From mboxrd@z Thu Jan 1 00:00:00 1970 Received: by passt.top (Postfix, from userid 1000) id 9D8725A0271; Sat, 23 Sep 2023 00:06:10 +0200 (CEST) From: Stefano Brivio To: David Gibson , Matej Hrica Subject: [PATCH RFT 0/5] Fixes and a workaround for TCP stalls with small buffers Date: Sat, 23 Sep 2023 00:06:05 +0200 Message-Id: <20230922220610.58767-1-sbrivio@redhat.com> X-Mailer: git-send-email 2.39.2 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Message-ID-Hash: QKXIHGMMLXGA6WTZ4L64DAMXDIQWLOP5 X-Message-ID-Hash: QKXIHGMMLXGA6WTZ4L64DAMXDIQWLOP5 X-MailFrom: sbrivio@passt.top X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: passt-dev@passt.top X-Mailman-Version: 3.3.8 Precedence: list List-Id: Development discussion and patches for passt Archived-At: Archived-At: List-Archive: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: The fundamental patch here is 3/5, which is a workaround for a rather surprising kernel behaviour we seem to be hitting. This all comes from the investigation around https://bugs.passt.top/show_bug.cgi?id=74. I can't hit stalls anymore and throughput looks finally good to me (~3.5gbps with 208 KiB rmem_max and wmem_max), but... please test. Stefano Brivio (5): tcp: Fix comment to tcp_sock_consume() tcp: Reset STALLED flag on ACK only, check for pending socket data tcp: Force TCP_WINDOW_CLAMP before resetting STALLED flag tcp, tap: Don't increase tap-side sequence counter for dropped frames passt.1: Add note about tuning rmem_max and wmem_max for throughput passt.1 | 33 +++++++++++++++++++++++++ tap.c | 10 +++++--- tap.h | 2 +- tcp.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++---------- 4 files changed, 102 insertions(+), 17 deletions(-) -- 2.39.2