[LU-9132] Tuning max_sectors_kb on mount

• Type: Bug
• Resolution: Fixed
• Priority: Minor
• Fix Version/s: Lustre 2.10.0
• Severity: 3
• Assignee: Niu Yawei (Inactive)
• Reporter: Niu Yawei (Inactive)

Description

Sometimes user doesn't want the max_sectors_kb being overwritten on MDT/OST mount, we should provide a way for user to have more control over this important parameter, a environment variable MOUNT_LUSTRE_MAX_SECTORS_KB is introduced for this purpose:

• When MOUNT_LUSTRE_MAX_SECTORS_KB isn't set, change the max_sectors_kb to max_hw_sectors_kb;
• When MOUNT_LUSTRE_MAX_SECTORS_KB is set to 0 or a non-decimal value, leave the old max_sectors_kb setting untouched;
• When MOUNT_LUSTRE_MAX_SECTORS_KB is set to a valid decimal value, change the max_sectors_kb to this value;

Issue Links

• is duplicated by: LU-9551 I/O errors when lustre uses multipath devices
• is related to: LU-10510 Fix 'over max size limit' issue
• is related to: LU-11736 Do not apply bulk IO tuning on MDT or MGT devices
• is related to: LU-12297 Add an option to disable mount.lustre automatical tune