MySQL performance concern
Hello everyone, I am experimenting with MySQL running on FreeBSD and comparing with another (older) setup running on a Linux box. My results show that performance on Linux is significantly better than FreeBSD although the hardware is weaker. I'd appreciate your comments and ideas. Here's the setup: 1) FreeBSD 8.1-STABLE amd64 (Tue Sep 14 15:29:22 PDT 2010) running on a SuperMicro machine with 2 x Dual Core Xeon E5502 1.87Ghz ; 4 x SAS 15K in RAID10 setup under ZFS (two mirrored pairs) and 2 x SSD X25-E partitioned for: 8G for ZIL and the rest for L2ARC; 16G ram with 8 of them given to mysql and tons of free. 2) Linux Gentoo with 3 SATA disks in hardware RAID5 with similar cpu/motherboard and same memory size. The sole application that runs is a python script which inserts a batch of lines at a time. Only myisam is used as a format. Here's the problem: On the Linux box it manages to push around *5800*inserts/second while on the FreeBSD box it's only *4000/*second. MySQL version is 5.1.51 During this load the disk subsystem on FreeBSD is pretty much idle (both the SSDs and the SAS disks). CPU utilization contributed to mysqld is only around 30%. So I am clearly heavily under-utilizing the hardware. Linuxthreads support for 64bit architectures is not available so I couldn't try that but aside from that I tried recompiling mysql with all the different Makefile options available without any effect. Changing the recordsize in zfs to 8K doesn't make any difference. Tried percona binary without any luck. Let me know what additional information would be useful and I'll provide it here. Thank you in advance for your comments and suggestions. Cheers, Rumen Telbizov ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: MySQL performance concern
On 02/10/2010 08:06:52, Rumen Telbizov wrote: Hello everyone, I am experimenting with MySQL running on FreeBSD and comparing with another (older) setup running on a Linux box. My results show that performance on Linux is significantly better than FreeBSD although the hardware is weaker. I'd appreciate your comments and ideas. Here's the setup: 1) FreeBSD 8.1-STABLE amd64 (Tue Sep 14 15:29:22 PDT 2010) running on a SuperMicro machine with 2 x Dual Core Xeon E5502 1.87Ghz ; 4 x SAS 15K in RAID10 setup under ZFS (two mirrored pairs) and 2 x SSD X25-E partitioned for: 8G for ZIL and the rest for L2ARC; 16G ram with 8 of them given to mysql and tons of free. 2) Linux Gentoo with 3 SATA disks in hardware RAID5 with similar cpu/motherboard and same memory size. The sole application that runs is a python script which inserts a batch of lines at a time. Only myisam is used as a format. Here's the problem: On the Linux box it manages to push around *5800*inserts/second while on the FreeBSD box it's only *4000/*second. MySQL version is 5.1.51 During this load the disk subsystem on FreeBSD is pretty much idle (both the SSDs and the SAS disks). CPU utilization contributed to mysqld is only around 30%. So I am clearly heavily under-utilizing the hardware. Linuxthreads support for 64bit architectures is not available so I couldn't try that but aside from that I tried recompiling mysql with all the different Makefile options available without any effect. Changing the recordsize in zfs to 8K doesn't make any difference. Tried percona binary without any luck. Let me know what additional information would be useful and I'll provide it here. Thank you in advance for your comments and suggestions. Um... a fairly obvious point, but have you tuned the mysql configuration appropriately on both machines? I'd guess you have, but you didn't mention it. As I recall, the default configuration you get out of the box with mysql is suitable for a machine with something like 64MB RAM. Not at all appropriate nowadays where dedicated DB server hardware would be more likely to have 64*G*B than 64*M*B... Cheers, Matthew -- Dr Matthew J Seaman MA, D.Phil. 7 Priory Courtyard Flat 3 PGP: http://www.infracaninophile.co.uk/pgpkey Ramsgate JID: matt...@infracaninophile.co.uk Kent, CT11 9PW signature.asc Description: OpenPGP digital signature
60s boot hang on Xen running 8-STABLE when using ATA_CAM
I rebuilt my 8-STABLE kernel today using ATA_CAM to use the ada driver on my Xen VPS and found that the boot will hang for 60s, apparently because a CD image hasn't been configured for the virtual CD-ROM drive? After the run_interrupt_driven_hooks: still waiting after 60 seconds for xpt_config message, the boot continues and the system appears to work fine. Timecounter TSC frequency 285054 Hz quality 800 Timecounters tick every 10.000 msec lo0: bpf attached ata0: reset tp1 mask=03 ostat0=50 ostat1=00 ata0: stat0=0x50 err=0x01 lsb=0x00 msb=0x00 ata0: stat1=0x00 err=0x01 lsb=0xff msb=0xff ata0: reset tp2 stat0=50 stat1=00 devices=0x1 (aprobe0:ata0:0:0:0): SIGNATURE: ata1: reset tp1 mask=03 ostat0=50 ostat1=41 ata1: stat0=0x50 err=0x01 lsb=0xff msb=0xff ata1: stat1=0x00 err=0x01 lsb=0x14 msb=0xeb ata1: reset tp2 stat0=50 stat1=00 devices=0x20001 (aprobe0:ata1:0:0:0): SIGNATURE: ata1: reset tp1 mask=03 ostat0=50 ostat1=00 ata1: stat0=0x50 err=0x01 lsb=0xff msb=0xff ata1: stat1=0x00 err=0x01 lsb=0x14 msb=0xeb ata1: reset tp2 stat0=50 stat1=00 devices=0x20001 (aprobe0:ata1:0:0:0): ATA_IDENTIFY. ACB: ec 00 00 00 00 40 00 00 00 00 00 00 (aprobe0:ata1:0:0:0): CAM status: Command timeout (aprobe0:ata1:0:0:0): SIGNATURE: run_interrupt_driven_hooks: still waiting after 60 seconds for xpt_config ata1: reset tp1 mask=03 ostat0=50 ostat1=00 ata1: stat0=0x50 err=0x01 lsb=0xff msb=0xff ata1: stat1=0x00 err=0x01 lsb=0x14 msb=0xeb ata1: reset tp2 stat0=50 stat1=00 devices=0x20001 (aprobe0:ata1:0:0:0): ATA_IDENTIFY. ACB: ec 00 00 00 00 40 00 00 00 00 00 00 (aprobe0:ata1:0:0:0): CAM status: Command timeout (aprobe0:ata1:0:1:0): SIGNATURE: eb14 ada0 at ata0 bus 0 scbus0 target 0 lun 0 ada0: QEMU HARDDISK 0.9.1 ATA-7GEOM: new disk ada0 device ada0: Serial Number QM1 ada0: 16.700MB/s transfers (WDMA2, PIO 8192bytes) ada0: 10752MB (22020096 512 byte sectors: 16H 63S/T 16383C) A full verbose dmesg is available at http://www.cran.org.uk/~brucec/freebsd/dmesg.ATA_CAM.hang.txt -- Bruce Cran ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: MySQL performance concern
On Sat, 02 Oct 2010 09:06:52 +0200, Rumen Telbizov telbi...@gmail.com wrote: Hello everyone, I am experimenting with MySQL running on FreeBSD and comparing with another (older) setup running on a Linux box. My results show that performance on Linux is significantly better than FreeBSD although the hardware is weaker. I'd appreciate your comments and ideas. Here's the setup: 1) FreeBSD 8.1-STABLE amd64 (Tue Sep 14 15:29:22 PDT 2010) running on a SuperMicro machine with 2 x Dual Core Xeon E5502 1.87Ghz ; 4 x SAS 15K in RAID10 setup under ZFS (two mirrored pairs) and 2 x SSD X25-E partitioned for: 8G for ZIL and the rest for L2ARC; 16G ram with 8 of them given to mysql and tons of free. 2) Linux Gentoo with 3 SATA disks in hardware RAID5 with similar cpu/motherboard and same memory size. The sole application that runs is a python script which inserts a batch of lines at a time. Only myisam is used as a format. Here's the problem: On the Linux box it manages to push around *5800*inserts/second while on the FreeBSD box it's only *4000/*second. MySQL version is 5.1.51 During this load the disk subsystem on FreeBSD is pretty much idle (both the SSDs and the SAS disks). CPU utilization contributed to mysqld is only around 30%. So I am clearly heavily under-utilizing the hardware. Linuxthreads support for 64bit architectures is not available so I couldn't try that but aside from that I tried recompiling mysql with all the different Makefile options available without any effect. Changing the recordsize in zfs to 8K doesn't make any difference. Tried percona binary without any luck. Let me know what additional information would be useful and I'll provide it here. Thank you in advance for your comments and suggestions. Cheers, Rumen Telbizov Your app is singlethreaded I presume, so the multi-cores are not relevant in this story. Do you have the same indexes on the tables on both servers? Do they both have the same way to connect with mysql? Unix sockets or localhost? Do they both run mysql 5.1.51, because you mention the Linux one is older? Ronald. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
device names changes for adX.
