAID5 and there you should use SATA with NCQ drivers unless, your applicaton is really weird and needs something extremely speedy. Then, however, you could go for RAID 0+1 and get perfomance that SCSI will never get you. -- Regards, Artem Kuchin IT Legion Ltd. Moscow, Russia www.itlegion.ru [EMAIL PROTECTED] +7 095 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
man 4 ar on 5.4
See man 4 ar I think it is fully outdated, bease ar is an RAID storage device, as i see when i use Promise TX2000 Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Current status of nullfs and/or unionfs?
Eirik Ø verby [EMAIL PROTECTED] wrote: Before I start playing with this again, I'd like to know if any work has been done on either of these in 5.x. Specifically, I'm currently running 5.3-p6 or newer on all the systems, and as of yesterday I've been using 5.4-prerelease (cvsup) on a couple of test systems. Hi. I am running on 5.3-STABLE since december 2004. We run 14 jails and use nullfs for some shared parts. Everything is just fine. I tryed unionfs, it worked stable but i didn't do what i wanted it to do or probably i didn't get its usage right :) -- Regards, Artem Kuchin IT Legion Ltd. Moscow, Russia www.itlegion.ru [EMAIL PROTECTED] +7 095 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Need really cheap IDE mirroring PCI controlled for FreebBSD 4.10
pete wright [EMAIL PROTECTED] wrote: On Wed, 2 Mar 2005 17:27:07 +0300, Artem Kuchin [EMAIL PROTECTED] wrote: Can anybody recommend cheap IDE mirroring PCI (2.0, not 2.1 or 2.2) controller with just 2 IDE ports which works fine with FreeBSD 4.10 ? It is to be installed on a very old motherboard (1998) and two 40GB IDE driver (more or less modern ones, at least not used ones for sure). sorry I don't know of any really cheap one's off hand, altho I do have experience with 3Ware RAID cards on 4.x. They seemed to work well, and they are less expensive than proper SCSI cards...altho slower. If cost really an issue would it be worth mirroring your disks in software via VINUM? Well, i don't trust software raids. But 3ware is probably one of the most expensive raid 0,1 controllers. There must be something around 40$ which freebsd supports. Does anyone known any model? -- Regards, Artem Kuchin IT Legion Ltd. Moscow, Russia www.itlegion.ru [EMAIL PROTECTED] +7 095 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Need really cheap IDE mirroring PCI controlled for FreebBSD 4.10
Gerald de la Pascua [EMAIL PROTECTED] wrote: we have had very good experiences with the basic 3ware cards, I would recommend them, easy to install, reliable, and good perfomance, in the uk they cost just over 100 pounds, so a similar price to two disks to plug into them. When a disk fails you would willingly pay many times this amount, 3ware controllers are one of the most expensive ones. I am sure there are good controllers which cost a lot less and work with freebsd. Do you know any? Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Need really cheap IDE mirroring PCI controlled for FreebBSD 4.10
Can anybody recommend cheap IDE mirroring PCI (2.0, not 2.1 or 2.2) controller with just 2 IDE ports which works fine with FreeBSD 4.10 ? It is to be installed on a very old motherboard (1998) and two 40GB IDE driver (more or less modern ones, at least not used ones for sure). -- Regards, Artem Kuchin IT Legion Ltd. Moscow, Russia www.itlegion.ru [EMAIL PROTECTED] +7 095 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: How to make ipfw consider MAC-IP match?
Scot Hetzel [EMAIL PROTECTED] wrote: On Mon, 14 Feb 2005 23:58:03 +0300, Artem Kuchin [EMAIL PROTECTED] wrote: Hi! I have a table with ethernet (MAC) addresses matching IPs. It is used to build dhcp config file. But regardless of that any user can assign his neighbour ips while that pc is turned off and use it to access internet. The local ips are 192.168. and are behind natd. I am running 5.3-STABLE and have heard that ipfw2 can in someway use MAC addresses, but how do I setup ipfw in such a way that it allows certain IP only from one and only one MAC address? I hope you are getting my idea. You would add the following to the end of your IPFW rule for each IP Address you want to restrict. pass all from 192.168.0.10 to any mac any 10:20:30:40:50:60 Where 10:20:30:40:50:60 is the MAC addr for IP addr 192.168.0.10. I have tried static arp today and it seems like it works. As others mentions, it is possible SOMETIMES to change mac address of a nic, so static arp may fail as well as this firewall rule. So, i am wondering which method is better static arp entries or ipfw rules? Artem ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
How to make ipfw consider MAC-IP match?
