7ca9921dc5
OBS-URL: https://build.opensuse.org/package/show/Base:System/nfs-utils?expand=0&rev=cb75ed5e603b8f9de3c067835cc9fc07
159 lines
6.2 KiB
Diff
159 lines
6.2 KiB
Diff
---
|
|
utils/mount/nfs.man | 83 +++++++++++++++++++++++++++++++++++++++++++++++++
|
|
utils/mount/nfsmount.c | 3 +
|
|
utils/mount/stropts.c | 13 +++++++
|
|
3 files changed, 99 insertions(+)
|
|
|
|
--- nfs-utils-1.2.3.orig/utils/mount/nfs.man
|
|
+++ nfs-utils-1.2.3/utils/mount/nfs.man
|
|
@@ -504,6 +504,8 @@ Specifying a netid that uses TCP forces
|
|
command and the NFS client to use TCP.
|
|
Specifying a netid that uses UDP forces all traffic types to use UDP.
|
|
.IP
|
|
+.B Before using NFS over UDP, please refer to the section WARNINGS below.
|
|
+.IP
|
|
If the
|
|
.B proto
|
|
mount option is not specified, the
|
|
@@ -518,6 +520,8 @@ The
|
|
option is an alternative to specifying
|
|
.BR proto=udp.
|
|
It is included for compatibility with other operating systems.
|
|
+.IP
|
|
+.B Before using NFS over UDP, please refer to the section WARNINGS below.
|
|
.TP 1.5i
|
|
.B tcp
|
|
The
|
|
@@ -932,6 +936,8 @@ in a single frame) is advised. This r
|
|
the loss of a single MTU-sized network frame results in the loss of
|
|
an entire large read or write request.
|
|
.P
|
|
+Please see also the WARNINGS section below.
|
|
+.P
|
|
TCP is the default transport protocol used for all modern NFS
|
|
implementations. It performs well in almost every conceivable
|
|
network environment and provides excellent guarantees against data
|
|
@@ -1480,6 +1486,83 @@ of Access Control Lists that are semanti
|
|
NFS version 4 ACLs are not fully compatible with POSIX ACLs; as such,
|
|
some translation between the two is required
|
|
in an environment that mixes POSIX ACLs and NFS version 4.
|
|
+.SH WARNINGS
|
|
+Using NFS over UDP on high-speed links such as Gigabit
|
|
+.BR "can cause silent data corruption" .
|
|
+.P
|
|
+The problem can be triggered at high loads, and is caused by problems in
|
|
+IP fragment reassembly. NFS read and writes typically transmit UDP packets
|
|
+of 4 Kilobytes or more, which have to be broken up into several fragments
|
|
+in order to be sent over the Ethernet link, which limits packets to 1500
|
|
+bytes by default. This process happens at the IP network layer and is
|
|
+called fragmentation.
|
|
+.P
|
|
+In order to identify fragments that belong together, IP assigns a 16bit
|
|
+.I IP ID
|
|
+value to each packet; fragments generated from the same UDP packet
|
|
+will have the same IP ID. The receiving system will collect these
|
|
+fragments and combine them to form the original UDP packet. This process
|
|
+is called reassembly. The default timeout for packet reassembly is
|
|
+30 seconds; if the network stack does not receive all fragments of
|
|
+a given packet within this interval, it assumes the missing fragment(s)
|
|
+got lost and discards those it already received.
|
|
+.P
|
|
+The problem this creates over high-speed links is that it is possible
|
|
+to send more than 65536 packets within 30 seconds. In fact, with
|
|
+heavy NFS traffic one can observe that the IP IDs repeat after about
|
|
+5 seconds.
|
|
+.P
|
|
+This has serious effects on reassembly: if one fragment gets lost,
|
|
+another fragment
|
|
+.I from a different packet
|
|
+but with the
|
|
+.I same IP ID
|
|
+will arrive within the 30 second timeout, and the network stack will
|
|
+combine these fragments to form a new packet. Most of the time, network
|
|
+layers above IP will detect this mismatched reassembly - in the case
|
|
+of UDP, the UDP checksum, which is a 16 bit checksum over the entire
|
|
+packet payload, will usually not match, and UDP will discard the
|
|
+bad packet.