Hi, When I installed FreeBSD 8.1-RELEASE (freebsd-update) the adX devices changed index number and the machine obviously didnt boot. Due to this I hesitate to install 8.1 on my servers remote. How do I know if and to what the devices will change? -- Peter Ankerstål pe...@pean.org http://www.pean.org/ ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: device names changes for adX.
Peter Ankerstål wrote: Hi, When I installed FreeBSD 8.1-RELEASE (freebsd-update) the adX devices changed index number and the machine obviously didnt boot. Due to this I hesitate to install 8.1 on my servers remote. How do I know if and to what the devices will change? -- Peter Ankerstål pe...@pean.org http://www.pean.org/ ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org label your filesystems and mount them by label rather than by device name. see man glabel -- SY, Marat
Broken SASL/Kerberos authentication: openldap client GSSAPI authentication segfaults on FreeBSD 8.1 Release too
Hello I use the system as a mail server (Cyrus Impad) which I authenticate against Kerberos5 (Windows Active Directory) with Cyrus SASL (saslauthd -a kerberos5). Here are the details: cyrus-imapd-2.3.16_2 The cyrus mail server, supporting POP3 and IMAP4 protocols cyrus-sasl-2.1.23 RFC SASL (Simple Authentication and Security Layer) cyrus-sasl-saslauthd-2.1.23 SASL authentication server for cyrus-sasl2 My system: FreeBSD acsvfbsd04.acutronic.ch 8.1-RELEASE FreeBSD 8.1-RELEASE #0: Thu Sep 30 12:33:18 CEST 2010 mar...@acsvfbsd04.acutronic.ch:/usr/obj/usr/src/sys/GENERIC i386 After I upgaded from 7.2 to 8.1 the SASL authentication (with Kerberos5) is broken. See http://docs.freebsd.org/cgi/getmsg.cgi?fetch=301304+0+archive/2010/freebsd-stable/20100718.freebsd-stable and the following threads. See alo PR 147454. I did what you suggested in different threads around july regarding the subject: 1. cvsup a fresh copy of RELEASE 8.1 in /usr/src 2. Now I apply the patch in /usr/src with patch -p1 -E patch name 3. Now I make buildworld make buidlkernel make installkernel and I get the following messages: cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb acc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/ker cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb make: don't know how to make /usr/obj/usr/src/tmp/usr/lib/libpthread.a. Stop *** Error code 2 Stop in /usr/src. What I'm doing wrong? Kind regards, -- Martin Schweizer off...@pc-service.ch PC-Service M. Schweizer GmbH; Bannholzstrasse 6; CH-8608 Bubikon Tel. +41 55 243 30 00; Fax: +41 55 243 33 22 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
out of HDD space - zfs degraded
Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt - no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing to stdout at offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output to stdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28A at scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28A at scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28A at scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28A at scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28A at scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28A at scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AAB at scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02 at scbus10 target 0 lun 0 (pass9,ada8) I'm not yet sure if the drive is fully dead or not. This is not a hot-swap box. I'm guessing the first step is to get ada0 back online and then in the zpool. However, I'm reluctant to do a 'camcontrol scan' on this box as it it froze up the system the last time I tried that: http://docs.freebsd.org/cgi/mid.cgi?4C78FF01.5020500 Any suggestions for getting the drive back
Re: device names changes for adX.
On Sat, Oct 02, 2010 at 02:55:02PM +0200, Peter Ankerstål wrote: When I installed FreeBSD 8.1-RELEASE (freebsd-update) the adX devices changed index number and the machine obviously didnt boot. Due to this I hesitate to install 8.1 on my servers remote. How do I know if and to what the devices will change? Please see this thread: http://www.mail-archive.com/freebsd-stable@freebsd.org/msg112349.html -- | Jeremy Chadwick j...@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Broken SASL/Kerberos authentication: openldap client GSSAPI authentication segfaults on FreeBSD 8.1 Release too
On Sat, Oct 02, 2010 at 03:11:07PM +0200, Martin Schweizer wrote: [...] 3. Now I make buildworld make buidlkernel make installkernel and I get the following messages: [...] cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb make: don't know how to make /usr/obj/usr/src/tmp/usr/lib/libpthread.a. Stop *** Error code 2 Stop in /usr/src. What I'm doing wrong? Did you specify any -j flags during your make buildworld (ex. make -j2 buildworld)? If so, please remove them and restart the build. Then you will see where the actual compile/make error happens. From the above output, it doesn't look like it's related to the Kerberos or libgssapi stuff. -- | Jeremy Chadwick j...@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: out of HDD space - zfs degraded
On Sat, Oct 02, 2010 at 09:43:30AM -0400, Dan Langille wrote: Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt - no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing to stdout at offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output to stdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28A at scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28A at scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28A at scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28A at scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28A at scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28A at scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AAB at scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02 at scbus10 target 0 lun 0 (pass9,ada8) I'm not yet sure if the drive is fully dead or not. This is not a hot-swap box. It looks to me like the disk labelled gpt/disk06-live literally stopped responding to commands. The errors you see are coming from the OS and the siis(4) controller, and
Re: device names changes for adX.
