[LU-10070] PFL self-extending file layout

• Type: New Feature
• Resolution: Fixed
• Priority: Minor
• Fix Version/s: Lustre 2.13.0
• Affects Version/s: Lustre 2.10.0
• Labels: FLR2
• Assignee: Vitaly Fertman
• Reporter: Andreas Dilger

Description

One interesting idea discussed at LAD was to have a PFL layout that is "self extending".

For several use cases, such as HSM partial-file release/restore, partial-file migration to/from burst buffers, partial-file FLR resync it is advantageous to avoid the need to restore/migrate/resync the entire file at once, but rather only to process the required chunks of the file.

Essentially, a PFL file would have the normal few components that define the start of the file (e.g. [0-32MB), [32MB-1GB), [1GB-16GB)) and they would be instantiated as with normal PFL today. What is new for "self-extending layouts" is that the last component becomes the template for additional components (as needed) rather than having a component to "EOF" that freezes the layout of the rest of the file.

This avoids the overhead of explicitly specifying many identical components for the file, only in order to limit the size of the components that need to be processed.

Issue Links

• is related to: LU-9096 sanity test_253: File creation failed after rm
• is related to: LU-12681 Data corruption - due incorrect KMS with SEL files
• is related to: LU-12712 sanity-pfl tests triggering “not SEL magic on SEL file”
• is related to: LU-13395 unable to set "--comp-flags=prefer" on a new file
• is related to: LU-13589 PFL "lfs setstripe -E 1M -S 65536" incorrectly parses stripe_size units
• is related to: LU-9846 Overstriping - more than stripe per OST per component
• is related to: LU-10169 Spillover space
• is related to: LU-13058 Intermediate component removal (PFL/SEL)
• is related to: LU-9479 sanity test 184d 244: don't instantiate PFL component when taking group lock
• is related to: LU-9809 RTDS(Real-Time Dynamic Striping): A policy based striping framework
• is related to: LUDOC-436 Self Extending Layout Documentation
• is related to: LU-8998 Progressive File Layout (PFL)
• is related to: LU-9771 FLR1: Landing tickets for File Level Redundancy Phase 1
• is related to: LU-10808 DoM: component end should align with dom_stripesize
• is related to: LU-7880 add OST/MDT performance statistics to obd_statfs

Comments

[Gerrit Updater]

Oleg Drokin ([e-mail]) merged in patch https://review.whamcloud.com/35232/
Subject: LU-10070 ldlm: layout lock fixes
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 51f23ffa4dae3015da627203fb6f160db4911bee

[Gerrit Updater]

Vitaly Fertman ([e-mail]) uploaded a new patch: https://review.whamcloud.com/35270
Subject: LU-10070 lod: layout_del memleak
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: d97c1343529fd4c38be5226772d0f2d9543db854

[Gerrit Updater]

Vitaly Fertman ([e-mail]) uploaded a new patch: https://review.whamcloud.com/35232
Subject: LU-10070 ldlm: layout lock fixes
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 9e58fe77666aac33bf78d2f6fb67dee2532e3ae7

[Gerrit Updater]

Vitaly Fertman ([e-mail]) uploaded a new patch: https://review.whamcloud.com/35182
Subject: LU-10070 lod: SEL: let's discuss here
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 6d4b80add15eb9ad49e8c3fbcf2b830611127c68

[Gerrit Updater]

Vitaly Fertman ([e-mail]) uploaded a new patch: https://review.whamcloud.com/35144
Subject: LU-10070 lod: SEL: interoperability support
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 2a651609247d5041bbc2c16935396fa445a9bbcd

[Cory Spitz]

http://wiki.lustre.org/Release_2.13.0 has been updated with reviewers and testers of record.

[Patrick Farrell (Inactive)]

A general comment:
We should add a sanity-lfsck test (probably in a separate patch?), to verify that SEL layouts work with lfsck.  I verified this by hand during development, by leaving all the test generated files in place and running lfsck, but we should have test(s).

A good model is the lfsck tests added in the foreign layout patches:

https://review.whamcloud.com/#/c/33755/

https://review.whamcloud.com/#/c/34087/

I can think of a few cases I'd want to test.

1. Just create an SEL layout, don't do anything to it (or write a little data, but don't use the SEL portion), run sanity-lfsck & verify no changes
2. Same, but extend the layout once, then lfsck (Maybe don't need 1 & 2 - Could just extend once before testing)

3. Same, but "exhaust" an SEL component so you get component removal, then lfsck

4. Repeat a component and run sanity-lfsck

[Gerrit Updater]

Vitaly Fertman ([e-mail]) uploaded a new patch: https://review.whamcloud.com/34909
Subject: LU-10070 utils: SEL: lfs find & getstripe support
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: f05c0aac0d46d75ed3b3284400cef2b3423f349d

[Gerrit Updater]

Andreas Dilger ([e-mail]) merged in patch https://review.whamcloud.com/34470/
Subject: LU-10070 tests: Fix replay-single test_85b
Project: fs/lustre-release
Branch: b2_12
Current Patch Set:
Commit: c590eaa213e6333531e775b100bfb78c952f4d79

[Gerrit Updater]

Andreas Dilger ([e-mail]) uploaded a new patch: https://review.whamcloud.com/34470
Subject: LU-10070 tests: Fix replay-single test_85b
Project: fs/lustre-release
Branch: b2_12
Current Patch Set: 1
Commit: 58e4fd508397464ab67295641f5dbc7c8b11cc9b

[Gerrit Updater]

Oleg Drokin ([e-mail]) merged in patch https://review.whamcloud.com/34406/
Subject: LU-10070 tests: Fix replay-single test_85b
Project: fs/lustre-release
Branch: b2_10
Current Patch Set:
Commit: e501749abdcf5513eb4a4eb19919bcbd295ad410