[lustre-devel] Clarification requested on safety of `lfs migrate` during concurrent writes
Ls Li <[email protected]> Tue, 17 Jun 2025 08:47:31 +0000
| Newsgroups | org.lustre.lists.lustre-devel |
|---|---|
| Message-ID | <OS7PR01MB11902B49B65F82E851AE8D0C7C473A@OS7PR01MB11902.jpnprd01.prod.outlook.com> |
--===============3698265523555589354==
Content-Language: en-US
Content-Type: multipart/alternative;
boundary="_000_OS7PR01MB11902B49B65F82E851AE8D0C7C473AOS7PR01MB11902jp_"
--_000_OS7PR01MB11902B49B65F82E851AE8D0C7C473AOS7PR01MB11902jp_
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Dear Lustre developers,
I am evaluating the use of `lfs migrate` to perform online OST data migrati=
on in a production environment where I/O activity must remain uninterrupted=
.
While reviewing the help output of the tool, I noticed the warning:
"(may be not safe with concurrent writes)"
After tracing the commit history, I found that this warning was introduced =
in the following patch:
https://review.whamcloud.com/c/fs/lustre-release/+/13754
Based on my reading of the implementation:
- When using the `--block` option, a group lock appears to be used to prote=
ct the migration operation.
- When using `--non-block`, a lease mechanism is in place, and migration is=
aborted if conflicting access is detected.
However, I would like to better understand the scenarios in which this oper=
ation may still be considered unsafe.
Could you kindly clarify the following:
1. Under what conditions does `lfs migrate` pose a risk when concurrent wri=
tes are happening?
2. Specifically, if client processes are appending to or modifying files du=
ring `--non-block` migration, what types of issues might arise (e.g., metad=
ata corruption, partial migration, or data inconsistency)?
3. Is the `--block` option considered completely safe under concurrent writ=
e loads, or are there known edge cases where group locking may be insuffici=
ent?
Any technical explanation, known limitations, or recommended best practices=
would be greatly appreciated.
Thank you very much for your time and insights.
Best regards
--_000_OS7PR01MB11902B49B65F82E851AE8D0C7C473AOS7PR01MB11902jp_
Content-Type: text/html; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<html>
<head>
<meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Diso-8859-=
1">
<style type=3D"text/css" style=3D"display:none;"> P {margin-top:0;margin-bo=
ttom:0;} </style>
</head>
<body dir=3D"ltr">
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
Dear Lustre developers,</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
I am evaluating the use of `lfs migrate` to perform online OST data migrati=
on in a production environment where I/O activity must remain uninterrupted=
.</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
While reviewing the help output of the tool, I noticed the warning:</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
"(may be not safe with concurrent writes)"</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
After tracing the commit history, I found that this warning was introduced =
in the following patch:</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
https://review.whamcloud.com/c/fs/lustre-release/+/13754</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
Based on my reading of the implementation:</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
- When using the `--block` option, a group lock appears to be used to prote=
ct the migration operation.</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
- When using `--non-block`, a lease mechanism is in place, and migration is=
aborted if conflicting access is detected.</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
However, I would like to better understand the scenarios in which this oper=
ation may still be considered unsafe.</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
Could you kindly clarify the following:</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
1. Under what conditions does `lfs migrate` pose a risk when concurrent wri=
tes are happening?</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
2. Specifically, if client processes are appending to or modifying files du=
ring `--non-block` migration, what types of issues might arise (e.g., metad=
ata corruption, partial migration, or data inconsistency)?</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
3. Is the `--block` option considered completely safe under concurrent writ=
e loads, or are there known edge cases where group locking may be insuffici=
ent?</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
Any technical explanation, known limitations, or recommended best practices=
would be greatly appreciated.</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
Thank you very much for your time and insights.</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
<br>
</div>
<div class=3D"elementToProof" style=3D"font-family: Aptos, Aptos_EmbeddedFo=
nt, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; c=
olor: rgb(0, 0, 0);">
Best regards</div>
</body>
</html>
--_000_OS7PR01MB11902B49B65F82E851AE8D0C7C473AOS7PR01MB11902jp_--
--===============3698265523555589354==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
_______________________________________________
lustre-devel mailing list
[email protected]
http://lists.lustre.org/listinfo.cgi/lustre-devel-lustre.org
--===============3698265523555589354==--