|
|
+.P
|
|
+However, the UDP checksum is 16 bit only, so there is a chance of 1 in
|
|
+65536 that it will match even if the packet payload is completely
|
|
+random (which very often isn't the case). If that is the case,
|
|
+silent data corruption will occur.
|
|
+.P
|
|
+This potential should be taken seriously, at least on Gigabit
|
|
+Ethernet.
|
|
+Network speeds of 100Mbit/s should be considered less
|
|
+problematic, because with most traffic patterns IP ID wrap around
|
|
+will take much longer than 30 seconds.
|
|
+.P
|
|
+It is therefore strongly recommended to use
|
|
+.BR "NFS over TCP where possible" ,
|
|
+since TCP does not perform fragmentation.
|
|
+.P
|
|
+If you absolutely have to use NFS over UDP over Gigabit Ethernet,
|
|
+some steps can be taken to mitigate the problem and reduce the
|
|
+probability of corruption:
|
|
+.TP +1.5i
|
|
+.I Jumbo frames:
|
|
+Many Gigabit network cards are capable of transmitting
|
|
+frames bigger than the 1500 byte limit of traditional Ethernet, typically
|
|
+9000 bytes. Using jumbo frames of 9000 bytes will allow you to run NFS over
|
|
+UDP at a page size of 8K without fragmentation. Of course, this is
|
|
+only feasible if all involved stations support jumbo frames.
|
|
+.IP
|
|
+To enable a machine to send jumbo frames on cards that support it,
|
|
+it is sufficient to configure the interface for a MTU value of 9000.
|
|
+.TP +1.5i
|
|
+.I Lower reassembly timeout:
|
|
+By lowering this timeout below the time it takes the IP ID counter
|
|
+to wrap around, incorrect reassembly of fragments can be prevented
|
|
+as well. To do so, simply write the new timeout value (in seconds)
|
|
+to the file
|
|
+.BR /proc/sys/net/ipv4/ipfrag_time .
|
|
+.IP
|
|
+A value of 2 seconds will greatly reduce the probability of IPID clashes on
|
|
+a single Gigabit link, while still allowing for a reasonable timeout
|
|
+when receiving fragmented traffic from distant peers.
|
|
.SH FILES
|
|
.TP 1.5i
|
|
.I /etc/fstab
|
|
--- nfs-utils-1.2.3.orig/utils/mount/nfsmount.c
|
|
+++ nfs-utils-1.2.3/utils/mount/nfsmount.c
|
|
@@ -264,6 +264,9 @@ parse_options(char *old_opts, struct nfs
|
|
if (!strcmp(opteq+1, "udp")) {
|
|
nfs_pmap->pm_prot = IPPROTO_UDP;
|
|
mnt_pmap->pm_prot = IPPROTO_UDP;
|
|
+ fprintf(stderr,
|
|
+ "Using NFS over UDP can cause data corruption.\n"
|
|
+ "Please refer to the WARNINGS section of the nfs(5) manual page.\n");
|
|
#if NFS_MOUNT_VERSION >= 2
|
|
data->flags &= ~NFS_MOUNT_TCP;
|
|
} else if (!strcmp(opteq+1, "tcp") &&
|
|
--- nfs-utils-1.2.3.orig/utils/mount/stropts.c
|
|
+++ nfs-utils-1.2.3/utils/mount/stropts.c
|
|
@@ -569,11 +569,24 @@ static int nfs_sys_mount(struct nfsmount
|
|
{
|
|
char *options = NULL;
|
|
int result;
|
|
+ char *proto;
|
|
+ static int once = 0;
|
|
|
|
if (po_join(opts, &options) == PO_FAILED) {
|
|
errno = EIO;
|
|
return 0;
|
|
}
|
|
+ if (po_contains(mi->options, "udp"))
|
|
+ proto = "udp";
|
|
+ else
|
|
+ proto = po_get(mi->options, "proto");
|
|
+ if (proto && strcmp(proto, "udp") == 0 && !once) {
|
|
+ fprintf(stderr,
|
|
+ "Using NFS over UDP can cause data corruption.\n"
|
|
+ "Please refer to the WARNINGS section of the nfs(5) manual page.\n");
|
|
+ once=1;
|
|
+ }
|
|
+
|
|
|
|
if (mi->fake)
|
|
return 1;
|