Peter Ankerstål wrote: Hi, When I installed FreeBSD 8.1-RELEASE (freebsd-update) the adX devices changed index number and the machine obviously didnt boot. Due to this I hesitate to install 8.1 on my servers remote. How do I know if and to what the devices will change? -- Peter Ankerstål pe...@pean.org http://www.pean.org/ ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org label your filesystems and mount them by label rather than by device name. see man glabel -- SY, Marat Thanks, I may try that. But how will this affect ZFS raidz set up to use ad-drives? Like this: tankONLINE 0 0 0 raidz1ONLINE 0 0 0 ad10s2 ONLINE 0 0 0 ad12ONLINE 0 0 0 ad14ONLINE 0 0 0 ad16ONLINE 0 0 0 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: RELENG_7 em problems (and RELENG_8)
Hi Jack, Two quick notes about the new driver. On the server that was having nic lockups, so far so good. Saturday AM, the box would take a lot of level0 dumps as well as do about 70Mb/s of outbound rsync traffic. By now, the nic would have wedged at least once So far so good! On different, new box, I decided to try HEAD, with the new driver, and ran into problems with the onboard nic e...@pci0:0:25:0:class=0x02 card=0x00368086 chip=0x10f08086 rev=0x06 hdr=0x00 vendor = 'Intel Corporation' class = network subclass = ethernet cap 01[c8] = powerspec 2 supports D0 D3 current D0 cap 05[d0] = MSI supports 1 message, 64 bit enabled with 1 message cap 13[e0] = PCI Advanced Features: FLR TP em0: Intel(R) PRO/1000 Network Connection 7.0.5 port 0xf020-0xf03f mem 0xfe50-0xfe51,0xfe527000-0xfe527fff irq 20 at device 25.0 on pci0 em0: Using MSI interrupt em0: [FILTER] em0: Ethernet address: 70:71:bc:09:5e:aa This is an intel branded desktop board acpi0: INTEL DH55TC on motherboard I find I have to disable rx and tx csum on the interface, otherwise there are a lot of re-transmits due to missed packets. tcpdump implies the packets are going out, but it seems never to get out. The mother board is at the office on an unmanaged switch right now, so I dont have any stats from the switch. But tcpdump shows a lot of outbound re-transmits. Turning off rxcsum and txcsum fixes the problem. dev.em.0.%desc: Intel(R) PRO/1000 Network Connection 7.0.8 dev.em.0.%driver: em dev.em.0.%location: slot=25 function=0 handle=\_SB_.PCI0.GBE_ dev.em.0.%pnpinfo: vendor=0x8086 device=0x10f0 subvendor=0x8086 subdevice=0x0036 class=0x02 dev.em.0.%parent: pci0 dev.em.0.nvm: -1 dev.em.0.rx_int_delay: 0 dev.em.0.tx_int_delay: 66 dev.em.0.rx_abs_int_delay: 66 dev.em.0.tx_abs_int_delay: 66 dev.em.0.rx_processing_limit: 100 dev.em.0.link_irq: 0 dev.em.0.mbuf_alloc_fail: 0 dev.em.0.cluster_alloc_fail: 0 dev.em.0.dropped: 0 dev.em.0.tx_dma_fail: 0 dev.em.0.rx_overruns: 0 dev.em.0.watchdog_timeouts: 0 dev.em.0.device_control: 1074790976 dev.em.0.rx_control: 67141634 dev.em.0.fc_high_water: 8192 dev.em.0.fc_low_water: 6692 dev.em.0.queue0.txd_head: 15 dev.em.0.queue0.txd_tail: 17 dev.em.0.queue0.tx_irq: 0 dev.em.0.queue0.no_desc_avail: 0 dev.em.0.queue0.rxd_head: 843 dev.em.0.queue0.rxd_tail: 842 dev.em.0.queue0.rx_irq: 0 dev.em.0.mac_stats.excess_coll: 0 dev.em.0.mac_stats.single_coll: 0 dev.em.0.mac_stats.multiple_coll: 0 dev.em.0.mac_stats.late_coll: 0 dev.em.0.mac_stats.collision_count: 0 dev.em.0.mac_stats.symbol_errors: 0 dev.em.0.mac_stats.sequence_errors: 0 dev.em.0.mac_stats.defer_count: 0 dev.em.0.mac_stats.missed_packets: 0 dev.em.0.mac_stats.recv_no_buff: 0 dev.em.0.mac_stats.recv_undersize: 0 dev.em.0.mac_stats.recv_fragmented: 0 dev.em.0.mac_stats.recv_oversize: 0 dev.em.0.mac_stats.recv_jabber: 0 dev.em.0.mac_stats.recv_errs: 0 dev.em.0.mac_stats.crc_errs: 0 dev.em.0.mac_stats.alignment_errs: 0 dev.em.0.mac_stats.coll_ext_errs: 0 dev.em.0.mac_stats.xon_recvd: 80 dev.em.0.mac_stats.xon_txd: 0 dev.em.0.mac_stats.xoff_recvd: 82 dev.em.0.mac_stats.xoff_txd: 0 dev.em.0.mac_stats.total_pkts_recvd: 35697 dev.em.0.mac_stats.good_pkts_recvd: 35535 dev.em.0.mac_stats.bcast_pkts_recvd: 231 dev.em.0.mac_stats.mcast_pkts_recvd: 85 dev.em.0.mac_stats.rx_frames_64: 0 dev.em.0.mac_stats.rx_frames_65_127: 0 dev.em.0.mac_stats.rx_frames_128_255: 0 dev.em.0.mac_stats.rx_frames_256_511: 0 dev.em.0.mac_stats.rx_frames_512_1023: 0 dev.em.0.mac_stats.rx_frames_1024_1522: 0 dev.em.0.mac_stats.good_octets_recvd: 14878015 dev.em.0.mac_stats.good_octets_txd: 14051783 dev.em.0.mac_stats.total_pkts_txd: 45313 dev.em.0.mac_stats.good_pkts_txd: 45313 dev.em.0.mac_stats.bcast_pkts_txd: 3 dev.em.0.mac_stats.mcast_pkts_txd: 5 dev.em.0.mac_stats.tx_frames_64: 0 dev.em.0.mac_stats.tx_frames_65_127: 0 dev.em.0.mac_stats.tx_frames_128_255: 0 dev.em.0.mac_stats.tx_frames_256_511: 0 dev.em.0.mac_stats.tx_frames_512_1023: 0 dev.em.0.mac_stats.tx_frames_1024_1522: 0 dev.em.0.mac_stats.tso_txd: 2788 dev.em.0.mac_stats.tso_ctx_fail: 0 dev.em.0.interrupts.asserts: 48733 dev.em.0.interrupts.rx_pkt_timer: 0 dev.em.0.interrupts.rx_abs_timer: 0 dev.em.0.interrupts.tx_pkt_timer: 0 dev.em.0.interrupts.tx_abs_timer: 0 dev.em.0.interrupts.tx_queue_empty: 0 dev.em.0.interrupts.tx_queue_min_thresh: 0 dev.em.0.interrupts.rx_desc_min_thresh: 0 dev.em.0.interrupts.rx_overrun: 0 dev.em.0.wake: 0 At 08:00 PM 9/26/2010, Jack Vogel wrote: The system I've had stress tests running on has 82574 LOMs, so I hope it will solve the problem, will see tomorrow morning at how things have held up... Jack On Sun, Sep 26, 2010 at 4:43 PM, Mike Tancsa mailto:m...@sentex.netm...@sentex.net wrote: At 06:19 PM 9/26/2010, Jack Vogel wrote: Your em1 is using MSI not MSIX and thus can't have multiple queues. I'm not sure whats broken from what you show here. I will try to get the new driver out shortly for you
RE: if_rtdel: error 47 (netgraph or mpd issue?)
