From: Richard Henwood Date: Wed, 22 May 2013 14:08:01 +0000 (-0500) Subject: LUDOC-146 benchmark: water-down obdfilter-survey warning. X-Git-Tag: 2.5.0~48 X-Git-Url: https://git.whamcloud.com/gitweb?a=commitdiff_plain;h=refs%2Fchanges%2F16%2F6416%2F10;p=doc%2Fmanual.git LUDOC-146 benchmark: water-down obdfilter-survey warning. The obdfilter-survey uses a different object sequence (2) compared to normal filesystem objects (currently always 0), so the two do not collide. The manual now indicates that obdfilter-survey may not destroy production data. A brief description of the object sequence difference between obdfilter_survey and normal objects is included. The task to provide evidence to reduce the vagueness of this warning is LU-3444. Signed-off-by: Richard Henwood Change-Id: Iac5fd3d9a89906dd04290ab62b2cff43ece29e53 Reviewed-on: http://review.whamcloud.com/6416 Tested-by: Hudson --- diff --git a/BenchmarkingTests.xml b/BenchmarkingTests.xml index 8bead1f..3502cba 100644 --- a/BenchmarkingTests.xml +++ b/BenchmarkingTests.xml @@ -204,7 +204,7 @@ - The obdfilter_survey script is destructive and should not be run on devices that containing existing data that needs to be preserved. Thus, tests using obdfilter_survey should be run before the Lustre file system is placed in production. + The obdfilter_survey script is potentially destructive and there is a small risk data may be lost. To reduce this risk, obdfilter_survey should not be run on devices that contain data that needs to be preserved. Thus, the best time to run obdfilter_survey is before the Lustre file system is put into production. The reason obdfilter_survey may be safe to run on a production file system is because it creates objects with object sequence 2. Normal file system objects are typically created with object sequence 0. If the obdfilter_survey test is terminated before it completes, some small amount of space is leaked. you can either ignore it or reformat the file system.