From bugmaster at FreeBSD.org Mon Jan 5 11:06:59 2009 From: bugmaster at FreeBSD.org (FreeBSD bugmaster) Date: Mon Jan 5 11:09:12 2009 Subject: Current problem reports assigned to freebsd-scsi@FreeBSD.org Message-ID: <200901051106.n05B6wdm002915@freefall.freebsd.org> Note: to view an individual PR, use: http://www.freebsd.org/cgi/query-pr.cgi?pr=(number). The following is a listing of current problems submitted by FreeBSD users. These represent problem reports covering all versions including experimental development code and obsolete releases. S Tracker Resp. Description -------------------------------------------------------------------------------- o kern/129602 scsi [ahd] ahd(4) gets confused and wedges SCSI bus o kern/128452 scsi [sa] [panic] Accessing SCSI tape drive randomly crashe o kern/128245 scsi [scsi] "inquiry data fails comparison at DV1 step" [re o kern/127927 scsi [isp] isp(4) target driver crashes kernel when set up o kern/126866 scsi [isp] [panic] kernel panic on card initialization o kern/124667 scsi [amd] [panic] FreeBSD-7 kernel page faults at amd-scsi o kern/123674 scsi [ahc] ahc driver dumping o kern/123666 scsi [aac] attach fails with Adaptec SAS RAID 3805 controll o sparc/121676 scsi [iscsi] iscontrol do not connect iscsi-target on sparc o kern/120487 scsi [sg] scsi_sg incompatible with scanners o kern/120247 scsi [mpt] FreeBSD 6.3 and LSI Logic 1030 = only 3.300MB/s o kern/119668 scsi [cam] [patch] certain errors are too verbose comparing o kern/114597 scsi [sym] System hangs at SCSI bus reset with dual HBAs o kern/110847 scsi [ahd] Tyan U320 onboard problem with more than 3 disks o kern/99954 scsi [ahc] reading from DVD failes on 6.x [regression] o kern/94838 scsi Kernel panic while mounting SD card with lock switch o o kern/92798 scsi [ahc] SCSI problem with timeouts o kern/90282 scsi [sym] SCSI bus resets cause loss of ch device o kern/76178 scsi [ahd] Problem with ahd and large SCSI Raid system o kern/74627 scsi [ahc] [hang] Adaptec 2940U2W Can't boot 5.3 s kern/61165 scsi [panic] kernel page fault after calling cam_send_ccb o kern/60641 scsi [sym] Sporadic SCSI bus resets with 53C810 under load o kern/60598 scsi wire down of scsi devices conflicts with config s kern/57398 scsi [mly] Current fails to install on mly(4) based RAID di o kern/52638 scsi [panic] SCSI U320 on SMP server won't run faster than o kern/44587 scsi dev/dpt/dpt.h is missing defines required for DPT_HAND o kern/40895 scsi wierd kernel / device driver bug o kern/39388 scsi ncr/sym drivers fail with 53c810 and more than 256MB m o kern/38828 scsi [dpt] [request] DPT PM2012B/90 doesn't work o kern/35234 scsi World access to /dev/pass? (for scanner) requires acce 30 problems total. From asossi at dotcom.ts.it Mon Jan 5 17:18:11 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Mon Jan 5 17:18:19 2009 Subject: ISCSI slow to read from DELL MD3000i Message-ID: <496239E8.4020607@dotcom.ts.it> Hello, I manage an web/mail/DB server. We recently purchased a DELL MD3000i server with ISCSI interface. I tested the MD3000i with FreeBSD 7.0-RELEASE, i recompiled the kernel myself but the ISCSI communication results slow. Below configuration: net configuration: MD3000i FreeBSD 7.0 controller 0 interface 0: 192.168.253.254 |__| switch 1GB |__|netcard 0: 192.168.253.1 (re0)| controller 1 interface 0: 192.168.253.253 | |192.168.253.X | | | | | | controller 0 interface 1: 192.168.252.254 |__| switch 1GB |__|netcard 1: 192.168.252.1 (re1)| controller 1 interface 1: 192.168.252.253 | |192.168.252.X | | | manage interface 0: 192.168.0.249 |__| switch 10/100 MB |_.... internal net manage interface 1: 192.168.0.248 | |192.168.0.X | /etc/iscsi.conf: port 3260 nas_dotcom { TargetAddress = 192.168.253.254 TargetName = iqn.1984-05.com.dell:powervault.6001ec9000f192210000000048a44372 initiatorName = iqn.2005-01.il.ac.huji.cs::web.dotcom.ts.it } web# sysctl net.iscsi net.iscsi.driver_version: 2.1.0 net.iscsi.isid: ?DIB00 net.iscsi.sessions: 1 net.iscsi.0.targetname: iqn.1984-05.com.dell:powervault.6001ec9000f192210000000048a44372 net.iscsi.0.targeaddress: 192.168.253.254 net.iscsi.0.stats: recv=71479 sent=71479 flags=0x0000019f pdus-alloc=0 pdus-max=5 cws=385 cmd=b499 exp=b499 max=b619 stat=b49b itt=b499 net.iscsi.0.douio: 0 net.iscsi.0.pid: 612 web# sysctl kern.cam kern.cam.cam_srch_hi: 0 kern.cam.scsi_delay: 5000 kern.cam.cd.changer.max_busy_seconds: 15 kern.cam.cd.changer.min_busy_seconds: 5 kern.cam.da.da_send_ordered: 1 kern.cam.da.default_timeout: 60 kern.cam.da.retry_count: 4 kern.cam.da.0.minimum_cmd_size: 6 kern.cam.da.1.minimum_cmd_size: 6 kern.cam.da.2.minimum_cmd_size: 6 kern.cam.da.3.minimum_cmd_size: 6 I tryed with the ISCSI driver I found in FreeBSD 7.0, with the same driver patched with the patch I found there (http://lists.freebsd.org/pipermail/freebsd-scsi/2008-February/003383.html) and alse with the driver ISCSI 2.1 downloaded from Danny's ftp. All test have same results: about 820~850KB/s. eg: web# dd if=/dev/zero of=/usr/local/www/tmp count=1m 1048576+0 records in 1048576+0 records out 536870912 bytes transferred in 654.398700 secs (820403 bytes/sec) and simultaneously web# netstat -w 1 -I re0 input (re0) output packets errs bytes packets errs bytes colls 0 0 0 0 0 0 0 123 0 8550 234 0 343180 0 300 0 20952 564 0 824808 0 325 0 22698 611 0 893542 0 300 0 20952 564 0 824808 0 325 0 22698 611 0 893542 0 300 0 20952 564 0 824808 0 .... and more re1 has no traffic. But at the end i try read from ISCSI. Read is more quickly. eg: web# dd if=/usr/local/www/tmp of=/usr/tmp 1048576+0 records in 1048576+0 records out 536870912 bytes transferred in 19.636577 secs (27340351 bytes/sec) and simultaneously: web# netstat -w 1 -I re0 input (re0) output packets errs bytes packets errs bytes colls 0 0 0 0 0 0 0 2210 0 3296084 1156 0 78744 0 16420 0 24493888 8567 0 582558 0 13031 0 19427130 6809 0 463074 0 20638 0 30786236 10768 0 732288 0 17296 0 25791540 9032 0 614160 0 20347 0 30347462 10615 0 721854 0 20254 0 30210156 10567 0 718590 0 .... and more re1 has no traffic. I searched but found nothing that helps me, the only thing that triggered my attention was this Microsoft's User's Guide (http://www.microsoft.com/downloads/details.aspx?familyid=12CB3C1A-15D6-4585-B385-BEFD1319F825&displaylang=en). It seems interesting at least the chapter 'Addressing Slow Performance with iSCSI clusters' Thanks in advance for yours help. -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From danny at cs.huji.ac.il Tue Jan 6 13:49:35 2009 From: danny at cs.huji.ac.il (Danny Braniss) Date: Tue Jan 6 13:49:42 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: <496239E8.4020607@dotcom.ts.it> References: <496239E8.4020607@dotcom.ts.it> Message-ID: sorry for the top potst, my MUI screws up the quoatet message. check: ftp://ftp.cs.huji.ac.il/users/danny/freebsd/iscsi-2.1.tar.gz danny > Hello,> I manage an web/mail/DB server. We recently purchased a DELL MD3000i > server with ISCSI interface. I tested the MD3000i with FreeBSD > 7.0-RELEASE, i recompiled the kernel myself but the ISCSI communication > results slow.> Below configuration:> > net configuration:> MD3000i > FreeBSD 7.0> controller 0 interface 0: 192.168.253.254 |__| switch 1GB > |__|netcard 0: 192.168.253.1 (re0)|> controller 1 interface 0: 192.168.253.253 | |192.168.253.X | | > |> | > | > |> controller 0 interface 1: 192.168.252.254 |__| switch 1GB > |__|netcard 1: 192.168.252.1 (re1)|> controller 1 interface 1: 192.168.252.253 | |192.168.252.X | | > |> > manage interface 0: 192.168.0.249 |__| switch 10/100 MB |_.... > internal net> manage interface 1: 192.168.0.248 | |192.168.0.X =|> > /etc/iscsi.conf:> port 3260> nas_dotcom {> TargetAddress = 192.168.253.254> TargetName = > iqn.1984-05.com.dell:powervault.6001ec9000f192210000000048a44372> initiatorName = iqn.2005-01.il.ac.huji.cs::web.dotcom.ts.it> }> > web# sysctl net.iscsi> net.iscsi.driver_version: 2.1.0> net.iscsi.isid: ??DIB00> net.iscsi.sessions: 1> net.iscsi.0.targetname: > iqn.1984-05.com.dell:powervault.6001ec9000f192210000000048a44372> net.iscsi.0.targeaddress: 192.168.253.254> net.iscsi.0.stats: recv=71479 sent=71479 flags=0x0000019f pdus-allo=c=0 > pdus-max=5 cws=385 cmd=b499 exp=b499 max=b619 stat=b49b itt==b499> net.iscsi.0.douio: 0> net.iscsi.0.pid: 612> > web# sysctl kern.cam> kern.cam.cam_srch_hi: 0> kern.cam.scsi_delay: 5000> kern.cam.cd.changer.max_busy_seconds: 15> kern.cam.cd.changer.min_busy_seconds: 5> kern.cam.da.da_send_ordered: 1> kern.cam.da.default_timeout: 60> kern.cam.da.retry_count: 4> kern.cam.da.0.minimum_cmd_size: 6> kern.cam.da.1.minimum_cmd_size: 6> kern.cam.da.2.minimum_cmd_size: 6> kern.cam.da.3.minimum_cmd_size: 6> > > I tryed with the ISCSI driver I found in FreeBSD 7.0, with the same > driver patched with the patch I found there > (http://lists.freebsd.org/pipermail/freebsd-scsi/2008-February/003383.htm=l) > and alse with the driver ISCSI 2.1 downloaded from Danny's ftp.> All test have same results: about 820~850KB/s.> > eg:> web# dd if=/dev/zero of=/usr/local/www/tmp count=1m> 1048576+0 records in> 1048576+0 records out> 536870912 bytes transferred in 654.398700 secs (820403 bytes/sec)> > and simultaneously> web# netstat -w 1 -I re0> input (re0) output> packets errs bytes packets errs bytes colls> 0 0 0 0 0 0 0> 123 0 8550 234 0 343180 0> 300 0 20952 564 0 824808 0> 325 0 22698 611 0 893542 0> 300 0 20952 564 0 824808 0> 325 0 22698 611 0 893542 0> 300 0 20952 564 0 824808 0> .... and more> re1 has no traffic.> > But at the end i try read from ISCSI. Read is more quickly.> eg:> web# dd if=/usr/local/www/tmp of=/usr/tmp> 1048576+0 records in> 1048576+0 records out> 536870912 bytes transferred in 19.636577 secs (27340351 bytes/sec)> > and simultaneously:> web# netstat -w 1 -I re0> input (re0) output> packets errs bytes packets errs bytes colls> 0 0 0 0 0 0 0> 2210 0 3296084 1156 0 78744 0> 16420 0 24493888 8567 0 582558 0> 13031 0 19427130 6809 0 463074 0> 20638 0 30786236 10768 0 732288 0> 17296 0 25791540 9032 0 614160 0> 20347 0 30347462 10615 0 721854 0> 20254 0 30210156 10567 0 718590 0> .... and more> re1 has no traffic.> > I searched but found nothing that helps me, the only thing that > triggered my attention was this Microsoft's User's Guide > (http://www.microsoft.com/downloads/details.aspx?familyid=12CB3C1A-15D6=-4585-B385-BEFD1319F825&displaylang=en). > > It seems interesting at least the chapter 'Addressing Slow Performance > with iSCSI clusters'> > Thanks in advance for yours help.> > -- > Sossi Andrej> -------------------------> DotCom Information technology> > Via Biancospino, 9> 34151 - Opicina (TS)> Italy> > tel: +39 040 2158191> fax: +39 040 0641954> E-mail: asossi@dotcom.ts.it> ----------------------------> > Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le= informazioni contenute in questo messaggio sono riservate e ad uso esclu=sivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto =per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo= a terzi, dandocene gentilmente comunicazione. Grazie> > This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain= confidential and/or privileged information. If you are not the addressee= or authorized to receive this for the addressee, you must not use, copy,= disclose or take any action based on this message or any information her=ein. If you have received this message in error, please advise the sender= immediately by reply e-mail and delete this message. Thank you for your =cooperation.> > _______________________________________________> freebsd-scsi@freebsd.org mailing list> http://lists.freebsd.org/mailman/listinfo/freebsd-scsi> To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org"> From nglrossi at gmail.com Tue Jan 6 18:03:14 2009 From: nglrossi at gmail.com (Angelo) Date: Tue Jan 6 18:03:21 2009 Subject: iscsi client hangs performing I/O on a dead target Message-ID: <6c1e076a0901060938i5450a1fnc4dd68ff9690862d@mail.gmail.com> Hi, I'm experimenting on iscsi; both the target and the initiator are vmware virtual machines and are running 7.0-RELEASE. So far everything works fine except that the client hangs forever (state is PHYSWR) if it is accessing (dd if=/dev/zero of=/dev/da0) the device while it "dies" (shutdown of the target machine). Is this the expected behaviour? I would like to be able to configure a timeout so the command that is trying to access the unavailable device fails and I can handle the problem but I can't find anything in iscontrol man pages. Thanks, Angelo From imp at bsdimp.com Wed Jan 7 03:38:33 2009 From: imp at bsdimp.com (M. Warner Losh) Date: Wed Jan 7 03:38:40 2009 Subject: Patch review Message-ID: <20090106.203736.