DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Yao, Lei A" <lei.a.yao@intel.com>
To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>,
	"Lin, Xueqin" <xueqin.lin@intel.com>,
	"Yigit, Ferruh" <ferruh.yigit@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, "Xu, Qian Q" <qian.q.xu@intel.com>,
	"Li, WenjieX A" <wenjiex.a.li@intel.com>,
	"Wang, FengqinX" <fengqinx.wang@intel.com>,
	"Wang, Yinan" <yinan.wang@intel.com>,
	"Jerin Jacob Kollanukkaran" <jerinj@marvell.com>,
	"thomas@monjalon.net" <thomas@monjalon.net>,
	"arybchenko@solarflare.com" <arybchenko@solarflare.com>,
	"Iremonger, Bernard" <bernard.iremonger@intel.com>,
	"alialnu@mellanox.com" <alialnu@mellanox.com>,
	 "Zhang, Qi Z" <qi.z.zhang@intel.com>
Subject: Re: [dpdk-dev] [PATCH v6 3/4] app/testpmd: move pkt prepare logic into a separate function
Date: Tue, 9 Apr 2019 12:24:01 +0000	[thread overview]
Message-ID: <2DBBFF226F7CF64BAFCA79B681719D954969777A@shsmsx102.ccr.corp.intel.com> (raw)
Message-ID: <20190409122401.g03KUGTnGGnIcQmSthCXoG9p__TYaHOH0BapRQKxQX0@z> (raw)
In-Reply-To: <CY4PR1801MB186319A2F80D0D3412C6180FDE2D0@CY4PR1801MB1863.namprd18.prod.outlook.com>



> -----Original Message-----
> From: Pavan Nikhilesh Bhagavatula [mailto:pbhagavatula@marvell.com]
> Sent: Tuesday, April 9, 2019 5:33 PM
> To: Lin, Xueqin <xueqin.lin@intel.com>; Yigit, Ferruh <ferruh.yigit@intel.com>
> Cc: dev@dpdk.org; Xu, Qian Q <qian.q.xu@intel.com>; Li, WenjieX A
> <wenjiex.a.li@intel.com>; Wang, FengqinX <fengqinx.wang@intel.com>;
> Yao, Lei A <lei.a.yao@intel.com>; Wang, Yinan <yinan.wang@intel.com>;
> Jerin Jacob Kollanukkaran <jerinj@marvell.com>; thomas@monjalon.net;
> arybchenko@solarflare.com; Iremonger, Bernard
> <bernard.iremonger@intel.com>; alialnu@mellanox.com; Zhang, Qi Z
> <qi.z.zhang@intel.com>
> Subject: RE: [dpdk-dev] [PATCH v6 3/4] app/testpmd: move pkt prepare logic
> into a separate function
> 
> Hi Lin,
> 
> Can you check if the following patch fixes the issue?
> http://patches.dpdk.org/patch/52395/
> 
> I wasn't able to catch this earlier.
> 
> Regards,
> Pavan

Hi, Pavan

With this patch, testpmd can generate packets with correct src
mac address at my side now. Thanks

BRs
Lei


> 
> >-----Original Message-----
> >From: Lin, Xueqin <xueqin.lin@intel.com>
> >Sent: Tuesday, April 9, 2019 2:58 PM
> >To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Yigit,
> Ferruh
> ><ferruh.yigit@intel.com>
> >Cc: dev@dpdk.org; Xu, Qian Q <qian.q.xu@intel.com>; Li, WenjieX A
> ><wenjiex.a.li@intel.com>; Wang, FengqinX <fengqinx.wang@intel.com>;
> Yao,
> >Lei A <lei.a.yao@intel.com>; Wang, Yinan <yinan.wang@intel.com>; Jerin
> Jacob
> >Kollanukkaran <jerinj@marvell.com>; thomas@monjalon.net;
> >arybchenko@solarflare.com; Iremonger, Bernard
> ><bernard.iremonger@intel.com>; alialnu@mellanox.com; Zhang, Qi Z
> ><qi.z.zhang@intel.com>
> >Subject: [EXT] RE: [dpdk-dev] [PATCH v6 3/4] app/testpmd: move pkt
> prepare
> >logic into a separate function
> >
> >External Email
> >
> >----------------------------------------------------------------------
> >Hi NIkhilesh,
> >
> >This patchset impacts some of 19.05 rc1 txonly/burst tests on Intel NIC. If
> set
> >txonly fwd, IXIA or tester peer can't receive packets that sent from app
> >generated.
