Date: Wed, 03 Dec 2014 10:41:05 +0000 From: bugzilla-noreply@freebsd.org To: freebsd-bugs@FreeBSD.org Subject: [Bug 195349] CAM status: Command timeout since upgrade to 10.1 Message-ID: <bug-195349-8-mSeUdmSvkQ@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-195349-8@https.bugs.freebsd.org/bugzilla/> References: <bug-195349-8@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=195349 --- Comment #9 from pascal.guitierrez@gmail.com --- Dec 1 17:44:06 nas01 kernel: ahcich3: Timeout on slot 6 port 0 Dec 1 17:44:06 nas01 kernel: ahcich3: is 00000008 cs 00000000 ss 00000000 rs 00000040 tfd 50 serr 00000000 cmd 00006617 Dec 1 17:44:06 nas01 kernel: (ada3:ahcich3:0:0:0): WRITE_FPDMA_QUEUED. ACB: 61 00 80 9e 2f 40 3e 00 00 01 00 00 Dec 1 17:44:06 nas01 kernel: (ada3:ahcich3:0:0:0): CAM status: Command timeout Dec 1 17:44:06 nas01 kernel: ahcich2: (ada3:Timeout on slot 15 port 0 Dec 1 17:44:06 nas01 kernel: ahcich3:0:ahcich2: 0:is 00000008 cs 00000000 ss 00000000 rs 00008000 tfd 40 serr 00000000 cmd 00006f17 Dec 1 17:44:06 nas01 kernel: 0): Retrying command Dec 1 17:44:06 nas01 kernel: (ada2:ahcich2:0:0:0): READ_FPDMA_QUEUED. ACB: 60 80 e8 a9 2f 40 3e 00 00 00 00 00 Dec 1 17:44:06 nas01 kernel: ahcich1: (ada2:ahcich2:0:0:0): CAM status: Command timeout pciconf -vl ahci0@pci0:0:17:0: class=0x010601 card=0x1609103c chip=0x43911002 rev=0x40 hdr=0x00 vendor = 'Advanced Micro Devices [AMD] nee ATI' device = 'SB7x0/SB8x0/SB9x0 SATA Controller [AHCI mode]' class = mass storage subclass = SATA dmesg: ahci0: <AMD SB7x0/SB8x0/SB9x0 AHCI SATA controller> port 0xd000-0xd007,0xc000-0xc003,0xb000-0xb007,0xa000-0xa003,0x9000-0x900f mem 0xfe6ffc00-0xfe6fffff irq 19 at device 17.0 on pci0 ahci0: AHCI v1.20 with 4 3Gbps ports, Port Multiplier supported This issue is reproduceable by causing load (such as zpool scrub). Seems to hit the issue much more frequently with > 2 disks in the pool - we see it on our HP microservers with 4 and 5 disks. Downgrading SATA to v1 (via loader hints) and disabling NCQ (via camcontrol tags -N 1) seems to delay, not fix the inevitable timeouts. -- You are receiving this mail because: You are the assignee for the bug.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-195349-8-mSeUdmSvkQ>