-1300543249.imp@bsdimp.com> What do people think of this? It is very useful when trying to recover a CD/DVD that's been scratched with ddrescue which handles all the retry logic. This patch is modeled after the kern.cam.da.retry_count sysctl and friends. This makes ddrescue about between 5x and 20x faster. The reason for the large delta is that it can now 'stream' past errors rather than doing a lot of reseeking when reading a large block size. I've also observed fewer hangs in one of the cheap DVD drives I tried this with, likely due to fewer forced retries frying its brain... Of course, all of this was with kern.cam.cd.retry_count = 0. I've not changed the default behavior. Comments? Warner P.S. I have a recollection that Scott Long sent me something akin to this, but I couldn't find it so I just recreated this trivial patch from scratch, cheating off of scsi_da.c. Index: cam/scsi/scsi_cd.c =================================================================== --- cam/scsi/scsi_cd.c (revision 186807) +++ cam/scsi/scsi_cd.c (working copy) @@ -292,6 +292,9 @@ PERIPHDRIVER_DECLARE(cd, cddriver); +#ifndef CD_DEFAULT_RETRY +#define CD_DEFAULT_RETRY 4 +#endif #ifndef CHANGER_MIN_BUSY_SECONDS #define CHANGER_MIN_BUSY_SECONDS 5 #endif @@ -299,11 +302,15 @@ #define CHANGER_MAX_BUSY_SECONDS 15 #endif +static int cd_retry_count = CD_DEFAULT_RETRY; static int changer_min_busy_seconds = CHANGER_MIN_BUSY_SECONDS; static int changer_max_busy_seconds = CHANGER_MAX_BUSY_SECONDS; SYSCTL_NODE(_kern_cam, OID_AUTO, cd, CTLFLAG_RD, 0, "CAM CDROM driver"); SYSCTL_NODE(_kern_cam_cd, OID_AUTO, changer, CTLFLAG_RD, 0, "CD Changer"); +SYSCTL_INT(_kern_cam_cd, OID_AUTO, retry_count, CTLFLAG_RW, + &cd_retry_count, 0, "Normal I/O retry count"); +TUNABLE_INT("kern.cam.cd.retry_count", &cd_retry_count); SYSCTL_INT(_kern_cam_cd_changer, OID_AUTO, min_busy_seconds, CTLFLAG_RW, &changer_min_busy_seconds, 0, "Minimum changer scheduling quantum"); TUNABLE_INT("kern.cam.cd.changer.min_busy_seconds", &changer_min_busy_seconds); @@ -1454,7 +1461,7 @@ devstat_start_transaction_bio(softc->disk->d_devstat, bp); scsi_read_write(&start_ccb->csio, - /*retries*/4, + /*retries*/cd_retry_count, /* cbfcnp */ cddone, MSG_SIMPLE_Q_TAG, /* read */bp->bio_cmd == BIO_READ, From danny at cs.huji.ac.il Wed Jan 7 09:33:27 2009 From: danny at cs.huji.ac.il (Danny Braniss) Date: Wed Jan 7 09:33:34 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: Your message of Tue, 6 Jan 2009 18:38:27 +0100 . Message-ID: > Hi, > > I'm experimenting on iscsi; both the target and the initiator are vmware > virtual machines and are running 7.0-RELEASE. > So far everything works fine except that the client hangs forever (state is > PHYSWR) if it is accessing (dd if=/dev/zero of=/dev/da0) the device while it > "dies" (shutdown of the target machine). > what happens when you bring back the target? > Is this the expected behaviour? > yes. but maybe it can be 'fixed', I'm concidering adding some kind of timeout flag/option. > I would like to be able to configure a timeout so the command that is trying > to access the unavailable device fails and I can handle the problem but I > can't find anything in iscontrol man pages. > > Thanks, > Angelo > _______________________________________________ > freebsd-scsi@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-scsi > To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" > From nglrossi at gmail.com Wed Jan 7 10:47:18 2009 From: nglrossi at gmail.com (Angelo) Date: Wed Jan 7 10:47:24 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: References: Message-ID: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> On Wed, Jan 7, 2009 at 10:33 AM, Danny Braniss wrote: > > Hi, > > > > I'm experimenting on iscsi; both the target and the initiator are vmware > > virtual machines and are running 7.0-RELEASE. > > So far everything works fine except that the client hangs forever (state > is > > PHYSWR) if it is accessing (dd if=/dev/zero of=/dev/da0) the device while > it > > "dies" (shutdown of the target machine). > > > what happens when you bring back the target? > > > Is this the expected behaviour? > > > yes. > but maybe it can be 'fixed', I'm concidering adding some kind of timeout > flag/option. > > > I would like to be able to configure a timeout so the command that is > trying > > to access the unavailable device fails and I can handle the problem but I > > can't find anything in iscontrol man pages. > > > > Thanks, > > Angelo > > _______________________________________________ > > freebsd-scsi@freebsd.org mailing list > > http://lists.freebsd.org/mailman/listinfo/freebsd-scsi > > To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" > > > > Hi Danny, thanks for your reply. when the target comes back it is reconnected properly by the initiator. The usage of iscsi I had in mind was an initiator connecting to two targets and using the two devices as parts of a raid 1 array. I was expecting that a failure on one of the disks (network down, target machine down) would be eventually detected and the raid turned to degraded but still usable. What happens now to me is that the whole raid device gets unusable for all the time the target is down. As I said before I am just experimenting. I don't know how other implementations of iscsi initiator work and maybe my idea is just insane :) Thanks, Angelo From danny at cs.huji.ac.il Wed Jan 7 13:28:00 2009 From: danny at cs.huji.ac.il (Danny Braniss) Date: Wed Jan 7 13:28:08 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> References: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> Message-ID: > ------=_Part_16620_23870833.1231325237102 > Content-Type: text/plain; charset=ISO-8859-1 > Content-Transfer-Encoding: 7bit > Content-Disposition: inline > > On Wed, Jan 7, 2009 at 10:33 AM, Danny Braniss wrote: > > > > Hi, > > > > > > I'm experimenting on iscsi; both the target and the initiator are vmware > > > virtual machines and are running 7.0-RELEASE. > > > So far everything works fine except that the client hangs forever (state > > is > > > PHYSWR) if it is accessing (dd if=/dev/zero of=/dev/da0) the device while > > it > > > "dies" (shutdown of the target machine). > > > > > what happens when you bring back the target? > > > > > Is this the expected behaviour? > > > > > yes. > > but maybe it can be 'fixed', I'm concidering adding some kind of timeout > > flag/option. > > > > > I would like to be able to configure a timeout so the command that is > > trying > > > to access the unavailable device fails and I can handle the problem but I > > > can't find anything in iscontrol man pages. > > > > > > Thanks, > > > Angelo > > > _______________________________________________ > > > freebsd-scsi@freebsd.org mailing list > > > http://lists.freebsd.org/mailman/listinfo/freebsd-scsi > > > To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" > > > > > > > Hi Danny, > > > thanks for your reply. > > when the target comes back it is reconnected properly by the initiator. > > The usage of iscsi I had in mind was an initiator connecting to two targets > and using the two devices as parts of a raid 1 array. > I was expecting that a failure on one of the disks (network down, target > machine down) would be eventually detected and the raid turned to degraded > but still usable. > What happens now to me is that the whole raid device gets unusable for all > the time the target is down. > > As I said before I am just experimenting. I don't know how other > implementations of iscsi initiator work and maybe my idea is just insane :) > I don't know either, the RFC does not mention this case - or maybe I missed it :-) But others have raised the issue, and so it got me thinking, but freebsd likes to panic if a disc goes away, so don't hold your breath for a solution soon. danny > Thanks, > Angelo From asossi at dotcom.ts.it Wed Jan 7 14:23:36 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Wed Jan 7 14:23:44 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: References: Message-ID: <4964BA40.5080307@dotcom.ts.it> Danny Braniss wrote: > wups, didn't read all your mail, sorry, > try increasing tht tag opening, in the config file add > tag = 64 > for example, or via camcontrol > > danny > I modify my iscsi.conf by adding tags = 64 (and no tag). Now works fine, about 43MB/s. Thank You very match. But what means this parameter? -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From nglrossi at gmail.com Wed Jan 7 17:17:35 2009 From: nglrossi at gmail.com (Angelo) Date: Wed Jan 7 17:17:42 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: References: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> Message-ID: <6c1e076a0901070917p52d32078qff616449c963f6fc@mail.gmail.com> Danny, this sounds great (except for the panic, but I guess this would at least be the same behaviour of two scsi disks configured in raid1 with one failing). I'll keep an eye on the changes and be glad to help testing if you implement the timeout setting! thanks, Angelo On Wed, Jan 7, 2009 at 2:27 PM, Danny Braniss wrote: > > ------=_Part_16620_23870833.1231325237102 > > Content-Type: text/plain; charset=ISO-8859-1 > > Content-Transfer-Encoding: 7bit > > Content-Disposition: inline > > > > On Wed, Jan 7, 2009 at 10:33 AM, Danny Braniss > wrote: > > > > > > Hi, > > > > > > > > I'm experimenting on iscsi; both the target and the initiator are > vmware > > > > virtual machines and are running 7.0-RELEASE. > > > > So far everything works fine except that the client hangs forever > (state > > > is > > > > PHYSWR) if it is accessing (dd if=/dev/zero of=/dev/da0) the device > while > > > it > > > > "dies" (shutdown of the target machine). > > > > > > > what happens when you bring back the target? > > > > > > > Is this the expected behaviour? > > > > > > > yes. > > > but maybe it can be 'fixed', I'm concidering adding some kind of > timeout > > > flag/option. > > > > > > > I would like to be able to configure a timeout so the command that is > > > trying > > > > to access the unavailable device fails and I can handle the problem > but I > > > > can't find anything in iscontrol man pages. > > > > > > > > > Thanks, > > > > Angelo > > > > _______________________________________________ > > > > freebsd-scsi@freebsd.org mailing list > > > > http://lists.freebsd.org/mailman/listinfo/freebsd-scsi > > > > To unsubscribe, send any mail to " > freebsd-scsi-unsubscribe@freebsd.org" > > > > > > > > > > Hi Danny, > > > > > > thanks for your reply. > > > > when the target comes back it is reconnected properly by the initiator. > > > > The usage of iscsi I had in mind was an initiator connecting to two > targets > > and using the two devices as parts of a raid 1 array. > > I was expecting that a failure on one of the disks (network down, target > > machine down) would be eventually detected and the raid turned to > degraded > > but still usable. > > What happens now to me is that the whole raid device gets unusable for > all > > the time the target is down. > > > > As I said before I am just experimenting. I don't know how other > > implementations of iscsi initiator work and maybe my idea is just insane > :) > > > I don't know either, the RFC does not mention this case - or maybe I missed > it > :-) > But others have raised the issue, and so it got me thinking, but freebsd > likes > to > panic if a disc goes away, so don't hold your breath for a solution soon. > > danny > > > Thanks, > > Angelo > > From andrew at modulus.org Wed Jan 7 23:45:32 2009 From: andrew at modulus.org (Andrew Snow) Date: Wed Jan 7 23:45:39 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: References: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> Message-ID: <49653A7D.30906@modulus.org> Danny Braniss wrote: > freebsd likes to > panic if a disc goes away, so don't hold your breath for a solution soon. You hit the nail on the head. This is going to be a increasingly bad problem as we continue pushing in this of networked storage. It would be REALLY nice, if an I/O fails, to simply have the process attempting the I/O to be killed, instead of bringing the machine to its knees and locking up or panic the kernel. - Andrew From andrew at modulus.org Thu Jan 8 02:40:35 2009 From: andrew at modulus.org (Andrew Snow) Date: Thu Jan 8 02:40:44 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> References: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> Message-ID: <49656791.1000809@modulus.org> > I was expecting that a failure on one of the disks (network down, target > machine down) would be eventually detected and the raid turned to degraded > but still usable. > What happens now to me is that the whole raid device gets unusable for all > the time the target is down. If you're using gmirror, you might want to experiment with this setting: kern.geom.mirror.timeout Set it to something reasonably low like 10 seconds, and it will ignore an iSCSI device that is not responding more rapidly. From peterjeremy at optushome.com.au Thu Jan 8 09:37:54 2009 From: peterjeremy at optushome.com.au (Peter Jeremy) Date: Thu Jan 8 09:38:00 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: <49653A7D.30906@modulus.org> References: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> <49653A7D.30906@modulus.org> Message-ID: <20090108071749.GM87057@server.vk2pj.dyndns.org> On 2009-Jan-08 10:27:57 +1100, Andrew Snow wrote: >It would be REALLY nice, if an I/O fails, to simply have the process >attempting the I/O to be killed, instead of bringing the machine to its >knees and locking up or panic the kernel. And if it was that easy, it would have been done about a decade ago. -- Peter Jeremy Please excuse any delays as the result of my ISP's inability to implement an MTA that is either RFC2821-compliant or matches their claimed behaviour. