Re: Shooting trouble on a PCI bus hang
On 06/14/11 20:52, Ansar Mohammed wrote: Hello All, I have a system that is intermitently hanging during the initial PCI bus scan during boot. I have turned on verbose logging and I cannot break to debugger as its a hang. Can someone guide me to the relevant code section where PCI bus enumeration occurs so that I may modify the kernel source to output even more debug info. My hang occurs at the end of this partial dmesg output. Thank you! pci0: on pcib0 pci0: domain=0, physical bus=0 found-> vendor=0x100b, dev=0x0028, revid=0x21 domain=0, bus=0, slot=1, func=0 class=06-00-00, hdrtype=0x00, mfdev=1 cmdreg=0x0005, statreg=0x0220, cachelnsz=8 (dwords) lattimer=0xf8 (7440 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) map[10]: type I/O Port, range 32, base 0xac1c, size 2, enabled found-> vendor=0x100b, dev=0x0030, revid=0x00 domain=0, bus=0, slot=1, func=1 class=03-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0003, statreg=0x0220, cachelnsz=8 (dwords) lattimer=0x00 (0 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) map[10]: type Memory, range 32, base 0x4100, size 24, enabled map[14]: type Memory, range 32, base 0x40ffc000, size 14, enabled map[18]: type Memory, range 32, base 0x40ff8000, size 14, enabled map[1c]: type Memory, range 32, base 0x40ff4000, size 14, enabled found-> vendor=0x10ec, dev=0x8139, revid=0x10 domain=0, bus=0, slot=14, func=0 class=02-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0290, cachelnsz=0 (dwords) lattimer=0x40 (1920 ns), mingnt=0x20 (8000 ns), maxlat=0x40 (16000 ns) intpin=a, irq=11 powerspec 2 supports D0 D1 D2 D3 current D0 map[10]: type I/O Port, range 32, base 0xef00, size 8, enabled map[14]: type Memory, range 32, base 0xeff0, size 8, enabled $PIR: 0:14 INTA routed to irq 11 found-> vendor=0x1022, dev=0x2090, revid=0x03 domain=0, bus=0, slot=15, func=0 class=06-01-00, hdrtype=0x00, mfdev=1 cmdreg=0x0009, statreg=0x02a0, cachelnsz=8 (dwords) lattimer=0x40 (1920 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) map[10]: type I/O Port, range 32, base 0x6000, size 3, enabled map[14]: type I/O Port, range 32, base 0x6100, size 8, enabled map[18]: type I/O Port, range 32, base 0x6200, size 6, enabled map[1c]: type I/O Port, range 32, base 0, size 5, enabled map[20]: type I/O Port, range 32, base 0x9d00, size 7, enabled map[24]: type I/O Port, range 32, base 0x9c00, size 6, enabled ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org" Before you do anything else, get another set of hardware and try the same thing on it. I had a similar problem that turned out to be a bad SATA controller. It was only by accident that we had two identical systems, one good and one bad. -- Patrick Powell Astart Technologies papow...@astart.com1530 Jamacha Road, Suite X, Network and System San Diego, CA 92019 Consulting 858-874-6543 Web Site: www.astart.com ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Why user time of the process depends on machine load?
When I test performance of the code, I always observe dependency of CPU user time on the presence of other CPU intense processes. Same CPU-only deterministic process that on the quiet machine completes in 220 user seconds in the presence of, for example, kde rebuild would complete in 261, 266 or even 379 user seconds. I am talking about times shown by time(1), not actual an execution time. It's the same time as getrusage(2) returns in ru_utime field. Why time that process takes in user seconds depends on what other processes are running? FreeBSD-8.2 STABLE on i7 CPU @ 9200 @ 2.67GHz. Yuri ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Re: Why user time of the process depends on machine load?
In the last episode (Jun 15), Yuri said: > When I test performance of the code, I always observe dependency of CPU > user time on the presence of other CPU intense processes. Same CPU-only > deterministic process that on the quiet machine completes in 220 user > seconds in the presence of, for example, kde rebuild would complete in > 261, 266 or even 379 user seconds. I am talking about times shown by > time(1), not actual an execution time. It's the same time as getrusage(2) > returns in ru_utime field. > > Why time that process takes in user seconds depends on what other > processes are running? > > FreeBSD-8.2 STABLE on i7 CPU @ 9200 @ 2.67GHz. Some possible factors: o Intel Turbo Boost, which raises the clock rate of a single core if the other cores are idle. A single process on an idle system will run faster. o i7 chips have a shared L3 cache across all cores, so a single process on an idle system will tend to have more of its data in cache compared to a system with multiple processes, so it spends less time waiting for slower physical memory lookups. o Process accounting isn't exact. I may be wrong, but I don't think timestamps are taken every time a syscall is invoked and returns. Some time marked as "user" may actually be "system" time, in which case you may be seeing the effect of contention in the kernel as more processes are run. You may be able to disable Turbo Boot in your BIOS, which you can use to determine how much of the single-process speedup is due to that. Unrelated but still interesting note on your particular CPU: http://www.passmark.com/forum/showthread.php?t=2256 -- Dan Nelson dnel...@allantgroup.com ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Re: Why user time of the process depends on machine load?
Hi, On Wed, Jun 15, 2011 at 2:55 PM, Dan Nelson wrote: > In the last episode (Jun 15), Yuri said: >> When I test performance of the code, I always observe dependency of CPU >> user time on the presence of other CPU intense processes. Same CPU-only >> deterministic process that on the quiet machine completes in 220 user >> seconds in the presence of, for example, kde rebuild would complete in >> 261, 266 or even 379 user seconds. I am talking about times shown by >> time(1), not actual an execution time. It's the same time as getrusage(2) >> returns in ru_utime field. >> >> Why time that process takes in user seconds depends on what other >> processes are running? >> >> FreeBSD-8.2 STABLE on i7 CPU @ 9200 @ 2.67GHz. > > Some possible factors: > > o Intel Turbo Boost, which raises the clock rate of a single core if the > other cores are idle. A single process on an idle system will run faster. > > o i7 chips have a shared L3 cache across all cores, so a single process on > an idle system will tend to have more of its data in cache compared to a > system with multiple processes, so it spends less time waiting for slower > physical memory lookups. > > o Process accounting isn't exact. I may be wrong, but I don't think > timestamps are taken every time a syscall is invoked and returns. Some > time marked as "user" may actually be "system" time, in which case you may > be seeing the effect of contention in the kernel as more processes are > run. I would add hyper-threading to the list. Once you don't have enough real cores available to do the job, things do tend to slow down, unless your process is heavily i/o bound. The time process spends on a hyper-thread when it's not active still counts towards total time consumed by the process. --Artem > > You may be able to disable Turbo Boot in your BIOS, which you can use to > determine how much of the single-process speedup is due to that. > > Unrelated but still interesting note on your particular CPU: > http://www.passmark.com/forum/showthread.php?t=2256 > > -- > Dan Nelson > dnel...@allantgroup.com > ___ > freebsd-hackers@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-hackers > To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org" > ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