FYI, I disabled ipv6 in mpd as well as set ipv6_enable=NO and the box has been stable for 2 weeks now. Previously, it would crash every 5 days or so. Something in inet6 or mpd ? ---Mike At 01:59 PM 9/17/2010, Mike Tancsa wrote: At 12:51 PM 9/10/2010, Mike Tancsa wrote: FYI, I enabled witness in the kernel and am seeing the following uma_zalloc_arg: zone 128 with the following non-sleepable locks held: exclusive rw ifnet_rw (ifnet_rw) r = 0 (0xc0b56ec4) locked @ /usr/src/sys/net/if.c:419 Hi, Another crash. I had it break to the serial debugger this time Fatal trap 12: page fault while in kernel mode cpuid = 1; apic id = 01 fault virtual address = 0x24 fault code = supervisor read, page not present instruction pointer = 0x20:0xc64c79e4 stack pointer = 0x28:0xe7c84864 frame pointer = 0x28:0xe7c84a9c code segment= base 0x0, limit 0xf, type 0x1b = DPL 0, pres 1, def32 1, gran 1 processor eflags= interrupt enabled, resume, IOPL = 0 current process = 1280 (mpd5) [thread pid 1280 tid 100096 ] Stopped at ng_path2noderef+0x174: testb $0x1,0x24(%esi) db bt Tracing pid 1280 tid 100096 td 0xc58f7780 ng_path2noderef(cace4b80,cb0a5350,e7c84ab8,e7c84ab4,0,...) at ng_path2noderef+0x174 ng_address_path(cace4b80,c64d4400,cb0a5350,0,28885ba0,...) at ng_address_path+0x40 ngc_send(cb66db44,0,cb2f4500,cba946f0,0,...) at ngc_send+0x182 sosend_generic(cb66db44,cba946f0,e7c84bec,0,0,...) at sosend_generic+0x50d sosend(cb66db44,cba946f0,e7c84bec,0,0,...) at sosend+0x3f kern_sendit(c58f7780,8d,e7c84c60,0,0,...) at kern_sendit+0x107 sendit(0,cba946f0,7,e7c84c7c,1,...) at sendit+0xb1 sendto(c58f7780,e7c84cf8,c093d225,c091bcfe,282,...) at sendto+0x48 syscall(e7c84d38) at syscall+0x1da Xint0x80_syscall() at Xint0x80_syscall+0x21 --- syscall (133, FreeBSD ELF32, sendto), eip = 0x284b13c7, esp = 0xbf9fe4cc, ebp = 0xbf9fe4f8 --- db where Tracing pid 1280 tid 100096 td 0xc58f7780 ng_path2noderef(cace4b80,cb0a5350,e7c84ab8,e7c84ab4,0,...) at ng_path2noderef+0x174 ng_address_path(cace4b80,c64d4400,cb0a5350,0,28885ba0,...) at ng_address_path+0x40 ngc_send(cb66db44,0,cb2f4500,cba946f0,0,...) at ngc_send+0x182 sosend_generic(cb66db44,cba946f0,e7c84bec,0,0,...) at sosend_generic+0x50d sosend(cb66db44,cba946f0,e7c84bec,0,0,...) at sosend+0x3f kern_sendit(c58f7780,8d,e7c84c60,0,0,...) at kern_sendit+0x107 sendit(0,cba946f0,7,e7c84c7c,1,...) at sendit+0xb1 sendto(c58f7780,e7c84cf8,c093d225,c091bcfe,282,...) at sendto+0x48 syscall(e7c84d38) at syscall+0x1da Xint0x80_syscall() at Xint0x80_syscall+0x21 --- syscall (133, FreeBSD ELF32, sendto), eip = 0x284b13c7, esp = 0xbf9fe4cc, ebp = 0xbf9fe4f8 --- db show locks exclusive sx so_snd_sx (so_snd_sx) r = 0 (0xcb66dc64) locked @ /usr/src/sys/kern/uipc_sockbuf.c:148 db show alllocks Process 1928 (sshd) thread 0xc6402a00 (100094) exclusive sx so_rcv_sx (so_rcv_sx) r = 0 (0xc669a898) locked @ /usr/src/sys/kern/uipc_sockbuf.c:148 Process 1281 (ng_queue) thread 0xc58f6a00 (100057) shared rw radix node head (radix node head) r = 0 (0xc56e1580) locked @ /usr/src/sys/net/route.c:362 Process 1280 (mpd5) thread 0xc58f7780 (100096) exclusive sx so_snd_sx (so_snd_sx) r = 0 (0xcb66dc64) locked @ /usr/src/sys/kern/uipc_sockbuf.c:148 db call doadump() Physical memory: 2032 MB Dumping 274 MB: 259 243 227 211 195 179 163 147 131 115 99 83 67 51 35 19 3 Dump complete panic: GNU gdb 6.1.1 [FreeBSD] Copyright 2004 Free Software Foundation, Inc. GDB is free software, covered by the GNU General Public License, and you are welcome to change it and/or distribute copies of it under certain conditions. Type show copying to see the conditions. There is absolutely no warranty for GDB. Type show warranty for details. This GDB was configured as i386-marcel-freebsd... Unread portion of the kernel message buffer: Fatal trap 12: page fault while in kernel mode cpuid = 1; apic id = 01 fault virtual address = 0x24 fault code = supervisor read, page not present instruction pointer = 0x20:0xc64c79e4 stack pointer = 0x28:0xe7c84864 frame pointer = 0x28:0xe7c84a9c code segment= base 0x0, limit 0xf, type 0x1b = DPL 0, pres 1, def32 1, gran 1 processor eflags= interrupt enabled, resume, IOPL = 0 current process = 1280 (mpd5) Physical memory: 2032 MB Dumping 274 MB: 259 243 227 211 195 179 163 147 131 115 99 83 67 51 35 19 3 #0 doadump () at pcpu.h:231 231 pcpu.h: No such file or directory. in pcpu.h (kgdb) #0 doadump () at pcpu.h:231 #1 0xc04a5899 in db_fncall (dummy1=1, dummy2=0, dummy3=-1061510048, dummy4=0xe7c84600 ) at /usr/src/sys/ddb/db_command.c:548 #2 0xc04a5c91 in db_command (last_cmdp=0xc09cf71c, cmd_table=0x0, dopager=1) at /usr/src/sys/ddb/db_command.c:445 #3 0xc04a5dea in db_command_loop () at /usr/src/sys/ddb/db_command.c:498 #4 0xc04a7c6d
Re: MySQL performance concern
When you say similar hardware whets the actual spec? What do you have set in my.cnf? What config options are you using for zfs? - Original Message - From: Rumen Telbizov telbi...@gmail.com To: freebsd-stable@freebsd.org Sent: Saturday, October 02, 2010 8:06 AM Subject: MySQL performance concern Hello everyone, I am experimenting with MySQL running on FreeBSD and comparing with another (older) setup running on a Linux box. My results show that performance on Linux is significantly better than FreeBSD although the hardware is weaker. I'd appreciate your comments and ideas. Here's the setup: 1) FreeBSD 8.1-STABLE amd64 (Tue Sep 14 15:29:22 PDT 2010) running on a SuperMicro machine with 2 x Dual Core Xeon E5502 1.87Ghz ; 4 x SAS 15K in RAID10 setup under ZFS (two mirrored pairs) and 2 x SSD X25-E partitioned for: 8G for ZIL and the rest for L2ARC; 16G ram with 8 of them given to mysql and tons of free. 2) Linux Gentoo with 3 SATA disks in hardware RAID5 with similar cpu/motherboard and same memory size. The sole application that runs is a python script which inserts a batch of lines at a time. Only myisam is used as a format. Here's the problem: On the Linux box it manages to push around *5800*inserts/second while on the FreeBSD box it's only *4000/*second. MySQL version is 5.1.51 During this load the disk subsystem on FreeBSD is pretty much idle (both the SSDs and the SAS disks). CPU utilization contributed to mysqld is only around 30%. So I am clearly heavily under-utilizing the hardware. Linuxthreads support for 64bit architectures is not available so I couldn't try that but aside from that I tried recompiling mysql with all the different Makefile options available without any effect. Changing the recordsize in zfs to 8K doesn't make any difference. Tried percona binary without any luck. Let me know what additional information would be useful and I'll provide it here. Thank you in advance for your comments and suggestions. Cheers, Rumen Telbizov ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmas...@multiplay.co.uk. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: device names changes for adX.
