Whamcloud - gitweb
LU-14641 osd-ldiskfs: write commit declaring improvement 05/45505/2
authorWang Shilong <wshilong@ddn.com>
Mon, 26 Apr 2021 03:23:26 +0000 (11:23 +0800)
committerAndreas Dilger <adilger@whamcloud.com>
Sun, 14 Nov 2021 03:09:25 +0000 (03:09 +0000)
commit1734c4746d98dfa6fc6559841be8028a22465718
tree8a88a1deeccc9b6482c1d14f5a26823630377274
parentb5f71a7e7528831a0a2c7d02b5bd98d68fcb1855
LU-14641 osd-ldiskfs: write commit declaring improvement

This patch try to:

1)extent bytes could be missed to increase with less than
1M, fix to to compare it with current value, and decay
it for every allocation.

2)with system space usage growing up, mballoc codes won't
try best to scan block group to align best free extent as
we can. So extent bytes per extent could be decayed to a
very small value, this could make us reserve too many credits.
We could be more optimistic in the credit reservations, even
in a case where the filesystem is nearly full, it is extremely
unlikely that the worst case would ever be hit.

3)Add extent bytes stats and debug ability to analysis
over reservation problem.

Lustre-change: https://review.whamcloud.com/43446
Lustre-commit: 0f81c5ae973bf7fba45b6ba7f9c5f4fb1f6eadcb

Signed-off-by: Wang Shilong <wshilong@ddn.com>
Change-Id: I357c4a855147ba26a9e9bbe9ab1269bcfd44e5f3
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/45505
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Tested-by: Maloo <maloo@whamcloud.com>
lustre/osd-ldiskfs/osd_io.c
lustre/osd-ldiskfs/osd_lproc.c