[LU-12559] Reconnecting from idle exposes import in IMP_NEW state, resulting in EIO

• Type: Bug
• Resolution: Fixed
• Priority: Major
• Fix Version/s: Lustre 2.13.0, Lustre 2.12.3
• Assignee: Patrick Farrell (Inactive)
• Reporter: Patrick Farrell (Inactive)

Description

When reconnecting idle imports (in ptlrpc_request_alloc_internal and ptlrpc_disconnect_idle_interpret), we set the import state to IMP_NEW, and then release the import lock before immediately calling ptlrpc_connect_import, which immediately takes the import lock.

However, there's a small gap where an import in the IMP_NEW state is exposed.

This can cause messages sent in this interval to fail, like this:

ptlrpc_import_delay_req()) @@@ Uninitialized import. req@[...]x1638589897143744/t0(0) o101->[....]-OST0000-osc-[...]@o2ib:28/4 lens 328/400 e 0 to 0 dl 0 ref 2 fl Rpc:/0/ffffffff rc 0/-1

        } else if (imp->imp_state == LUSTRE_IMP_NEW) {
                DEBUG_REQ(D_ERROR, req, "Uninitialized import.");
                *status = -EIO;

The solution is to not release the import lock, so this gap does not exist.

Comments

[Gerrit Updater]

Oleg Drokin ([e-mail]) merged in patch https://review.whamcloud.com/36215/
Subject: LU-12559 ptlrpc: Hold imp lock for idle reconnect
Project: fs/lustre-release
Branch: b2_12
Current Patch Set:
Commit: df5d7a7816e8472397e5f99fd2d44d4cd2a4754d

[Gerrit Updater]

Minh Diep ([e-mail]) uploaded a new patch: https://review.whamcloud.com/36215
Subject: LU-12559 ptlrpc: Hold imp lock for idle reconnect
Project: fs/lustre-release
Branch: b2_12
Current Patch Set: 1
Commit: ae0990a1183993e7e05c864a033ff771b72cc523

[Peter Jones]

Landed for 2.13

[Gerrit Updater]

Oleg Drokin ([e-mail]) merged in patch https://review.whamcloud.com/35530/
Subject: LU-12559 ptlrpc: Hold imp lock for idle reconnect
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: e9472c54ac820c3a0db2318a6ef894c3971e6e0b

[Gerrit Updater]

Patrick Farrell ([e-mail]) uploaded a new patch: https://review.whamcloud.com/35530
Subject: LU-12559 ptlrpc: Hold imp lock for idle reconnect
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: f31f64e77d5664ade4b40859263afc062861283c