From 2d12ad950b0c2a89d82f5d258309ad23aa70fc38 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 11 May 2023 13:19:45 +0800 Subject: ceph: trigger to flush the buffer when making snapshot The 'i_wr_ref' is used to track the 'Fb' caps, while whenever the 'Fb' caps is took the kclient will always take the 'Fw' caps at the same time. That means it will always be a false check in __ceph_finish_cap_snap(). When writing to buffer the kclient will take both 'Fb|Fw' caps and then write the contents to the buffer pages by increasing the 'i_wrbuffer_ref' and then just release both 'Fb|Fw'. This is different with the user space libcephfs, which will keep the 'Fb' being took and use 'i_wr_ref' instead of 'i_wrbuffer_ref' to track this until the buffer is flushed to Rados. We need to defer flushing the capsnap until the corresponding buffer pages are all flushed to Rados, and at the same time just trigger to flush the buffer pages immediately. Link: https://tracker.ceph.com/issues/48640 Link: https://tracker.ceph.com/issues/59343 Signed-off-by: Xiubo Li Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 6 ++++++ fs/ceph/snap.c | 9 ++++++--- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'fs/ceph') diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 2321e5ddb664..6fb73e3a7f8e 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3109,6 +3109,12 @@ static void __ceph_put_cap_refs(struct ceph_inode_info *ci, int had, } if (had & CEPH_CAP_FILE_WR) { if (--ci->i_wr_ref == 0) { + /* + * The Fb caps will always be took and released + * together with the Fw caps. + */ + WARN_ON_ONCE(ci->i_wb_ref); + last++; check_flushsnaps = true; if (ci->i_wrbuffer_ref_head == 0 && diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 2e73ba62bd7a..343d738448dc 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -675,14 +675,17 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, return 0; } - /* Fb cap still in use, delay it */ - if (ci->i_wb_ref) { + /* + * Defer flushing the capsnap if the dirty buffer not flushed yet. + * And trigger to flush the buffer immediately. + */ + if (ci->i_wrbuffer_ref) { dout("%s %p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu " "used WRBUFFER, delaying\n", __func__, inode, ceph_vinop(inode), capsnap, capsnap->context, capsnap->context->seq, ceph_cap_string(capsnap->dirty), capsnap->size); - capsnap->writing = 1; + ceph_queue_writeback(inode); return 0; } -- cgit v1.2.3