On 02/10/2010 15:29:49, Peter Ankerstål wrote: Peter Ankerstål wrote: When I installed FreeBSD 8.1-RELEASE (freebsd-update) the adX devices changed index number and the machine obviously didnt boot. Due to this I hesitate to install 8.1 on my servers remote. How do I know if and to what the devices will change? label your filesystems and mount them by label rather than by device name. see man glabel Thanks, I may try that. But how will this affect ZFS raidz set up to use ad-drives? Like this: tankONLINE 0 0 0 raidz1ONLINE 0 0 0 ad10s2 ONLINE 0 0 0 ad12ONLINE 0 0 0 ad14ONLINE 0 0 0 ad16ONLINE 0 0 0 It actually shouldn't matter. ZFS writes metadata about the zpools, zdevs etc. it knows about onto the drives, and if it can read the drive and see the metadata, it can reconstruct itself. You can take disks out of a ZFS setup, shuffle them, stick them back into the wrong slots, and ZFS will still work. Similarly, you can use glabel to name the disks, and switch to using that, and everything should still work. In fact, if you glabel the disks while ZFS is still active, it should instantly recognise all the new names and update the 'zpool status' output on the fly. Actually, that last is probably the right way to do things -- you'll update the zpool.cache that way, which means that ZFS will come up without any remedial action after reboot. Cheers, Matthew -- Dr Matthew J Seaman MA, D.Phil. 7 Priory Courtyard Flat 3 PGP: http://www.infracaninophile.co.uk/pgpkey Ramsgate JID: matt...@infracaninophile.co.uk Kent, CT11 9PW signature.asc Description: OpenPGP digital signature
Re: device names changes for adX.
On Sat, 02 Oct 2010 16:13:28 +0100 Matthew Seaman m.sea...@infracaninophile.co.uk wrote: In fact, if you glabel the disks while ZFS is still active, it should instantly recognise all the new names and update the 'zpool status' output on the fly. Actually, that last is probably the right way to do things -- you'll update the zpool.cache that way, which means that ZFS will come up without any remedial action after reboot. Since glabel writes metadata to disk, won't doing this on a disk with a filesystem corrupt something? -- Bruce Cran ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: Broken SASL/Kerberos authentication: openldap client GSSAPI authentication segfaults on FreeBSD 8.1 Release too
Hello Jeremy Am Sat, Oct 02, 2010 at 07:11:46AM -0700 Jeremy Chadwick schrieb: On Sat, Oct 02, 2010 at 03:11:07PM +0200, Martin Schweizer wrote: [...] 3. Now I make buildworld make buidlkernel make installkernel and I get the following messages: [...] cc -fpic -DPIC -O2 -pipe -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi -I/usr/src/kerberos5/lib/libgssapi/../../../crypto/heimdal/lib/gssapi/krb5 -I/usr/src/kerb make: don't know how to make /usr/obj/usr/src/tmp/usr/lib/libpthread.a. Stop *** Error code 2 Stop in /usr/src. What I'm doing wrong? Did you specify any -j flags during your make buildworld (ex. make -j2 buildworld)? If so, please remove them and restart the build. Then you will see where the actual compile/make error happens. From the above output, it doesn't look like it's related to the Kerberos or libgssapi stuff. No, I did not use any flags when I did start make buildworld. Regards, -- Martin Schweizer off...@pc-service.ch PC-Service M. Schweizer GmbH; Bannholzstrasse 6; CH-8608 Bubikon Tel. +41 55 243 30 00; Fax: +41 55 243 33 22 ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
utmp.h exists or not in RELENG_8?
My system is RELENG_8 and I have checkout by via csup today. It shows that utmp.h still exists in RELENG_8. But when I see this PR: http://www.freebsd.org/cgi/query-pr.cgi?pr=ports/149945 I have decided to check in the http://www.freebsd.org/cgi/cvsweb.cgi/src/include/?only_with_tag=RELENG_8 ... It shows that utmp.h has been removed. But in the http://sources.freebsd.org/RELENG_8/src/include/ shows a different story as it exists. I am confusing... Is it supposed to be deleted in CVS when it did the SVN-CVS? Or what? I don't have svn installed in my system at the moment, so can't check it now. Please add me in the CC as I am not in the list. Cheers, Mezz -- mezz.free...@gmail.com - m...@freebsd.org FreeBSD GNOME Team http://www.FreeBSD.org/gnome/ - gn...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: utmp.h exists or not in RELENG_8?
On Sat, Oct 02, 2010 at 12:22:22PM -0500, Jeremy Messenger wrote: My system is RELENG_8 and I have checkout by via csup today. It shows that utmp.h still exists in RELENG_8. But when I see this PR: http://www.freebsd.org/cgi/query-pr.cgi?pr=ports/149945 I have decided to check in the http://www.freebsd.org/cgi/cvsweb.cgi/src/include/?only_with_tag=RELENG_8 ... It shows that utmp.h has been removed. But in the http://sources.freebsd.org/RELENG_8/src/include/ shows a different story as it exists. I am confusing... Is it supposed to be deleted in CVS when it did the SVN-CVS? Or what? I don't have svn installed in my system at the moment, so can't check it now. utmp.h has been removed in HEAD (9.x) but is still present in 8.x and earlier branches. It looks like cvsweb is buggy in this area. The build error in ports/149945 may be caused by a stray utmpx related file found by the configure process. Partly because the various unix variant developers have made a mess of utmp/utmpx, the code to use it is rather fragile. -- Jilles Tjoelker ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: utmp.h exists or not in RELENG_8?
On 2 October 2010 21:22, Jeremy Messenger mezz.free...@gmail.com wrote: My system is RELENG_8 and I have checkout by via csup today. It shows that utmp.h still exists in RELENG_8. But when I see this PR: http://www.freebsd.org/cgi/query-pr.cgi?pr=ports/149945 I have decided to check in the http://www.freebsd.org/cgi/cvsweb.cgi/src/include/?only_with_tag=RELENG_8 ... It shows that utmp.h has been removed. But in the http://sources.freebsd.org/RELENG_8/src/include/ shows a different story as it exists. I am confusing... Is it supposed to be deleted in CVS when it did the SVN-CVS? Or what? I don't have svn installed in my system at the moment, so can't check it now. Please add me in the CC as I am not in the list. I have a suspect, cvsweb.cgi handles such case incorrectly, i.e. when file is removed in MAIN branch, but it exists in BRANCH_X, then passing the only_with_tag=RELENG_X will show such file in Attic. -- wbr, pluknet ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
is there a bug in AWK on 6.x and 7.x (fixed in 8.x)?