Hi! I have a table with ethernet (MAC) addresses matching IPs. It is used to build dhcp config file. But regardless of that any user can assign his neighbour ips while that pc is turned off and use it to access internet. The local ips are 192.168. and are behind natd. I am running 5.3-STABLE and have heard that ipfw2 can in someway use MAC addresses, but how do I setup ipfw in such a way that it allows certain IP only from one and only one MAC address? I hope you are getting my idea. -- Regards, Artem Kuchin ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: How to make ipfw consider MAC-IP match?
Chris Dillon [EMAIL PROTECTED] wrote: On Mon, 14 Feb 2005, Artem Kuchin wrote: I have a table with ethernet (MAC) addresses matching IPs. It is used to build dhcp config file. But regardless of that any user can assign his neighbour ips while that pc is turned off and use it to access internet. The local ips are 192.168. and are behind natd. I am running 5.3-STABLE and have heard that ipfw2 can in someway use MAC addresses, but how do I setup ipfw in such a way that it allows certain IP only from one and only one MAC address? I hope you are getting my idea. What you probably want is static ARP entries. arp -s 192.168.1.1 00:11:22:33:44:55 But that still won't stop someone from changing their IP address and MAC address to match, it just makes it harder. To prevent that kind of thing you need to use 802.1x authentication or maybe even PPPoE. Um.. I just have read tutorial about PPPoE and did not find anything about matching IP and MAC addresses. So, if i use PPPoE i still need to do static ARP (i did not undestrand, how i somebody can match mac and ip with static arp except that he actually get the physical NIC from somebody's computer). Also, as i see, users on PPPoE can login from any computer and get their IP address.It will not work because of static arp, but still, there are getting their address. And the last thing, if i am to migrate to PPPoE this basically means i will need to give up DHCP, because PPP will serve IPs, not DHCP. Right? And now the theory question. While i am running pppoe server on some ethernet interface what disallows any user to use that interface as a ip gateway without any pppoe? Just assigned themselves an ip, ignoring pppoe and using the server as a gateway. I am probably missing some point here. -- Regards, Artem Kuchin ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Lock up problems with 5.3-STABLE (was: Cannot build kernel withoptions WITNESS)
I would suspect the jail code at this point here is my kernel config for my smp machine Dual Athlon-mp 40 gig ide hd 1024 Ram xl0 nic device 100mbit fdx Well, i am currently suspecting Hyperthreading code. I have disabled it and turned back memory disk and all jails. The box is running stable for last 3 days. You dont' have HT cpus, so you have only 2 logical, but i HAD 4. Now i have 2 logical cpus, which are real cpus. Let's see what happens in the next 4 days. Regards, Artem Kuchin IT Legion Ltd. Moscow, Russia www.itlegion.ru [EMAIL PROTECTED] +7 095 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Lock up problems with 5.3-STABLE (was: Cannot build kernel with options WITNESS)
On Sun, 23 Jan 2005, Artem Kuchin wrote: On Sat, 22 Jan 2005, Artem Kuchin wrote: I cvssed just an hour ago. 5.3-STABLE and cannot build kernel with WITNES. It complains: This occurs when building WITNESS without DDB in the kernel, which was not a tested build case when I added show alllocks, and apparently is a relatively uncommon configuration as you're the first person to bump into it. I've just committed the fix as subr_witness.c:1.187 in HEAD, and subr_witness.c:1.178.2.4 in RELENG_5. Please let me know if this doesn't fix the problem for you. It fixed the problem. I am actually stuggling with unpredictable weird lock ups, when the host can be pinged but i cannot connect via ssh/telnet or httpd or anything else. It happens w/o any visible reason. I am running several jails with mysql and apache in each and canot make the whole system stable yet. This is typically a sign of one of two problems: - The system is live locked due to very high load, so the ithread, netisrs, etc, in the kernel run fine, but user processes don't get a chance to run. - The system is dead locked due to user space processes getting wedged on common locks, but the kernel ithreads and netisrs can keep on responding. I generally assume that it's a deadlock as opposed to a live lock. I'd compile a kernel with DDB, KDB, WITNESS, and BREAK_TO_DEBUGGER. When the system appears to wedge, break into the debugger using a console or serial break (FYI: serial break is more reliable, and you get the benefit of being able to easily copy and paste debugging output using the serial console