Hi, I raised this Bug already in launchpad under the following link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/991040 and I was asked to raise a bug in here and refer this bug issue reference back to launchpad then. I feel a bit insecure about how to report a bug in here the right way and hope not to disturb a formal consent. So here is a copy of the initial bug issue text from launchpad: ---- On my fresh Ubuntu 12.04 on a Dell Precision (Ubuntu certified right?) with a premium Inted Server SSD I am forced to make the following experience. During boot I have to wait for 20 seconds due to the following scenario: Excerpt of dmesg | grep ata: [ 7.718628] ata1: link is slow to respond, please be patient (ready=0) [ 12.365148] ata1: COMRESET failed (errno=-16) [ 17.723437] ata1: link is slow to respond, please be patient (ready=0) [ 22.369960] ata1: COMRESET failed (errno=-16) [ 27.728248] ata1: link is slow to respond, please be patient (ready=0) [ 57.398789] ata1: COMRESET failed (errno=-16) [ 57.398800] ata1: limiting SATA link speed to 1.5 Gbps [ 57.718702] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 310) After that the Intel SSD is connected in limited SATA1 mode to the system. :-( The same SSD works on the same machine just fine under windows 7, thus I think one can exclude hardware issues here. SSD Info: hdparm -I /dev/sdc: /dev/sdc: ATA device, with non-removable media Model Number: SSDSA2SH064G1GC INTEL Serial Number: CVEM005500N4064KGN Firmware Revision: 045C8860 Transport: Serial, ATA8-AST, SATA 1.0a, SATA II Extensions, SATA Rev 2.5, SATA Rev 2.6 Standards: Used: ATA/ATAPI-7 T13 1532D revision 1 Supported: 7 6 5 4 Configuration: Logical max current cylinders 16383 16383 heads 16 16 sectors/track 63 63 -- CHS current addressable sectors: 16514064 LBA user addressable sectors: 125045424 LBA48 user addressable sectors: 125045424 Logical Sector size: 512 bytes Physical Sector size: 512 bytes device size with M = 1024*1024: 61057 MBytes device size with M = 1000*1000: 64023 MBytes (64 GB) cache/buffer size = unknown Nominal Media Rotation Rate: Solid State Device Capabilities: LBA, IORDY(can be disabled) Queue depth: 31 Standby timer values: spec'd by Standard, no device specific minimum R/W multiple sector transfer: Max = 16 Current = 16 DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6 Cycle time: min=120ns recommended=120ns PIO: pio0 pio1 pio2 pio3 pio4 Cycle time: no flow control=120ns IORDY flow control=120ns Commands/features: Enabled Supported: * SMART feature set Security Mode feature set * Power Management feature set * Write cache * Look-ahead * Host Protected Area feature set * WRITE_BUFFER command * READ_BUFFER command * NOP cmd * DOWNLOAD_MICROCODE * 48-bit Address feature set * Device Configuration Overlay feature set * Mandatory FLUSH_CACHE * FLUSH_CACHE_EXT * SMART error logging * SMART self-test * General Purpose Logging feature set * 64-bit World wide name * IDLE_IMMEDIATE with UNLOAD * WRITE_UNCORRECTABLE_EXT command * {READ,WRITE}_DMA_EXT_GPL commands * Segmented DOWNLOAD_MICROCODE * Gen1 signaling speed (1.5Gb/s) * Gen2 signaling speed (3.0Gb/s) * Native Command Queueing (NCQ) Device-initiated interface power management * Software settings preservation Security: Master password revision code = 65534 supported not enabled not locked frozen not expired: security count supported: enhanced erase 2min for SECURITY ERASE UNIT. 2min for ENHANCED SECURITY ERASE UNIT. Logical Unit WWN Device Identifier: 50015179591c56b6 NAA : 5 IEEE OUI : 001517 Unique ID : 9591c56b6 Checksum: correct I assume that any further information is attached by the 'ubuntu-bug linux' command to that issue. Please help, as I would like to decrease my boot time from now 1 Minute a bit further AND most important of course I want to use a SATA mode that is capable of deliver data as fast as the super expensive drive can do it also under Ubuntu! Thank you for your work! cue
Exactly the same problem occurs for me with a Crucial M4 SSD. As well as in Ubuntu 12.04, I have seen issue in Mageia 2 & Arch (both using kernel 3.4.2) The issue can not be seen in kernel 2.6.37.6 as shipped with the Slackware 13.37. Thanks
Have you tried setting libahci.skip_host_reset=1 as kernel boot parameter? This fixed the comreset issue for me. However, I don't know if it has other implications. There's also an email thread on the linux kernel list on this issue: http://comments.gmane.org/gmane.linux.kernel/1247563
(In reply to comment #2) > There's also an email thread on the linux kernel list on this issue: > > http://comments.gmane.org/gmane.linux.kernel/1247563 Kernel 3.5 has a fix for that issue in rev 66583c9, please see if that fixes your problem. That issue was only introduced in 3.3, so it doesn't account for the original report, as Ubuntu 12.04 ships with 3.2. Additionally, I'm seeing this behaviour on 3.5.0 when resuming from suspend. Hardware: SATA controller [0106]: Intel Corporation Panther Point 6 port SATA Controller [AHCI mode] [8086:1e03] (rev 04) (prog-if 01 [AHCI 1.0]) ATA device, with non-removable media Model Number: C400-MTFDDAK256MAM Firmware Revision: 05TD Transport: Serial, ATA8-AST, SATA 1.0a, SATA II Extensions, SATA Rev 2.5, SATA Rev 2.6, SATA Rev 3.0 So, Ivy Bridge AHCI controller, and Micron C400 (AKA Crucial M4) SSD. I've tried reverting 66583c9, d408e2b and 7faa33d, but the problem still exists here. So (for me at least), that rules out this being related to those the changesets discussed in the above thread. I have a little difficulty testing on < 3.3-RC1 because of Ivy Bridge hangs (and I need this laptop functional for work, but it's the only system I can reproduce on). Happy to take some advice on what bisects to try. I'm going to try an SSD firmware update in case that's the culprit in my case, but it's interesting to me that all the reporters so far are citing SSDs being the issue.
Unfortunately, I've not been able to obtain a firmware update for my hardware at this stage, happy to perform any testing suggested.
I suffered this problem too on a Arch Linux Kernel using a Intel SSD X25-M 80GB: $ uname -a Linux luegisland 3.9.5-1-ARCH #1 SMP PREEMPT Sat Jun 8 09:22:45 CEST 2013 x86_64 GNU/Linux I could resolve this issue by updating the firmware (used to be 2CV102HD, now the version is 2CV102M3).
I get this every time i resume from sleep(to RAM). On linux 4.0.2. However obviously ata1 is my ssd and ata3 is my WD 640GB green drive. [47517.277041] ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300) [47517.279050] ata1.00: configured for UDMA/133 [47517.284047] ata7: SATA link down (SStatus 0 SControl 300) [47517.287044] ata8: SATA link down (SStatus 0 SControl 300) [47522.325048] ata3: link is slow to respond, please be patient (ready=0) [47527.014272] ata3: COMRESET failed (errno=-16) [47528.491405] ata3: SATA link up 3.0 Gbps (SStatus 123 SControl 300) [47528.522316] ata3.00: configured for UDMA/133