I think there is a bug in AWK in base of FreeBSD 6.x and 7.x (tested on 6.4 i386 and 7.3 i386) I have this simple test case, where I want 2 columns from GeoIP CSV file: awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv It should produce output like this: # awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 (above is taken from FreeBSD 8.1 i386) On FreeBSD 6.4 and 7.3 it results in broken first line: awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0,1.7.255.255,16777216,17301503,AU,Australia- 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 There are no errors in CSV file, it doesn't metter if I delete the affected first line from the file. It is reproducible with handmade file: # cat test.csv 1.9.0.0,1.9.255.255,17367040,17432575,MY,Malaysia 1.10.10.0,1.10.10.255,17435136,17435391,AU,Australia 1.11.0.0,1.11.255.255,17498112,17563647,KR,Korea, Republic of 1.12.0.0,1.15.255.255,17563648,17825791,CN,China 1.16.0.0,1.19.255.255,17825792,18087935,KR,Korea, Republic of 1.21.0.0,1.21.255.255,18153472,18219007,JP,Japan # awk 'FS=, { print $1-$2 }' test.csv 1.9.0.0,1.9.255.255,17367040,17432575,MY,Malaysia- 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 1.16.0.0-1.19.255.255 1.21.0.0-1.21.255.255 As it works in 8.1, can it be fixed in 7-STABLE? (I don't know if it was purposely fixed or if it is coincidence of newer version of AWK in 8.x) Should I file PR for it? Miroslav Lachman ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: MySQL performance concern
Hello everyone, Here's the requested information below: FreeBSD mysql 5.1.51: my.cnf: skip-external-locking key_buffer_size = 8192M max_allowed_packet = 16M table_open_cache = 2048 sort_buffer_size = 64M read_buffer_size = 8M read_rnd_buffer_size = 16M myisam_sort_buffer_size = 256M thread_cache_size = 64 query_cache_size = 32M thread_concurrency = 8 max_heap_table_size = 6G hardware: FreeBSD 8.1-STABLE amd64 (Tue Sep 14 15:29:22 PDT 2010) running on a SuperMicro machine with X8DTU motherboard and 2 x Dual Core Xeon E5502 1.87Ghz ; 4 x SAS 15K in RAID10 setup under ZFS (two mirrored pairs) and 2 x SSD X25-E partitioned for: 8G for ZIL and the rest for L2ARC; 16G RAM. Disk controller is LSI 4Hi in IT (Initiator Target) mode. -- Linux Gentoo (2.6.18-164.10.1.el5.028stab067.4) mysql 5.1.50 -- my.cnf: skip-external-locking key_buffer = 4G max_heap_table_size = 6G max_allowed_packet = 1M table_cache = 64 sort_buffer_size= 512K net_buffer_length = 8K read_buffer_size= 256K read_rnd_buffer_size= 512K myisam_sort_buffer_size = 8M Linux runs as an OpenVZ VE inside CentOS. It's the only VE and has all the memory allocated to it hardware node: 2 x Xeon Quad E5410 @ 2.33GHz on SuperMicro X7DBU motherboard; 16G RAM; 4 SATA 1T disks in hardware raid 5 attached to a 3ware controller; NO SSDs Some other notes: * It is indeed a single thread which inserts into the mysql so yes it's only one core which handles the application and another one for MySQL. What is interesting here, like I mentioned, is that on FreeBSD mysql process doesn't get more than 30-40% CPU utilization. So it has a lot of headroom. gstat also shows 0% disk load * It is exactly the same database schema. In fact it's only one table that's inserted heavily into. It is a partition table with only one HASH index which looks something like this: PRIMARY KEY (`IntField`,`DateField`,`Varchar150Field`) USING HASH. The speed difference is obvious right from the beginning. I don't have to wait for any data to accrue to see a degradation. I don't wait for more than a 100'000 records to be processed. * Application maintains only 1 local TCP connection to mysql. They both run on the same host * As for the ZFS. Here's the pool configuration: pool: tank config: NAME STATE READ WRITE CKSUM tank ONLINE 0 0 0 mirror ONLINE 0 0 0 gpt/tank0 ONLINE 0 0 0 gpt/tank1 ONLINE 0 0 0 mirror ONLINE 0 0 0 gpt/tank2 ONLINE 0 0 0 gpt/tank3 ONLINE 0 0 0 logs ONLINE 0 0 0 mirror ONLINE 0 0 0 gpt/zil0 ONLINE 0 0 0 gpt/zil1 ONLINE 0 0 0 cache gpt/l2arc0 ONLINE 0 0 0 gpt/l2arc1 ONLINE 0 0 0 pool: zroot config: NAMESTATE READ WRITE CKSUM zroot ONLINE 0 0 0 mirrorONLINE 0 0 0 gpt/zroot0 ONLINE 0 0 0 gpt/zroot1 ONLINE 0 0 0 zroot is a couple of small partitions from two of the same SAS disks. zil and l2arc are 8 and 22G partitions from 32G SSDs I pretty much have no zfs tuning done since from what I've found there shouldn't be any needed since I'm running 8.1 on a 64bit machine. Let me know if you'd like me to experiment with any ... Some additional information: # sysctl vm.kmem_size vm.kmem_size: 5539958784 # sysctl vm.kmem_size_max vm.kmem_size_max: 329853485875 # sysctl vfs.zfs.arc_max vfs.zfs.arc_max: 4466216960 I think this answers all the questions so far. Let me know what you think. I might be missing something obvious. Thank you, Rumen Telbizov ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: utmp.h exists or not in RELENG_8?
Thanks all, it's cvsweb bug then.. Cheers, Mezz On Sat, Oct 2, 2010 at 12:22 PM, Jeremy Messenger mezz.free...@gmail.com wrote: My system is RELENG_8 and I have checkout by via csup today. It shows that utmp.h still exists in RELENG_8. But when I see this PR: http://www.freebsd.org/cgi/query-pr.cgi?pr=ports/149945 I have decided to check in the http://www.freebsd.org/cgi/cvsweb.cgi/src/include/?only_with_tag=RELENG_8 ... It shows that utmp.h has been removed. But in the http://sources.freebsd.org/RELENG_8/src/include/ shows a different story as it exists. I am confusing... Is it supposed to be deleted in CVS when it did the SVN-CVS? Or what? I don't have svn installed in my system at the moment, so can't check it now. Please add me in the CC as I am not in the list. Cheers, Mezz -- mezz.free...@gmail.com - m...@freebsd.org FreeBSD GNOME Team http://www.FreeBSD.org/gnome/ - gn...@freebsd.org -- mezz.free...@gmail.com - m...@freebsd.org FreeBSD GNOME Team http://www.FreeBSD.org/gnome/ - gn...@freebsd.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: is there a bug in AWK on 6.x and 7.x (fixed in 8.x)?
Damian Weber wrote: On Sat, 2 Oct 2010, Miroslav Lachman wrote: Date: Sat, 02 Oct 2010 21:58:27 +0200 From: Miroslav Lachman000.f...@quip.cz To: freebsd-stablefreebsd-stable@freebsd.org Subject: is there a bug in AWK on 6.x and 7.x (fixed in 8.x)? I think there is a bug in AWK in base of FreeBSD 6.x and 7.x (tested on 6.4 i386 and 7.3 i386) I have this simple test case, where I want 2 columns from GeoIP CSV file: awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv It should produce output like this: # awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 (above is taken from FreeBSD 8.1 i386) On FreeBSD 6.4 and 7.3 it results in broken first line: awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0,1.7.255.255,16777216,17301503,AU,Australia- 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 Are you sure the command above contains a valid variable assignment? I am not AWK expert, so maybe you are right. I just found this difference between 7.x and 8.x. But if if works for other lines, why it doesn't work fot the first line too? Anyway, thank you for working examples, I will use them! Another working example from 6.4 is: awk -F , '{ print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 The following works on both 7.3-STABLE and 8.1-STABLE $ awk -v FS=, '{ print $1-$2; }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 The following works as well $ awk '{ print $1-$2; }' FS=, GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 Or, using a BEGIN section for assignment... $ awk 'BEGIN {FS=,} { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 As a side note, gawk shows the following output on 7-STABLE and 8-STABLE $ gawk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0,1.7.255.255,16777216,17301503,AU,Australia- 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 ... which means the new behaviour of awk on 8-STABLE seems to break compatibility with gawk at that point. -- Damian ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: is there a bug in AWK on 6.x and 7.x (fixed in 8.x)?