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 195 bytes Desc: not available Url : http://lists.freebsd.org/pipermail/freebsd-scsi/attachments/20090108/2db96918/attachment.pgp From asossi at dotcom.ts.it Thu Jan 8 15:39:02 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Thu Jan 8 15:39:09 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: References: Message-ID: <49661D6D.1090602@dotcom.ts.it> Danny Braniss wrote: >> Danny Braniss wrote: >> >>> wups, didn't read all your mail, sorry, >>> try increasing tht tag opening, in the config file add >>> tag = 64 >>> for example, or via camcontrol >>> >>> danny >>> >>> >> I modify my iscsi.conf by adding tags = 64 (and no tag). Now works fine, >> about 43MB/s. Thank You very match. >> >> But what means this parameter? >> > > is the max number of commands that can be sent without waiting for ack. I set > it > too concervative :-( > I made many tests with different tags values and checked the writing speed with dd. 0 (default) -> ~850kB/s 1 -> ~850kB/s 2 -> ~6.5MB/s 3 -> ~40MB/s 4 -> ~49MB/s 8 -> ~49MB/s ... I think that NAS server sends ACK after 4 commands. Is it correct? Is it possible that the NAS server modifies this behavior? Can I set tags at 4 or is it smarter to keep it higher? Thanks. -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From asossi at dotcom.ts.it Thu Jan 8 17:18:28 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Thu Jan 8 17:18:36 2009 Subject: ISCSI and multipath Message-ID: <496634BB.9050902@dotcom.ts.it> Another question about MD3000i. My MD3000i have 2 controller and every controller have 2 net interface. My FreeBSD server is connect on NAS server with 2 network cards throw out 2 switch on th 2 networks. (192.168.253.X and 192.168.252.X). In the official manual is written if the primary controller (or net) have a problem the NAS automatically switch disks drive on second controller. For this is required MPIO on Windows or MPP on Linux. It is supported also on FreeBSD? Thanks in advance. -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From andrew at modulus.org Fri Jan 9 01:03:47 2009 From: andrew at modulus.org (Andrew Snow) Date: Fri Jan 9 01:03:54 2009 Subject: ISCSI and multipath In-Reply-To: <496634BB.9050902@dotcom.ts.it> References: <496634BB.9050902@dotcom.ts.it> Message-ID: <4966A25E.4070803@modulus.org> Sossi Andrej wrote: > Another question about MD3000i. > My MD3000i have 2 controller and every controller have 2 net interface. > My FreeBSD server is connect on NAS server with 2 network cards throw > out 2 switch on th 2 networks. (192.168.253.X and 192.168.252.X). > In the official manual is written if the primary controller (or net) > have a problem the NAS automatically switch disks drive on second > controller. For this is required MPIO on Windows or MPP on Linux. It is > supported also on FreeBSD? If you only wanted to do failover at the network level with shared IP address, you could use lagg. However, since you have different IP subnets for each network, you probably want to look at using geom_fox. You set up two iSCSI connections, one to each controller, and geom_fox on top to make it appear as a single disk device. Hope that helps! - Andrew From gpalmer at freebsd.org Fri Jan 9 06:13:27 2009 From: gpalmer at freebsd.org (Gary Palmer) Date: Fri Jan 9 06:13:35 2009 Subject: ISCSI and multipath In-Reply-To: <4966A25E.4070803@modulus.org> References: <496634BB.9050902@dotcom.ts.it> <4966A25E.4070803@modulus.org> Message-ID: <20090109061324.GD81380@in-addr.com> On Fri, Jan 09, 2009 at 12:03:26PM +1100, Andrew Snow wrote: > Sossi Andrej wrote: > >Another question about MD3000i. > >My MD3000i have 2 controller and every controller have 2 net interface. > >My FreeBSD server is connect on NAS server with 2 network cards throw > >out 2 switch on th 2 networks. (192.168.253.X and 192.168.252.X). > >In the official manual is written if the primary controller (or net) > >have a problem the NAS automatically switch disks drive on second > >controller. For this is required MPIO on Windows or MPP on Linux. It is > >supported also on FreeBSD? > > If you only wanted to do failover at the network level with shared IP > address, you could use lagg. > > However, since you have different IP subnets for each network, you > probably want to look at using geom_fox. You set up two iSCSI > connections, one to each controller, and geom_fox on top to make it > appear as a single disk device. FreeBSD 7.0 and later also has geom_multipath, which I've been told (no experience) is a better approach. I suggest you review documentation for both and make your own decision Regards, Gary From danny at cs.huji.ac.il Fri Jan 9 06:38:05 2009 From: danny at cs.huji.ac.il (Danny Braniss) Date: Fri Jan 9 06:38:12 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: Your message of Thu, 08 Jan 2009 16:36:13 +0100 . Message-ID: > Danny Braniss wrote: > >> Danny Braniss wrote: > >> > >>> wups, didn't read all your mail, sorry, > >>> try increasing tht tag opening, in the config file add > >>> tag = 64 > >>> for example, or via camcontrol > >>> > >>> danny > >>> > >>> > >> I modify my iscsi.conf by adding tags = 64 (and no tag). Now works fine, > >> about 43MB/s. Thank You very match. > >> RTFM :-) > >> But what means this parameter? > >> > > > > is the max number of commands that can be sent without waiting for ack. I set > > it > > too concervative :-( > > > I made many tests with different tags values and checked the writing > speed with dd. > 0 (default) -> ~850kB/s > 1 -> ~850kB/s > 2 -> ~6.5MB/s > 3 -> ~40MB/s > 4 -> ~49MB/s > 8 -> ~49MB/s > ... > > I think that NAS server sends ACK after 4 commands. Is it correct? in a simplistic way yes, it depends on how much memory the target has, the speed of its disks, and of course, the software :-) > Is it > possible that the NAS server modifies this behavior? Can I set tags at 4 > or is it smarter to keep it higher? > among many other things, it depends on how much memory you have, but I would set it somewhat higher, 8 or 16. try running several dd's simultaneously. danny From ivoras at freebsd.org Mon Jan 12 02:05:07 2009 From: ivoras at freebsd.org (Ivan Voras) Date: Mon Jan 12 02:05:13 2009 Subject: iscsi client hangs performing I/O on a dead target In-Reply-To: <49653A7D.30906@modulus.org> References: <6c1e076a0901070247l7c006efajda8fddee84c337a@mail.gmail.com> <49653A7D.30906@modulus.org> Message-ID: Andrew Snow wrote: > Danny Braniss wrote: >> freebsd likes to >> panic if a disc goes away, so don't hold your breath for a solution soon. > > > You hit the nail on the head. This is going to be a increasingly bad > problem as we continue pushing in this of networked storage. > > It would be REALLY nice, if an I/O fails, to simply have the process > attempting the I/O to be killed, instead of bringing the machine to its > knees and locking up or panic the kernel. There have been some commits recently related to this problem - you could try running 8-CURRENT and see if it's addressed. -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 252 bytes Desc: OpenPGP digital signature Url : http://lists.freebsd.org/pipermail/freebsd-scsi/attachments/20090112/2607d4b8/signature.pgp From bugmaster at FreeBSD.org Mon Jan 12 03:07:00 2009 From: bugmaster at FreeBSD.org (FreeBSD bugmaster) Date: Mon Jan 12 03:09:07 2009 Subject: Current problem reports assigned to freebsd-scsi@FreeBSD.org Message-ID: <200901121106.n0CB6wor092118@freefall.freebsd.org> Note: to view an individual PR, use: http://www.freebsd.org/cgi/query-pr.cgi?pr=(number). The following is a listing of current problems submitted by FreeBSD users. These represent problem reports covering all versions including experimental development code and obsolete releases. S Tracker Resp. Description -------------------------------------------------------------------------------- o kern/129602 scsi [ahd] ahd(4) gets confused and wedges SCSI bus o kern/128452 scsi [sa] [panic] Accessing SCSI tape drive randomly crashe o kern/128245 scsi [scsi] "inquiry data fails comparison at DV1 step" [re o kern/127927 scsi [isp] isp(4) target driver crashes kernel when set up o kern/126866 scsi [isp] [panic] kernel panic on card initialization o kern/124667 scsi [amd] [panic] FreeBSD-7 kernel page faults at amd-scsi o kern/123674 scsi [ahc] ahc driver dumping o kern/123666 scsi [aac] attach fails with Adaptec SAS RAID 3805 controll o sparc/121676 scsi [iscsi] iscontrol do not connect iscsi-target on sparc o kern/120487 scsi [sg] scsi_sg incompatible with scanners o kern/120247 scsi [mpt] FreeBSD 6.3 and LSI Logic 1030 = only 3.300MB/s o kern/119668 scsi [cam] [patch] certain errors are too verbose comparing o kern/114597 scsi [sym] System hangs at SCSI bus reset with dual HBAs o kern/110847 scsi [ahd] Tyan U320 onboard problem with more than 3 disks o kern/99954 scsi [ahc] reading from DVD failes on 6.x [regression] o kern/94838 scsi Kernel panic while mounting SD card with lock switch o o kern/92798 scsi [ahc] SCSI problem with timeouts o kern/90282 scsi [sym] SCSI bus resets cause loss of ch device o kern/76178 scsi [ahd] Problem with ahd and large SCSI Raid system o kern/74627 scsi [ahc] [hang] Adaptec 2940U2W Can't boot 5.3 s kern/61165 scsi [panic] kernel page fault after calling cam_send_ccb o kern/60641 scsi [sym] Sporadic SCSI bus resets with 53C810 under load o kern/60598 scsi wire down of scsi devices conflicts with config s kern/57398 scsi [mly] Current fails to install on mly(4) based RAID di o kern/52638 scsi [panic] SCSI U320 on SMP server won't run faster than o kern/44587 scsi dev/dpt/dpt.h is missing defines required for DPT_HAND o kern/40895 scsi wierd kernel / device driver bug o kern/39388 scsi ncr/sym drivers fail with 53c810 and more than 256MB m o kern/38828 scsi [dpt] [request] DPT PM2012B/90 doesn't work o kern/35234 scsi World access to /dev/pass? (for scanner) requires acce 30 problems total. From asossi at dotcom.ts.it Wed Jan 14 03:56:40 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Wed Jan 14 03:56:48 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: References: Message-ID: <496DD248.1020502@dotcom.ts.it> Danny Braniss wrote: >> Danny Braniss wrote: >> >>>> Danny Braniss wrote: >>>> >>>> >>>>> wups, didn't read all your mail, sorry, >>>>> try increasing tht tag opening, in the config file add >>>>> tag = 64 >>>>> for example, or via camcontrol >>>>> >>>>> danny >>>>> >>>>> >>>>> >>>> I modify my iscsi.conf by adding tags = 64 (and no tag). Now works fine, >>>> about 43MB/s. Thank You very match. >>>> >>>> > RTFM :-) > > [...] > danny > In last 2-3 months I searched the (F) manual, but I didn't find any! Where is the manual?... In this week I did many tests on ISCSI and found another problem with slow writing. I created 7 virtual disk on my NAS server. The first 4 disks (/dev/da0 - /dev/da3) work fine, the other 3 (/dev/da4 - /dev/da6) are slow. I found this depends from parameter ISCSI_MAX_LUNS defined in file iscsi.h, set 4. I tried to increase this value, but with all values higher of 4 the initiator prints error: iscontrol[602]: ISCSIGETCAM failed: 25 Is it possible to manage more than 4 disk without degrading the performance? Thanks in advance. -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From morganw at chemikals.org Wed Jan 14 04:23:38 2009 From: morganw at chemikals.org (Wes Morgan) Date: Wed Jan 14 04:23:45 2009 Subject: SMART status of SATA drives on SAS controller Message-ID: I've got 8 SATA2 drives in an zfs raidz2 on an LSI controller (1068 I believe, mpt driver), and one of them seems to be acting strangely. I'd like to get the smart status without pulling it out of the array and dropping it onto an ATA controller, but I don't seem to be able to for any of the drives. Using the device type as both "SAT" and "SCSI", neither will successfully show the full output. Is there any way around this? Error below... === START OF INFORMATION SECTION === Device Model: WDC WD5002ABYS-01B1B0 Serial Number: WD-WCASY3240847 Firmware Version: 02.03B02 User Capacity: 500,107,862,016 bytes Device is: Not in smartctl database [for details use: -P showall] ATA Version is: 8 ATA Standard is: Exact ATA specification draft version not indicated Local Time is: Wed Jan 14 06:14:18 2009 CST SMART support is: Available - device has SMART capability. SMART support is: Enabled === START OF ENABLE/DISABLE COMMANDS SECTION === SMART Enabled. (pass4:mpt0:0:4:0): ATA COMMAND PASS THROUGH(16). CDB: 85 6 2c 0 da 0 0 0 0 0 4f 0 c2 0 b0 0 (pass4:mpt0:0:4:0): CAM Status: SCSI Status Error (pass4:mpt0:0:4:0): SCSI Status: Check Condition (pass4:mpt0:0:4:0): RECOVERED ERROR asc:0,1d (pass4:mpt0:0:4:0): ATA pass through information available SMART Disabled. Use option -s with argument 'on' to enable it. From danny at cs.huji.ac.il Wed Jan 14 05:10:13 2009 From: danny at cs.huji.ac.il (Danny Braniss) Date: Wed Jan 14 05:10:20 