> >This is high issue, block some cases test. Detailed information as below,
> need
> >you to check it soon.
> >
> >*DPDK version:  19.05.0-rc1
> >*NIC hardware: Fortville_eagle/Fortville_spirit/Niantic
> >Environment: one NIC port connect with another NIC port, or one NIC port
> >connect with IXIA
> >
> >Test Setup
> >1. Bind port to igb_uio or vfio
> >2. On DUT, setup testpmd:
> >    ./x86_64-native-linuxapp-gcc/app/testpmd -c 0x1e -n 4  -- -i --rxq=4 --
> txq=4 --
> >port-topology=loop 3. Set txonly forward, start testpmd
> >testpmd>set fwd txonly
> >testpmd>start
> >4. Dump packets from tester NIC port or IXIA, find no packets were
> received on
> >the PORT0.
> >tcpdump -i <tester_interface> -v
> >
> >Best regards,
> >Xueqin
> >
> >> -----Original Message-----
> >> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Pavan Nikhilesh
> >> Bhagavatula
> >> Sent: Tuesday, April 2, 2019 5:54 PM
> >> To: Jerin Jacob Kollanukkaran <jerinj@marvell.com>;
> >> thomas@monjalon.net; arybchenko@solarflare.com; Yigit, Ferruh
> >> <ferruh.yigit@intel.com>; Iremonger, Bernard
> >> <bernard.iremonger@intel.com>; alialnu@mellanox.com
> >> Cc: dev@dpdk.org; Pavan Nikhilesh Bhagavatula
> >> <pbhagavatula@marvell.com>
> >> Subject: [dpdk-dev] [PATCH v6 3/4] app/testpmd: move pkt prepare logic
> >> into a separate function
> >>
> >> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
> >>
> >> Move the packet prepare logic into a separate function so that it can
> >> be reused later.
> >>
> >> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
> >> ---
> >>  app/test-pmd/txonly.c | 163
> >> +++++++++++++++++++++---------------------
> >>  1 file changed, 83 insertions(+), 80 deletions(-)
> >>
> >> diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c index
> >> 65171c1d1..56ca0ad24 100644
> >> --- a/app/test-pmd/txonly.c
> >> +++ b/app/test-pmd/txonly.c
> >> @@ -148,6 +148,80 @@ setup_pkt_udp_ip_headers(struct ipv4_hdr
> *ip_hdr,
> >>  	ip_hdr->hdr_checksum = (uint16_t) ip_cksum;  }
> >>
> >> +static inline bool
> >> +pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
> >> +		struct ether_hdr *eth_hdr, const uint16_t vlan_tci,
> >> +		const uint16_t vlan_tci_outer, const uint64_t ol_flags) {
> >> +	struct rte_mbuf *pkt_segs[RTE_MAX_SEGS_PER_PKT];
> >> +	uint8_t  ip_var = RTE_PER_LCORE(_ip_var);
