Re: Reliably trigger-able ZFS panic
Tue, 04 Mar 2008 03:27:35 +0800，Xin LI <[EMAIL PROTECTED]>: The kernel is FreeBSD fs12.sina.com.cn 7.0-STABLE FreeBSD 7.0-STABLE #0: Sun Mar 2 18:50:05 CST 2008 [EMAIL PROTECTED]:/usr/obj/usr/src/sys/ZFORK amd64 the get all at below: fs12# zfs get all NAME PROPERTY VALUE SOURCE midpool type filesystem - midpool creation Fri Feb 29 15:01 2008 - midpool used 11.1M - midpool available 2.65T - midpool referenced 44.7K - midpool compressratio 1.00x - midpool mountedyes- midpool quota none default midpool reservationnone default midpool recordsize 128K default midpool mountpoint /mnt/ztest local midpool sharenfs offdefault midpool checksum on default midpool compressionoffdefault midpool atime on default midpool deviceson default midpool exec on default midpool setuid on default midpool readonly offdefault midpool jailed offdefault midpool snapdirhidden default midpool aclmodegroupmask default midpool aclinherit secure default midpool canmount on default midpool shareiscsi offdefault midpool xattr offtemporary midpool copies 1 default fs12# zpool get all midpool NAME PROPERTY VALUE SOURCE midpool bootfs- default Pawel Jakub Dawidek wrote: On Sun, Mar 02, 2008 at 03:49:03AM -0800, LI Xin wrote: Hi, The following iozone test case on ZFS would reliably trigger panic: /usr/local/bin/iozone -M -e -+u -T -t 128 -S 4096 -L 64 -R -r 4k -s 30g -i 0 -i 1 -i 2 -i 8 -+p 70 -C Thanks, I'll try to reproduce it. [...] #19 0xb55d in z_deflateInit2_ (strm=0xff00042dc8e0, level=70109184, method=68351768, windowBits=68351600, memLevel=76231808, strategy=76231808, version=Cannot access memory at address 0x00040010 ) at /usr/src/sys/modules/zfs/../../contrib/opensolaris/uts/common/zmod/deflate.c:318 Can you send me your FS configuration? zfs get all your/file/system I see that you use compression on this dataset? It was all default configuration. The pool was a RAID-Z2 without hotspare disk. The box is now running some other tests (not FreeBSD) at our Beijing Lab and we don't have remote hands in the nights, so I'm afraid that I will not be able to provide further information at this moment. Please let me know if the test run will not provoke the problem and I will ask them to see if they can spare the box in the weekend for me. Cheers, -- The Power to Serve ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: Reliably trigger-able ZFS panic
Pawel Jakub Dawidek wrote: > On Sun, Mar 02, 2008 at 03:49:03AM -0800, LI Xin wrote: >> Hi, >> >> The following iozone test case on ZFS would reliably trigger panic: >> >> /usr/local/bin/iozone -M -e -+u -T -t 128 -S 4096 -L 64 -R -r 4k -s 30g >> -i 0 -i 1 -i 2 -i 8 -+p 70 -C > > Thanks, I'll try to reproduce it. > > [...] > >> #19 0xb55d in z_deflateInit2_ (strm=0xff00042dc8e0, >> level=70109184, method=68351768, >> windowBits=68351600, memLevel=76231808, strategy=76231808, >> version=Cannot access memory at address 0x00040010 >> ) >> at >> /usr/src/sys/modules/zfs/../../contrib/opensolaris/uts/common/zmod/deflate.c:318 > > Can you send me your FS configuration? zfs get all your/file/system > I see that you use compression on this dataset? It was all default configuration. The pool was a RAID-Z2 without hotspare disk. The box is now running some other tests (not FreeBSD) at our Beijing Lab and we don't have remote hands in the nights, so I'm afraid that I will not be able to provide further information at this moment. Please let me know if the test run will not provoke the problem and I will ask them to see if they can spare the box in the weekend for me. Cheers, -- Xin LI <[EMAIL PROTECTED]> http://www.delphij.net/ FreeBSD - The Power to Serve! ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: Reliably trigger-able ZFS panic
On Sun, Mar 02, 2008 at 03:49:03AM -0800, LI Xin wrote: > Hi, > > The following iozone test case on ZFS would reliably trigger panic: > > /usr/local/bin/iozone -M -e -+u -T -t 128 -S 4096 -L 64 -R -r 4k -s 30g > -i 0 -i 1 -i 2 -i 8 -+p 70 -C Thanks, I'll try to reproduce it. [...] > #19 0xb55d in z_deflateInit2_ (strm=0xff00042dc8e0, > level=70109184, method=68351768, > windowBits=68351600, memLevel=76231808, strategy=76231808, > version=Cannot access memory at address 0x00040010 > ) > at > /usr/src/sys/modules/zfs/../../contrib/opensolaris/uts/common/zmod/deflate.c:318 Can you send me your FS configuration? zfs get all your/file/system I see that you use compression on this dataset? -- Pawel Jakub Dawidek http://www.wheel.pl [EMAIL PROTECTED] http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! pgpBXXAkxJmmK.pgp Description: PGP signature
Re: Reliably trigger-able ZFS panic
LI Xin wrote: > Hi, > > The following iozone test case on ZFS would reliably trigger panic: > > /usr/local/bin/iozone -M -e -+u -T -t 128 -S 4096 -L 64 -R -r 4k -s 30g > -i 0 -i 1 -i 2 -i 8 -+p 70 -C It can also be (eventually) triggered by "blogbench -c 100 -i 30 -r 50 -w 10 -W 10" and heavy IO load on "real" multithreaded applications like mysql (both iozone and blogbench are multithreaded). signature.asc Description: OpenPGP digital signature