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: <496DD248.1020502@dotcom.ts.it> References: <496DD248.1020502@dotcom.ts.it> Message-ID: > Danny Braniss wrote: > >> Danny Braniss wrote: > >> > >>>> Danny Braniss wrote: > >>>> > >>>> > >>>>> wups, didn't read all your mail, sorry, > >>>>> try increasing tht tag opening, in the config file add > >>>>> tag = 64 > >>>>> for example, or via camcontrol > >>>>> > >>>>> danny > >>>>> > >>>>> > >>>>> > >>>> I modify my iscsi.conf by adding tags = 64 (and no tag). Now works fine, > >>>> about 43MB/s. Thank You very match. > >>>> > >>>> > > RTFM :-) > > > > [...] > > danny > > > In last 2-3 months I searched the (F) manual, but I didn't find any! > Where is the manual?... > man -k iscsi iscontrol(8) - login/negotiator/control for an iSCSI initiator session iscsi.conf(5) - key options to be negotiated in an iSCSI session iscsi_initiator(4) - kernel driver for the iSCSI protocol iscsi-target(8) - service remote iSCSI requests targets(5) - configuration file for iSCSI targets > In this week I did many tests on ISCSI and found another problem with > slow writing. I created 7 virtual disk on my NAS server. The first 4 > disks (/dev/da0 - /dev/da3) work fine, the other 3 (/dev/da4 - /dev/da6) > are slow. > I found this depends from parameter ISCSI_MAX_LUNS defined in file > iscsi.h, set 4. I tried to increase this value, but with all values > higher of 4 the initiator prints error: > iscontrol[602]: ISCSIGETCAM failed: 25 > did you recompile the driver? > Is it possible to manage more than 4 disk without degrading the performance? > are you sure that da4,5,6 actually are disks? they might be just files ... ls -ls /dev/da? > Thanks in advance. > chiao :-) danny > -- > Sossi Andrej > ------------------------- > DotCom Information technology > > Via Biancospino, 9 > 34151 - Opicina (TS) > Italy > > tel: +39 040 2158191 > fax: +39 040 0641954 > E-mail: asossi@dotcom.ts.it > ---------------------------- > > Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie > > This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. > From asossi at dotcom.ts.it Wed Jan 14 05:31:12 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Wed Jan 14 05:31:19 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: References: <496DD248.1020502@dotcom.ts.it> Message-ID: <496DE872.70900@dotcom.ts.it> Danny Braniss wrote: >> Danny Braniss wrote: >> >>>> Danny Braniss wrote: >>>> >>>> >>>>>> Danny Braniss wrote: >>>>>> >>>>>> >>>>>> >>>>>>> wups, didn't read all your mail, sorry, >>>>>>> try increasing tht tag opening, in the config file add >>>>>>> tag = 64 >>>>>>> for example, or via camcontrol >>>>>>> >>>>>>> danny >>>>>>> >>>>>>> >>>>>>> >>>>>>> >>>>>> I modify my iscsi.conf by adding tags = 64 (and no tag). Now works fine, >>>>>> about 43MB/s. Thank You very match. >>>>>> >>>>>> >>>>>> >>> RTFM :-) >>> >>> [...] >>> danny >>> >>> >> In last 2-3 months I searched the (F) manual, but I didn't find any! >> Where is the manual?... >> >> > > man -k iscsi > iscontrol(8) - login/negotiator/control for an iSCSI initiator > session > iscsi.conf(5) - key options to be negotiated in an iSCSI session > iscsi_initiator(4) - kernel driver for the iSCSI protocol > iscsi-target(8) - service remote iSCSI requests > targets(5) - configuration file for iSCSI targets > > >> In this week I did many tests on ISCSI and found another problem with >> slow writing. I created 7 virtual disk on my NAS server. The first 4 >> disks (/dev/da0 - /dev/da3) work fine, the other 3 (/dev/da4 - /dev/da6) >> are slow. >> I found this depends from parameter ISCSI_MAX_LUNS defined in file >> iscsi.h, set 4. I tried to increase this value, but with all values >> higher of 4 the initiator prints error: >> iscontrol[602]: ISCSIGETCAM failed: 25 >> >> > did you recompile the driver? > Yes, I recompiled all kernel source. I do many test whit and without module. Is it necessary to post my kernel configuration? > >> Is it possible to manage more than 4 disk without degrading the performance? >> >> > are you sure that da4,5,6 actually are disks? they might be just files ... > ls -ls /dev/da? > # ls -ls /dev/da* 0 crw-r----- 1 root operator 0, 87 Jan 14 12:12 /dev/da0 0 crw-r----- 1 root operator 0, 92 Jan 14 12:12 /dev/da0s1 0 crw-r----- 1 root operator 0, 95 Jan 14 12:12 /dev/da0s1c 0 crw-r----- 1 root operator 0, 96 Jan 14 12:12 /dev/da0s1d 0 crw-r----- 1 root operator 0, 93 Jan 14 12:12 /dev/da1 0 crw-r----- 1 root operator 0, 99 Jan 14 12:12 /dev/da1s1 0 crw-r----- 1 root operator 0, 106 Jan 14 12:12 /dev/da1s1c 0 crw-r----- 1 root operator 0, 107 Jan 14 12:12 /dev/da1s1d 0 crw-r----- 1 root operator 0, 94 Jan 14 12:12 /dev/da2 0 crw-r----- 1 root operator 0, 100 Jan 14 12:12 /dev/da2s1 0 crw-r----- 1 root operator 0, 108 Jan 14 12:12 /dev/da2s1c 0 crw-r----- 1 root operator 0, 109 Jan 14 12:12 /dev/da2s1d 0 crw-r----- 1 root operator 0, 97 Jan 14 12:12 /dev/da3 0 crw-r----- 1 root operator 0, 104 Jan 14 12:12 /dev/da3s1 0 crw-r----- 1 root operator 0, 112 Jan 14 12:12 /dev/da3s1c 0 crw-r----- 1 root operator 0, 113 Jan 14 12:12 /dev/da3s1d 0 crw-r----- 1 root operator 0, 98 Jan 14 12:12 /dev/da4 0 crw-r----- 1 root operator 0, 105 Jan 14 12:12 /dev/da4s1 0 crw-r----- 1 root operator 0, 114 Jan 14 12:12 /dev/da4s1c 0 crw-r----- 1 root operator 0, 115 Jan 14 12:12 /dev/da4s1d 0 crw-r----- 1 root operator 0, 101 Jan 14 12:12 /dev/da5 0 crw-r----- 1 root operator 0, 110 Jan 14 12:12 /dev/da5s1 0 crw-r----- 1 root operator 0, 116 Jan 14 12:12 /dev/da5s1c 0 crw-r----- 1 root operator 0, 117 Jan 14 12:12 /dev/da5s1d 0 crw-r----- 1 root operator 0, 102 Jan 14 12:12 /dev/da6 0 crw-r----- 1 root operator 0, 111 Jan 14 12:12 /dev/da6s1 0 crw-r----- 1 root operator 0, 118 Jan 14 12:12 /dev/da6s1c 0 crw-r----- 1 root operator 0, 119 Jan 14 12:12 /dev/da6s1d Initially I work with 4 disks for real data and then create another 3 for tests data. Disks da4,5,6 is identical configured on the NAS as first 4. > >> Thanks in advance. >> >> > > chiao :-) > > danny > >> [...] -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From asossi at dotcom.ts.it Wed Jan 14 05:36:46 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Wed Jan 14 05:36:51 2009 Subject: rc script for I SCSI Message-ID: <496DE9BF.9020007@dotcom.ts.it> Hello, I have NAS server with ISCSI. I must mount ISCSI disks at boot time, but I didn't find any article on how to do this. Then I wrote a rc script to help me to mount disks at boot time. ----------------- #!/bin/sh # # PROVIDE: iscsi # REQUIRE: NETWORKING # BEFORE: mountlate iscontrol_enable=${iscontrol_enable-"NO"} iscontrol_flags=${iscontrol_flags-""} iscontrol_pidfile=${iscontrol_pidfile-"/var/run/iscontrol.pid"} . /etc/rc.subr name="iscontrol" rcvar=`set_rcvar` command="/sbin/${name}" load_rc_config $name pidfile="${iscontrol_pidfile}" start_cmd="echo \"Starting ${name}.\"; /usr/bin/nice -5 ${command} ${iscontrol_flags} ${command_args}; sleep 2" run_rc_command "$1" ----------------- The disk to mount must be in fstab file with the 'late' option. Eg: /dev/da0s1d /mnt/iscsi ufs rw,late 0 0 Is this the correct way to do this? If yes, is it possible to insert this script in the future version of FreeBSD? Thanks. -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From danny at cs.huji.ac.il Wed Jan 14 06:42:11 2009 From: danny at cs.huji.ac.il (Danny Braniss) Date: Wed Jan 14 06:42:17 2009 Subject: rc script for I SCSI In-Reply-To: Your message of Wed, 14 Jan 2009 14:33:51 +0100 . Message-ID: this is an early attempt: #!/bin/sh # PROVIDE: iscsi # REQUIRE: NETWORKING # BEFORE: DAEMON # KEYWORD: nojail shutdown # # Add the following lines to /etc/rc.conf to enable iscsi: # # iscsi_enable="YES" # iscsi_fstab="/etc/fstab.iscsi" . /etc/rc.subr . /cs/share/etc/rc.subr name=iscsi rcvar=`set_rcvar` command=/sbin/iscontrol iscsi_enable=${iscsi_enable:-"NO"} iscsi_fstab=${iscsi_fstab:-"/etc/fstab.iscsi"} iscsi_exports=${iscsi_exports:-"/etc/exports.iscsi"} iscsi_debug=${iscsi_debug:-0} start_cmd="iscsi_start" faststop_cmp="iscsi_stop" stop_cmd="iscsi_stop" start_precmd="iscontrol_precmd" iscontrol_prog=${iscontrol_prog:-"iscontrol"} iscontrol_log=${iscontrol_log:-"/var/log/$iscontrol_prog"} iscontrol_syslog=${iscontrol_syslog:-"644 3 100 * JC"} iscontrol_precmd() { setup_syslog "$iscontrol_prog" "$iscontrol_log" "$iscontrol_syslog" } iscsi_wait() { dev=$1 trap "echo 'wait loop cancelled'; exit 1" 2 count=0 while true; do if [ -c $dev ]; then break; fi if [ $count -eq 0 ]; then echo -n Waiting for ${dev}': ' fi count=$((${count} + 1)) if [ $count -eq 6 ]; then echo " Failed for dev=$dev" return 0 break fi echo -n '.' sleep 5; done echo "$dev ok." return 1 } iscsi_start() { # # load needed modules for m in iscsi_initiator geom_label; do kldstat -qm $m || kldload $m done sysctl debug.iscsi_initiator=$iscsi_debug # # start iscontrol for each target if [ -n "${iscsi_targets}" ]; then for target in ${iscsi_targets}; do ${command} ${rc_flags} -n ${target} done fi if [ -f "${iscsi_fstab}" ]; then while read spec file type opt t1 t2 do case ${spec} in \#*|'') ;; *) if iscsi_wait ${spec}; then break; fi echo type=$type spec=$spec file=$file fsck -p ${spec} && mkdir -p ${file} && mount ${spec} ${file} chmod 755 ${file} ;; esac done < ${iscsi_fstab} fi if [ -f "${iscsi_exports}" ]; then cat ${iscsi_exports} >> /etc/exports #/etc/rc.d/mountd reload kill -1 `cat /var/run/mountd.pid` fi if checkyesno zfs_enable; then if checkyesno iscsi_zfs; then sleep 4 zpool import -d /dev/label -a # presumably we can ignore zfs mount -a share -a and swapon # some zfs dataset may be exported "legacy", so hup mountd kill -1 `cat /var/run/mountd.pid` fi fi } iscsi_stop() { echo 'iscsi stopping' while read spec file type opt t1 t2 do case ${spec} in \#*|'') ;; *) echo iscsi: umount $spec umount -fv $spec ;; esac done < ${iscsi_fstab} } load_rc_config $name run_rc_command "$1" From scottl at samsco.org Wed Jan 14 06:56:50 2009 From: scottl at samsco.org (Scott Long) Date: Wed Jan 14 06:56:56 2009 Subject: SMART status of SATA drives on SAS controller In-Reply-To: References: Message-ID: <496DF83D.4090904@samsco.org> A tweak is needed to smartctl to make this work. See below. FreeBSD needs to become more aware of the ATA Passthrough feature of SCSI, but for now this patch with let smartctl work correctly. --- os_freebsd.cpp.orig 2008-03-04 15:09:47.000000000 -0700 +++ os_freebsd.cpp 2008-09-23 09:43:01.000000000 -0600 @@ -525,7 +524,7 @@ return -1; } - if ((ccb->ccb_h.status & CAM_STATUS_MASK) != CAM_REQ_CMP) { + if (((ccb->ccb_h.status & CAM_STATUS_MASK) != CAM_REQ_CMP) && ((ccb->ccb_h.status & CAM_STATUS_MASK) != CAM_SCSI_STATUS_ERROR)) { #if __FreeBSD_version > 500000 cam_error_print(cam_dev,ccb,CAM_ESF_ALL,CAM_EPF_ALL,stderr); #endif Scott Wes Morgan wrote: > I've got 8 SATA2 drives in an zfs raidz2 on an LSI controller (1068 I > believe, mpt driver), and one of them seems to be acting strangely. I'd > like to get the smart status without pulling it out of the array and > dropping it onto an ATA controller, but I don't seem to be able to for > any of the drives. Using the device type as both "SAT" and "SCSI", > neither will successfully show the full output. Is there any way around > this? Error below... > > > === START OF INFORMATION SECTION === > Device Model: WDC WD5002ABYS-01B1B0 > Serial Number: WD-WCASY3240847 > Firmware Version: 02.03B02 > User Capacity: 500,107,862,016 bytes > Device is: Not in smartctl database [for details use: -P showall] > ATA Version is: 8 > ATA Standard is: Exact ATA specification draft version not indicated > Local Time is: Wed Jan 14 06:14:18 2009 CST > SMART support is: Available - device has SMART capability. > SMART support is: Enabled > > === START OF ENABLE/DISABLE COMMANDS SECTION === > SMART Enabled. > (pass4:mpt0:0:4:0): ATA COMMAND PASS THROUGH(16). CDB: 85 6 2c 0 da 0 0 > 0 0 0 4f 0 c2 0 b0 0 > (pass4:mpt0:0:4:0): CAM Status: SCSI Status Error > (pass4:mpt0:0:4:0): SCSI Status: Check Condition > (pass4:mpt0:0:4:0): RECOVERED ERROR asc:0,1d > (pass4:mpt0:0:4:0): ATA pass through information available > SMART Disabled. Use option -s with argument 'on' to enable it. > _______________________________________________ > freebsd-scsi@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-scsi > To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" From asossi at dotcom.ts.it Wed Jan 14 07:24:27 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Wed Jan 14 07:24:34 2009 Subject: ISCSI and multipath In-Reply-To: <20090109061324.GD81380@in-addr.com> References: <496634BB.9050902@dotcom.ts.it> <4966A25E.4070803@modulus.org> <20090109061324.GD81380@in-addr.com> Message-ID: <496E02FB.9090000@dotcom.ts.it> Gary Palmer wrote: > On Fri, Jan 09, 2009 at 12:03:26PM +1100, Andrew Snow wrote: > >> Sossi Andrej wrote: >> >>> Another question about MD3000i. >>> My MD3000i have 2 controller and every controller have 2 net interface. >>> My FreeBSD server is connect on NAS server with 2 network cards throw >>> out 2 switch on th 2 networks. (192.168.253.X and 192.168.252.X). >>> In the official manual is written if the primary controller (or net) >>> have a problem the NAS automatically switch disks drive on second >>> controller. For this is required MPIO on Windows or MPP on Linux. It is >>> supported also on FreeBSD? >>> >> If you only wanted to do failover at the network level with shared IP >> address, you could use lagg. >> >> However, since you have different IP subnets for each network, you >> probably want to look at using geom_fox. You set up two iSCSI >> connections, one to each controller, and geom_fox on top to make it >> appear as a single disk device. >> > > FreeBSD 7.0 and later also has geom_multipath, which I've been > told (no experience) is a better approach. I suggest you > review documentation for both and make your own decision > > Regards, > > Gary > I read geom_fox an geom_mirror man pages. I think the geom_mirror is best way, but not everything is clear for me. This is scenario: NAS server: controller 0 interface 0: 192.168.253.254 controller 1 interface 0: 192.168.253.253 controller 0 interface 1: 192.168.252.254 controller 1 interface 1: 192.168.252.253 FreeBSD: re0: 192.168.253.1 re1: 192.168.252.1 FreeBSD is connected through 2 switches, one for net 192.168.253.X and one for 192.168.252.X. In the iscsi.conf file my target is 192.168.253.254. ISCSI initiator creates only one device for disk. If I will use geom_multipath, I must launch initiator 2 times (or 4 times), each for one interface. Then I must configure geom_multipart device for /dev/da0 , /dev/da5, ... Is this correct? If yes, I plan some tests and then I will write the results. Thanks -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From morganw at chemikals.org Wed Jan 14 19:21:00 2009 From: morganw at chemikals.org (Wes Morgan) Date: Wed Jan 14 19:21:07 2009 Subject: SMART status of SATA drives on SAS controller In-Reply-To: <496DF83D.4090904@samsco.org> References: <496DF83D.4090904@samsco.org> Message-ID: On Wed, 14 Jan 2009, Scott Long wrote: > A tweak is needed to smartctl to make this work. See below. FreeBSD needs > to become more aware of the ATA Passthrough feature of SCSI, but > for now this patch with let smartctl work correctly. Thanks, this works great. > --- os_freebsd.cpp.orig 2008-03-04 15:09:47.000000000 -0700 > +++ os_freebsd.cpp 2008-09-23 09:43:01.000000000 -0600 > @@ -525,7 +524,7 @@ > return -1; > } > > - if ((ccb->ccb_h.status & CAM_STATUS_MASK) != CAM_REQ_CMP) { > + if (((ccb->ccb_h.status & CAM_STATUS_MASK) != CAM_REQ_CMP) && > ((ccb->ccb_h.status & CAM_STATUS_MASK) != CAM_SCSI_STATUS_ERROR)) { > #if __FreeBSD_version > 500000 > cam_error_print(cam_dev,ccb,CAM_ESF_ALL,CAM_EPF_ALL,stderr); > #endif > > > > Scott > > > Wes Morgan wrote: >> I've got 8 SATA2 drives in an zfs raidz2 on an LSI controller (1068 I >> believe, mpt driver), and one of them seems to be acting strangely. I'd >> like to get the smart status without pulling it out of the array and >> dropping it onto an ATA controller, but I don't seem to be able to for any >> of the drives. Using the device type as both "SAT" and "SCSI", neither will >> successfully show the full output. Is there any way around this? Error >> below... >> >> >> === START OF INFORMATION SECTION === >> Device Model: WDC WD5002ABYS-01B1B0 >> Serial Number: WD-WCASY3240847 >> Firmware Version: 02.03B02 >> User Capacity: 500,107,862,016 bytes >> Device is: Not in smartctl database [for details use: -P showall] >> ATA Version is: 8 >> ATA Standard is: Exact ATA specification draft version not indicated >> Local Time is: Wed Jan 14 06:14:18 2009 CST >> SMART support is: Available - device has SMART capability. >> SMART support is: Enabled >> >> === START OF ENABLE/DISABLE COMMANDS SECTION === >> SMART Enabled. >> (pass4:mpt0:0:4:0): ATA COMMAND PASS THROUGH(16). CDB: 85 6 2c 0 da 0 0 0 0 >> 0 4f 0 c2 0 b0 0 >> (pass4:mpt0:0:4:0): CAM Status: SCSI Status Error >> (pass4:mpt0:0:4:0): SCSI Status: Check Condition >> (pass4:mpt0:0:4:0): RECOVERED ERROR asc:0,1d >> (pass4:mpt0:0:4:0): ATA pass through information available >> SMART Disabled. Use option -s with argument 'on' to enable it. >> _______________________________________________ >> freebsd-scsi@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-scsi >> To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" > From asossi at dotcom.ts.it Thu Jan 15 07:58:45 2009 From: asossi at dotcom.ts.it (Sossi Andrej) Date: Thu Jan 15 07:58:51 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: References: Message-ID: <496F5C80.9030406@dotcom.ts.it> Danny Braniss write: > [...] > >>>> In this week I did many tests on ISCSI and found another problem with >>>> slow writing. I created 7 virtual disk on my NAS server. The first 4 >>>> disks (/dev/da0 - /dev/da3) work fine, the other 3 (/dev/da4 - /dev/da6) >>>> are slow. >>>> I found this depends from parameter ISCSI_MAX_LUNS defined in file >>>> iscsi.h, set 4. I tried to increase this value, but with all values >>>> higher of 4 the initiator prints error: >>>> iscontrol[602]: ISCSIGETCAM failed: 25 >>>> >>>> > arg, I will fix this in the next release, but for now, recompile iscontrol too. > > [...] > > danny > I forgot to compile iscontrol. Sorry. Now it works fine. R/W speed is now ~48Mb/s on disks da0-3 and ~32Mb/s on disks da4-6. I set ISCSI_MAX_LUNS at value 16. Speed 32Mb/s is good for my job, but... why is there this difference? Thanks for another reply. -- Sossi Andrej ------------------------- DotCom Information technology Via Biancospino, 9 34151 - Opicina (TS) Italy tel: +39 040 2158191 fax: +39 040 0641954 E-mail: asossi@dotcom.ts.it ---------------------------- Ai sensi del D.lgs n. 196 del 30.06.03 (Codice Privacy) si precisa che le informazioni contenute in questo messaggio sono riservate e ad uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La preghiamo di eliminarlo senza copiarlo e di non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie This message, for the D.lgs n. 196 / 30.06.03 (Privacy Code), may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. From danny at cs.huji.ac.il Thu Jan 15 08:17:09 2009 From: danny at cs.huji.ac.il (Danny Braniss) Date: Thu Jan 15 08:17:16 2009 Subject: ISCSI slow to read from DELL MD3000i In-Reply-To: <496F5C80.9030406@dotcom.ts.it> References: <496F5C80.9030406@dotcom.ts.it> Message-ID: > Danny Braniss write: > > [...] > > > >>>> In this week I did many tests on ISCSI and found another problem with > >>>> slow writing. I created 7 virtual disk on my NAS server. The first 4 > >>>> disks (/dev/da0 - /dev/da3) work fine, the other 3 (/dev/da4 - /dev/da6) > >>>> are slow. > >>>> I found this depends from parameter ISCSI_MAX_LUNS defined in file > >>>> iscsi.h, set 4. I tried to increase this value, but with all values > >>>> higher of 4 the initiator prints error: > >>>> iscontrol[602]: ISCSIGETCAM failed: 25 > >>>> > >>>> > > arg, I will fix this in the next release, but for now, recompile iscontrol too. > > > > [...] > > > > danny > > > I forgot to compile iscontrol. Sorry. don't be sorry, it's my fault. > Now it works fine. > R/W speed is now ~48Mb/s on disks da0-3 and ~32Mb/s on disks da4-6. I > set ISCSI_MAX_LUNS at value 16. Speed 32Mb/s is good for my job, but... > why is there this difference? don't know, there shouldn't be any difference, make sure they all have the same tag opening, > Thanks for another reply. thank you for testing! danny PS: the email I sent you before was almost correct answer to the wrong question. From gavin at FreeBSD.org Sun Jan 18 09:09:16 2009 From: gavin at FreeBSD.org (gavin@FreeBSD.org) Date: Sun Jan 18 09:09:28 2009 Subject: kern/130621: [mpt] tranfer rate is inscrutable slow when use lsi21320-is raid0 mode and have some other problems Message-ID: <200901181709.n0IH9FR9092938@freefall.freebsd.org> Old Synopsis: the tranfer rate is inscrutable slow when use lsi21320-is raid0 mode and have some other problems New Synopsis: [mpt] tranfer rate is inscrutable slow when use lsi21320-is raid0 mode and have some other problems Responsible-Changed-From-To: freebsd-bugs->freebsd-scsi Responsible-Changed-By: gavin Responsible-Changed-When: Sun Jan 18 17:03:04 UTC 2009 Responsible-Changed-Why: Over to maintainer(s). To submitter: to be honest you are probably better off submitting one PR for each of these issues (missing passX devices, intermittant 3.3MB/s detected speed) as I suspect they are not connected to each other. If you dodo that, mention this PR so that we remember to close it. Thanks! http://www.freebsd.org/cgi/query-pr.cgi?pr=130621 From bugmaster at FreeBSD.org Mon Jan 19 03:07:05 2009 From: bugmaster at FreeBSD.org (FreeBSD bugmaster) Date: Mon Jan 19 03:08:59 2009 Subject: Current problem reports assigned to freebsd-scsi@FreeBSD.org Message-ID: <200901191107.n0JB74bX063093@freefall.freebsd.org> Note: to view an individual PR, use: http://www.freebsd.org/cgi/query-pr.cgi?pr=(number). The following is a listing of current problems submitted by FreeBSD users. These represent problem reports covering all versions including experimental development code and obsolete releases. S Tracker Resp. Description -------------------------------------------------------------------------------- o kern/130621 scsi [mpt] tranfer rate is inscrutable slow when use lsi213 o kern/129602 scsi [ahd] ahd(4) gets confused and wedges SCSI bus o kern/128452 scsi [sa] [panic] Accessing SCSI tape drive randomly crashe o kern/128245 scsi [scsi] "inquiry data fails comparison at DV1 step" [re o kern/127927 scsi [isp] isp(4) target driver crashes kernel when set up o kern/126866 scsi [isp] [panic] kernel panic on card initialization o kern/124667 scsi [amd] [panic] FreeBSD-7 kernel page faults at amd-scsi o kern/123674 scsi [ahc] ahc driver dumping o kern/123666 scsi [aac] attach fails with Adaptec SAS RAID 3805 controll o sparc/121676 scsi [iscsi] iscontrol do not connect iscsi-target on sparc o kern/120487 scsi [sg] scsi_sg incompatible with scanners o kern/120247 scsi [mpt] FreeBSD 6.3 and LSI Logic 1030 = only 3.300MB/s o kern/119668 scsi [cam] [patch] certain errors are too verbose comparing o kern/114597 scsi [sym] System hangs at SCSI bus reset with dual HBAs o kern/110847 scsi [ahd] Tyan U320 onboard problem with more than 3 disks o kern/99954 scsi [ahc] reading from DVD failes on 6.x [regression] o kern/94838 scsi Kernel panic while mounting SD card with lock switch o o kern/92798 scsi [ahc] SCSI problem with timeouts o kern/90282 scsi [sym] SCSI bus resets cause loss of ch device o kern/76178 scsi [ahd] Problem with ahd and large SCSI Raid system o kern/74627 scsi [ahc] [hang] Adaptec 2940U2W Can't boot 5.3 s kern/61165 scsi [panic] kernel page fault after calling cam_send_ccb o kern/60641 scsi [sym] Sporadic SCSI bus resets with 53C810 under load o kern/60598 scsi wire down of scsi devices conflicts with config s kern/57398 scsi [mly] Current fails to install on mly(4) based RAID di o kern/52638 scsi [panic] SCSI U320 on SMP server won't run faster than o kern/44587 scsi dev/dpt/dpt.h is missing defines required for DPT_HAND o kern/40895 scsi wierd kernel / device driver bug o kern/39388 scsi ncr/sym drivers fail with 53c810 and more than 256MB m o kern/38828 scsi [dpt] [request] DPT PM2012B/90 doesn't work o kern/35234 scsi World access to /dev/pass? (for scanner) requires acce 31 problems total. From linimon at FreeBSD.org Mon Jan 19 07:34:48 2009 From: linimon at FreeBSD.org (linimon@FreeBSD.org) Date: Mon Jan 19 07:34:55 2009 Subject: kern/130735: [cam] [patch] pass M_NOWAIT to the malloc() call inside cdreaddvdstructure() Message-ID: <200901191534.n0JFYkWT069538@freefall.freebsd.org> Old Synopsis: [patch] pass M_NOWAIT to the malloc() call inside cdreaddvdstructure() New Synopsis: [cam] [patch] pass M_NOWAIT to the malloc() call inside cdreaddvdstructure() Responsible-Changed-From-To: freebsd-bugs->freebsd-scsi Responsible-Changed-By: linimon Responsible-Changed-When: Mon Jan 19 15:34:25 UTC 2009 Responsible-Changed-Why: Over to maintainer(s). http://www.freebsd.org/cgi/query-pr.cgi?pr=130735 From rea-fbsd at codelabs.ru Mon Jan 19 11:30:04 2009 From: rea-fbsd at codelabs.ru (Eygene Ryabinkin) Date: Mon Jan 19 11:30:10 2009 Subject: kern/130735: [patch] pass M_NOWAIT to the malloc() call inside cdreaddvdstructure() Message-ID: <200901191930.n0JJU3Sf041556@freefall.freebsd.org> The following reply was made to PR kern/130735; it has been noted by GNATS. From: Eygene Ryabinkin To: Jaakko Heinonen Cc: bug-followup@FreeBSD.org Subject: Re: kern/130735: [patch] pass M_NOWAIT to the malloc() call inside cdreaddvdstructure() Date: Mon, 19 Jan 2009 22:25:28 +0300 --WIyZ46R2i8wDzkSu Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Jakko, good day. Mon, Jan 19, 2009 at 05:06:47PM +0200, Jaakko Heinonen wrote: > On 2009-01-19, Eygene Ryabinkin wrote: > > --- a/sys/cam/scsi/scsi_cd.c > > +++ b/sys/cam/scsi/scsi_cd.c > > @@ -4063,7 +4063,7 @@ cdreaddvdstructure(struct cam_periph *periph, struct dvd_struct *dvdstruct) > > } > > > > if (length != 0) { > > - databuf = malloc(length, M_DEVBUF, M_WAITOK | M_ZERO); > > + databuf = malloc(length, M_DEVBUF, M_NOWAIT | M_ZERO); > > } else > > databuf = NULL; > > This change doesn't look correct. If you use M_NOWAIT malloc(9) can fail > and return NULL. Good catch -- I wasn't aware of it. The attached patch should be slightly better. -- Eygene _ ___ _.