The only qdiscs that check subqueue state before dequeue'ing are PRIO and RR. The other qdiscs, including the default pfifo_fast qdisc, will allow traffic bound for subqueue 0 through to hard_start_xmit. The check for netif_queue_stopped() is done above in pkt_sched.h, so it is unnecessary for qdisc_restart(). However, if the underlying driver is multiqueue capable, and only sets queue states on subqueues, this will allow packets to enter the driver when it's currently unable to process packets, r...

The only qdiscs that check subqueue state before dequeue'ing are PRIO and RR. The other qdiscs, including the default pfifo_fast qdisc, will allow traffic bound for subqueue 0 through to hard_start_xmit. The check for netif_queue_stopped() is done above in pkt_sched.h, so it is unnecessary for qdisc_restart(). However, if the underlying driver is multiqueue capable, and only sets queue states on subqueues, this will allow packets to enter the driver when it's currently unable to process packets, r...

No problem. I would like to have helped more, but it's slow going given my lack of network stack knowledge. If I get any more interesting data, It didn't seem to be noticeable at 1 client. Unless scatterlist processing is going to cause cacheline bouncing, I don't see why this hurts more as you add CPUs? -

[Empty message]

Doesn't help (with vanilla kernel -- Herbert's patch applied). data_len histogram drops to 0 and goes to len (I guess that's not surprising). Performance is pretty similar (ie. not good). I'll look at allocator patterns next. -

From: Jesse Brandeburg <jesse.brandeburg@intel.com> mii-tool can cause the driver to call msleep during nway reset, bugzilla.kernel.org bug 8430. Fix by simply calling reinit_locked outside of the spinlock, which is safe from ethtool, so it should be safe from here. Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com> --- drivers/net/e1000/e1000_main.c | 13 +++---------- 1 files changed, 3 insertions(+), 10 dele...

From: Joe Perches <joe@perches.com> Add functions for reg_pattern_test and reg_set_and check Changed macros to use these functions Compiled x86, untested Size decreased ~2K old: $ size drivers/net/e1000e/ethtool.o text data bss dec hex filename 14461 0 0 14461 387d drivers/net/e1000e/ethtool.o new: $ size drivers/net/e1000e/ethtool.o text data bss dec hex filename 12498 0 0 12498 30d2 drivers/net/e1000e...

formerly e1000/e1000e only updated traffic counters once every 2 seconds with the register values of bytes/packets. With newer code however in the interrupt and polling code we can real-time fill in these values in the netstats struct for users to see. Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com> --- drivers/net/e1000/e1000_main.c | 10 ++++++---- 1 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index ...

Otherwise TCP might violate packet ordering principles that FRTO is based on. If conventional recovery path is chosen, this won't be significant at all. In practice, any small enough value will be sufficient to provide proper operation for FRTO, yet other users of snd_cwnd might benefit from a "close enough" value. FRTO's formula is now equal to what tcp_enter_cwr() uses. FRTO used to check application limitedness a bit differently but I changed that in commit 575ee7140dabe9b9c4f66f4f867039b97e...

With 2.6.23.1: # pwd ; find . -name nf_conntrack_max /proc/sys/net ./netfilter/nf_conntrack_max ./nf_conntrack_max Both sysctls operate on the same underlying value, though, so no real problem. -

Replace the nfs_server and mount_server address fields in the nfs_parsed_mount_data structure with a "struct sockaddr_storage" and a length, instead of a "struct sockaddr_in". Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- fs/nfs/client.c | 11 +++++----- fs/nfs/internal.h | 6 ++++-- fs/nfs/super.c | 56 +++++++++++++++++++++++++++++++++-------------------- 3 files changed, 44 insertions(+), 29 deletions(-) ...

Some mount options pass in a string IP address. Let's parse these strings in a separate function since this is done for at least two different mount options. This allows us to support IPv6 string addresses more easily in a subsequent patch Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- fs/nfs/super.c | 20 ++++++++++++++------ 1 files changed, 14 insertions(+), 6 deletions(-) diff --git a/fs/nfs/super.c b/fs/nfs/...

If fs_enet is build as module, on PPC_CPM_NEW_BINDING platforms mii-fec/mii-bitbang should be build as module, as well. On other platforms, mii-fec/mii-bitbang must be included into the main module. Otherwise some symbols remain undefined. Additionally, fs_enet uses libphy, so add a select PHYLIB. Building modules, stage 2. MODPOST 5 modules ERROR: "fs_scc_ops" [drivers/net/fs_enet/fs_enet.ko] undefined! make[1]: *** [__modpost] Error 1 make: *** [modules] Error 2 Signed-off-by: Jochen Fri...

