From 32850a2e3ed06394a0086acc19b484ddf4a2cef6 Mon Sep 17 00:00:00 2001 From: John Snow Date: Wed, 27 Mar 2019 17:22:19 +0100 Subject: [PATCH 080/163] block/nbd-client: use traces instead of noisy error_report_err RH-Author: John Snow Message-id: <20190327172308.31077-7-jsnow@redhat.com> Patchwork-id: 85183 O-Subject: [RHEL-7.7 qemu-kvm-rhev PATCH 06/55] block/nbd-client: use traces instead of noisy error_report_err Bugzilla: 1691009 RH-Acked-by: Stefan Hajnoczi RH-Acked-by: Max Reitz RH-Acked-by: Miroslav Rezanina From: Vladimir Sementsov-Ogievskiy Reduce extra noise of nbd-client, change 083 correspondingly. In various commits (be41c100 in 2.10, f140e300 in 2.11, 78a33ab in 2.12), we added spots where qemu as an NBD client would report problems communicating with the server to stderr, because there was no where else to send the error to. However, this is racy, particularly since the most common source of these errors is when either the client or the server abruptly hangs up, leaving one coroutine to report the error only if it wins (or loses) the race in attempting the read from the server before another thread completes its cleanup of a protocol error that caused the disconnect in the first place. The race is also apparent in the fact that differences in the flush behavior of the server can alter the frequency of encountering the race in the client (see commit 6d39db96). Rather than polluting stderr, it's better to just trace these situations, for use by developers debugging a flaky connection, particularly since the real error that either triggers the abrupt disconnection in the first place, or that results from the EIO when a request can't receive a reply, DOES make it back to the user in the normal Error propagation channels. Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20181102151152.288399-4-vsementsov@virtuozzo.com> [eblake: drop depedence on error hint, enhance commit message] Signed-off-by: Eric Blake (cherry picked from commit d8b4bad846f08ff0f167b46dc156a5310b750484) Signed-off-by: John Snow Signed-off-by: Miroslav Rezanina --- block/nbd-client.c | 23 +++++++++++++++++++---- block/trace-events | 4 ++++ tests/qemu-iotests/083.out | 28 ---------------------------- 3 files changed, 23 insertions(+), 32 deletions(-) diff --git a/block/nbd-client.c b/block/nbd-client.c index fc5b7ed..ef32075 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -28,6 +28,8 @@ */ #include "qemu/osdep.h" + +#include "trace.h" #include "qapi/error.h" #include "nbd-client.h" @@ -79,7 +81,8 @@ static coroutine_fn void nbd_read_reply_entry(void *opaque) assert(s->reply.handle == 0); ret = nbd_receive_reply(s->ioc, &s->reply, &local_err); if (local_err) { - error_report_err(local_err); + trace_nbd_read_reply_entry_fail(ret, error_get_pretty(local_err)); + error_free(local_err); } if (ret <= 0) { break; @@ -771,7 +774,11 @@ static int nbd_co_request(BlockDriverState *bs, NBDRequest *request, ret = nbd_co_receive_return_code(client, request->handle, &local_err); if (local_err) { - error_report_err(local_err); + trace_nbd_co_request_fail(request->from, request->len, request->handle, + request->flags, request->type, + nbd_cmd_lookup(request->type), + ret, error_get_pretty(local_err)); + error_free(local_err); } return ret; } @@ -802,7 +809,11 @@ int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, ret = nbd_co_receive_cmdread_reply(client, request.handle, offset, qiov, &local_err); if (local_err) { - error_report_err(local_err); + trace_nbd_co_request_fail(request.from, request.len, request.handle, + request.flags, request.type, + nbd_cmd_lookup(request.type), + ret, error_get_pretty(local_err)); + error_free(local_err); } return ret; } @@ -925,7 +936,11 @@ int coroutine_fn nbd_client_co_block_status(BlockDriverState *bs, ret = nbd_co_receive_blockstatus_reply(client, request.handle, bytes, &extent, &local_err); if (local_err) { - error_report_err(local_err); + trace_nbd_co_request_fail(request.from, request.len, request.handle, + request.flags, request.type, + nbd_cmd_lookup(request.type), + ret, error_get_pretty(local_err)); + error_free(local_err); } if (ret < 0) { return ret; diff --git a/block/trace-events b/block/trace-events index c35287b..6d4d399 100644 --- a/block/trace-events +++ b/block/trace-events @@ -150,3 +150,7 @@ nvme_free_req_queue_wait(void *q) "q %p" nvme_cmd_map_qiov(void *s, void *cmd, void *req, void *qiov, int entries) "s %p cmd %p req %p qiov %p entries %d" nvme_cmd_map_qiov_pages(void *s, int i, uint64_t page) "s %p page[%d] 0x%"PRIx64 nvme_cmd_map_qiov_iov(void *s, int i, void *page, int pages) "s %p iov[%d] %p pages %d" + +# block/nbd-client.c +nbd_read_reply_entry_fail(int ret, const char *err) "ret = %d, err: %s" +nbd_co_request_fail(uint64_t from, uint32_t len, uint64_t handle, uint16_t flags, uint16_t type, const char *name, int ret, const char *err) "Request failed { .from = %" PRIu64", .len = %" PRIu32 ", .handle = %" PRIu64 ", .flags = 0x%" PRIx16 ", .type = %" PRIu16 " (%s) } ret = %d, err: %s" diff --git a/tests/qemu-iotests/083.out b/tests/qemu-iotests/083.out index f9af8bb..7419722 100644 --- a/tests/qemu-iotests/083.out +++ b/tests/qemu-iotests/083.out @@ -41,8 +41,6 @@ can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect after neg2 === -Unable to read from socket: Connection reset by peer -Connection closed read failed: Input/output error === Check disconnect 8 neg2 === @@ -55,40 +53,30 @@ can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect before request === -Unable to read from socket: Connection reset by peer -Connection closed read failed: Input/output error === Check disconnect after request === -Connection closed read failed: Input/output error === Check disconnect before reply === -Connection closed read failed: Input/output error === Check disconnect after reply === -Unexpected end-of-file before all bytes were read read failed: Input/output error === Check disconnect 4 reply === -Unexpected end-of-file before all bytes were read -Connection closed read failed: Input/output error === Check disconnect 8 reply === -Unexpected end-of-file before all bytes were read -Connection closed read failed: Input/output error === Check disconnect before data === -Unexpected end-of-file before all bytes were read read failed: Input/output error === Check disconnect after data === @@ -118,8 +106,6 @@ can't open device nbd+tcp://127.0.0.1:PORT/ === Check disconnect after neg-classic === -Unable to read from socket: Connection reset by peer -Connection closed read failed: Input/output error === Check disconnect before neg1 === @@ -164,8 +150,6 @@ can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock === Check disconnect after neg2 === -Unable to read from socket: Connection reset by peer -Connection closed read failed: Input/output error === Check disconnect 8 neg2 === @@ -178,40 +162,30 @@ can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock === Check disconnect before request === -Unable to read from socket: Connection reset by peer -Connection closed read failed: Input/output error === Check disconnect after request === -Connection closed read failed: Input/output error === Check disconnect before reply === -Connection closed read failed: Input/output error === Check disconnect after reply === -Unexpected end-of-file before all bytes were read read failed: Input/output error === Check disconnect 4 reply === -Unexpected end-of-file before all bytes were read -Connection closed read failed: Input/output error === Check disconnect 8 reply === -Unexpected end-of-file before all bytes were read -Connection closed read failed: Input/output error === Check disconnect before data === -Unexpected end-of-file before all bytes were read read failed: Input/output error === Check disconnect after data === @@ -241,8 +215,6 @@ can't open device nbd+unix:///?socket=TEST_DIR/nbd.sock === Check disconnect after neg-classic === -Unable to read from socket: Connection reset by peer -Connection closed read failed: Input/output error *** done -- 1.8.3.1