--. # \`.|\..----...-'` `-._.-'_.-'` # Remember that it is hard / ' ` , __.--' # to read the on-line manual )/' _/ \ `-_, / # while single-stepping the kernel. `-'" `"\_ ,_.-;_.-\_ ', fsc/as # _.-'_./ {_.' ; / # -- FreeBSD Developers handbook {_.-``-' {_/ # --WIyZ46R2i8wDzkSu Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=p --- sys/cam/scsi/scsi_cd.c.orig 2007-07-21 22:07:45.000000000 +0400 +++ sys/cam/scsi/scsi_cd.c 2009-01-19 22:19:18.000000000 +0300 @@ -4063,7 +4063,11 @@ } if (length != 0) { - databuf = malloc(length, M_DEVBUF, M_WAITOK | M_ZERO); + databuf = malloc(length, M_DEVBUF, M_NOWAIT | M_ZERO); + if (databuf == NULL) { + error = ENOMEM; + goto bailout; + } } else databuf = NULL; --WIyZ46R2i8wDzkSu-- From andreyns at gmail.com Mon Jan 19 20:43:19 2009 From: andreyns at gmail.com (Sukharew N Andrew) Date: Mon Jan 19 20:43:48 2009 Subject: Can't connect Sun StorEdge 3310 to FreeBSD 7.1 Message-ID: <7aab6650901192021j768ed9d4v98650039f937734e@mail.gmail.com> Hello. At time when OS starting seen next lines run_interrupt_driven_hooks: still waiting after 60 seconds for xpt_config run_interrupt_driven_hooks: still waiting after 120 seconds for xpt_config (probe15:ciss0:32:0:0): Begin Domain Validation (probe17:ciss0:32:2:0): Begin Domain Validation (probe15:ciss0:32:0:0): inquiry data fails comparison at DV1 step (probe17:ciss0:32:2:0): inquiry data fails comparison at DV1 step (probe15:ciss0:32:0:0): Leave Domain Validation (probe17:ciss0:32:2:0): Leave Domain Validation run_interrupt_driven_hooks: still waiting after 180 seconds for xpt_config run_interrupt_driven_hooks: still waiting after 240 seconds for xpt_config da0 at ciss0 bus 0 target 0 lun 0 da0: Fixed Direct Access SCSI-0 device da0: 135.168MB/s transfers da0: 138919MB (284506560 512 byte sectors: 255H 32S/T 34866C) ses0 at ciss0 bus 32 target 0 lun 0 ses0: Removable Enclosure Services SCSI-4 device ses0: 135.168MB/s transfers ses0: SCSI-3 SES Device ses1 at ciss0 bus 32 target 2 lun 0 ses1: Removable Enclosure Services SCSI-4 device ses1: 135.168MB/s transfers ses1: SCSI-3 SES Device When I'm doing "camcontrol rescan all" I see next lines in /var/log/messages: cam_periph_alloc: attempt to re-allocate valid device pass0 rejected passasync: Unable to attach new device due to status 0x6: CCB request was invalid cam_periph_alloc: attempt to re-allocate valid device da0 rejected daasync: Unable to attach to new device due to status 0x6 How can I use storedge ? -- ------------------ With best regards Sukharew N Andrew From spork at bway.net Sat Jan 24 15:53:24 2009 From: spork at bway.net (Charles Sprickman) Date: Sat Jan 24 15:53:32 2009 Subject: 7.1 and mpt, slow writes Message-ID: Hi all, I had this one figured out in 6.x, but I'm not seeing a similar fix in 7.x. I have a Dell Poweredge 860 with a Dell-branded LSI controller: mpt0: port 0xec00-0xecff mem 0xfe9fc000-0xfe9fffff,0xfe9e0000-0xfe9effff irq 16 at device 8.0 on pci2 mpt0: [ITHREAD] mpt0: MPI Version=1.5.13.0 mpt0: Capabilities: ( RAID-0 RAID-1E RAID-1 ) mpt0: 1 Active Volume (2 Max) mpt0: 2 Hidden Drive Members (10 Max) ... mpt0:vol0(mpt0:0:0): Settings ( Hot-Plug-Spares High-Priority-ReSync ) mpt0:vol0(mpt0:0:0): Using Spare Pool: 0 mpt0:vol0(mpt0:0:0): 2 Members: (mpt0:1:32:0): Primary Online (mpt0:1:1:0): Secondary Online mpt0:vol0(mpt0:0:0): RAID-1 - Optimal mpt0:vol0(mpt0:0:0): Status ( Enabled ) (mpt0:vol0:1): Physical (mpt0:0:1:0), Pass-thru (mpt0:1:0:0) (mpt0:vol0:1): Online (mpt0:vol0:0): Physical (mpt0:0:32:0), Pass-thru (mpt0:1:1:0) (mpt0:vol0:0): Online da0 at mpt0 bus 0 target 0 lun 0 da0: Fixed Direct Access SCSI-5 device da0: 300.000MB/s transfers da0: 75340MB (154296320 512 byte sectors: 255H 63S/T 9604C) Basic tests with dd and bonnie show that writes are much slower than reads: [root@uniweb /jails]# dd if=/dev/zero of=foo count=1000M ^C1293952+0 records in 1293951+0 records out 662502912 bytes transferred in 97.712971 secs (6780092 bytes/sec) [root@uniweb /jails]# dd if=foo of=/dev/null 1293952+0 records in 1293952+0 records out 662503424 bytes transferred in 5.065705 secs (130782076 bytes/sec) Version 1.93d ------Sequential Output------ --Sequential Input- --Random- Concurrency 1 -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks-- Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP uniweb.bway.n 2016M 220 99 6744 2 5985 2 417 99 58007 14 245.8 8 Latency 42611us 297ms 3053ms 24821us 43190us 4987ms Version 1.93d ------Sequential Create------ --------Random Create-------- uniweb.bway.net -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete-- files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP 16 65 0 +++++ +++ 118 0 69 0 +++++ +++ 127 0 Latency 332ms 36us 496ms 209ms 27us 2164ms In 6.x, I was able to resolve this by enabling the write cache on the drives via a loader tunable, "hw.mpt.enable_sata_wc". That seems to be gone in 7.x. Is there a new way to set this? I see no mention of the wc options at all in the mpt manpage. Also, do we have any way to monitor/manage these cards natively yet? Thanks, Charles ___ Charles Sprickman NetEng/SysAdmin Bway.net - New York's Best Internet - www.bway.net spork@bway.net - 212.655.9344 From lawrence.auster at att.net Sun Jan 25 07:46:47 2009 From: lawrence.auster at att.net (Lawrence Auster) Date: Sun Jan 25 07:46:59 2009 Subject: Why are the Zionist leaders in Israel so happy about the new President? Message-ID: <20090125151655.GYQJ28583.cdptpa-omta05.mail.rr.com@2ao1z> Why is the President of Israel, the terrorist who just oversaw the Zionist mass murder and maiming of thousands of Palestinians so happy that Obama is President of the USA? by David Duke Read the excerpt from the Israeli News about how President Perez and Israel think that Obama’s becoming U.S. President is great day for Israel. "Israel’s President Shimon Peres ecstatic over the election of Obama" Ronen Medzini Israel News Jan. 21 “Today is a great day not only for the United States of America, but for the entire world,” President Shimon Peres wrote in a letter addressed to Barack Obama on the day of his inauguration as president of the United States. “Obama was elected by the United States, but as a matter of fact, he was chosen by the whole of humankind,” Why is Peres so ecstatic? Why shouldn’t he be, he knows that Obama is completely in the grip of the extremist Jewish Zionists in America, and he knows that the greater Obama’s popularity and idol worship, the more Obama can do for the International Zionist Cause. Any thinking and caring human being who realizes that the Zionist-controlled American foreign policy has been a disaster for the robbed and murdered people of Palestine, Lebanon, Iraq and a catastrophe for the 50,000 American wounded in Iraq and Afghanistan, as well as an economic catastrophe for the hardworking Americans who pay trillions to finance these wars for Israel — must wake up the fact that supporting Obama and increasing his popularity will only aid Zionist terrorism, war, and their murder and oppression of the Palestinians. It will also hasten the economic suffering of billions of people around the world as his popularity enables him to more easily aid the Zionist International Bankers steal the wealth of the United States, Europe and the world. Obama is totally in the bloodstained and green ink- stained hands of the Zionists. The hard truth is that the more good will and support Obama has also gives more power to support the Zionist agenda! Mark my words. The Obama Presidency will be disaster for America and for the world. Obama was put into office by the Zionists. His top two cohorts for years have been the radical Jews David Axelrod and Rahm Emmanuel. Both have long records of radical Zionism and have been attack dogs against anyone perceived as having the slightest opposition to Israel. One such victim was Sen. Charles Percy, who both men worked to defeat and destroy because he dared to only be 99 percent rather than 100 percent pro-Israel. Rahm Emmanuel, a dual citizen of Israel who went to fight for Israel, he has a long pedigree of Jewish extremism. His father served in the Irgun Terrorist Gang and he himself is named after an Irgun terrorist. Zionist leaders in Chicago actually call Obama “the first Jewish President” and boast that Jews were key players in Obama’s every step up the ladder to President. from the very earliest days, extremist Jews were the largest contributors to his campaign. In the beginning of his Presidential bid, three Hollywood Jews that constantly make movies about Jewish suffering, but never about the Zionist terrorism and theft against the Palestinian people, Steven Spielberg, David Geffen, and Jeffrey Katzenberg raised 1.2 million for Obama in a single Hollywood party. By the time Obama’s campaign was in full swing, he had huge support from the criminal Zionist International Banking firms such as Goldman Sachs and Lehman brothers. Goldman Sachs was Obama’s biggest single contributor, and his vast war chest came not from American manufacturing firms like GM or even American oil companies, (not one was in his top twenty) it was overwhelmingly dominated by Zionist international bankers, the same ones whose thievery and fraud are giving the world this economic depression. For those looking for meaningful social and political change, do you really think it will come from this man who has already been bought heart, head and soul by the most powerful czars of the international financial establishment and the biggest globalists in the world? I know that many are desperate for change, so desperate that you want to believe anything. But in the face of these facts can’t you see that Obama will be even more dangerous to freedom and justice than even George Bush and his band of Neocons were. What better way to wipe out George Bush’s hated legacy and make the world believe that America has really changed than with the election of Obama. But, all the real Zionist power, Zionist media power, and Zionist financial power in America is still in place, even stronger than ever. Many Americans and others around the world who want to do good are now telling us how wonderful Obama will be as president. What a great change it will be from the old policies. This is because of the Zionist-Controlled media hype, promoting Obama. The fact is that these poor sods are ignorantly helping the radical Zionist agenda in Israel and around the world. Every day that you don’t help expose Obama for the Zionist servant that he actually is, his popularity will be a greater danger to peace and freedom. If the Zionist terrorist Shimon Perez is happy about the coronation of Obama, then why in the hell should you be? –David Duke Source : http://www.davidduke.com/general/7303_7303.html ------------------------------------- You or someone using your email adress is currently subscribed to the Lawrence Auster Newletter. If you wish to unsubscribe from our mailing list, please let us know by calling to 1 212 865 1284 Thanks, Lawrence Auster, 238 W 101 St Apt. 3B New York, NY 10025 Contact: lawrence.auster@att.net ------------------------------------- From bugmaster at FreeBSD.org Mon Jan 26 03:07:06 2009 From: bugmaster at FreeBSD.org (FreeBSD bugmaster) Date: Mon Jan 26 03:08:58 2009 Subject: Current problem reports assigned to freebsd-scsi@FreeBSD.org Message-ID: <200901261107.n0QB72P1024386@freefall.freebsd.org> Note: to view an individual PR, use: http://www.freebsd.org/cgi/query-pr.cgi?pr=(number). The following is a listing of current problems submitted by FreeBSD users. These represent problem reports covering all versions including experimental development code and obsolete releases. S Tracker Resp. Description -------------------------------------------------------------------------------- o kern/130735 scsi [cam] [patch] pass M_NOWAIT to the malloc() call insid o kern/130621 scsi [mpt] tranfer rate is inscrutable slow when use lsi213 o kern/129602 scsi [ahd] ahd(4) gets confused and wedges SCSI bus o kern/128452 scsi [sa] [panic] Accessing SCSI tape drive randomly crashe o kern/128245 scsi [scsi] "inquiry data fails comparison at DV1 step" [re o kern/127927 scsi [isp] isp(4) target driver crashes kernel when set up o kern/126866 scsi [isp] [panic] kernel panic on card initialization o kern/124667 scsi [amd] [panic] FreeBSD-7 kernel page faults at amd-scsi o kern/123674 scsi [ahc] ahc driver dumping o kern/123666 scsi [aac] attach fails with Adaptec SAS RAID 3805 controll o sparc/121676 scsi [iscsi] iscontrol do not connect iscsi-target on sparc o kern/120487 scsi [sg] scsi_sg incompatible with scanners o kern/120247 scsi [mpt] FreeBSD 6.3 and LSI Logic 1030 = only 3.300MB/s o kern/119668 scsi [cam] [patch] certain errors are too verbose comparing o kern/114597 scsi [sym] System hangs at SCSI bus reset with dual HBAs o kern/110847 scsi [ahd] Tyan U320 onboard problem with more than 3 disks o kern/99954 scsi [ahc] reading from