> >> +	struct rte_mbuf *pkt_seg;
> >> +	uint32_t nb_segs, pkt_len;
> >> +	uint8_t i;
> >> +
> >> +	if (unlikely(tx_pkt_split == TX_PKT_SPLIT_RND))
> >> +		nb_segs = random() % tx_pkt_nb_segs + 1;
> >> +	else
> >> +		nb_segs = tx_pkt_nb_segs;
> >> +
> >> +	if (nb_segs > 1) {
> >> +		if (rte_mempool_get_bulk(mbp, (void **)pkt_segs,
> nb_segs))
> >> +			return false;
> >> +	}
> >> +
> >> +	rte_pktmbuf_reset_headroom(pkt);
> >> +	pkt->data_len = tx_pkt_seg_lengths[0];
> >> +	pkt->ol_flags = ol_flags;
> >> +	pkt->vlan_tci = vlan_tci;
> >> +	pkt->vlan_tci_outer = vlan_tci_outer;
> >> +	pkt->l2_len = sizeof(struct ether_hdr);
> >> +	pkt->l3_len = sizeof(struct ipv4_hdr);
> >> +
> >> +	pkt_len = pkt->data_len;
> >> +	pkt_seg = pkt;
> >> +	for (i = 1; i < nb_segs; i++) {
> >> +		pkt_seg->next = pkt_segs[i - 1];
> >> +		pkt_seg = pkt_seg->next;
> >> +		pkt_seg->data_len = tx_pkt_seg_lengths[i];
> >> +		pkt_len += pkt_seg->data_len;
> >> +	}
> >> +	pkt_seg->next = NULL; /* Last segment of packet. */
> >> +	/*
> >> +	 * Copy headers in first packet segment(s).
> >> +	 */
> >> +	copy_buf_to_pkt(eth_hdr, sizeof(eth_hdr), pkt, 0);
> >> +	copy_buf_to_pkt(&pkt_ip_hdr, sizeof(pkt_ip_hdr), pkt,
> >> +			sizeof(struct ether_hdr));
> >> +	if (txonly_multi_flow) {
> >> +		struct ipv4_hdr *ip_hdr;
> >> +		uint32_t addr;
> >> +
> >> +		ip_hdr = rte_pktmbuf_mtod_offset(pkt,
> >> +				struct ipv4_hdr *,
> >> +				sizeof(struct ether_hdr));
> >> +		/*
> >> +		 * Generate multiple flows by varying IP src addr. This
> >> +		 * enables packets are well distributed by RSS in
> >> +		 * receiver side if any and txonly mode can be a decent
> >> +		 * packet generator for developer's quick performance
> >> +		 * regression test.
> >> +		 */
> >> +		addr = (IP_DST_ADDR | (ip_var++ << 8)) + rte_lcore_id();
> >> +		ip_hdr->src_addr = rte_cpu_to_be_32(addr);
> >> +	}
> >> +	copy_buf_to_pkt(&pkt_udp_hdr, sizeof(pkt_udp_hdr), pkt,
> >> +			sizeof(struct ether_hdr) +
> >> +			sizeof(struct ipv4_hdr));
> >> +	/*
> >> +	 * Complete first mbuf of packet and append it to the
> >> +	 * burst of packets to be transmitted.
> >> +	 */
> >> +	pkt->nb_segs = nb_segs;
> >> +	pkt->pkt_len = pkt_len;
> >> +
> >> +	return true;
> >> +}
> >> +
> >>  /*
> >>   * Transmit a burst of multi-segments packets.