On Sat, 2 Oct 2010, Miroslav Lachman wrote: Date: Sat, 02 Oct 2010 21:58:27 +0200 From: Miroslav Lachman 000.f...@quip.cz To: freebsd-stable freebsd-stable@freebsd.org Subject: is there a bug in AWK on 6.x and 7.x (fixed in 8.x)? I think there is a bug in AWK in base of FreeBSD 6.x and 7.x (tested on 6.4 i386 and 7.3 i386) I have this simple test case, where I want 2 columns from GeoIP CSV file: awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv It should produce output like this: # awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 (above is taken from FreeBSD 8.1 i386) On FreeBSD 6.4 and 7.3 it results in broken first line: awk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0,1.7.255.255,16777216,17301503,AU,Australia- 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 Are you sure the command above contains a valid variable assignment? The following works on both 7.3-STABLE and 8.1-STABLE $ awk -v FS=, '{ print $1-$2; }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 The following works as well $ awk '{ print $1-$2; }' FS=, GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 Or, using a BEGIN section for assignment... $ awk 'BEGIN {FS=,} { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0-1.7.255.255 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 As a side note, gawk shows the following output on 7-STABLE and 8-STABLE $ gawk 'FS=, { print $1-$2 }' GeoIPCountryWhois.csv | head -n 5 1.0.0.0,1.7.255.255,16777216,17301503,AU,Australia- 1.9.0.0-1.9.255.255 1.10.10.0-1.10.10.255 1.11.0.0-1.11.255.255 1.12.0.0-1.15.255.255 ... which means the new behaviour of awk on 8-STABLE seems to break compatibility with gawk at that point. -- Damian ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: out of HDD space - zfs degraded
On 10/2/2010 10:19 AM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 09:43:30AM -0400, Dan Langille wrote: Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt- no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing tostdout at offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output tostdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28A at scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28A at scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28A at scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28A at scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28A at scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28A at scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AAB at scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01 at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02at scbus10 target 0 lun 0 (pass9,ada8) I'm not yet sure if the drive is fully dead or not. This is not a hot-swap box. It looks to me like the disk labelled gpt/disk06-live literally stopped responding to commands. The errors you see are coming from the OS and the siis(4) controller, and both indicate the actual hard
Re: MySQL performance concern
On Sat, Oct 02, 2010 at 01:18:20PM -0700, Rumen Telbizov wrote: Hello everyone, Here's the requested information below: The tunings between your Linux and FreeBSD instances differ severely, and some of the variables don't even exist any longer (example: table_cache is now known as table_open_cache as of MySQL 5.1.3, and probably key_buffer vs. key_buffer_size too). Can you please rule out MySQL tunings being responsible for the problem? Here are your configuration bits, more sanely written: FreeBSD Linux -- -- -- MySQL version 5.1.51 5.1.50 -- -- -- my.cnf tuning FreeBSD Linux -- -- -- key_buffer_size8 GB key_buffer 4 GB max_allowed_packet16 MB1 MB table_open_cache2048 table_cache 64 sort_buffer_size 64 MB 512 KB read_buffer_size 8 MB 256 KB read_rnd_buffer_size 16 MB 512 KB net_buffer_length 8 KB myisam_sort_buffer_size 256 MB8 MB thread_cache_size 64 query_cache_size 32 MB thread_concurrency 8 max_heap_table_size6 GB6 GB -- -- -- Can you also please provide top output for the mysqld process on FreeBSD? * As for the ZFS. Here's the pool configuration: If you move things to UFS2, does the problem disappear? You might not be seeing any disk I/O on the filesystem with gstat because ZFS ARC could have all of the data in it. -- | Jeremy Chadwick j...@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: out of HDD space - zfs degraded
On Sat, Oct 02, 2010 at 06:09:25PM -0400, Dan Langille wrote: On 10/2/2010 10:19 AM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 09:43:30AM -0400, Dan Langille wrote: Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt- no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing tostdout at offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output tostdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28A at scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28A at scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28A at scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28A at scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28A at scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28A at scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AAB at scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01 at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02at scbus10 target 0 lun 0 (pass9,ada8) I'm not yet sure if the drive is fully dead or not. This is not a hot-swap box. It looks to me like the disk labelled
Re: out of HDD space - zfs degraded
On 10/2/2010 6:36 PM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 06:09:25PM -0400, Dan Langille wrote: On 10/2/2010 10:19 AM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 09:43:30AM -0400, Dan Langille wrote: Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt- no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing tostdout at offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output tostdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28Aat scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28Aat scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28Aat scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28Aat scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28Aat scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28Aat scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AAB at scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01 at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02 at scbus10 target 0 lun 0 (pass9,ada8) I'm not yet sure if the drive is fully dead or not. This is not a hot-swap box. It looks to me like the disk labelled gpt/disk06-live literally stopped responding
Re: out of HDD space - zfs degraded
On Sat, Oct 02, 2010 at 07:23:16PM -0400, Dan Langille wrote: On 10/2/2010 6:36 PM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 06:09:25PM -0400, Dan Langille wrote: On 10/2/2010 10:19 AM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 09:43:30AM -0400, Dan Langille wrote: Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt- no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing tostdout at offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output tostdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28Aat scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28Aat scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28Aat scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28Aat scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28Aat scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28Aat scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AAB at scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01 at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02 at scbus10 target 0 lun 0
Re: MySQL performance concern