Move more address family dependencies to a helper function. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> --- fs/nfs/super.c | 40 ++++++++++++++++++++++++++++++++-------- 1 files changed, 32 insertions(+), 8 deletions(-) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 7dc56ce..1831394 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1573,6 +1573,31 @@ static void nfs4_fill_super(struct super_block *sb) } /* + * If the user didn't specify a port, set the port num...

Universal addresses are defined in RFC 1833 and clarified in RFC 3530. We need to use them in several places in the NFS and RPC clients, so move the relevant definition and block comment to an appropriate global include file. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> --- include/linux/sunrpc/msg_prot.h | 39 ++++++++++++++++++++++++++++++++++ net/sunrpc/rpcb_clnt.c | 45 +++------------------------------------ 2 files changed, 42 insertions(+), 42 deletions(-) d...

The nfs_client's cl_ipaddr field needs to be larger to hold strings that represent IPv6 addresses. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- include/linux/nfs_fs_sb.h | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 8a3061c..f2a0f20 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -63,7 +63,7 @@ struct nf...

Change the addr field in the nfs_clone_mount structure to store a "struct sockaddr *" to support non-IPv4 addresses in the NFS client. Note this is mostly a cosmetic change, and does not actually allow referrals using IPv6 addresses. The existing referral code assumes that the server returns a string that represents an IPv4 address. This code needs to support hostnames and IPv6 addresses as well as IPv4 addresses, thus it will need to be restructured in order to handle DNS resolution in user spac...

Adjust arguments and callers of nfs_find_client() to pass a "struct sockaddr *" instead of "struct sockaddr_in *" to support non-IPv4 addresses. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- fs/nfs/callback.c | 3 +-- fs/nfs/callback_proc.c | 4 ++-- fs/nfs/client.c | 4 ++-- fs/nfs/internal.h | 2 +- 4 files changed, 6 insertions(+), 7 deletions(-) diff --git a/fs/nfs/callback.c b/fs/nf...

Adjust the arguments and callers of __nfs_find_client() to pass a "struct sockaddr *" instead of a "struct sockaddr_in *" so that non-IPv4 addresses can be passed into __nfs_find_client(). A subsequent patch adds support for IPv6 addresses to __nfs_find_client(). Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- fs/nfs/client.c | 14 +++++++++----- 1 files changed, 9 insertions(+), 5 deletions(-) diff --git a/fs/nfs/c...

To support non-IPv4 addresses, adjust the arguments and callers of nfs_alloc_client() to pass in a "struct sockaddr *" and length instead of a "struct sockaddr_in *". Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- fs/nfs/client.c | 9 ++++++--- 1 files changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 53bf8ab..c1ee3d3 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @...

Change the addr field in the cb_getattrargs struct to a "struct sockaddr *" to support non-IPv4 addresses. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- fs/nfs/callback.h | 2 +- fs/nfs/callback_proc.c | 2 +- fs/nfs/callback_xdr.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index c2bb14e..ec0ffd9 100644 --- a/fs/nfs/callback.h +++ b/fs/...

The client side peer address is available in callback_proc.c, so move a dprintk out of fs/nfs/callback.c and into fs/nfs/callback_proc.c. This is more consistent with other debugging messages, and the proc routines have more information about each request to display. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Aurelien Charbon <aurelien.charbon@ext.bull.net> --- fs/nfs/callback.c | 4 ---- fs/nfs/callback_proc.c | 12 +++++++++++- 2 files changed, 11 inserti...

Ensure that the RPC buffer size specified for NFSv4 SETCLIENTID procedures matches what we are encoding into the buffer. See the definition of struct nfs4_setclientid {} and the encode_setclientid() function. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> --- fs/nfs/nfs4xdr.c | 10 ++++++---- include/linux/nfs_xdr.h | 13 +++++++------ 2 files changed, 13 insertions(+), 10 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index eae46f0..93e8ebf 100644 --- ...

These 25 patches add support for AF_INET6 addresses to the NFS client. This is a request for review of the proposed changes. This series does not add support for AF_INET6 addresses to the Linux NLM or NSM implementations, nor does it add support in the NFS server. To use an IPv6 NFS server, the mount.nfs command will pass in an IPv6 server address via the "addr" option. IPv6 support in mount.nfs is yet to be implemented. This series has been tested only with IPv4 addresses to ensure there are ...

I am getting "hw csum failure" messages with sky2. I have seen this problem reported elsewhere with a fibre NIC, but I am using a copper NIC. It seems to be triggered by SMP. It is easy to reproduce in 2.6.23. 2.6.24-rc2-git3 still has the problem, but it happens less frequently. To reproduce the problem, I am using a simple network benchmark program that I wrote that basically does send()/recv() as fast as possible using a memory buffer (null data, no disk I/O, no data integrity checking). Th...