> >>   */
> >> @@ -155,10 +229,8 @@ static void
> >>  pkt_burst_transmit(struct fwd_stream *fs)  {
> >>  	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
> >> -	struct rte_mbuf *pkt_segs[RTE_MAX_SEGS_PER_PKT];
> >>  	struct rte_port *txp;
> >>  	struct rte_mbuf *pkt;
> >> -	struct rte_mbuf *pkt_seg;
> >>  	struct rte_mempool *mbp;
> >>  	struct ether_hdr eth_hdr;
> >>  	uint16_t nb_tx;
> >> @@ -166,15 +238,12 @@ pkt_burst_transmit(struct fwd_stream *fs)
> >>  	uint16_t vlan_tci, vlan_tci_outer;
> >>  	uint32_t retry;
> >>  	uint64_t ol_flags = 0;
> >> -	uint8_t  ip_var = RTE_PER_LCORE(_ip_var);
> >> -	uint8_t  i;
> >>  	uint64_t tx_offloads;
> >>  #ifdef RTE_TEST_PMD_RECORD_CORE_CYCLES
> >>  	uint64_t start_tsc;
> >>  	uint64_t end_tsc;
> >>  	uint64_t core_cycles;
> >>  #endif
> >> -	uint32_t nb_segs, pkt_len;
> >>
> >>  #ifdef RTE_TEST_PMD_RECORD_CORE_CYCLES
> >>  	start_tsc = rte_rdtsc();
> >> @@ -201,85 +270,19 @@ pkt_burst_transmit(struct fwd_stream *fs)
> >>
> >>  	for (nb_pkt = 0; nb_pkt < nb_pkt_per_burst; nb_pkt++) {
> >>  		pkt = rte_mbuf_raw_alloc(mbp);
> >> -		if (pkt == NULL) {
> >> -		nomore_mbuf:
> >> -			if (nb_pkt == 0)
> >> -				return;
> >> +		if (pkt == NULL)
> >> +			break;
> >> +		if (unlikely(!pkt_burst_prepare(pkt, mbp, &eth_hdr, vlan_tci,
> >> +						vlan_tci_outer, ol_flags))) {
> >> +			rte_pktmbuf_free(pkt);
> >>  			break;
> >>  		}
> >> -
> >> -		/*
> >> -		 * Using raw alloc is good to improve performance,
> >> -		 * but some consumers may use the headroom and so
> >> -		 * decrement data_off. We need to make sure it is
> >> -		 * reset to default value.
> >> -		 */
> >> -		rte_pktmbuf_reset_headroom(pkt);
> >> -		pkt->data_len = tx_pkt_seg_lengths[0];
> >> -		pkt_seg = pkt;
> >> -
> >> -		if (tx_pkt_split == TX_PKT_SPLIT_RND)
> >> -			nb_segs = random() % tx_pkt_nb_segs + 1;
> >> -		else
> >> -			nb_segs = tx_pkt_nb_segs;
> >> -
> >> -		if (nb_segs > 1) {
> >> -			if (rte_mempool_get_bulk(mbp, (void **)pkt_segs,
> >> -							nb_segs)) {
> >> -				rte_pktmbuf_free(pkt);
> >> -				goto nomore_mbuf;
> >> -			}
> >> -		}
> >> -
> >> -		pkt_len = pkt->data_len;
> >> -		for (i = 1; i < nb_segs; i++) {
> >> -			pkt_seg->next = pkt_segs[i - 1];
> >> -			pkt_seg = pkt_seg->next;
> >> -			pkt_seg->data_len = tx_pkt_seg_lengths[i];
> >> -			pkt_len += pkt_seg->data_len;
> >> -		}
> >> -		pkt_seg->next = NULL; /* Last segment of packet. */
> >> -
> >> -		/*
> >> -		 * Copy headers in first packet segment(s).
> >> -		 */
> >> -		copy_buf_to_pkt(&eth_hdr, sizeof(eth_hdr), pkt, 0);
> >> -		copy_buf_to_pkt(&pkt_ip_hdr, sizeof(pkt_ip_hdr), pkt,
> >> -				sizeof(struct ether_hdr));
> >> -		if (txonly_multi_flow) {
> >> -			struct ipv4_hdr *ip_hdr;
> >> -			uint32_t addr;
> >> -
> >> -			ip_hdr = rte_pktmbuf_mtod_offset(pkt,
> >> -					struct ipv4_hdr *,
> >> -					sizeof(struct ether_hdr));
> >> -			/*
> >> -			 * Generate multiple flows by varying IP src addr. This
> >> -			 * enables packets are well distributed by RSS in
> >> -			 * receiver side if any and txonly mode can be a
> >> decent
> >> -			 * packet generator for developer's quick
> >> performance
> >> -			 * regression test.
