[LU-17980] improve ldiskfs "-o discard" performance

• Type: Improvement
• Resolution: Unresolved
• Priority: Minor
• Labels: NVME ldiskfs performance
• Assignee: Dongyang Li
• Reporter: Andreas Dilger

Description

The current "-o discard" mount option for ldiskfs enables on-the-fly TRIM of underlying flash devices (or thinly-provisioned LUNs). However, the current implementation hurts performance because it tracks each block free request explicitly in memory, and submits trim requests to storage on transaction commit.

It would be better to have an async worker thread to issue the TRIM commands using the standard fstrim mechanism, and do this on a per-blockgroup basis, rather than tracking and issuing the trim on a per-extent basis. This reduces both memory and IO overhead, by aggregating TRIM commands for many blocks in a single group.

This would be based on the patches in LU-14712 that make the TRIM state for a block group persistent, so that running TRIM with mke2fs does not also lead to fstrim resubmitting TRIM requests for all of the groups again immediately after mount/remount.

Issue Links

• Clones: LU-14712 make TRIM state persistent across reboots
• is related to: LU-16750 optimize ldiskfs internal metadata allocation for hybrid storage LUNs
• is related to: LU-19158 export fstrim statistics from ext4/ldiskfs
• is related to: LU-14438 backport ldiskfs mballoc patches