Code Review for illumos-gate

Prepared by:Arne Jansen (arne) on 2014-Oct-31 10:14 +0100 MET
Workspace:/home/git/arne/illumos/illumos-gate (at d6d1fd3f6689)
Compare against: HEAD~ (at cefd41bc3095)
Summary of changes: 199 lines changed: 142 ins; 21 del; 36 mod; 15324 unchg
Patch of changes: illumos-gate.patch
Printable review: illumos-gate.pdf

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/dmu_objset.c

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
147 lines changed: 109 ins; 15 del; 23 mod; 1769 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/spa.c

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
8 lines changed: 2 ins; 2 del; 4 mod; 6542 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/sys/dmu.h

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
1 line changed: 1 ins; 0 del; 0 mod; 829 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/sys/dmu_objset.h

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
2 lines changed: 2 ins; 0 del; 0 mod; 179 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/sys/vdev.h

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
1 line changed: 1 ins; 0 del; 0 mod; 164 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/sys/zil.h

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
5 lines changed: 3 ins; 0 del; 2 mod; 427 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/vdev.c

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
21 lines changed: 21 ins; 0 del; 0 mod; 3302 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw usr/src/uts/common/fs/zfs/zil.c

5269 zfs: zpool import slow
While importing a pool all objsets are enumerated twice, once to check
the zil log chains and once to claim them. On pools with many datasets
this process might take a substantial amount of time.
Speed up the process by parallelizing it utilizing a taskq. The number
of parallel tasks is limited to 4 times the number of leaf vdevs.
14 lines changed: 3 ins; 4 del; 7 mod; 2112 unchg

This code review page was prepared using /home/git/arne/illumos/illumos-gate/usr/src/tools/scripts/webrev. Webrev is maintained by the illumos project. The latest version may be obtained here.