DVD failes on 6.x [regression] o kern/94838 scsi Kernel panic while mounting SD card with lock switch o o kern/92798 scsi [ahc] SCSI problem with timeouts o kern/90282 scsi [sym] SCSI bus resets cause loss of ch device o kern/76178 scsi [ahd] Problem with ahd and large SCSI Raid system o kern/74627 scsi [ahc] [hang] Adaptec 2940U2W Can't boot 5.3 s kern/61165 scsi [panic] kernel page fault after calling cam_send_ccb o kern/60641 scsi [sym] Sporadic SCSI bus resets with 53C810 under load o kern/60598 scsi wire down of scsi devices conflicts with config s kern/57398 scsi [mly] Current fails to install on mly(4) based RAID di o kern/52638 scsi [panic] SCSI U320 on SMP server won't run faster than o kern/44587 scsi dev/dpt/dpt.h is missing defines required for DPT_HAND o kern/40895 scsi wierd kernel / device driver bug o kern/39388 scsi ncr/sym drivers fail with 53c810 and more than 256MB m o kern/38828 scsi [dpt] [request] DPT PM2012B/90 doesn't work o kern/35234 scsi World access to /dev/pass? (for scanner) requires acce 32 problems total. From thomas at FreeBSD.org Tue Jan 27 02:42:08 2009 From: thomas at FreeBSD.org (thomas@FreeBSD.org) Date: Tue Jan 27 02:42:15 2009 Subject: kern/131032: hald causing panic in scsi_sg Message-ID: <200901271042.n0RAg7uF035562@freefall.freebsd.org> Old Synopsis: hald causing panic in atapicam New Synopsis: hald causing panic in scsi_sg Responsible-Changed-From-To: freebsd-bugs->freebsd-scsi Responsible-Changed-By: thomas Responsible-Changed-When: Tue Jan 27 10:39:49 UTC 2009 Responsible-Changed-Why: Problem isn't in ATAPI/CAM, might be in generic SCSI code, over to SCSI maintainers for futher assessment. http://www.freebsd.org/cgi/query-pr.cgi?pr=131032 From kamikaze at bsdforen.de Tue Jan 27 02:50:02 2009 From: kamikaze at bsdforen.de (Dominic Fandrey) Date: Tue Jan 27 02:50:09 2009 Subject: kern/131032: hald causing panic in atapicam Message-ID: <200901271050.n0RAo2wf035690@freefall.freebsd.org> The following reply was made to PR kern/131032; it has been noted by GNATS. From: Dominic Fandrey To: Thomas Quinot Cc: bug-followup@FreeBSD.org, scottl@freebsd.org Subject: Re: kern/131032: hald causing panic in atapicam Date: Tue, 27 Jan 2009 11:31:49 +0100 Thomas Quinot wrote: > * Dominic Fandrey, 2009-01-27 : > >> It's that line. I don't think it's supposed to be there: >> at /usr/src/sys/modules/cam/../../cam/scsi/scsi_sg.c:798 > > This module is part of the generic CAM layer, which sits *above* the > various SCSI transport modules (e.g. ATAPI/CAM and umass). It is *not* > part of ATAPI/CAM, and it is fully expected that this generic code is > involved when using umass devices. > >> As you said atapicam shouldn't be involved at all, so why >> is an atapicam funtion doing a giant-locked read? > > This is *not* an ATAPI/CAM function. > > Thomas. > OK, so thanks for clarifying that. It doesn't get me rid of the panic, though. So I assume I should CC someone involved with SCSI. Regards From thomas at FreeBSD.ORG Tue Jan 27 02:50:04 2009 From: thomas at FreeBSD.ORG (Thomas Quinot) Date: Tue Jan 27 02:50:20 2009 Subject: kern/131032: hald causing panic in atapicam Message-ID: <200901271050.n0RAo3Tp035721@freefall.freebsd.org> The following reply was made to PR kern/131032; it has been noted by GNATS. From: Thomas Quinot To: Dominic Fandrey Cc: bug-followup@FreeBSD.org, scottl@freebsd.org Subject: Re: kern/131032: hald causing panic in atapicam Date: Tue, 27 Jan 2009 11:43:43 +0100 --PEIAKu/WMn1b1Hv9 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline * Dominic Fandrey, 2009-01-27 : > OK, so thanks for clarifying that. It doesn't get me rid of the panic, > though. So I assume I should CC someone involved with SCSI. Right. I've reassigned this PR to freebsd-scsi for now. Thomas. --PEIAKu/WMn1b1Hv9 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (FreeBSD) iD8DBQFJfuVeAE1UuDk9JGkRAmjeAJ0Vbdu5N4nYOyW+8X/YWKH13SECgwCeIs58 awVynC6xudEplaN7GXcClX4= =4kws -----END PGP SIGNATURE----- --PEIAKu/WMn1b1Hv9-- From gigimorphe at yahoo.com Wed Jan 28 13:39:45 2009 From: gigimorphe at yahoo.com (gigi71) Date: Wed Jan 28 13:39:51 2009 Subject: cn't figure out hp rack enclosure A3312A on asc 29160 bulk adaptec scsi controller Message-ID: <21715309.post@talk.nabble.com> hi i try to connect this old fox (hp rack enclosure A3312A) on my fujitsu siemens prolinea server with asc 29160 bulk adaptec scsi controller but when i do the scanning i got no device message i have also terminated the end of enclosure the diskd r df (diferental) or i am wrong or i have no good cable or the adaptec card is new to this old storage.any idea? i am good on neetworking also on progrming but i haven't got time to play enough with scsi.(but i like them more than ide or sata) can youlease enyone help me what to do or give me the right direction. thank you again gigi -- View this message in context: http://www.nabble.com/cn%27t-figure-out-hp-rack-enclosure-A3312A-on-asc-29160-bulk-adaptec-scsi-controller-tp21715309p21715309.html Sent from the freebsd-scsi mailing list archive at Nabble.com. From lawrence.auster at att.net Thu Jan 29 14:29:05 2009 From: lawrence.auster at att.net (Lawrence Auster) Date: Thu Jan 29 14:29:48 2009 Subject: The =?iso-8859-1?q?=93Military=2C?= Industrial =?iso-8859-1?q?Complex=94?= is no more -- The Hidden Massive Racial Discrimination in America against Whites Message-ID: <20090129220534.LWMS12540.fed1rmmtao106.cox.net@fed1rmimpo03.cox.net> The “Military, Industrial Complex” is no more. Today it is the Political, Financial and Media — Zionist Complex! 1/28/2009 An short essay by Dr. David Duke The “Military-Industrial complex” really has no relevance to the real holders of global power today. America is the most powerful military and economic nation on earth. The powers that control the levers of political power in America possess the greatest power the world has ever seen. Who really has power over the government today? Is it the fabled “Military, Industrial Complex”? An effective gauge of direct political power in America is “to discover who provided the pivotal amounts of the billion-dollar recent campaigns for U.S. President. You can look directly at campaign contributions for every candidate from the Federal Election Commission in order to find out who holds the real power in politics. So, who holds the real power over the American political establishment? Let’s first look at who does not hold much power over the establishment. 1) It is not the military. There is not any organized military monetary influence or even significant political influence of the military over the politicians. In fact, no one in military positions of authority are allowed to openly get involved in politics. No active sergeant, lieutenant, or General can send out a directive to the men under him to support or oppose a particular candidate (the one exception I know to that was when the Louisiana commanding general of the National Guard, under Jewish influence, sent a letter to all national guardsmen telling them that it was their “patriotic duty” to vote against David Duke and for the Liberal corrupt former Governor, Edwin Edwards. Even that caused a scandal in military circles, as it should have. 2) It is NOT major manufacturing or even the huge oil companies. There was not one oil company and only a couple of legitimate manufacturing or industrial concerns on Obama and McCain’s top twenty contributor list. The list was completely dominated by Zionist international banking firms. If one combines every defense contractor’s contributions the money they give in politics is minuscule compared to Zionist international banks. They don’t even come close to the power in lobbying that AIPAC and a couple of dozen more Jewish extremist organizations have. Jewish lobbyists literally get almost unanimous support in Congress for outrageous giveaways to Israel, a nation that has committed terrorism against us and killed or maimed scores of Americans. I am not talking about contracts here, I am speaking about giving away billions of dollars to a foreign nation. So, so much for the media-popularized term, the military-industrial complex In direct political money and lobbying then, Zionists are the undisputed masters of the American political establishment. In addition to their control through the use of money as an inducement or a threat, they have tens of thousands of Jewish extremists scattered throughout the entire bureaucracy who are very conscious of supporting their brethren and supporting the organized Jewish agenda. They also are ready to act against any Gentile who dares to go against Israel or the Jewish agenda. How will a Jewish federal judge rule in a huge litigation issue between Jewish and non-Jewish parties? Why was the biggest robber in the history of the world, Bernie Madoff who stole over 50 billion dollars and who ruined tens of thousands of families, only charged with one criminal count, and allowed to stay in his luxury apartment to await trial? Is there an organized Jewish agenda? Absolutely. In fact, the leading and most powerful Jewish groups have a supra-organization called the Council of Presidents (composed of the most powerful 5 dozen Jewish organizations in America). They issue detailed positions not just on Mideast policy but on many other issues that have nothing to do with Israel, aspects of domestic policy including issues such as opening America’s borders. They even assume positions on issues that you wouldn’t even think would have unanimity among Jews, such as abortion rights. Their job is to make sure that Jewish power is absolutely united on what they decide are their common agendas. Next, we must talk about one of the most influential parts of the American political process, the mass media. The media, such as the NY Times and the Washington Post (the newspaper read by every member of America’s government and bureaucracy in Washington). The Washington Post can determine even what issues Congress will discuss and it greatly affects the publicity for or against those issues. Broadcast and cable television also have an enormous impact, and we can include movies, books, magazines and the newspaper chains that reach down into almost every American community. As my chapters in Jewish Supremacism on “Jewish Media Supremacy” document, the ownership, depth and breadth of Jewish influence in the media is simply breathtaking. In media, whether you speak of owners, administrators, managers, editors, producers, writers, correspondents, pundits and reporters, there is an army of Jews who are animated by the Holocaust and the issues of the organized Jewish community. If you haven’t yet read them, you simply must see the evidence on the Jewish supremacy in media I have compiled in my books Jewish Supremacism and My Awakening. The other great seat of establishment power is simply money, huge sums of money and the willingness to use those funds on behalf of an agenda. The biggest concentrations of wealth in the world today are in the Zionist international banks, and in financial groups that the Jews completely control such as the Federal Reserve Corporation, the same forces that have led us to the doorstep of a great depression. It is no accident that Alan Greenspan and Ben Shalom Bernanke are the last two of the Federal Reserve czars. Even in days of World War I, an immensely rich, Jewish international banker, Jacob Schiff, voiced pride in the fact that he was instrumental in weakening Czarist Russia (the government that Jews universally hated), and that he supported Russia’s enemies so as to make Russia ripe for communist overthrow (Jewish groups brag of his help to Japan in the Russo-Japanese War so as to hurt the Russian government). Schiff also gave millions of dollars to directly finance the Jews who led and organized the Russian revolution and the Bolshevik terror in Russia. There is no disputing of these facts. Plenty of Jewish history books detail all of it. So, frankly, financial power in the control of people who will use it for an agenda is also a key ingredient of real power. Again, the financial power in the hands of modern day Jacob Schiff’s, is an incredibly powerful weapon. So forget about the “Military-Industrial Complex.” That is passe. In today’s world it makes more sense to speak about the “Political, Financial and Media Zionist complex.” That is the real core of power that bends everything whether it be local laws, or giant corporations, to its will. Even if one of the world’s richest firms, such as Microsoft (which is now by the way run by a Jewish extremist), would buck the political, financial, and media Zionist complex, it would be broken by government fiat, the Jewish-influenced courts (such as anti-trust actions), and by vicious attacks by the Jewish-influenced media. Microsoft would either be dismembered or destroyed. Such are the realities of the modern world. There is no longer a “military industrial complex,” but there is a Political and media and financial Zionist complex that rules us and aims to control the whole world. No single part of this behemoth can be