Le 20/10/15 17:58, Garrett D'Amore a écrit :
> It could be related.  If a device cannot flush buffers to disk it may wind up 
> just holding them in memory.  That would be defective behavior though.  
> 
> What is your storage subsystem made up of?
> 


I'm on a Supermicro H8SGL-F with:
> richard@omnis:/home/richard$ pfexec lspci |grep SATA
> 00:11.0 SATA controller: Advanced Micro Devices, Inc. [AMD/ATI] 
> SB7x0/SB8x0/SB9x0 SATA Controller [AHCI mode]

and
> Oct 19 18:51:41 omnis sata: [ID 663010 kern.info] /pci@0,0/pci1002,4391@11 :
> Oct 19 18:51:41 omnis sata: [ID 761595 kern.info]     SATA disk device at 
> port 4
> Oct 19 18:51:41 omnis sata: [ID 846691 kern.info]     model Samsung SSD 840 
> PRO Series              
> Oct 19 18:51:41 omnis sata: [ID 693010 kern.info]     firmware DXM04B0Q
> Oct 19 18:51:41 omnis sata: [ID 163988 kern.info]     serial number 
> S12RNEAD309080D     
> Oct 19 18:51:41 omnis sata: [ID 479077 kern.info]     ATA/ATAPI-9 supported, 
> majver 0x3fc minver 0x39
> Oct 19 18:51:41 omnis sata: [ID 594940 kern.info]     supported features:
> Oct 19 18:51:41 omnis sata: [ID 981177 kern.info]      48-bit LBA, DMA, 
> Native Command Queueing, SMART, SMART self-test
> Oct 19 18:51:41 omnis sata: [ID 996592 kern.info]     SATA Gen3 signaling 
> speed (6.0Gbps)
> Oct 19 18:51:41 omnis sata: [ID 349649 kern.info]     Supported queue depth 32
> Oct 19 18:51:41 omnis sata: [ID 349649 kern.info]     capacity = 500118192 
> sectors
> Oct 19 18:51:41 omnis scsi: [ID 583861 kern.info] sd3 at ahci0: target 4 lun 0
> Oct 19 18:51:41 omnis genunix: [ID 936769 kern.info] sd3 is 
> /pci@0,0/pci1002,4391@11/disk@4,0
> Oct 19 18:51:41 omnis genunix: [ID 408114 kern.info] 
> /pci@0,0/pci1002,4391@11/disk@4,0 (sd3) online
> Oct 19 18:51:41 omnis sata: [ID 663010 kern.info] /pci@0,0/pci1002,4391@11 :
> Oct 19 18:51:41 omnis sata: [ID 761595 kern.info]     SATA disk device at 
> port 5
> Oct 19 18:51:41 omnis sata: [ID 846691 kern.info]     model INTEL 
> SSDSA2M080G2GN                    
> Oct 19 18:51:41 omnis sata: [ID 693010 kern.info]     firmware 2CV102M3
> Oct 19 18:51:41 omnis sata: [ID 163988 kern.info]     serial number 
> CVPO00700560080BGN  
> Oct 19 18:51:41 omnis sata: [ID 479077 kern.info]     ATA/ATAPI-7 supported, 
> majver 0xfc minver 0x1a
> Oct 19 18:51:41 omnis sata: [ID 594940 kern.info]     supported features:
> Oct 19 18:51:41 omnis sata: [ID 981177 kern.info]      48-bit LBA, DMA, 
> Native Command Queueing, SMART, SMART self-test
> Oct 19 18:51:41 omnis sata: [ID 643337 kern.info]     SATA Gen2 signaling 
> speed (3.0Gbps)
> Oct 19 18:51:41 omnis sata: [ID 349649 kern.info]     Supported queue depth 32
> Oct 19 18:51:41 omnis sata: [ID 349649 kern.info]     capacity = 156301488 
> sectors
> O

where rpool is the INTEL and dpool is the SAMSUNG, both SSDs.


I just happened to notice prior to the traceback posted that the following was 
logged in messages:
> Oct 19 19:50:48 omnis genunix: [ID 843051 kern.info] NOTICE: SUNW-MSG-ID: 
> SUNOS-8000-0G, TYPE: Error, VER: 1, SEVERITY: Major
> Oct 19 19:50:48 omnis unix: [ID 836849 kern.notice] 
> Oct 19 19:50:48 omnis ^Mpanic[cpu0]/thread=ffffff003d0cbc40: 
> Oct 19 19:50:48 omnis genunix: [ID 918906 kern.notice] I/O to pool 'rpool' 
> appears to be hung.
> Oct 19 19:50:48 omnis unix: [ID 100000 kern.notice] 

if it was rpool, then is it possible my INTEL SSD is crapping out?  I've always 
wanted to make it more or less RO

looking in /var/tmp, it appears there's some something redirecting TMP there 
for compiler temporaries, 
that could choke the INTEL quickly on this system...


-- 
Richard PALO



-------------------------------------------
illumos-discuss
Archives: https://www.listbox.com/member/archive/182180/=now
RSS Feed: https://www.listbox.com/member/archive/rss/182180/21175430-2e6923be
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21175430&id_secret=21175430-6a77cda4
Powered by Listbox: http://www.listbox.com

Reply via email to