Re: ata command timeout
Jeff Garzik wrote: > Mark Lord wrote: >> I don't believe that. Command timeouts never happen on healthy systems, >> unless we have a driver bug. Okay, so I can imagine a pathological case >> of a full queue (NCQ) with all 32 commands taking longer than usual due >> to ECC retries in the firmware.. > > It's not quite so black and white. There have definitely been interrupt > delivery problems that cause command timeouts. Also, Intel PIIX BMDMA > (all standard PCI IDE, I think?) is defined to /not/ send an interrupt, > when a DMA error occurs. The driver is instructed to time out the > transaction, and start recovery by deducing the state of things from the > DMA status bits. > > Nonetheless, I mostly agree with your statement. The two most common > causes of timeouts that I see are interrupt delivery problems, and > driver bugs. Oh.. well. My experience is that it's much more common on SATA compared to PATA. SATA link seems to be one of the most vulnerable parts to interference. When PSU has the slightest of problem, SATA drives timeout or give transmission problems. System often survives brief fluctuation in power input (e.g. when the compressor starts up) but SATA link sometimes reports error after such event. Or just buy a static generator and apply it to your computer case. Generally system is perfectly okay with that but the SATA devices tend to complain or timeout. Those condition might not be considered too healthy in any server environment but they do occur on cheap desktop environment. I mean, a lot of people are putting 10USD PSU into their desktop machines. So, yeah, it might be a driver or other problem but if problem is very intermittent, I tend to lean toward transient hardware problem and that's primarily why I wanna make EH kick in and recover faster. Thanks. -- tejun - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
Mark Lord wrote: I don't believe that. Command timeouts never happen on healthy systems, unless we have a driver bug. Okay, so I can imagine a pathological case of a full queue (NCQ) with all 32 commands taking longer than usual due to ECC retries in the firmware.. It's not quite so black and white. There have definitely been interrupt delivery problems that cause command timeouts. Also, Intel PIIX BMDMA (all standard PCI IDE, I think?) is defined to /not/ send an interrupt, when a DMA error occurs. The driver is instructed to time out the transaction, and start recovery by deducing the state of things from the DMA status bits. Nonetheless, I mostly agree with your statement. The two most common causes of timeouts that I see are interrupt delivery problems, and driver bugs. Jeff - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
Tejun Heo wrote: [EMAIL PROTECTED] wrote: .. ata1: command timeout Feb 19 20:39:31 linux kernel: ata1: no sense translation for status: 0x40 Feb 19 20:39:31 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI SK/ASC/ASCQ 0xb/00/00 Feb 19 20:39:31 linux kernel: ata1: status=0x40 { DriveReady } Feb 19 20:39:31 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 Feb 19 20:39:31 linux kernel: sda: Current: sense key: Aborted Command Feb 19 20:39:31 linux kernel: Additional sense: No additional sense information Feb 19 20:39:31 linux kernel: end_request: I/O error, dev sda, sector 89553479 without any other ill-effects that I know of(I did smart tests on the drive; all passed successfully). I have read that hddtemp may be the cause of this (I am running version 0.3) so is there any reason to worry and prepare for a HDD replacement? Not really. If the problem occurs very infrequently, you don't need to worry about it too much. Command timeouts do occur on otherwise healthy systems from time to time. I don't believe that. Command timeouts never happen on healthy systems, unless we have a driver bug. Okay, so I can imagine a pathological case of a full queue (NCQ) with all 32 commands taking longer than usual due to ECC retries in the firmware.. But in real life, on a desktop, timeouts never happen as a normal event. I wonder what's *really* wrong here? Cheers - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