> >> -			 */
> >> -			addr = (IP_DST_ADDR | (ip_var++ << 8)) +
> >> rte_lcore_id();
> >> -			ip_hdr->src_addr = rte_cpu_to_be_32(addr);
> >> -		}
> >> -		copy_buf_to_pkt(&pkt_udp_hdr, sizeof(pkt_udp_hdr), pkt,
> >> -				sizeof(struct ether_hdr) +
> >> -				sizeof(struct ipv4_hdr));
> >> -
> >> -		/*
> >> -		 * Complete first mbuf of packet and append it to the
> >> -		 * burst of packets to be transmitted.
> >> -		 */
> >> -		pkt->nb_segs = nb_segs;
> >> -		pkt->pkt_len = pkt_len;
> >> -		pkt->ol_flags = ol_flags;
> >> -		pkt->vlan_tci = vlan_tci;
> >> -		pkt->vlan_tci_outer = vlan_tci_outer;
> >> -		pkt->l2_len = sizeof(struct ether_hdr);
> >> -		pkt->l3_len = sizeof(struct ipv4_hdr);
> >>  		pkts_burst[nb_pkt] = pkt;
> >>  	}
> >> +
> >> +	if (nb_pkt == 0)
> >> +		return;
> >> +
> >>  	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst,
> >> nb_pkt);
> >>  	/*
> >>  	 * Retry if necessary
> >> --
> >> 2.21.0


  parent reply	other threads:[~2019-04-09 12:24 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-28 19:42 [dpdk-dev] [PATCH] app/testpmd: use mempool bulk get for txonly mode Pavan Nikhilesh Bhagavatula
2019-03-01  7:38 ` Andrew Rybchenko
2019-03-01  8:45   ` [dpdk-dev] [EXT] " Pavan Nikhilesh Bhagavatula
2019-03-01 13:47 ` [dpdk-dev] [PATCH v2] app/testpmd: add " Pavan Nikhilesh Bhagavatula
2019-03-19 16:48   ` Ferruh Yigit
2019-03-19 16:48     ` Ferruh Yigit
2019-03-20  4:53     ` Pavan Nikhilesh Bhagavatula
2019-03-20  4:53       ` Pavan Nikhilesh Bhagavatula
2019-03-26  8:43       ` Ferruh Yigit
2019-03-26  8:43         ` Ferruh Yigit
2019-03-26 11:00   ` Thomas Monjalon
2019-03-26 11:00     ` Thomas Monjalon
2019-03-26 11:50     ` Iremonger, Bernard
2019-03-26 11:50       ` Iremonger, Bernard
2019-03-26 12:06       ` Pavan Nikhilesh Bhagavatula
2019-03-26 12:06         ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:16         ` Jerin Jacob Kollanukkaran
2019-03-26 13:16           ` Jerin Jacob Kollanukkaran
2019-03-26 12:26 ` [dpdk-dev] [PATCH v3 1/2] app/testpmd: optimize testpmd " Pavan Nikhilesh Bhagavatula
2019-03-26 12:26   ` Pavan Nikhilesh Bhagavatula
2019-03-26 12:27   ` [dpdk-dev] [PATCH v3 2/2] app/testpmd: add mempool bulk get for " Pavan Nikhilesh Bhagavatula
2019-03-26 12:27     ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:03 ` [dpdk-dev] [PATCH v4 1/2] app/testpmd: optimize testpmd " Pavan Nikhilesh Bhagavatula
2019-03-26 13:03   ` Pavan Nikhilesh Bhagavatula
2019-03-26 13:03   ` [dpdk-dev] [PATCH v4 2/2] app/testpmd: add mempool bulk get for " Pavan Nikhilesh Bhagavatula
2019-03-26 13:03     ` Pavan Nikhilesh Bhagavatula
2019-03-26 16:13   ` [dpdk-dev] [PATCH v4 1/2] app/testpmd: optimize testpmd " Iremonger, Bernard
2019-03-26 16:13     ` Iremonger, Bernard
2019-03-31 13:14 ` [dpdk-dev] [PATCH v5 " Pavan Nikhilesh Bhagavatula
2019-03-31 13:14   ` Pavan Nikhilesh Bhagavatula
