From df9f86faf3ee610527ed02031fe7dd3c8b752e44 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 1 Nov 2010 15:49:23 -0700 Subject: ceph: fix small seq message skipping If the client gets out of sync with the server message sequence number, we normally skip low seq messages (ones we already received). The skip code was also incrementing the expected seq, such that all subsequent messages also appeared old and got skipped, and an eventual timeout on the osd connection. This resulted in some lagging requests and console messages like [233480.882885] ceph: skipping osd22 10.138.138.13:6804 seq 2016, expected 2017 [233480.882919] ceph: skipping osd22 10.138.138.13:6804 seq 2017, expected 2018 [233480.882963] ceph: skipping osd22 10.138.138.13:6804 seq 2018, expected 2019 [233480.883488] ceph: skipping osd22 10.138.138.13:6804 seq 2019, expected 2020 [233485.219558] ceph: skipping osd22 10.138.138.13:6804 seq 2020, expected 2021 [233485.906595] ceph: skipping osd22 10.138.138.13:6804 seq 2021, expected 2022 [233490.379536] ceph: skipping osd22 10.138.138.13:6804 seq 2022, expected 2023 [233495.523260] ceph: skipping osd22 10.138.138.13:6804 seq 2023, expected 2024 [233495.923194] ceph: skipping osd22 10.138.138.13:6804 seq 2024, expected 2025 [233500.534614] ceph: tid 6023602 timed out on osd22, will reset osd Reported-by: Theodore Ts'o Signed-off-by: Sage Weil --- net/ceph/messenger.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/ceph') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 0e8157ee5d43..d379abf873bc 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1532,14 +1532,13 @@ static int read_partial_message(struct ceph_connection *con) /* verify seq# */ seq = le64_to_cpu(con->in_hdr.seq); if ((s64)seq - (s64)con->in_seq < 1) { - pr_info("skipping %s%lld %s seq %lld, expected %lld\n", + pr_info("skipping %s%lld %s seq %lld expected %lld\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - sizeof(m->footer); con->in_tag = CEPH_MSGR_TAG_READY; - con->in_seq++; return 0; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", -- cgit v1.2.3