lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20100904042809.2655.42894.sendpatchset@jupiter1-ltc-lp2.austin.ibm.com>
Date:	Fri, 03 Sep 2010 23:28:09 -0500
From:	Santiago Leon <santil@...ux.vnet.ibm.com>
To:	netdev@...r.kernel.org
Cc:	brking@...ux.vnet.ibm.com,
	Santiago Leon <santil@...ux.vnet.ibm.com>, anton@...ba.org
Subject: [patch 02/21] ibmveth: batch rx buffer replacement

At the moment we try and replenish the receive ring on every rx interrupt.
We even have a pool->threshold but aren't using it.

To limit the maximum latency incurred when refilling, change the threshold
from 1/2 to 7/8 and reduce the largest rx pool from 768 buffers to 512 which
should be more than enough.

Signed-off-by: Anton Blanchard <anton@...ba.org>
Signed-off-by: Santiago Leon <santil@...ux.vnet.ibm.com>
---

Index: net-next-2.6/drivers/net/ibmveth.c
===================================================================
--- net-next-2.6.orig//drivers/net/ibmveth.c	2010-09-03 22:18:36.000000000 -0500
+++ net-next-2.6/drivers/net/ibmveth.c	2010-09-03 22:18:37.000000000 -0500
@@ -178,7 +178,7 @@ static void ibmveth_init_buffer_pool(str
 	pool->size = pool_size;
 	pool->index = pool_index;
 	pool->buff_size = buff_size;
-	pool->threshold = pool_size / 2;
+	pool->threshold = pool_size * 7 / 8;
 	pool->active = pool_active;
 }
 
@@ -315,10 +315,13 @@ static void ibmveth_replenish_task(struc
 
 	adapter->replenish_task_cycles++;
 
-	for (i = (IbmVethNumBufferPools - 1); i >= 0; i--)
-		if(adapter->rx_buff_pool[i].active)
-			ibmveth_replenish_buffer_pool(adapter,
-						     &adapter->rx_buff_pool[i]);
+	for (i = (IbmVethNumBufferPools - 1); i >= 0; i--) {
+		struct ibmveth_buff_pool *pool = &adapter->rx_buff_pool[i];
+
+		if (pool->active &&
+		    (atomic_read(&pool->available) < pool->threshold))
+			ibmveth_replenish_buffer_pool(adapter, pool);
+	}
 
 	adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8);
 }
Index: net-next-2.6/drivers/net/ibmveth.h
===================================================================
--- net-next-2.6.orig//drivers/net/ibmveth.h	2010-09-03 22:17:03.000000000 -0500
+++ net-next-2.6/drivers/net/ibmveth.h	2010-09-03 22:18:37.000000000 -0500
@@ -102,7 +102,7 @@ static inline long h_illan_attributes(un
 #define IBMVETH_MAX_BUF_SIZE (1024 * 128)
 
 static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 };
-static int pool_count[] = { 256, 768, 256, 256, 256 };
+static int pool_count[] = { 256, 512, 256, 256, 256 };
 static int pool_active[] = { 1, 1, 0, 0, 0};
 
 #define IBM_VETH_INVALID_MAP ((u16)0xffff)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