Hi Jens, I had the same problem a few month ago when ADMA with NFORCE4 was introduced in 2.6.21 kernel. I suspected a SAMSUNG HD401LJ to be the bad drive. Someone from the list mentioned that a bad/weak PSU may be responsible for the trouble. It was hard for me to believe that this was the case, since my system only uses 130W at full load and my former 350W PSU had 170W output power. And I never had any trouble with this setup before. Moreover my system worked fine with ADMA disabled -> you can switch off ADMA with bootparam "sata_nv.adma=0" in grub. So I really thought the drive or some bug caused my problem. But now I got the chance to try out a new PSU 550W Seasonic. With the new PSU I don't get the reset errors anymore and my box stopped freezing, my System works fine for 2 weeks now. It seems like NFORCE4 in ADMA Mode is very sensitive if there are power issues. Cheers ----- Ursprüngliche Mail ---- Von: Jens Prüfer <jens.pruefer@xxxxxx> An: jgarzik@xxxxxxxxx CC: linux-ide@xxxxxxxxxxxxxxx Gesendet: Mittwoch, den 24. Oktober 2007, 20:33:53 Uhr Betreff: Possible NCQ problem with Seagate ST3250620NS/nForce 4 Hi, I am experiencing reproducible timeout problems when using NCQ-enabled kernels (tried various Debian and Ubuntu kernels as well as vanilla 2.6.23.1. It runs ok for a few minutes, but the first time there is any real load on the drive, it freezes (heaps of timeouts) until NCQ gets switched off. --- snip --- [ 202.616000] ata1: EH in ADMA mode, notifier 0x0 notifier_error 0x0 gen_ctl 0x1501000 status 0x400 next cpb count 0x4 next cpb idx 0x0 [ 202.616000] ata1: CPB 0: ctl_flags 0x1f, resp_flags 0x0 [ 202.616000] ata1: CPB 1: ctl_flags 0x1f, resp_flags 0x0 [ 202.616000] ata1: CPB 2: ctl_flags 0x1f, resp_flags 0x0 [ 202.616000] ata1: CPB 3: ctl_flags 0x1f, resp_flags 0x0 [ 202.616000] ata1: CPB 4: ctl_flags 0x1f, resp_flags 0x0 [ 202.616000] ata1: timeout waiting for ADMA IDLE, stat=0x400 [ 202.616000] ata1: timeout waiting for ADMA LEGACY, stat=0x400 [ 202.616000] ata1.00: exception Emask 0x0 SAct 0x1f SErr 0x0 action 0x2 frozen [ 202.616000] ata1.00: cmd 61/00:00:b5:d1:28/02:00:17:00:00/40 tag 0 cdb 0x0 data 262144 out [ 202.616000] res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout) [ 202.616000] ata1.00: cmd 61/78:08:b5:d3:28/01:00:17:00:00/40 tag 1 cdb 0x0 data 192512 out [ 202.616000] res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout) [ 202.616000] ata1.00: cmd 61/08:10:a5:45:27/00:00:17:00:00/40 tag 2 cdb 0x0 data 4096 out [ 202.616000] res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout) [ 202.616000] ata1.00: cmd 60/10:18:15:4e:b9/00:00:1a:00:00/40 tag 3 cdb 0x0 data 8192 in [ 202.616000] res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout) [ 202.616000] ata1.00: cmd 60/08:20:25:4a:df/00:00:1a:00:00/40 tag 4 cdb 0x0 data 4096 in [ 202.616000] res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout) [ 202.932000] ata1: soft resetting port [ 203.088000] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300) [ 203.248000] ata1.00: configured for UDMA/133 [ 203.248000] ata1: EH complete [ 203.248000] sd 0:0:0:0: [sda] 488397168 512-byte hardware sectors (250059 MB) [ 203.248000] sd 0:0:0:0: [sda] Write Protect is off [ 203.248000] sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00 [ 203.252000] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA [ 233.248000] ata1: EH in ADMA mode, notifier 0x0 notifier_error 0x0 gen_ctl 0x1501000 status 0x400 next cpb count 0x4 next cpb idx 0x0 [ 233.248000] ata1: CPB 0: ctl_flags 0x1f, resp_flags 0x0 [ 233.248000] ata1: CPB 1: ctl_flags 0x1f, resp_flags 0x0 [ 233.248000] ata1: CPB 2: ctl_flags 0x1f, resp_flags 0x0 [ 233.248000] ata1: CPB 3: ctl_flags 0x1f, resp_flags 0x0 [ 233.248000] ata1: CPB 4: ctl_flags 0x1f, resp_flags 0x0 [ 233.248000] ata1: timeout waiting for ADMA IDLE, stat=0x400 [ 233.248000] ata1: timeout waiting for ADMA LEGACY, stat=0x400 [ 233.248000] ata1.00: NCQ disabled due to excessive errors --- snap --- The device is a Seagate ST3250620NS. Maybe it should be blacklisted as well? Anyhow, I cannot find any boot parameter to switch off NCQ and circumvent the freezing of the drive. Something like the "noacpi" option (maybe noncq?) would be nice. Or am I missing something? Cheers, Jens Prüfer - To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html Jetzt Mails schnell in einem Vorschaufenster überfliegen. Dies und viel mehr bietet das neue Yahoo! Mail - www.yahoo.de/mail - To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html