You similar hardware specs are hardly similar an 8 core 2.3Ghz box vs a 4 core 1.8Ghz according to Intel cpu comparison:- http://ark.intel.com/Compare.aspx?ids=37092,33080, If you want to compare you really need to do so on the same hardware or all bets are off. Regards Steve - Original Message - From: Rumen Telbizov To: Steven Hartland Cc: freebsd-stable@freebsd.org Sent: Saturday, October 02, 2010 9:18 PM Subject: Re: MySQL performance concern Hello everyone, Here's the requested information below: FreeBSD mysql 5.1.51: my.cnf: skip-external-locking key_buffer_size = 8192M max_allowed_packet = 16M table_open_cache = 2048 sort_buffer_size = 64M read_buffer_size = 8M read_rnd_buffer_size = 16M myisam_sort_buffer_size = 256M thread_cache_size = 64 query_cache_size = 32M thread_concurrency = 8 max_heap_table_size = 6G hardware: FreeBSD 8.1-STABLE amd64 (Tue Sep 14 15:29:22 PDT 2010) running on a SuperMicro machine with X8DTU motherboard and 2 x Dual Core Xeon E5502 1.87Ghz ; 4 x SAS 15K in RAID10 setup under ZFS (two mirrored pairs) and 2 x SSD X25-E partitioned for: 8G for ZIL and the rest for L2ARC; 16G RAM. Disk controller is LSI 4Hi in IT (Initiator Target) mode. -- Linux Gentoo (2.6.18-164.10.1.el5.028stab067.4) mysql 5.1.50 -- my.cnf: skip-external-locking key_buffer = 4G max_heap_table_size = 6G max_allowed_packet = 1M table_cache = 64 sort_buffer_size= 512K net_buffer_length = 8K read_buffer_size= 256K read_rnd_buffer_size= 512K myisam_sort_buffer_size = 8M Linux runs as an OpenVZ VE inside CentOS. It's the only VE and has all the memory allocated to it hardware node: 2 x Xeon Quad E5410 @ 2.33GHz on SuperMicro X7DBU motherboard; 16G RAM; 4 SATA 1T disks in hardware raid 5 attached to a 3ware controller; NO SSDs Some other notes: * It is indeed a single thread which inserts into the mysql so yes it's only one core which handles the application and another one for MySQL. What is interesting here, like I mentioned, is that on FreeBSD mysql process doesn't get more than 30-40% CPU utilization. So it has a lot of headroom. gstat also shows 0% disk load * It is exactly the same database schema. In fact it's only one table that's inserted heavily into. It is a partition table with only one HASH index which looks something like this: PRIMARY KEY (`IntField`,`DateField`,`Varchar150Field`) USING HASH. The speed difference is obvious right from the beginning. I don't have to wait for any data to accrue to see a degradation. I don't wait for more than a 100'000 records to be processed. * Application maintains only 1 local TCP connection to mysql. They both run on the same host * As for the ZFS. Here's the pool configuration: pool: tank config: NAME STATE READ WRITE CKSUM tank ONLINE 0 0 0 mirror ONLINE 0 0 0 gpt/tank0 ONLINE 0 0 0 gpt/tank1 ONLINE 0 0 0 mirror ONLINE 0 0 0 gpt/tank2 ONLINE 0 0 0 gpt/tank3 ONLINE 0 0 0 logs ONLINE 0 0 0 mirror ONLINE 0 0 0 gpt/zil0 ONLINE 0 0 0 gpt/zil1 ONLINE 0 0 0 cache gpt/l2arc0 ONLINE 0 0 0 gpt/l2arc1 ONLINE 0 0 0 pool: zroot config: NAMESTATE READ WRITE CKSUM zroot ONLINE 0 0 0 mirrorONLINE 0 0 0 gpt/zroot0 ONLINE 0 0 0 gpt/zroot1 ONLINE 0 0 0 zroot is a couple of small partitions from two of the same SAS disks. zil and l2arc are 8 and 22G partitions from 32G SSDs I pretty much have no zfs tuning done since from what I've found there shouldn't be any needed since I'm running 8.1 on a 64bit machine. Let me know if you'd like me to experiment with any ... Some additional information: # sysctl vm.kmem_size vm.kmem_size: 5539958784 # sysctl vm.kmem_size_max vm.kmem_size_max: 329853485875 # sysctl vfs.zfs.arc_max vfs.zfs.arc_max: 4466216960 I think this answers all the questions so far. Let me know what you think. I might be missing something obvious. Thank you, Rumen Telbizov This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of
Re: out of HDD space - zfs degraded
On 10/2/2010 7:50 PM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 07:23:16PM -0400, Dan Langille wrote: On 10/2/2010 6:36 PM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 06:09:25PM -0400, Dan Langille wrote: On 10/2/2010 10:19 AM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 09:43:30AM -0400, Dan Langille wrote: Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt- no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing tostdoutat offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output tostdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28A at scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28A at scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28A at scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28A at scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28A at scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28A at scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AABat scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01 at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02 at scbus10 target 0 lun 0 (pass9,ada8) I'm not yet sure if the drive is fully dead or
Panic: attempted pmap_enter on 2MB page
What does the above mentioned panic mean? I'm booting from an mfsroot off of a DVD with a loader.conf like this: autoboot_delay=5 mfsroot_load=YES mfsroot_type=mfs_root mfsroot_name=/mfsboot vfs.root.mountfrom=ufs:md0 vfs.root.mountfrom.options=rw kern.ipc.nmbclusters=32768 net.inet.tcp.tcbhashsize=16384 vm.pmap.pg_ps_enabled=1 vm.kmem_size=2G accf_http_load=YES net.inet.tcp.syncache.hashsize=1024 net.inet.tcp.syncache.bucketlimit=100 This is FreeBSD 8.1-RELEASE amd64 running with the debugger installed into the kernel. Thanks in advance for any insight provided. :) -- Dave Hayes - Consultant - Altadena CA, USA - d...@jetcafe.org The opinions expressed above are entirely my own No one is lazy except in the pursuit of another one's goal. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to freebsd-stable-unsubscr...@freebsd.org
Re: out of HDD space - zfs degraded
On 10/2/2010 10:04 PM, Dan Langille wrote: On 10/2/2010 7:50 PM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 07:23:16PM -0400, Dan Langille wrote: On 10/2/2010 6:36 PM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 06:09:25PM -0400, Dan Langille wrote: On 10/2/2010 10:19 AM, Jeremy Chadwick wrote: On Sat, Oct 02, 2010 at 09:43:30AM -0400, Dan Langille wrote: Overnight I was running a zfs send | zfs receive (both within the same system / zpool). The system ran out of space, a drive went off line, and the system is degraded. This is a raidz2 array running on FreeBSD 8.1-STABLE #0: Sat Sep 18 23:43:48 EDT 2010. The following logs are also available at http://www.langille.org/tmp/zfs-space.txt- no line wrapping This is what was running: # time zfs send storage/bac...@transfer | mbuffer | zfs receive storage/compressed/bacula-mbuffer in @ 0.0 kB/s, out @ 0.0 kB/s, 3670 GB total, buffer 100% fullcannot receive new filesystem stream: out of space mbuffer: error: outputThread: error writing tostdoutat offset 0x395917c4000: Broken pipe summary: 3670 GByte in 10 h 40 min 97.8 MB/s mbuffer: warning: error during output tostdout: Broken pipe warning: cannot send 'storage/bac...@transfer': Broken pipe real640m48.423s user8m52.660s sys 211m40.862s Looking in the logs, I see this: Oct 2 00:50:53 kraken kernel: (ada0:siisch0:0:0:0): lost device Oct 2 00:50:54 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:54 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:54 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:55 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:55 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:55 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:56 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:56 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:56 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:57 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:57 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:57 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:58 kraken kernel: siisch0: Timeout on slot 30 Oct 2 00:50:58 kraken kernel: siisch0: siis_timeout is 0004 ss 4000 rs 4000 es sts 801f0040 serr Oct 2 00:50:58 kraken kernel: siisch0: Error while READ LOG EXT Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=270336 size=8192 error=6 Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): Synchronize cache failed Oct 2 00:50:59 kraken kernel: (ada0:siisch0:0:0:0): removing device entry Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187564032 size=8192 error=6 Oct 2 00:50:59 kraken root: ZFS: vdev I/O failure, zpool=storage path=/dev/gpt/disk06-live offset=2000187826176 size=8192 error=6 $ zpool status pool: storage state: DEGRADED scrub: scrub in progress for 5h32m, 17.16% done, 26h44m to go config: NAME STATE READ WRITE CKSUM storage DEGRADED 0 0 0 raidz2 DEGRADED 0 0 0 gpt/disk01-live ONLINE 0 0 0 gpt/disk02-live ONLINE 0 0 0 gpt/disk03-live ONLINE 0 0 0 gpt/disk04-live ONLINE 0 0 0 gpt/disk05-live ONLINE 0 0 0 gpt/disk06-live REMOVED 0 0 0 gpt/disk07-live ONLINE 0 0 0 $ zfs list NAMEUSED AVAIL REFER MOUNTPOINT storage6.97T 1.91T 1.75G /storage storage/bacula 4.72T 1.91T 4.29T /storage/bacula storage/compressed 2.25T 1.91T 46.9K /storage/compressed storage/compressed/bacula 2.25T 1.91T 42.7K /storage/compressed/bacula storage/pgsql 5.50G 1.91T 5.50G /storage/pgsql $ sudo camcontrol devlist Password: Hitachi HDS722020ALA330 JKAOA28A at scbus2 target 0 lun 0 (pass1,ada1) Hitachi HDS722020ALA330 JKAOA28A at scbus3 target 0 lun 0 (pass2,ada2) Hitachi HDS722020ALA330 JKAOA28A at scbus4 target 0 lun 0 (pass3,ada3) Hitachi HDS722020ALA330 JKAOA28A at scbus5 target 0 lun 0 (pass4,ada4) Hitachi HDS722020ALA330 JKAOA28A at scbus6 target 0 lun 0 (pass5,ada5) Hitachi HDS722020ALA330 JKAOA28A at scbus7 target 0 lun 0 (pass6,ada6) ST380815AS 4.AABat scbus8 target 0 lun 0 (pass7,ada7) TSSTcorp CDDVDW SH-S223C SB01 at scbus9 target 0 lun 0 (cd0,pass8) WDC WD1600AAJS-75M0A0 02.03E02 at scbus10 target 0 lun 0