when maxPacketSize has been uncommented, it did change rx_connection struct
behavoir, rx_connection is being called on vos (userspace code)
Or I am not reading the header correctly?
struct rx_connection {
struct rx_connection *next; /* on hash chain _or_ free list */
struct rx_peer *peer;
#endif
#ifdef RX_ENABLE_LOCKS
afs_kmutex_t conn_call_lock; /* locks conn_call_cv */
afs_kcondvar_t conn_call_cv;
afs_kmutex_t conn_data_lock; /* locks packet data */
#endif
afs_uint32 epoch; /* Process start time of client side of
connection */
afs_uint32 cid; /* Connection id (call channel is bottom bits)
*/
afs_int32 error; /* If this connection is in error, this is it */
#ifdef KDUMP_RX_LOCK
struct rx_call_rx_lock *call[RX_MAXCALLS];
#else
struct rx_call *call[RX_MAXCALLS];
#endif
afs_uint32 callNumber[RX_MAXCALLS]; /* Current call numbers */
afs_uint32 serial; /* Next outgoing packet serial number */
afs_uint32 lastSerial; /* # of last packet received, for computing
skew */
afs_int32 maxSerial; /* largest serial number seen on incoming
packets */
afs_int32 maxPacketSize; /* max packet size should be per-connection
since */
.........................
............................................
--- On Sat, 2/11/12, Simon Wilkinson <[email protected]> wrote:
From: Simon Wilkinson <[email protected]>
Subject: Re: [OpenAFS] replication over slower bandwidth
To: [email protected]
Cc: "Neil Davies" <[email protected]>, "OpenAFS Info"
<[email protected]>, "Jeffrey Altman" <[email protected]>
Received: Saturday, February 11, 2012, 12:27 PM
On 10 Feb 2012, at 04:29, Jeffrey Altman wrote:
> That field was commented out before OpenAFS and maxPacketSize was not
> referenced anywhere in the source code. What restoring that field to
> rx.h does is force the struct rxevent * values that follow it to become
> properly aligned in 64-bit builds.
>
> Lack of proper alignment can really hurt.
I'm a little confused here. The System V ABI, which Linux claims to follow,
specifies that pointers are 8 byte aligned - see Figure 3.1 of
http://www.x86-64.org/documentation/abi.pdf
Given that your speed improvements are from vos release, this must be userspace
code, so I'm not certain that this is an alignment issue.
Cheers,
Simon.
_______________________________________________
OpenAFS-info mailing list
[email protected]
https://lists.openafs.org/mailman/listinfo/openafs-info
