From 6327a8d740daf40a21b2c77dba0d626ea9b1f373 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 11 Aug 2021 08:08:32 -0400 Subject: [PATCH] doc: document that NEARFULL conditions can result in slow writes The change to doing sync I/Os when we're in NEARFULL conditions apparently caught some folks by surprise. Add something to clarify that to the kclient debugging docs. Also, remove the incomplete sentence that follows it, which contains no useful information. Fixes: https://tracker.ceph.com/issues/49406 Signed-off-by: Jeff Layton --- doc/cephfs/troubleshooting.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/cephfs/troubleshooting.rst b/doc/cephfs/troubleshooting.rst index 78ad18ddeb4..ea33019f043 100644 --- a/doc/cephfs/troubleshooting.rst +++ b/doc/cephfs/troubleshooting.rst @@ -124,8 +124,8 @@ slow requests are probably the ``mdsc`` and ``osdc`` files. * osdc: Dumps the current ops in-flight to OSDs (ie, file data IO) * osdmap: Dumps the current OSDMap epoch, pools, and OSDs -If there are no stuck requests but you have file IO which is not progressing, -you might have a... +If the data pool is in a NEARFULL condition, then the kernel cephfs client +will switch to doing writes synchronously, which is quite slow. Disconnected+Remounted FS ========================= -- 2.47.3