2019-03-31 13:14   ` [dpdk-dev] [PATCH v5 2/2] app/testpmd: add mempool bulk get for " Pavan Nikhilesh Bhagavatula
2019-03-31 13:14     ` Pavan Nikhilesh Bhagavatula
2019-04-01 20:25   ` [dpdk-dev] [PATCH v5 1/2] app/testpmd: optimize testpmd " Ferruh Yigit
2019-04-01 20:25     ` Ferruh Yigit
2019-04-01 20:53     ` Thomas Monjalon
2019-04-01 20:53       ` Thomas Monjalon
2019-04-02  1:03       ` Jerin Jacob Kollanukkaran
2019-04-02  1:03         ` Jerin Jacob Kollanukkaran
2019-04-02  7:06         ` Thomas Monjalon
2019-04-02  7:06           ` Thomas Monjalon
2019-04-02  8:31           ` Jerin Jacob Kollanukkaran
2019-04-02  8:31             ` Jerin Jacob Kollanukkaran
2019-04-02  9:03   ` Ali Alnubani
2019-04-02  9:03     ` Ali Alnubani
2019-04-02  9:06     ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:06       ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:53 ` [dpdk-dev] [PATCH v6 1/4] app/testpmd: move eth header generation outside the loop Pavan Nikhilesh Bhagavatula
2019-04-02  9:53   ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:53   ` [dpdk-dev] [PATCH v6 2/4] app/testpmd: use bulk ops for allocating segments Pavan Nikhilesh Bhagavatula
2019-04-02  9:53     ` Pavan Nikhilesh Bhagavatula
2019-04-02  9:53   ` [dpdk-dev] [PATCH v6 3/4] app/testpmd: move pkt prepare logic into a separate function Pavan Nikhilesh Bhagavatula
2019-04-02  9:53     ` Pavan Nikhilesh Bhagavatula
2019-04-09  9:28     ` Lin, Xueqin
2019-04-09  9:28       ` Lin, Xueqin
2019-04-09  9:32       ` Pavan Nikhilesh Bhagavatula
2019-04-09  9:32         ` Pavan Nikhilesh Bhagavatula
2019-04-09 12:24         ` Yao, Lei A [this message]
2019-04-09 12:24           ` Yao, Lei A
2019-04-09 12:29           ` Ferruh Yigit
2019-04-09 12:29             ` Ferruh Yigit
2019-04-02  9:53   ` [dpdk-dev] [PATCH v6 4/4] app/testpmd: add mempool bulk get for txonly mode Pavan Nikhilesh Bhagavatula
2019-04-02  9:53     ` Pavan Nikhilesh Bhagavatula
2019-04-02 15:21   ` [dpdk-dev] [PATCH v6 1/4] app/testpmd: move eth header generation outside the loop Raslan Darawsheh
2019-04-02 15:21     ` Raslan Darawsheh
2019-04-04 16:23   ` Ferruh Yigit
2019-04-04 16:23     ` Ferruh Yigit
2019-04-05 17:37   ` Ferruh Yigit
2019-04-05 17:37     ` Ferruh Yigit

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=2DBBFF226F7CF64BAFCA79B681719D954969777A@shsmsx102.ccr.corp.intel.com \
    --to=lei.a.yao@intel.com \
    --cc=alialnu@mellanox.com \
    --cc=arybchenko@solarflare.com \
    --cc=bernard.iremonger@intel.com \
    --cc=dev@dpdk.org \
    --cc=fengqinx.wang@intel.com \
    --cc=ferruh.yigit@intel.com \
    --cc=jerinj@marvell.com \
    --cc=pbhagavatula@marvell.com \
    --cc=qi.z.zhang@intel.com \
    --cc=qian.q.xu@intel.com \
    --cc=thomas@monjalon.net \
    --cc=wenjiex.a.li@intel.com \
    --cc=xueqin.lin@intel.com \
    --cc=yinan.wang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).