for DDB). Use show alllocks and show lockedvnods to examine most of the system's locking state. Changes are, either all the interesting processes are stacked up on VFS or VM locks, since those kinds of deadlocks produce the exact symptoms you describe: ping works fine because it only hits the netisr, but when you open TCP connections, the sshd (etc) block on VM or VFS locks attempting to fork new children or access a file in the file system name space. At first, the TCP connections will establish but there will be no application data; after a bit, they will not even return a SYN/ACK because the listen queue for the listen socket has filled. Well, i cvsed and reconpiled the kernel with WITNESS, INVARINATS, turned off adaptive giant and got a lock today at 7 am. Since the server is remotely controlled i took my digital camera because i cannot connect serial console to it and went to the server. I expetced to see some special message about something going wrong, break into debugger (CTRL+ALT+ESC) and to take some pictures of dumps of console. But, i saw nothing. The lasrt message on th screen was about ssh loging last evening and the last message in /var/log/all.log was about entropy save from cron. I could not break into debugger usinmg CTRL-ALT+ESC. I did nothing. So, it looked like a hard lock. At this point i would like to tell the whole story. We bought this server in may 2004 and decided to extemsively test the hardware while there were not 5.3. We actually expected it around august. SO, we installed 5-CURRENT and ran high load tests (cpu, memory, disk storage, network) from /usr/ports/benchmark at the same time and one-by-one several weeks. There were not a glitch. After that we turned it off and waited for RELEASE. RELEASE has come and we begun to setup the servre as it should work. As the server's primary mission is to host a buch of site we decided to setup jails for each site, So we did in december and put the server on prividers co-location severals kilometer away from the office. Next day the server locked up. We were surprised but just rebooted it, It locked up the next day gain. We cvsupped and rebuild the system and the jails. The server locked up the next day. During the new year break i have figureed that if there are more that one jail running the server locks withun 24 hours with very hight probablity and within 48 hours with 100% probability. I wrote into freebsd-stable about it. You have asked for debugger dump (pcpu, list of lock, e.t.c). I could not do it at that time, so, i did not reply and just cvsupped in the beginning of january and rebuilt the system and the jails again. Magically, after that i could run 5 jails (did not tried more) for over a week and i already decided that the bug was fixed and I could host the site. Alas, the next glitch did not wait to long. After a few more days i saw a srange situatuon - i could not connect to server using SSH. SSH replied about auth key or something like that. I rebootied the system and ssh worked fine. Still have no idea what that was, but i setuo IPFIREWALL and a telnet server for accept connection only from one ip address, so, if ssh fails I could use telnet. After that i moved a real site with perl scripts, 1GB database, mail account (using qmail+vpopmail) into one of the jails and the next day got the next problem: I could ping server, but could
Cannot build kernel with options WITNESS
device speaker #options DDB #options KDB #options BREAK_TO_DEBUGGER options INVARIANT_SUPPORT options INVARIANTS options WITNESS options WITNESS_KDB options WITNESS_SKIPSPIN #options ADAPTIVE_GIANT # Giant mutex is adaptive. Regards, Artem Kuchin IT Legion Ltd. Russia, Moscow www.itlegion.ru [EMAIL PROTECTED] +7 095 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Cannot build kernel with options WITNESS
On Sat, 22 Jan 2005, Artem Kuchin wrote: I cvssed just an hour ago. 5.3-STABLE and cannot build kernel with WITNES. It complains: This occurs when building WITNESS without DDB in the kernel, which was not a tested build case when I added show alllocks, and apparently is a relatively uncommon configuration as you're the first person to bump into it. I've just committed the fix as subr_witness.c:1.187 in HEAD, and subr_witness.c:1.178.2.4 in RELENG_5. Please let me know if this doesn't fix the problem for you. It fixed the problem. I am actually stuggling with unpredictable weird lock ups, when the host can be pinged but i cannot connect via ssh/telnet or httpd or anything else. It happens w/o any visible reason. I am running several jails with mysql and apache in each and canot make the whole system stable yet. Regards, Artem Kuchin IT Legion Ltd. Russia, Moscow www.itlegion.ru [EMAIL PROTECTED] +7 095 232-0338 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Server locks up if more than one jail in running