Tejun Heo wrote: [EMAIL PROTECTED] wrote: .. ata1: command timeout Feb 19 20:39:31 linux kernel: ata1: no sense translation for status: 0x40 Feb 19 20:39:31 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI SK/ASC/ASCQ 0xb/00/00 Feb 19 20:39:31 linux kernel: ata1: status=0x40 { DriveReady } Feb 19 20:39:31 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 Feb 19 20:39:31 linux kernel: sda: Current: sense key: Aborted Command Feb 19 20:39:31 linux kernel: Additional sense: No additional sense information Feb 19 20:39:31 linux kernel: end_request: I/O error, dev sda, sector 89553479 without any other ill-effects that I know of(I did smart tests on the drive; all passed successfully). I have read that hddtemp may be the cause of this (I am running version 0.3) so is there any reason to worry and prepare for a HDD replacement? Not really. If the problem occurs very infrequently, you don't need to worry about it too much. Command timeouts do occur on otherwise healthy systems from time to time. I don't believe that. Command timeouts never happen on healthy systems, unless we have a driver bug. Okay, so I can imagine a pathological case of a full queue (NCQ) with all 32 commands taking longer than usual due to ECC retries in the firmware.. But in real life, on a desktop, timeouts never happen as a normal event. I wonder what's *really* wrong here? Cheers - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
Mark Lord wrote: I don't believe that. Command timeouts never happen on healthy systems, unless we have a driver bug. Okay, so I can imagine a pathological case of a full queue (NCQ) with all 32 commands taking longer than usual due to ECC retries in the firmware.. It's not quite so black and white. There have definitely been interrupt delivery problems that cause command timeouts. Also, Intel PIIX BMDMA (all standard PCI IDE, I think?) is defined to /not/ send an interrupt, when a DMA error occurs. The driver is instructed to time out the transaction, and start recovery by deducing the state of things from the DMA status bits. Nonetheless, I mostly agree with your statement. The two most common causes of timeouts that I see are interrupt delivery problems, and driver bugs. Jeff - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
Jeff Garzik wrote: Mark Lord wrote: I don't believe that. Command timeouts never happen on healthy systems, unless we have a driver bug. Okay, so I can imagine a pathological case of a full queue (NCQ) with all 32 commands taking longer than usual due to ECC retries in the firmware.. It's not quite so black and white. There have definitely been interrupt delivery problems that cause command timeouts. Also, Intel PIIX BMDMA (all standard PCI IDE, I think?) is defined to /not/ send an interrupt, when a DMA error occurs. The driver is instructed to time out the transaction, and start recovery by deducing the state of things from the DMA status bits. Nonetheless, I mostly agree with your statement. The two most common causes of timeouts that I see are interrupt delivery problems, and driver bugs. Oh.. well. My experience is that it's much more common on SATA compared to PATA. SATA link seems to be one of the most vulnerable parts to interference. When PSU has the slightest of problem, SATA drives timeout or give transmission problems. System often survives brief fluctuation in power input (e.g. when the compressor starts up) but SATA link sometimes reports error after such event. Or just buy a static generator and apply it to your computer case. Generally system is perfectly okay with that but the SATA devices tend to complain or timeout. Those condition might not be considered too healthy in any server environment but they do occur on cheap desktop environment. I mean, a lot of people are putting 10USD PSU into their desktop machines. So, yeah, it might be a driver or other problem but if problem is very intermittent, I tend to lean toward transient hardware problem and that's primarily why I wanna make EH kick in and recover faster. Thanks. -- tejun - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
On Tue, 20 Feb 2007 13:07:50 +0900, Tejun Heo wrote > [EMAIL PROTECTED] wrote: > > Hello, > > > > I have been running 2.6.18 for two months and the last couple of days these > > error messages have appeared in my logs > > (sata_promise kernel module, sda:SATA sdb:PATA disks): > > > >ata1: command timeout > > Feb 17 22:23:14 linux kernel: ata1: no sense translation for status: 0x40 > > Feb 17 22:23:14 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI > > SK/ASC/ASCQ 0xb/00/00 > > Feb 17 22:23:14 linux kernel: ata1: status=0x40 { DriveReady } > > Feb 17 22:23:14 linux kernel: sd 0:0:0:0: SCSI error: return code = > > 0x0802 > > Feb 17 22:23:14 linux kernel: sda: Current: sense key: Aborted Command > > Feb 17 22:23:14 linux kernel: Additional sense: No additional sense > > information > > Feb 17 22:23:14 linux kernel: end_request: I/O error, dev sda, sector > > 145179585 > > Feb 17 22:23:14 linux kernel: Buffer I/O error on device sda2, logical > > block > > 2787300 > > Feb 17 22:23:14 linux kernel: lost page write due to I/O error on sda2 > > > > and > > > >ata1: command timeout > > Feb 19 20:39:31 linux kernel: ata1: no sense translation for status: 0x40 > > Feb 19 20:39:31 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI > > SK/ASC/ASCQ 0xb/00/00 > > Feb 19 20:39:31 linux kernel: ata1: status=0x40 { DriveReady } > > Feb 19 20:39:31 linux kernel: sd 0:0:0:0: SCSI error: return code = > > 0x0802 > > Feb 19 20:39:31 linux kernel: sda: Current: sense key: Aborted Command > > Feb 19 20:39:31 linux kernel: Additional sense: No additional sense > > information > > Feb 19 20:39:31 linux kernel: end_request: I/O error, dev sda, sector > > 89553479 > > > > without any other ill-effects that I know of(I did smart tests on the > > drive; > > all passed successfully). > > I have read that hddtemp may be the cause of this (I am running version > > 0.3) > > so is there any reason > > to worry and prepare for a HDD replacement? > > Not really. If the problem occurs very infrequently, you don't need > to worry about it too much. Command timeouts do occur on otherwise healthy > systems from time to time. > > -- > tejun > - I'm experiencing the exact same problem with my setup also with sata_promise. I have posted to the linux-ide list but it wasn't really acknowledged as a problem in the driver. Are these command timeouts? The log entry doesn't seem to say that - just an error with 'DriveReady' and command aborted. I would think some kind of retry should be performed (and if it is then logged too). The errors may be benign but the problem is when using software raid (md driver) that this error may cause a degraded array and worse a damaged array should a read error like this occur when an array is already degraded. The question is what happens after the error is reported, is the operation retried? In my situation the md layer receives the error and recovers by taking the data from another drive in the array. The fact that you are also experiencing this means it might be an issue that needs further investigation in my opinion. Regards, Marc -- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
[EMAIL PROTECTED] wrote: > Hello, > > I have been running 2.6.18 for two months and the last couple of days these > error messages have appeared in my logs > (sata_promise kernel module, sda:SATA sdb:PATA disks): > >ata1: command timeout > Feb 17 22:23:14 linux kernel: ata1: no sense translation for status: 0x40 > Feb 17 22:23:14 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI > SK/ASC/ASCQ 0xb/00/00 > Feb 17 22:23:14 linux kernel: ata1: status=0x40 { DriveReady } > Feb 17 22:23:14 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 > Feb 17 22:23:14 linux kernel: sda: Current: sense key: Aborted Command > Feb 17 22:23:14 linux kernel: Additional sense: No additional sense > information > Feb 17 22:23:14 linux kernel: end_request: I/O error, dev sda, sector > 145179585 > Feb 17 22:23:14 linux kernel: Buffer I/O error on device sda2, logical block > 2787300 > Feb 17 22:23:14 linux kernel: lost page write due to I/O error on sda2 > > and > >ata1: command timeout > Feb 19 20:39:31 linux kernel: ata1: no sense translation for status: 0x40 > Feb 19 20:39:31 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI > SK/ASC/ASCQ 0xb/00/00 > Feb 19 20:39:31 linux kernel: ata1: status=0x40 { DriveReady } > Feb 19 20:39:31 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 > Feb 19 20:39:31 linux kernel: sda: Current: sense key: Aborted Command > Feb 19 20:39:31 linux kernel: Additional sense: No additional sense > information > Feb 19 20:39:31 linux kernel: end_request: I/O error, dev sda, sector 89553479 > > without any other ill-effects that I know of(I did smart tests on the drive; > all passed successfully). > I have read that hddtemp may be the cause of this (I am running version 0.3) > so is there any reason > to worry and prepare for a HDD replacement? Not really. If the problem occurs very infrequently, you don't need to worry about it too much. Command timeouts do occur on otherwise healthy systems from time to time. -- tejun - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