defeated, because it can use its other assets to defend the section under attack. It can only be brought down by concentrating all our political and ideological fire right on the core the problem, International Zionism and its driving impetus: Jewish Supremacism. —Dr. David Duke Source : http://www.davidduke.com/general/forget-the-military-industrial-complex-today-its-the-political-financial-and-media-zionist-complex_7394.html ---- The Hidden Massive Racial Discrimination in America against Whites 1/29/2009 The main argument for affirmative action is that institutions should reflect racial percentages of population, if not there must be de facto racial discrimination. Here is the breakdown of students by race at America’s premier university, Obama’s alma mater, Harvard. Even though non-Jewish White Americans are almost 70 percent of the population and on average score much higher on entrance exams, they are only about 22 percent of the Harvard student body. So what race is really the victim of racial discrimination? For those who are truly dedicated to stopping racial discrimination, what are you going to do about this massive discrimination, or does it not matter to you because White people happen to be the victims? The hidden, massive racial discrimination that goes on in America against White people! A U.S. Government study offers proof that European Americans face massive institutional racial discrimination that affects millions of the most talented and educated of our people Introduction by Dr. David Duke – As most of you know, the term “white supremacist” has become literally a prefix of my name when I am in the news. It is the media’s way to condition readers not to pay attention to what I say because I am a “white supremacist.” The truth is I am not a White supremacist, and I seek no supremacy or control over any people, but I do demand that the rights of people of European descent to be respected as much as any other people’s rights. The fact is that in the United States of America, Canada, the UK in many areas of Europe Whites face a powerful state-sanctioned, and often mandated, racial discrimination against White people who are better-qualified than their non-White counterparts. It may be surprising to some reading this, but millions of discriminated against Whites are often poorer and who face more difficult social situations than many of their non-White counterparts who are being given preference over them. It also affects the most talented of our people. Many Whites are under the mistaken impression that the White victims of racial discrimination are mostly from the low income and low IQ sectors of the population. Nothing could be further from the truth. In actuality, the percentages of Whites who are victims of racial discrimination are much higher in the sectors of the White population with the highest intelligence and greatest abilities. The facts are shocking, but true. Most people know that most universities have programs of admittance that give less-qualified minorities preference over better-qualified Whites. Almost all of the Fortune 500 largest corporations have affirmative action and diversity programs that discriminate against White people, both male and female, in hiring. They also have programs of discrimination that favor non-Whites in promotions and advancement. This is true in the academic area as well. You can look at almost any academic department of any American university and you will see in place a strong racial bias for “minorities” in preface over Whites in hiring and advancement. Whether you are talking about a university History, English or Math department in almost any university these policies are in place and powerful. These racial discriminatory policies are real, and they can be easily proven to exist. But, now we thanks to a government study, there is even a more powerful way to show their real impact on tens of mi llions of White Americans. The brilliant economist and author whose pen name is Yggdrasil has compiled the data from the National Longitudinal Survey of Youth (NLSY) 1979, which was a massive study conducted by the Department of Labor to track the lives of 155,000 Americans by race, IQ, income, education and other factors to see how remedial efforts for minorities were doing. It was done after the installation of so called “affirmative action” programs which gave preference to non-White groups over whites. The NLSY study is meant to follow this huge sampling for their entire lives to see how diversity is working out for America. The data is from this ongoing study is tangible proof of the horrendous level of racial discrimination going on against White people. I will link you to Yggdrasil’s fine paper in a moment, but let me first give you a couple of snippets from his work that proves the existence of massive racial discrimination going on against our people. Here is a chart showing the ethnic breakdown of the most prestigious university in the United States of America: Harvard. America’s premier university is extremely expensive (unless you receive special grants and scholarships) and a degree from it just about guarantees its graduates the best paid and prestigious jobs America has to offer. Affirmative action advocates have long said the companies or institutions that don’t reflect the actual racial population percentages are de facto racist and discriminatory. So what is the situation at Harvard, non-Jewish Whites who are about 70 pecent of the American population are only about 22 percent of the Harvard student body. One should first consider the fact that Whites are represented in the top two percentile level on college admission tests on an average that is a 5 times higher rate than non-White groups. If one then factors in the fact that Whites are also 70 percent of the population, there should be at least 25 times more Whites who would be better qualified than the non-White students currently at Harvard. But even though these Whites are the best and brightest America has to offer they are limited to only 20 percent of Harvard students! Such is nothing more than blatant, racial discrimination. Another interesting fact one can gleam from this chart and many in the NLSY studies that Jewish over-representation is not based simply on the fact that Jews have a high intelligence, they often do twice as well as their intelligence bracket would indicate. Such would suggest the intra-tribal support system for group cohesion and advancements aids their success rate. The NLSY data also shows how incomes today in the USA correlate with race and intelligence. Let’s take a look NLSY tracking studies of intelligent White women, these are White women in the 90 to 97 percent IQ bracket as compared to Black women in that same high 90 to 97 percent IQ bracket. The average Black females of that IQ level earned an average of approximately $54,000 per year through 1996, whereas White females on the same IQ level earned only half of that amount, about $28,000 per year through 1996. When White women in the same intelligent bracket of Black women earn half of the average amount that the Black women do, that’s real racial discrimination. I am not referring here to a few White women who are at least equally qualified but getting half the salary that Black women do, I am talking about the average White women in America! The NLSY is a big enough sample that reflects the whole nation. In fact it is meant to. The average White woman of high intelligence earns one-half of what Black women do of the same intelligence! I obviously don’t like this racial discrimination against our people. Neither does the economist Yggdrasil. We advocate that the best person regardless of race gets whatever college admission or job or promotion their abilities dictate. We have no fear of how well our people will do on a fair playing field. Because we stand for true civil rights, human rights in the matter, we are called racists, and the real capper: “white supremacists.” There are many people in America and around the world who are ignorant of the facts of anti-White racial discrimination. The media acts like it doesn’t exist. Even after the election of an affirmative action African-American President, America is still painted as an anti-Black racist country. The truth is that European Americans are facing racial discrimination in the very institutions and nation that our forefathers created. Our movement is truly a liberation movement like any other in the world that strives for a people to free and live in society of our own values rather than oppressive society imposed upon us. We are not racists or supremacists trying to deny the rights of others. We are human rights activists defending our people’s rights and heritage. –Dr. David Duke Source & Charts : http://www.davidduke.com/general/the-real-racial-discrimination-that-goes-on-in-america_7407.html ----- Obama’s Mideast Jewish Wet Dream Team George Mitchell is the new American envoy now in the Mideast. Who is Mitchell and who are the key players in Obama’s Mideast policy team? First, let’s examine the major players on the Obama foreign policy team. Roger Cohen writing in The New York Times on January 11, 2009 wrote some things that if he were a Gentile would have earned him some attacks as an “anti-Semite.” He pointed out the incredible top-heavy pro-Zionist content of the team which is supposed to broker a fair and just peace in the Mideast. In discussing the team he identified them with these words: They include Dennis Ross (the veteran Clinton administration Mideast peace envoy who may now extend his brief to Iran) [a long-time Jewish Zionist]; James Steinberg [Jewish Zionist] (as deputy secretary of state) ; Dan Kurtzer [Jewish Zionist] (the former U.S. ambassador to Israel); Dan Shapiro [Jewish Zionist] (a longtime aide to Obama); and Martin Indyk [Jewish Zionist] another former ambassador to Israel who is close to the incoming secretary of state, Hillary Clinton.) Now, I have nothing against smart, driven, liberal, Jewish (or half-Jewish) males; I’ve looked in the mirror. I know or have talked to all these guys, except Shapiro. They’re knowledgeable, broad-minded and determined. Still, on the diversity front they fall short. On the change-you-can-believe-in front, they also leave something to be desired. Cohen did not even mention that the two closest advisers to Obama, the guys that filter almost everything that Obama see and hears and makes the day to day decisions of running the oval office. They are David Axelrod and Rahm Emmanuel, two long time dedicated Jewish extremists. Emmanuel, son of an Irgun terrorist and named after another Irgun terrorist, even fought in the Israeli Army. Now we come to the new envoy to the Mideast, George Mitchell of Maine, the man who is supposed to be a broadminded and just arbitrator between Israel and the Palestinians. The Jewish-influenced has made a big point of Mitchell’s Lebanese ancestry. What the Zionist media doesn’t tell you is that he has been completely under the control of AIPAC and radical Zionists for years. As Senate Majority Leader he rammed through everything Israel wanted. He even supported the Senate resolution that gave Israel unconditional support during the Zionist massacre of thousands of Gaza civilians. In fact, originally an appointee to the Senate, Mitchell owes his entire Senate career on the massive support given him in 1982 and since by AIPAC and 27 other Jewish extremist controlled political action committees that AIPAC arranged. AIPAC’s Tom Dine summarized AIPAC’s success in Mitchell’s election by saying that “American Jews are thus able to form our own foreign policy agenda.” Of course, Dine spoke the complete and unvarnished truth. American and Israeli extremist Jews do indeed control the foreign policy of the United States. Such control has long gone on in concert with past U.S. Presidents and it goes on today with Obama. Only difference is that today there is a greater danger because many in America and around the world falsely believe that Obama represents change. With the incredible respect and adulation given to Obama, he is in a much better position to support the Zionist war agenda and ultimately do far more harm than a discredited George Bush. Hold on to your hats, America. I predict Obama will usher in war and conflagration that will make George Bush’s presidency seem mild in comparison. He has already announced a doubling of American troops in Afghanistan. Can a catastrophic war with Iran be far behind? Jewish extremists want this war and Obama is completely under their control! – Dr. David Duke Source : http://www.davidduke.com/general/who-is-on-obamas-dream-team-for-mideast-peace_7380.html ------------------------------------- You or someone using your email adress is currently subscribed to the Lawrence Auster Newletter. If you wish to unsubscribe from our mailing list, please let us know by calling "to 1 212 865 1284 Thanks, Lawrence Auster, 238 W 101 St Apt. 3B New York, NY 10025 Contact: lawrence.auster@att.net -------------------------------------