I have a very bad problem. I need to seetup large number of jails (about 100) to do virtual hosting and i am doing it on 5.3-STABLE (not 5.3-RELEASE, i mean -STABLE which is cvsupped). So, when i setup one jail - everything runs fine for many days. If i setup one more jail or 3 or more - server locks up (freezes, hangs, becomes totally unsresponsive) within 48 hours. Sometime it runs only a couple hours, sometimes almost a couple of days. So, to diagnose the problem i setup a cron process which saves a lot of system statistics every minutes. The last working minute stats are included below as well as basic system configuration. Jails are complete distributions, but very basic services are running: cron, sshd. adjtimezone is disabled. All other records on /etc/crontab are left just like in distro. I really need help with this problem because i canno migrate to 5.3 because of it. And i really need 5.3 because of some new features. Maybe somone could help. SYSTEM: Multiprocessor. Dual XEON 2.667Ghz with HTT. 4GB DDR RAM. RAID 5 (4 SATA disks x 120gb) on 3Ware SATA controller in PCI 64 slot on Supermicro MB. dmesg -- Copyright (c) 1992-2004 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD 5.3-STABLE #4: Wed Dec 22 10:25:48 MSK 2004 [EMAIL PROTECTED]:/usr/obj/usr/src/sys/OMNI ACPI APIC Table: PTLTDAPIC Timecounter i8254 frequency 1193182 Hz quality 0 CPU: Intel(R) Xeon(TM) CPU 2.66GHz (2665.92-MHz 686-class CPU) Origin = GenuineIntel Id = 0xf25 Stepping = 5 Features=0xbfebfbffFPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,PBE Hyperthreading: 2 logical CPUs real memory = 4160225280 (3967 MB) avail memory = 4077481984 (3888 MB) FreeBSD/SMP: Multiprocessor System Detected: 4 CPUs cpu0 (BSP): APIC ID: 0 cpu1 (AP): APIC ID: 1 cpu2 (AP): APIC ID: 6 cpu3 (AP): APIC ID: 7 ioapic0 Version 2.0 irqs 0-23 on motherboard ioapic1 Version 2.0 irqs 24-47 on motherboard ioapic2 Version 2.0 irqs 48-71 on motherboard ioapic3 Version 2.0 irqs 72-95 on motherboard ioapic4 Version 2.0 irqs 96-119 on motherboard npx0: [FAST] npx0: math processor on motherboard npx0: INT 16 interface acpi0: PTLTD RSDT on motherboard acpi0: Power Button (fixed) Timecounter ACPI-fast frequency 3579545 Hz quality 1000 acpi_timer0: 24-bit timer at 3.579545MHz port 0x1008-0x100b on acpi0 cpu0: ACPI CPU (2 Cx states) on acpi0 cpu1: ACPI CPU (2 Cx states) on acpi0 cpu2: ACPI CPU (2 Cx states) on acpi0 cpu3: ACPI CPU (2 Cx states) on acpi0 pcib0: ACPI Host-PCI bridge port 0xcf8-0xcff on acpi0 pci0: ACPI PCI bus on pcib0 pci0: unknown at device 0.1 (no driver attached) pcib1: ACPI PCI-PCI bridge at device 2.0 on pci0 pci1: ACPI PCI bus on pcib1 pci1: base peripheral, interrupt controller at device 28.0 (no driver attached) pcib2: ACPI PCI-PCI bridge at device 29.0 on pci1 pci2: ACPI PCI bus on pcib2 pci1: base peripheral, interrupt controller at device 30.0 (no driver attached) pcib3: ACPI PCI-PCI bridge at device 31.0 on pci1 pci3: ACPI PCI bus on pcib3 em0: Intel(R) PRO/1000 Network Connection, Version - 1.7.35 port 0x3000-0x303f mem 0xfc20-0xfc21 irq 28 at device 2.0 on pci3 em0: Ethernet address: 00:30:48:2a:2d:bc em0: Speed:N/A Duplex:N/A em1: Intel(R) PRO/1000 Network Connection, Version - 1.7.35 port 0x3040-0x307f mem 0xfc22-0xfc23 irq 29 at device 2.1 on pci3 em1: Ethernet address: 00:30:48:2a:2d:bd em1: Speed:N/A Duplex:N/A pcib4: ACPI PCI-PCI bridge at device 3.0 on pci0 pci4: ACPI PCI bus on pcib4 pci4: base peripheral, interrupt controller at device 28.0 (no driver attached) pcib5: ACPI PCI-PCI bridge at device 29.0 on pci4 pci5: ACPI PCI bus on pcib5 pci4: base peripheral, interrupt controller at device 30.0 (no driver attached) pcib6: ACPI PCI-PCI bridge at device 31.0 on pci4 pci6: ACPI PCI bus on pcib6 twe0: 3ware Storage Controller. Driver version 1.50.01.002 port 0x4000-0x400f mem 0xfc80-0xfcff irq 72 at device 1.0 on pci6 twe0: [GIANT-LOCKED] twe0: 4 ports, Firmware FE7S 1.05.00.063, BIOS BE7X 1.08.00.048 uhci0: Intel 82801CA/CAM (ICH3) USB controller USB-A port 0x2000-0x201f irq 16 at device 29.0 on pci0 uhci0: [GIANT-LOCKED] usb0: Intel 82801CA/CAM (ICH3) USB controller USB-A on uhci0 usb0: USB revision 1.0 uhub0: Intel UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub0: 2 ports with 2 removable, self powered uhci1: Intel 82801CA/CAM (ICH3) USB controller USB-B port 0x2020-0x203f irq 19 at device 29.1 on pci0 uhci1: [GIANT-LOCKED] usb1: Intel 82801CA/CAM (ICH3) USB controller USB-B on uhci1 usb1: USB revision 1.0 uhub1: Intel UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub1: 2 ports with 2 removable, self powered uhci2: Intel 82801CA/CAM (ICH3) USB controller USB-C port 0x2040-0x205f irq 18 at device 29.2 on pci0 uhci2: [GIANT-LOCKED] usb2: