I had several pool corruptions on my test box recently, and recovery imports did inded take a large part of a week (the process starved my 8Gb RAM so the system hanged and had to be reset with the hardware reset button - and this contributed to the large timeframe). Luckily for me, these import attempts were cumulative, so after a while the system began working. It seems that the system crashed during a major deletion operation and needed more time to find and release the deferred-free blocks. Not sure if my success would apply to your situation though. iostat speeds can vary during pool maintenance operations (i.e. scrub and probably import and zdb walks too) depending on (metadata) fragmentation, CPU busy-ness, etc. A more relevant metric here is %busy for the disks. While researching my problem I found many older posts indicating that this is "normal", however setting some kernel values with mdb may help speed up the process and/or have it succeed.
To be short here, I can suggest that you read my recent threads from that timeframe: * (OI_148a) ZFS hangs when accessing the pool. How to trace what's happening? http://opensolaris.org/jive/thread.jspa?messageID=515689 * Questions on ZFS pool as a volume in another ZFS pool - details my system's setup http://opensolaris.org/jive/thread.jspa?threadID=138604&tstart=0 Since the system froze often by dropping into swap-hell, I had to create a watchdog which would initiate an ungraceful reboot if the conditions were "right". My FreeRAM-Watchdog code and compiled i386 binary and a primitive SMF service wrapper can be found here: http://thumper.cos.ru/~jim/freeram-watchdog-20110531-smf.tgz Other related forum threads: * zpool import hangs indefinitely (retry post in parts; too long?) http://opensolaris.org/jive/thread.jspa?threadID=131237 * zpool import hangs http://opensolaris.org/jive/thread.jspa?threadID=70205&tstart=15 ----- Original Message ----- From: Christian Becker <christian.frei...@googlemail.com> Date: Tuesday, May 31, 2011 18:02 Subject: [zfs-discuss] Importing Corrupted zpool never ends To: zfs-discuss@opensolaris.org > Hi There, > I need to import an corrupted ZPOOL after double-Crash (Mainboard and one > HDD) on a different system. > It is a RAIDZ1 - 3 HDDs - only 2 are working. > > Problem: spool import -f poolname runs and runs and runs. Looking after > iostat (not zpool iostat) it is doing something - but what? And why does it > last so long (2x 1.5TB - Atom System). > > iostat seems to read and write with something about 500kB/s - I hope that it > doesn't work through the whole 1500GB - that would need 40 Days... > > Hope someone could help me. > > Thanks allot > Chris > _______________________________________________ > zfs-discuss mailing list > zfs-discuss@opensolaris.org > http://mail.opensolaris.org/mailman/listinfo/zfs-discuss -- +============================================================+ | | | Климов Евгений, Jim Klimov | | технический директор CTO | | ЗАО "ЦОС и ВТ" JSC COS&HT | | | | +7-903-7705859 (cellular) mailto:jimkli...@cos.ru | | CC:ad...@cos.ru,jimkli...@gmail.com | +============================================================+ | () ascii ribbon campaign - against html mail | | /\ - against microsoft attachments | +============================================================+
_______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