[EMAIL PROTECTED] wrote: Hello, I have been running 2.6.18 for two months and the last couple of days these error messages have appeared in my logs (sata_promise kernel module, sda:SATA sdb:PATA disks): ata1: command timeout Feb 17 22:23:14 linux kernel: ata1: no sense translation for status: 0x40 Feb 17 22:23:14 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI SK/ASC/ASCQ 0xb/00/00 Feb 17 22:23:14 linux kernel: ata1: status=0x40 { DriveReady } Feb 17 22:23:14 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 Feb 17 22:23:14 linux kernel: sda: Current: sense key: Aborted Command Feb 17 22:23:14 linux kernel: Additional sense: No additional sense information Feb 17 22:23:14 linux kernel: end_request: I/O error, dev sda, sector 145179585 Feb 17 22:23:14 linux kernel: Buffer I/O error on device sda2, logical block 2787300 Feb 17 22:23:14 linux kernel: lost page write due to I/O error on sda2 and ata1: command timeout Feb 19 20:39:31 linux kernel: ata1: no sense translation for status: 0x40 Feb 19 20:39:31 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI SK/ASC/ASCQ 0xb/00/00 Feb 19 20:39:31 linux kernel: ata1: status=0x40 { DriveReady } Feb 19 20:39:31 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 Feb 19 20:39:31 linux kernel: sda: Current: sense key: Aborted Command Feb 19 20:39:31 linux kernel: Additional sense: No additional sense information Feb 19 20:39:31 linux kernel: end_request: I/O error, dev sda, sector 89553479 without any other ill-effects that I know of(I did smart tests on the drive; all passed successfully). I have read that hddtemp may be the cause of this (I am running version 0.3) so is there any reason to worry and prepare for a HDD replacement? Not really. If the problem occurs very infrequently, you don't need to worry about it too much. Command timeouts do occur on otherwise healthy systems from time to time. -- tejun - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: ata command timeout
On Tue, 20 Feb 2007 13:07:50 +0900, Tejun Heo wrote [EMAIL PROTECTED] wrote: Hello, I have been running 2.6.18 for two months and the last couple of days these error messages have appeared in my logs (sata_promise kernel module, sda:SATA sdb:PATA disks): ata1: command timeout Feb 17 22:23:14 linux kernel: ata1: no sense translation for status: 0x40 Feb 17 22:23:14 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI SK/ASC/ASCQ 0xb/00/00 Feb 17 22:23:14 linux kernel: ata1: status=0x40 { DriveReady } Feb 17 22:23:14 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 Feb 17 22:23:14 linux kernel: sda: Current: sense key: Aborted Command Feb 17 22:23:14 linux kernel: Additional sense: No additional sense information Feb 17 22:23:14 linux kernel: end_request: I/O error, dev sda, sector 145179585 Feb 17 22:23:14 linux kernel: Buffer I/O error on device sda2, logical block 2787300 Feb 17 22:23:14 linux kernel: lost page write due to I/O error on sda2 and ata1: command timeout Feb 19 20:39:31 linux kernel: ata1: no sense translation for status: 0x40 Feb 19 20:39:31 linux kernel: ata1: translated ATA stat/err 0x40/00 to SCSI SK/ASC/ASCQ 0xb/00/00 Feb 19 20:39:31 linux kernel: ata1: status=0x40 { DriveReady } Feb 19 20:39:31 linux kernel: sd 0:0:0:0: SCSI error: return code = 0x0802 Feb 19 20:39:31 linux kernel: sda: Current: sense key: Aborted Command Feb 19 20:39:31 linux kernel: Additional sense: No additional sense information Feb 19 20:39:31 linux kernel: end_request: I/O error, dev sda, sector 89553479 without any other ill-effects that I know of(I did smart tests on the drive; all passed successfully). I have read that hddtemp may be the cause of this (I am running version 0.3) so is there any reason to worry and prepare for a HDD replacement? Not really. If the problem occurs very infrequently, you don't need to worry about it too much. Command timeouts do occur on otherwise healthy systems from time to time. -- tejun - I'm experiencing the exact same problem with my setup also with sata_promise. I have posted to the linux-ide list but it wasn't really acknowledged as a problem in the driver. Are these command timeouts? The log entry doesn't seem to say that - just an error with 'DriveReady' and command aborted. I would think some kind of retry should be performed (and if it is then logged too). The errors may be benign but the problem is when using software raid (md driver) that this error may cause a degraded array and worse a damaged array should a read error like this occur when an array is already degraded. The question is what happens after the error is reported, is the operation retried? In my situation the md layer receives the error and recovers by taking the data from another drive in the array. The fact that you are also experiencing this means it might be an issue that needs further investigation in my opinion. Regards, Marc -- - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/