The migration code caches vmstate/ram writes into an iovec and flushes this every 128kb.
The QIOChannelTLS receives the iovec, but size GNUTLS cannot accept iovec data, it iterates calling send for each element. As a result of the migration data pattern, this results in GNUTLS putting writes on the wire that alternate between about 4k and 30 bytes. This is triggering the nagle algorithm on migration-test for many of the TLS test cases, resulting in a "go slow" for I/O that eventually hits the migration timeout configured by the test. Not every contributor reports seeing the "go slow" but for those who do see it, it hits >= 95% of the time for at least one of the migration TLS test cases run by 'make check'. While we could disable the nagle algorithm (and multifd channels already do this), that would just lead to lots of small TCP packets hitting the wire which is not good for throughput. The migration code flushes in batches of 128kb because it wants large writes for high throughput. The only way to achieve this in the TLS code is to bounce buffer the writes in order to flatten the iovec. We cannot fully flatten, however, since GNUTLS puts a cap on the max TLS record size it is willing to send, which is negotiated with the server, typically 16 kb out of the box. This patch thus queries the max TLS record size and then flattens the iovec into buffers of this size. If the iovec only contains a single element, bounce buffering is skipped to avoid the redundant copy. Signed-off-by: Daniel P. Berrangé <[email protected]> --- crypto/tlssession.c | 10 ++++++++++ include/crypto/tlssession.h | 2 ++ include/io/channel-tls.h | 2 ++ io/channel-tls.c | 35 ++++++++++++++++++++++++++++++----- io/trace-events | 1 + 5 files changed, 45 insertions(+), 5 deletions(-) diff --git a/crypto/tlssession.c b/crypto/tlssession.c index 314e3e96ba..cf4daf8544 100644 --- a/crypto/tlssession.c +++ b/crypto/tlssession.c @@ -653,6 +653,11 @@ qcrypto_tls_session_get_peer_name(QCryptoTLSSession *session) return NULL; } +size_t qcrypto_tls_session_get_send_buffer(QCryptoTLSSession *session) +{ + return gnutls_record_get_max_size(session->handle); +} + #else /* ! CONFIG_GNUTLS */ @@ -757,4 +762,9 @@ qcrypto_tls_session_get_peer_name(QCryptoTLSSession *sess) return NULL; } +size_t qcrypto_tls_session_get_send_buffer(QCryptoTLSSession *sess) +{ + return 1; +} + #endif diff --git a/include/crypto/tlssession.h b/include/crypto/tlssession.h index 28e419681e..b29648a0a9 100644 --- a/include/crypto/tlssession.h +++ b/include/crypto/tlssession.h @@ -369,4 +369,6 @@ int qcrypto_tls_session_get_key_size(QCryptoTLSSession *sess, */ char *qcrypto_tls_session_get_peer_name(QCryptoTLSSession *sess); +size_t qcrypto_tls_session_get_send_buffer(QCryptoTLSSession *sess); + #endif /* QCRYPTO_TLSSESSION_H */ diff --git a/include/io/channel-tls.h b/include/io/channel-tls.h index 7e9023570d..1c22a3fd07 100644 --- a/include/io/channel-tls.h +++ b/include/io/channel-tls.h @@ -50,6 +50,8 @@ struct QIOChannelTLS { QIOChannelShutdown shutdown; guint hs_ioc_tag; guint bye_ioc_tag; + char *send_buffer; + size_t send_buffer_len; }; /** diff --git a/io/channel-tls.c b/io/channel-tls.c index 31ec4d236d..ba2699786e 100644 --- a/io/channel-tls.c +++ b/io/channel-tls.c @@ -24,6 +24,7 @@ #include "io/channel-tls.h" #include "trace.h" #include "qemu/atomic.h" +#include "qemu/iov.h" static ssize_t qio_channel_tls_write_handler(const void *buf, @@ -201,6 +202,12 @@ static gboolean qio_channel_tls_handshake_task(QIOChannelTLS *ioc, } else { trace_qio_channel_tls_credentials_allow(ioc); } + + ioc->send_buffer_len = qcrypto_tls_session_get_send_buffer( + ioc->session); + ioc->send_buffer = g_new0(char, ioc->send_buffer_len); + trace_qio_channel_tls_send_buffer_len(ioc, ioc->send_buffer_len); + qio_task_complete(task); return TRUE; } else { @@ -376,6 +383,7 @@ static void qio_channel_tls_finalize(Object *obj) g_clear_handle_id(&ioc->bye_ioc_tag, g_source_remove); } + g_free(ioc->send_buffer); object_unref(OBJECT(ioc->master)); qcrypto_tls_session_free(ioc->session); } @@ -446,13 +454,30 @@ static ssize_t qio_channel_tls_writev(QIOChannel *ioc, Error **errp) { QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc); - size_t i; ssize_t done = 0; + size_t tot = iov_size(iov, niov); - for (i = 0 ; i < niov ; i++) { + /* Skip bounce buffer in simple case */ + if (niov == 1) { ssize_t ret = qcrypto_tls_session_write(tioc->session, - iov[i].iov_base, - iov[i].iov_len, + iov[0].iov_base, + iov[0].iov_len, + errp); + if (ret == QCRYPTO_TLS_SESSION_ERR_BLOCK) { + return QIO_CHANNEL_ERR_BLOCK; + } else if (ret < 0) { + return -1; + } + return ret; + } + + while (done < tot) { + size_t got = iov_to_buf(iov, niov, done, + tioc->send_buffer, + tioc->send_buffer_len); + ssize_t ret = qcrypto_tls_session_write(tioc->session, + tioc->send_buffer, + got, errp); if (ret == QCRYPTO_TLS_SESSION_ERR_BLOCK) { if (done) { @@ -464,7 +489,7 @@ static ssize_t qio_channel_tls_writev(QIOChannel *ioc, return -1; } done += ret; - if (ret < iov[i].iov_len) { + if (ret < got) { break; } } diff --git a/io/trace-events b/io/trace-events index ec91453335..88ebd5b478 100644 --- a/io/trace-events +++ b/io/trace-events @@ -44,6 +44,7 @@ qio_channel_tls_handshake_pending(void *ioc, int status) "TLS handshake pending qio_channel_tls_handshake_fail(void *ioc) "TLS handshake fail ioc=%p" qio_channel_tls_handshake_complete(void *ioc) "TLS handshake complete ioc=%p" qio_channel_tls_handshake_cancel(void *ioc) "TLS handshake cancel ioc=%p" +qio_channel_tls_send_buffer_len(void *ioc, int len) "TLS send buffer len ioc=%p len=%d" qio_channel_tls_bye_start(void *ioc) "TLS termination start ioc=%p" qio_channel_tls_bye_pending(void *ioc, int status) "TLS termination pending ioc=%p status=%d" qio_channel_tls_bye_fail(void *ioc) "TLS termination fail ioc=%p" -- 2.55.0
