[LU-12284] Inactive OST doesn't block client without lazystatfs feature Created: 10/May/19  Updated: 10/May/19

Status: Open
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.12.1
Fix Version/s: None

Type: Improvement Priority: Minor
Reporter: Li Xi Assignee: WC Triage
Resolution: Unresolved Votes: 0
Labels: None

Rank (Obsolete): 9223372036854775807

 Description   

On a server, I umounted the OST, and mount the clietn using “nolazystatfs ” option, expecting df to be blocked. However:

[root@el7-vm1 ~]# umount /mnt/lustre_ost0
[root@el7-vm2 ~]# mount -t lustre 10.0.1.148@tcp:/global -o nolazystatfs /mnt/global/

However, only the first "df" is blocked at all. Other "df" can be run without any block at all

[root@server17-el7-vm2 ~]# df
^C^C
[root@server17-el7-vm2 ~]# df
Filesystem             1K-blocks    Used Available Use% Mounted on
/dev/sda1               10189076 1632284   8016172  17% /
devtmpfs                  931196       0    931196   0% /dev
tmpfs                     941176       0    941176   0% /dev/shm
tmpfs                     941176    8496    932680   1% /run
tmpfs                     941176       0    941176   0% /sys/fs/cgroup
tmpfs                     188236       0    188236   0% /run/user/0
10.0.1.148@tcp:/global  14495148  107992  13551572   1% /mnt/global
[root@server17-el7-vm2 ~]# df
Filesystem             1K-blocks    Used Available Use% Mounted on
/dev/sda1               10189076 1632284   8016172  17% /
devtmpfs                  931196       0    931196   0% /dev
tmpfs                     941176       0    941176   0% /dev/shm
tmpfs                     941176    8496    932680   1% /run
tmpfs                     941176       0    941176   0% /sys/fs/cgroup
tmpfs                     188236       0    188236   0% /run/user/0
10.0.1.148@tcp:/global  14495148  107992  13551572   1% /mnt/global
[root@server17-el7-vm2 ~]# df
Filesystem             1K-blocks    Used Available Use% Mounted on
/dev/sda1               10189076 1632284   8016172  17% /
devtmpfs                  931196       0    931196   0% /dev
tmpfs                     941176       0    941176   0% /dev/shm
tmpfs                     941176    8496    932680   1% /run
tmpfs                     941176       0    941176   0% /sys/fs/cgroup
tmpfs                     188236       0    188236   0% /run/user/0
10.0.1.148@tcp:/global  14495148  107992  13551572   1% /mnt/global

This might not a big deal because I guess almost nobody wants to be blocked when running "df". However, it is not the expected behavior anyway. Am I misunderstanding the behavior of no-lazystatfs?


Generated at Sat Feb 10 02:51:14 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.